Did you know that, the operator of a scrubber machine has to follow the same path/pattern every single time they clean an area? It’s true, because otherwise people would be able to perceive the lines of movement of the scrubber on the floors, which are not considered aesthetically pleasing. The main corridors of an airport or a supermarket need to be cleaned longitudinally.

This job is so boring that industrial scrubber machines are increasingly being destroyed by the operators earlier and earlier. Therefore, scrubber manufacturers have changed their machines to be cheaper and with less electronics, resulting in lower life expectancy for their product.  The downside of this, is that in the long-term, due to replacement costs, end-user’s will spend more money to service their clients.

We are now in the midst of a global debate that is exploring the question, “Are robots taking jobs away or providing jobs for people?”  In the current economic climate, we need to decide if we want to maintain the status quo to protect low-profile jobs; or embrace advances that allow us to become more competitive and effective in our jobs, promote learning new skills, and provide jobs where human creativity and intelligence are necessary.

What do we want?

Here it is the specification sheet of the autonomous scrubber machine that Cognitive Robots can provide: specification sheet scrubber machines

Is this product good enough to solve the problem of automatic cleaning?

Is the market ready for this?  What do you think?

I received my PhD in Artificial Intelligence, in particular on cognitive models to simulate the way people think about space and time, to effectively move daily around their environment, without the use of any measurement tools. I applied those theoretical models to the movement of simulated robots through the streets of my hometown, Castellon, Spain. It was quite a theoretical thesis, and I really enjoyed working on it.

After I finished my PhD thesis, I went to a IJCAI (International Joint Conference on Artificial Intelligence) conference in Japan to present my research. The Robocup competition was going on at the same venue as the conference. For the first time, Sony was there presenting their cat and dog robot pets in a fiberglass showcase. The movements of those little robots were so well done, that I stood there looking at them in amazement for a very long time. I thought, “I want to be working with these robots”, “I want to include the technology that I just developed for my thesis to these robots”, “the best way for the robots to move through their environment is by using cognitive models, and I am going to make this happen”!

That was a very firm decision. After that, I created a research group at the University, with several PhD and undergraduate students, and started to work with that problem for many years, with highly productive results (if productivity can be measured in terms of papers written), that still were not giving us what I wanted: the robots moving around by using cognitive models. The problem was that the sensors of the robots were not providing the relevant information, that was needed for our theoretical cognitive models, they were just giving us numbers.

It wasn’t until we had a concrete challenge, that we put all the pieces together. The challenge was defined by the Robocup competition for the Aibos robots. The main sensor of the Aibos was the camera, and the treatment of images was done through colour. Although they also had a couple of infrared sensors, they were only useful for avoiding obstacles.

That problem consisted of a soccer field with regular landmarks (two goals and four corners) plus several undetermined, extra landmarks, of different sizes and colours on them. One Aibo robot was placed somewhere in the soccer field and had one minute to turn around and memorize all the landmarks around the field. After that minute, the robot was kidnapped from the field, all the extra-landmarks removed, and the robot placed again somewhere on the field. By using only the regular landmarks, the challenge was to make the robot go to 5 different locations on the field, defined by its (X,Y) coordinates, that were not know up to that moment.

I worked with several students in this challenge for several months. We never went to the real competition, (we didn’t have the funds) but I finally put all the pieces together in a weekend, and wrote a research article on how to use regular sensors to obtain relevant information, to be able to use cognitive models, to make the robot move around. I was so excited. I knew I had something big.

We published that paper, but didn’t publish any others related with that solution, to protect our IP. We received a lot of funding to prove the concept in scrubber machines, and some other research robots. Eventually, we applied for a patent and founded the company, Cognitive Robots. Once the company was created, we continued development with several improvements from the original prototype, and separated the “brain” from the “body”, to create our product, the “Cognitive Brain for Service Robotics ^®” (C-Brain), which is basically a set of sensors, and a computer, that is transforming data from the sensors into relevant information and running cognitive models to relate information, thereby providing knowledge and intelligence to every vehicle were the Cognitive Brain is installed.

With high definition cameras in the eyes, Diego San sees people, gestures, expressions, and uses AI modeled on human babies, to learn from people, the way that a baby hypothetically would. The facial expressions are important to establish a relationship, and communicate intuitively to people. As much a work of art as technology and science, this represents a step forward in the development of emotionally relevant robotics, building on previous work of David Hanson with the Machine Perception Lab such as the emotionally responsive Einstein shown at TED in 2009 (here another video).

Read more >

In 1970, the robotics professor Masahiro Mori coined the term uncanny valley, a hypothesis in the field of robotics and 3D computer animation, which holds that when human replicas look and act almost, but not perfectly, like actual human beings, it causes a response of revulsion among human observers. The “valley” refers to the dip in a graph of the comfort level of humans as a function of a robot‘s human likeness. The hypothesis has been linked to Ernst Jentsch‘s concept of “the uncanny” identified in a 1906 essay, “On the Psychology of the Uncanny” Jentsch’s conception was elaborated by Sigmund Freud in a 1919 essay entitled “The Uncanny” (“Das Unheimliche“).

Read more >

What I would say is that basic research is done to be used in a myriad of ways, so that can serve humans best.

And certainly this very advanced research in robotic expressions can help us to be closer to something as cute as Gumdrop, the 27-year old Bulgarian robot-actress.

It’s amazing stuff, and very important to realize the amount of work that needs to be done to prove a concept. Even when proven, the robot may not meet some of the needs of the user, and not a best seller anyway.

Next time you buy a sophisticated toy or a small (not so intelligent) vacuum cleaner, remember all of the time, money, research and work behind it!

Thank you iRobot for showing us this treasure!

————————————————————————————-

Robotics is not only a research field within artificial intelligence, but a field of application, one where all areas of artificial intelligence can be tested and integrated into a final result.

Amazing humanoid robots exhibit elegant and smooth motion capable of walking, running, and going up and down stairs.  They use their hands to protect themselves when falling, and to get up afterward.  They’re an example of the tremendous financial and human capital that is being devoted to research and development in the field of electronics, control and the design of robots.

Very often, the behavior of these robots contains a fixed number of pre-programmed instructions that are repeated regardless of  any changes in the environment. These robots have no autonomy, nor adaptation, to the changing environment, and therefore do not show intelligent behavior. We are amazed by the technology they provide, which is fantastic! But we can not infer that, because the robots are physically so realistic and the movements so precise and gentle, that they are able to do what we (people) do.

Let’s imagine that we see a robot in a film with a manipulator arm ironing a shirt. Today’s robotics technology is not advanced enough to be able to iron a shirt autonomously, as people do. Even if we see a robots arm grabbing the iron by the handle then sliding it over the fabric, (which has been placed there by a human) the speed of passage through the clothes and the number of times it will go through the same spot would surely be pre-programmed. If we were to lower the height of the ironing-board, the iron would probably float above the shirt at a height equal to that that we lowered the ironing-board, with the same movements, as if you were really ironing, without ever realizing that the iron is not touching the fabric. It would not be able to distinguish the effect of the iron on the shirt to determine whether it had any wrinkles, nor could it deduce wether the fabric still has wrinkles. Perhaps the iron is unplugged or the ironing program is not adjusted to the fabric type. Needless to say, the arm can not change the shirt being ironed and replace it with the next shirt to be ironed. Today’s robots can not autonomously iron, even if Hollywood would make it seem otherwise.

As in the robot-ironing example, there are many other things that robots can not currently do. We have seen so many movies that show advanced robotic skills, that the limits of science and technology in robotic intelligent behavior are unclear for most of the population, even for computer scientists not working directly in cognitive robotics.

Artificial Intelligence brings intelligent behavior to the robot, to be able to provide services to humans in unpredictable and changing environments, such as homes, hospitals, the work place, and all around us.

The basic contributions of AI in robotics are:

PERCEPTION – not only taking data from the environment, but transforming it into knowledge (and even wisdom) to be able to interpret and modify its behavior according to a result of this perception.

REASONING – drawing conclusions from data/knowledge taken from perception.

LEARNING - with new experiences, the robot needs to perceive and reason to obtain conclusions, but when the experiences are repeated, a learning process is required to store knowledge and speed up the process of intelligent response.

DECISION MAKING, or the ability to prioritize actions, is necessary to be able to be safe and effective in the solution of different autonomous applications.

HUMAN-ROBOT INTERACTION at many levels is also necessary. For example, natural language processing – understanding the meaning of sentences exchanged with humans, depending on the context and to be able to properly respond -, and emotions rapport.

We are going to analyze the first three areas a bit more in depth.

Any robot as an autonomous physical entity, has to perceive its environment, and interpret this perception, to move in a safe manner. Currently there are several types of sensors that can be used with robots:

• Sonar sensors emit an inaudible sonar beam in the direction perpendicular to the sensor itself. The time between the emission of sound and the subsequent reception of its rebound in the environment obstacles is a measure of the distance between the sensor and the perceived obstacle. This type of sensor is very inaccurate, because its measurements are highly dependent on the reflective surface of the sound beam.  Mistakes are technically very difficult to counter. The scope of these sensors is between 50 cm and 3 m approx.

• Infrared sensors emit an infrared light beam in the direction perpendicular to the sensor itself, and receive the rebound from the environment with light in a receiver. The distance between the sensor and the obstacle in the environment is also calculated using the time between transmission and reception. These sensors are very sensitive to changing ambient light, so they are not totally reliable. The scope of these sensors is 80 cm.

• The laser sensors  (laser emission) range depends on the type of laser used. As in the sonar and infrared sensors, the elapsed time between emission and the reception beam, calculates the distance to an obstacle in the environment. There are laser sensors that perform a sweep in a single 180 degree plane. There are others that 3-dimensionally scan the environment. This full scan can be equated to the view with a video camera, it makes a reconstruction of the entire environment based on points or distances from the sensor to the environment. Lasers are much more robust to environmental characteristics and their measurements are quite reliable. However, there are still very expensive.

• The Kinect sensor came to the market at the end of 2011, revolutionizing the robotic sensors spectrum. It contains an RGB camera, a depth sensor and a multi-array microphone running proprietary software, which provide full-body 3D motion capture, facial recognition and voice recognition capabilities. It is relatively easy to incorporate into the robot platform and software. The main drawbacks are that you can not recognize objects or faces (it only provides a cluster of color regions by distance) and it doesn’t work outdoors (yet).

• The video camera is the most promising sensor, it is quite inexpensive and provides more accurate information of the environment. While there are huge advances in this area and we are very close to consider this sensor as the main one, we are still not quite there yet.

Computer Vision is a very active field of AI, which has made great progress on specific issues, such as face recognition, or recognition of defects in ceramic glaze. “Object recognition” remains an unresolved issue in general. As an example, we understand the concept “chair”, and can identify any chair we see, even a new model that we’ve never seen before. And we recognize a chair even when its partially hidden behind other objects in a scene. This is not yet solved in computer vision. One very active research area in computer vision is “quick search of a specific object in a scene”, without processing the entire image.

One of the latest advances in the area is cognitive vision, which uses qualitative recognition of object shapes, their relationships and ontologies to connect those qualitative shapes with names of objects and the concepts that they represent. It has many benefits, one of which is automatic tagging and fast processing. This technology has been developed at the University Jaume I and Cognitive Robots under my supervision. This will be explained in more detail in another post.

The current situation in commercial service robots is that we need sensor integration of most (if not all) of the above mentioned types of sensors. With a unidirectional laser (very common in commercial service robots), the robots only perceive what is happening in the plane of the laser, the rest of the environment is not perceived. Sonar and infrared sensors are cheaper and can be placed around the robot. The kinect sensor provides 3D obstacle detection. The use of each type of sensor, its interpretation, treatment of inconsistent information, and the integration of information from various types of sensors, remains an open research topic.

The implementation of a reasoning process is also basic to service robotics. The reasoning process allows the robot to infer reliable conclusions from premises. For example, if the robot is perceiving landmarks in the room at a certain relative orientation, this orientation can be used by the robot to know its relative position in its movement through the environment. The biggest problem encountered in any reasoning method for robots is the management of uncertain and vague information of the data perceived. There are many types of reasoning, all remain open fields of research within Artificial Intelligence: logical reasoning systems, probabilistic reasoning systems, case-based reasoning, fuzzy logic, and qualitative reasoning. The latest reasoning techniques developed are mental processes of analogy. We use ‘Qualitative Reasoning‘ as the reasoning technique incorporated in our product, “Cognitive Brain for Service Robotics ®” at Cognitive Robots.

The robots also have to be able to learn from their own experience. Learning is essential in order for them to function in unknown environments. They must be able to store data (from environmental or behavioral processes) that have ever been helpful to achieve a goal. Learning may be a memory (more or less elaborate) of experiences, as well as how these are then used when needed. There are many learning techniques: Inductive learning through semantic networks, can learn a function from examples of its inputs and outputs; neural networks; belief networks, allow learning probabilistic functions; reinforcement learning, allows a robot to react appropriately in unfamiliar environments, based only on their perceptions and occasional rewards. Learning qualitative models that describe behaviors to solve different tasks is, in my opinion, a better way for robots to learn as humans learn .

Perception, reasoning and learning are the three pillars of intelligence (human and robotic).

If these pillars are implemented in the most cognitive way we know, and integrated in a highly modular way (to be able to substitute a solution for a better one without affecting the whole system), we have a sound foundation to include the decision making process to adapt the same robotic architecture to solve different tasks. This has been the way of thinking and operating at Cognitive Robots.

Gumdrop is one of the most cute and endearing robots that have been creating in film. This is a short film from Sky Captain and the World of Tomorrow director Kerry Conran is totally worthy of a feature length version, diving into the life of Grumdrop.

What are the features of this bot-actress that does not exist in our current robots yet?

• Gumdrop is flexible in her body and mouth movements
• Gumdrop has an intelligent communication
• Gumdrop has a history as an individual robot (“when I was a litte robot”, she recalls)

Find the full article about the movie here.

The current robot that reminds me to Gumdrop is Tico, from Adele Robotics. Look at the following video:

Do you find more differences?

Service robots often mean robots that assist the elderly, or help with the rehabilitation of medical patients. But the range of services that robots can perform is extremely broad.

From a robotic fish that uses artificial intelligence to detect and identify pollution in seawater created by SHOAL,

To a telepresence PatrolBot which will let disabled police officers and military veterans serve as distance patrol officers, filling a gap in both the lack of patrol staff, and the lack of available jobs for disabled vets and officers, developed by Florida International University.

To a can crusher robot, Dr. R.E. (Robotic Environmentalist) Cycler, from Florida Robotics, which crushes aluminum cans in its chest cavity and compacts them to less than a (presumably cubic) inch in size.

To this new Roomba competitor, the autonomous robot harvester created by Russian industrial designer Olga Kalugina, which collects trash in pedestrian areas such as shopping centers and streets.

Georgia Tech’s Golem Krang robot is being designed to emulate the feats of the TV character MacGyver, who could get himself and others out of problematic situations using ingenuity and objects immediately at hand. Aided by an algorithm that will help it reason like a human, Golem Krang will identify items in its environment that can become tools to accomplish necessary tasks, such as stacking boxes to climb over an obstacle, or breaking a window’s glass to escape a fire.

Finnish startup ZenRobotics has designed the ZenRobotics Recycler, a robotic recycling system that sorts and separates raw materials during construction and demolition, commercial and industrial, and municipal solid waste recovery operations. The system is based on off-the-shelf industrial robot components, which are controlled by artificial intelligence and equipped with multiple sensors to safely and efficiently remove materials from a waste stream. The sensors include visible spectrum cameras, near infrared, and 3D laser scanners that identify the different items, and the robot can learn from its mistakes, producing fewer contaminants in the harvested materials. It can also weigh and measure the items of separated trash, and can simultaneously sort, reclaim, and harvest.

The autonomous Vigilus Mobile Camera Platform, form Vigilant Robots, can be customized to create a robot that patrols interior spaces such as shopping malls, event centers, warehouses, and distribution centers as an adjunct to human security forces. It reports anomalies and sensor readings that exceed preset customer parameters, and can be customized with cameras, sensors, and access control devices. When installed, the robot is given a map of the site to be patrolled, which can be updated to reflect changes in layout, with customizable location names. Its battery lasts 10 hours without degradation.

The Clever Robots for Crops (CROPS) project is a multinational engineering effort to design an intelligent robot system with sophisticated sensing and manipulation abilities. It will selectively harvest the produce of high-value crops, identifying not only the correct plants, but fruits and vegetables at the correct stage of ripeness, including greenhouse vegetables, orchard fruits, and vinyard grapes.

DeLaval‘s voluntary milking system automates milk production to an extreme degree, letting cows decide when they need to be milked.

A robot being designed by computer vision and robotics company Blue River Technology will automate the backbreaking labor of weed pulling, eliminating the need to use harmful chemicals to kill weeds. The robotic weeder will employ image sensors in the implement (shown in red), as well as machine vision algorithms for recognizing and distinguishing among different types of plants.  September 10th 2012 Blue River Technology raised 3.1 M $.

Read more >

Do you have/know more examples of other companies that have products for service robotics?

Please, introduce it as a comment to this post.

Our brain is the starting point of our creation.

Do in life whatever you are passionate to do!

Sometimes we get too enclosed in our little boxes. This movie allows us to change perspective of live.

There is no mediocrity in Nature.

You probably have seen this video (more than 15 Million watches), but if not, please, remember that your passion is what drives you in live, both personally and professionally.

Enjoy!

Adele Robotics has launched Fiona, a project for the robotics community to create an artificial mind.

This is another example of Cloud Robotics and reproducing the Apps economy for the robotics industry, the future of robotics.

Congratulations Adele!

Open-source software is making it easier to reuse algorithms and allow engineers and researchers to focus on their problems of interest instead of reinventing the wheel for each project. Not an expert in path planning or don’t have the time (or patience) to implement SLAM? There’s a package for that. Manipulator control? Package for that too. Additionally, falling component prices and commercial-off-the-shelf (COTS) devices are making robotics hardware more available. This tutorial will teach you how to put together a simple remote teleoperation robot using these principles.

Read more >

Cognitive Brain for Service Robotics (R) from Cognitive Robots is created with ROS.

The overall goal of the project is to enhance the Kompai companion robotic platform from Robosoft (picture on the left) with the Cognitive Brain for Service Robotics ® (CBRAIN) from Cognitive Robots (picture on the right). The existing functionalities of the KOMPAI platform will remain and be enhanced with the cognitive capabilities of the CBRAIN.

The original capabilities of the Kompai at the beginning of the project were:

1. Autonomous navigation solution based on traditional techniques such as laser-based SLAM (Simultaneous Localization and Mapping).
2. Linear Obstacle detection at the height of the laser.
3. Advanced dialog: the robot can receive verbal commands and give verbal responses.

The initial limitations that where identify in the Kompai platform and were addressed in this project were:

• No automatic map building. A technician needs to manually create the map of each new environment (half day of work). Every single time the layout of that home is changed, the technician needs to go back to the home to re-learn the map of the environment for the robot.
• No 3D obstacle avoidance. The current sensor of the Kompai is a laser, which provide linear distance measurement of the obstacles at the height of the laser.
• Kompai is a passive robot, basically a computer with wheels waiting for the elderly to talk to the robot or press a button in its screen to start the interaction.
• Kompai does not have cleaning capabilities.

After 18 months of project, Cognitive Robot’s Cognitive Brain for Service Robotics has been integrated into the Kompai platform, and there is a summary of the main achievements of the project:

1. Autonomous map creation. Before the project, the Kompai platform needed a technician from Robosoft to create the map of a new home. With the C-Brain, the Kompai autonomously creates the map of any environment, not only the first time it arrives to a new home, but every time the owner changes the layout of the home – without the need to call a technician again.
2. Obstacle avoidance in 3D. Before the project, the Kompai was only able to perceive a line of the environment with the laser sensor, which was very dangerous in a home environment, with a lot of obstacles at different heights. Thanks to the incorporation of the Kinect sensor from the Cognitive Brain, the Kompai perceives and avoids 3D obstacles around the room.
3. Landmark perception / detection. The distances collected from both the laser and the Kinect sensors are processed to extract the most relevant landmarks of the environment (qualitative information), which allows the robot to reason and make decisions at a high level of abstraction. This is part of the patent pending, proprietary software of the “Cognitive Brain for Service Robotics” from Cognitive Robots.
4. A new navigation system has been incorporated into the system, which applies the ‘landmark perception/detection system’ (above explained) allowing the robot to reason and make further decisions.
5. Vacuum cleaning algorithms using the ‘landmark detection system’ allows the robot to know what it has been vacuum and what still needs to be vacuumed.
6. Decision making. Before the project, Kompai was a static robotic platform waiting for a ‘call to action’ by the user. With this new feature introduced from C-Brain, Kompai has become proactive and starts actions by itself to engage the user.
7. The architecture of the CBRAIN is an open architecture for the integration of already existing and newly developed cognitive and non-cognitive capabilities and competences.
8. One of the most important features of the CBRAIN architecture is its double modular aspect.

• The modularity in the hardware allows integrating new hardware components and removing or changing others to/from the system without affecting the rest of the components. Therefore the system can be easily enhanced with new sensors or actuators as necessary.
• The modularity in the software allows applying the same system to solve different tasks by
  changing only one component of the system without affecting the rest of the software components.

There is still some tuning work to do, but clearly the Kompai platform has considerably enhanced its capabilities thanks to the Cognitive Brain form C-Robots.

Congratulations to both teams for the nice job!

Once upon a time, when I finished my PhD dissertation, I went to the IJCAI conference in Kyoto, Japan, and the Robocup competition was taken place in the same venue. I absolutely fall in love with the Aibo dog and cat robots from Sony, that were exposed at the competition (before they were widely used at the same competition).

At that event I decided that I wanted to apply the results of my PhD to bring Intelligence to robots. And that is what I did. I started a research group at Jaume I University. My students play with the Aibos for years. And working on one of the challenges of the Robocup competition with my students, I put all the dots together, and after 10 years of research since my PhD was finished, the seed of Cognitive Robots was born. That technology became a patent pending for our company and is still ahead of the rest of the technology that brings Intelligence to the robots, as far as we know.

I have great memories about the Robocup competition. I agree that it is a great play ground to integrate and test technologies in the areas of AI and Robotics. And it is for sure much more that a toy test.

By Jason Falconer, October 8, 2012

University of Bonn’s Team NimbRo are commercializing a humanoid platform, NimbRo-OP, for €20,000 (US$26,000) to compete in RoboCup‘s TeenSize league. It sounds rather expensive, but it will save teams the trouble of prototyping their own, and the untold hours of research and development that would normally require.

Read more >

Shimon Schocken and Noam Nisan developed a curriculum for their students to build a computer, piece by piece. When they put the course online — giving away the tools, simulators, chip specifications and other building blocks — they were surprised that thousands jumped at the opportunity to learn, working independently as well as organizing their own classes in the first Massive Open Online Course (MOOC). A call to forget about grades and tap into the self-motivation to learn.

Shimon Schocken is a computer science professor and dedicated educator.

I completely agree with everything he says in this fantastic video, including his opinion about grades. Brilliant work! Congratulations Shimon, Noam and the rest of collaborators!

ROBOHELPER SASUKE helps lift a person into and out of bed using servo motors. The device has two rods connected by a sling that slides under the body. The sling is made of a special material and can accommodate a weight of 264 lbs (120 kg). Furthermore the arms can rotate up to 60 degrees, which allows the patient to comfortably transfer from a prone position to a sitting position.

ROBOHELPER LOVE – is an an automatic bodily waste disposal unit aimed at making bedpans a thing of the past. A cup wraps around the patient’s waist, fitted with sensors that automatically detect the presence of fluid and/or stool. The waste is quickly suctioned away into a holding tank, followed by a cleansing wash using room temperature water. The cup itself can be washed and sterilized automatically at the station. It can operate for up to 12 hours without supervision, making it ideal for overnight use.

Read more >

By Christopher Hall, September 28, 2012

FUROs, the new service robot from Korean robotics startup Future Robot can be defined as a hybrid between a smartphone and a smart machine.

According to Korea IT Times, the FURO interactive robot can provide a variety of services “by reading users’ intentions in different situations” by observing users’ movement, face and voice, and then conveying the “matched dialogue, facial expression, movement and necessary information.”

One buyer from Brazil, who ordered over 100 FUROs, came up with new business model – mobile (moving) advertisements. As FURO moves around in airports or exhibitions, they said, the back screens which are remotely operated can be utilized for advertisements while the front screen performs ordinary information services.

Read more >

Robohub launches its beta version and will start publicizing it September 26 at 9am EDT.

Robohub main focus is to provide high-quality information about robotics to the general public.

I am proud to announce that I am contributing to this organization with this blog.

Spanish start-up Aisoy Robotics is marketing a new robot that, while it may look similar to the famous Furby, is actually a fully programmable research and development platform.

The Aisoy1 II robot comes with a variety of sensors (touch, light, position, temperature, and camera), microphone and speaker, RGB LEDs in its body, and a 70 mini-LED matrix display (for animated lips). Four servos control the robot’s neck rotation, eyelids, and eyebrows. The platform doesn’t move.

The package includes a dialogue system for speech recognition and synthesis, as well as computer vision software for stuff like face and object recognition, all running on the Linux operating system. The company claims even complete novices can take advantage of these functions without having to learn how to code thanks to DIA, its visual programming tool. The program runs in HTML5 compatible browsers, allowing you to select nodes that control the robot’s various sensors and behaviors.

Read more >

As the Thymio II, a specific non-standard programming language is against the robotic community efforts for standardization. However, the fact that is HTML5 compatible contributes to the creation of the Robotics App Economy.

The most important feature of Aisoy1 II, which is not mentioned in the previous article, is its emotional motor, a very interesting AI feature at the service of developers for a very low price. As their creators said: ” humans would not take decisions without emotions”. This emotional motor can be a key factor for development of the robotic industry.

Very cute little and inexpensive robots that can help to promote robotics education at schools and colleges.

Very nice promotional video of Thymio II, the new educational robotic platform from the Swiss research institute EPFL (École Polytechnique Fédérale de Lausanne/Swiss Federal Institute of Technology).

Thymio II is available now, at a price of 99 Swiss francs (US$106).

Wheels can  be connected to user-supplied moving parts such as arms, propellers, winches, or just about anything else.

It also features a microphone and speaker, a 3-axis accelerometer, five proximity sensors, two ground sensors, a temperature sensor, and 39 LEDs which allow its body to illuminate in different colors.

It can accept programming via a USB connection (which is also used to charge its lithium-polymer battery) or a memory card slot. Programming is created using EPFL’s robotics-specific ASEBA language. This is a drawback considering the robotic community efforts for standardization with the Robotics Operating System (ROS).

Read more >

Toyota has unveiled a new assistant robot designed to help the disabled live more independently. Called the Human Support Robot (HSR), it represents the latest initiative in Toyota’s Partner Robot program and is intended to help out around the home by fetching things, opening curtains, and picking up objects that have fallen to the floor.

The HSR can be controlled using a simple graphical user interface via tablet PC. HSR has also an arm of 2.5 feet length and gripper. When not in use, the robot’s single arm is designed to fold in tightly to reduce its body’s overall diameter to just 14.5 inches

The robot has a telescopic body, which gives it a height of 2.7 to 4.3 feet.

The robot appears to have both a Prosense (Microsoft Kinect) sensor and stereo cameras in its head, which would allow it to sense depth and visually identify people and objects.

Expected price of the robot is unknown, but given that Japanese public health insurance will cover 90% of associated costs (a law designed specifically for robot technology that was passed recently), it seems HSR will have a decent shot at becoming a real consumer product, though it may take another couple of years of development.

Read more >

This is the company and the robot that Amazon has been contemplating to acquire to provide a complete automatic solution for the retail industry. The last piece of the puzzle after Amazon’s Kiva acquisition for $775 M.

By JOHN MARKOFF, September 18, 2012

Baxter, the first product of Rethink Robotics, an ambitious start-up company in a revived manufacturing district, is a significant bet that robots in the future will work directly with humans in the workplace.

Here in a brick factory that was once one of the first electrified manufacturing sites in New England, Rodney A. Brooks, the legendary roboticist who is Rethink’s founder, proves its safety by placing his head in the path of Baxter’s arm while it moves objects on an assembly line.

The $22,000 robot that Rethink will begin selling in October is the clearest evidence yet that robotics is more than a laboratory curiosity or a tool only for large companies with vast amounts of capital.

Baxter will come equipped with a library of simple tasks or behaviors.

Rethink itself has made a significant effort to design a robot that mimics biological systems. The concept is called behavioral robotics, a design approach that was pioneered by Dr. Brooks in the 1990s and was used by NASA to build an early generation of vehicles that explored Mars.

Dr. Brooks first proposed the idea in 1989 in a paper titled “Fast, Cheap and Out of Control: A Robot Invasion of the Solar System.” Rather than sending a costly system that had a traditional and expensive artificial intelligence based control system, fleets of inexpensive systems could explore like insects. It helped lead to Sojourner, an early Mars vehicle.

The next generation of robots will increasingly function as assistants to human workers, freeing them for functions like planning, design and troubleshooting.

Rethink’s strategy calls for the robot to double as a “platform,” a computerized system that other developers can add both hardware devices and software applications for particular purposes. It is based on open-source software efforts — including the Robot Operating System, or ROS, developed by the Silicon Valley company Willow Garage, and a separate project called OpenCV, or Open Source Computer Vision Library.

That will make it possible for independent developers to extend the system in directions that Rethink hasn’t considered, much in the same way the original Apple II computer had slots for additional peripheral cards.

“We will publish an interface for the end of the wrist,” Dr. Brooks said. That will mean that while Baxter comes with a simple hand, or “end effector,” it will be able to adapt the system with more complex and capable hands that will be able to perform tasks that require greater dexterity.

Read more >

To develop the system, the researchers started with a database made up of 250 categories of annotated photographs. Then, using Amazon’s Mechanical Turk crowd-sourcing service, they hired people to make rough sketches of objects from each of those categories. The resulting 20,000 sketches were then subjected to recognition and machine learning algorithms, in order to teach the system what general sort of sketches could be attributed to which categories. After seeing numerous examples of how various people drew a rabbit, for instance, it would learn that combinations of specific shapes usually meant “rabbit.”

Check out the video showing the performance of the application. It is amazing! This technology has a broad and very deep implication in many areas, robotics is just one.

The research  is  available online, together with a library of sample sketches, and other materials. The team is currently considering a ‘Pictionary’ type open source game to expand the systems’ drawing reference library.

Read More:

• ZigMag article
• FormFonts 3D Models article
• Computer Program Can Identify Rough Sketches – Brown University
• How Do Humans Sketch Objects – tu-berline.de

The rise of robotic automation in the manufacturing and packaging industry is often blamed for the steep job losses in U.S. manufacturing, along with the rampant outsourcing of labor to cheaper workforces. But a real look at the facts and stats show that things just aren’t that cut and dry.

Check out our infographic below and you’ll see the many ways in which robotics and the reshoring initiative can help increase manufacturing employment in the U.S. From providing improved safety measures in dangerous jobs, to introducing higher-paying, specialized positions that workers can be trained to fill, to laying out the true pros and cons of offshore outsourcing, this infographic sheds some light on the “other side” of the story.

Robots And Automation Bring Jobs Back To The U.S.

I love examples of how to do things. We learn so much from examples!

In this case the example shows both how you can use C# skills to build robots, and also how flexible the new Windows Store app model is when it comes to communicating with remote devices.

Read more >

Very sweet! The nice faces of the kids in the back compensate the ugly face of the dancing robot!

Read more >

In its current version, Cheetah is powered by an off-board hydraulic pump with a boom-like device keeping it centered on the treadmill. DARPA says improved control algorithms and a more powerful pump were responsible for the increase in speeds since the robot set its previous record.

Being developed and tested by Boston Dynamics under DARPA’s Maximum Mobility and Manipulation (M3) program, Cheetah is being designed to perform in emergency response, humanitarian assistance and military missions. With such applications certain to involve rough terrain, DARPA intends to test a prototype on natural terrain next year.

Big acquisitions and investments are taken place in this industry. Examples are the significant investment in Aldebaran Robotics, and the more spectacular acquisition of Kiva Systems by Amazon for $750 M. The case of Kiva Systems is very remarkable because Amazon is one of the main players of the Cloud Computing industry and their ultimate goal is to have fully automated logistics for retail sells. Kiva Systems provide a scalable, very reliable robotics solution to transport items in a warehouse. At this moment, the only time where a person is touching an item is to grab it from the shelf that is brought to him and place it in the box to send it out. Amazon is now making investigations to acquire a company expert on grasping / arm manipulators to automated the last piece of the system. Soon we will be able to buy the book we want, from our iPad or iPhone (or similar) and see in our screen how a robot is finding our book, transporting it to the door of the warehouse where an arm manipulator is placing it in our box. We will receive the book the same day or the day after, depending on the distance from the warehouse to our home. This is a successful story that it is happening while we speak.

However, there are many other robotic companies struggling to arrive to the market. Although robotics is a very hot topic, robots still need to have “more intelligence”, the software needs to be hardware independent and reusable, and the components need to be less expensive, so that the balance between price and benefits goes by far to the side of the benefits.

A comparable example in our recent history has been the iPhone: “too expensive, nobody would buy it”, said the competition, and they were wrong. Now everybody “have to have” a smartphone, the benefits have override the cost. Most people do not think about the cost, they only think about the amount of benefits they are going to get from it.

The great advantage of a smartphone is that it provides so many tools in a single, readily available, relatively inexpensive package.

Almost a million apps have been created for the iPhone, iPad and Android alone, greatly augmenting the usefulness of mobile devices [1]. Want to play games, track your workouts, write music? There are a plethora of apps to choose from, many of them free. This analysis—conducted for TechNet by Dr. Michael Mandel of South Mountain Economics, LLC—shows that the App Economy now is responsible for roughly 466,000 jobs in the United States in the last four years, since 2007 when the iPhone was introduced. This total includes jobs at ‘pure’ app firms such as Zynga, a San Francisco-based maker of Facebook game apps that went public in December 2011. App Economy employment also includes app-related jobs at large companies such as Electronic Arts, Amazon, and AT&T, as well as app ‘infrastructure’ jobs at core firms such as Google, Apple, and Facebook. In additional, the App Economy total includes employment spillovers to the rest of the economy. Our results also suggest that the App Economy is still growing at a rapid clip, which shouldn’t be a surprise to anyone.

In order to provide users with a wider range of engaging experiences, social networks and mobile operating systems have opened their platforms to developers, transforming the creation, distribution and consumption of digital content. We refer to this as the “App Economy.” In the App Economy, developers can create applications accessing unique features of the platforms, distribute applications digitally to a broad audience and regularly update existing applications”

The App Economy is only one way technology creates jobs. As explained here there is other ways in which robots create jobs.

The combination of ease of development and ease of delivery makes possible a stunning variety of apps.

Our claim is that this App Economy phenomenon in the mobile industry can be reproduced again in the robotic industry to help that industry take off.

In order to do so, we need to provide in the robotics world the same breeding ground as it exists for mobile platforms: ease of development and ease of delivery.

We need to assign capital to do it!

References:

[1] Mandel, M., “Where the Jobs Are: The App Economy”, TechNet 2012.

By THOMAS ROGERS, 08/20/2012

“Full robots with arms are still very expensive,” says Ashutosh Saxena, a professor in the department of computer science at Cornell, “but they are getting cheaper by the day.” He predicts that armless robots — capable of communicating verbally with the elderly and observing them in case of accidents — will hit the market within the next five years.

There’s just one hiccup: the elderly themselves.

Despite manufacturers’ hopes, robotic technology has proven to be alienating for many older people — even, the BBC reports, in Japan, a country with an intense, long-term love of all things robotic.

Alexander Libin, scientific director of simulation and education research at Medstar Health Research Institute, argues that one of the biggest challenges is that the elderly need to be able to communicate easily with them. Although many robots (and mobile phones) can now recognize voice commands, nonverbal cues pose a much bigger challenge. Libin, who has worked extensively on robot-patient interaction, believes that touch-sensitive technology — like the one used by Paro, the therapeutic seal robot — will play a large role in making robots palatable to seniors.

“The Japanese want robots to be like them,” says Libin, noting Japan’s long tradition of treating inanimate objects like living beings. In the United States, we’re more comfortable treating machines as machines. “We want things we can control.”

The path toward robot acceptance may also require  patience. Like other forms of social change, robot acceptance may simply require one generation to replace the previous one.

Read more >

Miimo is Honda’s entry into the growing robotic lawn mower market. Honda’s announcement comes hot on the heels of Bosch showing off its Indego mower. The Auto-Mower, Robby Garden XP, Evolution, and Robomow are some of the other examples of robotic lawn mowers to emerge in recent years. It is clear that this industry is growing at an exponential rate, and Honda is making sure to throw its name into the hat.

According to Honda, the Miimo “navigates the garden through an intelligent combination of controls, timers and real-time sensory feedback.” It knows the limits of your yard with a boundary wire that is installed either underground or in the grass. The wire sends an electronic signal to the Miimo and tells it to stay within that area.

Miimo uses a “ continuous cutting” system that cuts about three millimeters of grass at a time. You can choose between three cutting modes: random, directional, and mixed.

Miimo has a couple of unique features that Honda hopes will help it stand above the competition. The first of these is the fan that resides above the blades. This helps suck grass towards the blades and should offer a cleaner cut. Additionally, the mower’s three blades are flexible, designed to bend on impact with a hard object instead of breaking.

The Miimo will hit the market in early 2013.

Read more >

The “electronic nose” will eventually be developed into three platforms: a handheld device, which could be used for environmental monitoring, a smaller wearable version useful for monitoring air quality, and a smartphone-integrated system, which the team reports could detect a potentially harmful airborne agent.

This is a very important sensor to include into robots, as well.

Read more >

Researchers at Stanford University have developed a Wave Glider robot which tracks the migratory patterns of great white sharks off the California coast, near San Francisco.

Stanford marine scientists have spent the past 12 years tracking the migratory patterns of sharks by placing acoustic tags on the animals that send a signal to a receiver when they pass within 1,500 feet.

Their goal is to use revolutionary technology that increases our capacity to observe our oceans and census populations, improve fisheries management models, and monitor animal responses to climate change.

The surfing robot will receive audio information from the shark’s tags and then it will propel itself forward through the water to follow the animal in an unobtrusive manner. The surfboard part acts like a WiFi hotspot, pinging the research team with the latest data about the sharks’ movements.

The Stanford team has released a new iPhone and iPad app called Shark Net to model the sharks’ patterns and offer real-time notifications when the robot crosses paths with certain sharks. The idea behind the app is to allow everyone to explore the places where these sharks live, and to get to know them just like their friends on Facebook.

Read more >

San Antonio — August 15, 2012 — Southwest Research Institute (SwRI) is launching a cooperative research consortium to accelerate the development of ROS-Industrial, an open-source extension of ROS focused on the needs of industrial users.

ROS, which stands for Robot Operating System, is an open-source project providing a common framework of libraries and tools for a wide range of applications, particularly for service and research robots. The ROS-Industrial Consortium (RIC) will enable the industrial robotics community to apply the advanced capabilities of ROS for industrial applications quickly and easily using a common platform, the ROS-Industrial open source software program. The consortium will conduct foundational, precompetitive research and code development at the direction of the membership. Test results, data, recommendations and analysis generated by RIC will create a competitive advantage for its members and will be protected from public disclosure for a period of time.

ROS-Industrial will create code quality standards indicative of an industrial software product, to include rating/tracking code quality metrics, multi-level testing and documentation.

RIC will have its first kickoff meeting in early 2013. Annual membership fees vary depending on the size and type of organization.

For more information about the ROS-Industrial Consortium, see ric.swri.org or contact Evans at paul.evans@swri.org or (210) 522-2994.

Read more >

Cognitive Robot has also adopted ROS to develop its Cognitive Brain for Service Robotics.

Great job from Willow Garage. This is a nice example of the utility of robots in the near future. PR2 is too expensive to be acquired by a regular disable citizen, but you get the idea…

Read more >

For us humans, with our non-upgradeable, offline meat brains, the possibility of acquiring new skills by connecting our heads to a computer network is still science fiction. It is a reality for robots.

Cloud Robotics can allow the robot to access vast amounts of processing power, data and offload compute-intensive tasks like image processing and voice recognition and even download new skills instantly, Matrix-style.

There is an excellent post at ieee spectrum about Cloud Robotics that I absolute recommend to read for those who want to know what is next in the Robotics world.

Here are the benefits I see by using Cloud-enable robots:

• Provides a shared knowledge and skill/behaviour database, therefore we can make the robots smarter:
  • With common ontologies giving names and meaning of all kinds of things and concepts, the robots will be able to interchange knowledge and how to name and use things, or how to do things.

• Offloads heavy computing tasks to the cloud:
  • Cheaper, lighter and easy to maintain hardware.
  • Longer battery life.
  • Invisible software and hardware upgrades.

Any old robot full of dust, stored in the closets of the research labs of the world can be reused again by using the hardware and software infrastructure of the cloud.

There is also some drawbacks that we need to consider when we want to provide a solution to our clients which integrates Cloud Robotics:

•  It is necessary to careful define an equilibrium between software in the cloud and on-board depending on the application for several reasons:
  • The robot can become suddenly stupid if it looses internet connection.
  • It can be hacked.

I am starting to define a big research project on Cloud Robotics at University of Washington with the potential collaboration of Cognitive Robots. If you belong to a Robotics company or a research group and are interested in collaborating with us, please, send an email to mtescrig@uw.edu.

Your comments about benefits / drawbacks / examples of Cloud Robotics / groups that are working in the area / etc. are more than welcome.

by David Szondy August 2, 2012

Built by Hanson Robotics, Zeno’s open-platform software allows for custom tinkering by the purchaser, but the robot is currently programmed for a number of functions as well as speaking 26 languages. In the video, it asserts that it can carry on “conversations” and show “compassion.” It can also “deliver education curricula,” provide autism treatment therapy and can answer questions. It demonstrated the last of these by fielding spoken questions on astronomy, sports and films.

Zeno will be joined by a “female” counterpart called Alice in August of 2012. Neither, however, will be selling for the US$300 that Hanson had hoped for five years ago. Though no price has been set, current Hanson RoboKind robots are valued on its website at up to US$16,750. However, the company is still keen on breaking into the mass market and plans to roll out smaller, cheaper “cousins” for Zeno sometime in 2013.

Read more >

There is a huge amount of work done in this platform. Congratulations to the team. This platform brings robotics closer to the public.

iRobot and InTouch Health are working under a partnership and joint development and licensing agreement to develop the RP-VITA, which will allow doctors and other health specialists to not only visit patients remotely, but to robotically navigate through wards, access patient records and even carry out examinations.

The RP-VITA is a combination of iRobot’s Robot Ava mobile robotics platform and the InTouch Telemedicine System. This produces what the partners refer to as a an “expandable telemedicine technology platform.”

It’s controlled by a simple iPad interface and has an enhanced autonomous navigation capability. That means it can be sent where needed with a single click. Using its Obstacle Detection Obstacle Avoidance (ODOA) system, the robot can proceed to its location on its own, navigating the hospital quickly, safely and accurately.

The robot allows doctors and staff real-time access to important clinical data from the patient’s online files, but it also can transmit live information by means of its built-in electronic stethoscope or by linking to diagnostic devices such as otoscopes and ultrasound machines.

The RP-VITA is being unveiled to the public at the InTouch Health 7th Annual Clinical Innovations Forum (July 26-28, 2012) in Santa Barbara, CA.

Read more >

In fact, converting raw data into information (data in the context of other data) and hence into knowledge (information in the context of other information), is critical for understanding activities, behaviors, and in general the world we try to model. Both in the Robotics and the Computer Vision areas we try to model the real world where the humans are operating.

The type of knowledge that Robotics and Computer Vision need to obtain is Common Sense Knowledge. Contra intuitively, common sense knowledge is more difficult to model than expert knowledge, which can be quite easily modeled by expert systems (a more or less closed research area since the 70s).

Both in Robotics and Computer Vision areas, Probabilistic and Bayesian models have historically been used as the way to represent, reason and learn from the world. These methods have provided very good initial results. The problem is that they have never been scalable. That is why there is no commercial intelligent robot that has the full ability to serve people yet. Although there exist many preliminary solutions including artificial vision, the percentage of false positives or negatives are still too high to consider it as completely reliable, and therefore artificial vision is still an open research area.

The problems detected in the probabilistic approaches have been twofold:

• It is a brute force method with high computational cost.
• There is no use of common sense or any other cognitive approach to make sense of the numbers, therefore the improvements are limited.

We need “more intelligence” to be able to automate common sense.

Qualitative Representation and Reasoning, on the other hand, have been demonstrated to be a much better approach to model common sense information, by transforming  uncertainty and incomplete data into knowledge. Highly promising results have been obtained in the area of Robotics for autonomous Map Building, Localization and Navigation [1,2,3,4].

This is the approach that Cognitive Robots has followed since 1992.

20 years of research (at the University Jaume I, Spain) and development are now included in the most advanced intelligent system that can be incorporated into physical and virtual devices to increase their intelligent, in an immense variety of applications.

Cognitive Robots is now actively looking for commercial partnerships and investment capital to bring the company into the next level. If you are interested, please contact investors@c-robots.com.

References

1. Escrig, M.T., Peris, J.C, “The use of a reasoning process to solve the almost SLAM problem at the Robocup legged league”, Catalonian Conference on Artificial Intelligence, CCIA’05, 2005.

2. Peris, J.C, Escrig, M.T., “Cognitive Maps for mobile Robot Navigation: A Hybrid Representation Using Reference Systems”, 19th International Workshop on Qualitative Reasoning, Graz, Austria, pp. 179-185, ISBN 3-9502019-0-4, Graz, Austria, 2005.

3. Cognitive Robots S.L., USA pendent patent: “SYSTEMS AND METHODS FOR ESTABLISHING AN ENVIRONMENTAL REPRESENTATION”, October 2010.

4. Z. Falomir, Ll. Museros, L. Gonzalez-Abril, M.T. Escrig, J.A. Ortega, “A model for the qualitative description of images based on visual and spatial features”, Computer Vision and Image Understanding 116, 698–714, 2012.

by Jill Krasny  Jul. 20, 2012

AndyVision Future of Retail Project at Carnegie Mellon University. This project involves in-store digital signage for customers to browse the store’s 3D planograms, as well as an autonomous store-operations robot to assist in inventory management, including out-of-stock detection.

AndyVision manages inventory, but his influence might go farther than that, reports Motherboard’s Adam Clark Estes. Researchers say the lightweight, red-hoodied robot was built to “transform the shopping experience.”

Here, Estes explains how the “mechanized messenger” works:

“With the help of a video camera and an onboard computer that combines image-processing with machine learning algorithms, it can patrol the aisles counting stock and scanning for misplaced items … The data from the inventory scans are all sent to a large touchscreen, where customers can browse through what’s available in the store.”

By Sebastian Anthony on July 13, 2012

Mechanical engineers and roboticists working at MIT have developed an intelligent automobile co-pilot that sits in the background and only interferes if you’re about to have an accident. If you fall asleep, for example, the co-pilot activates and keeps you on the road until you wake up again.

Like other autonomous and semi-autonomous solutions, the MIT co-pilot [research paper] uses an on-board camera and laser rangefinder to identify obstacles. These obstacles are then combined with various data points — such as the driver’s performance, and the car’s speed, stability, and physical characteristics — to create constraints. The co-pilot stays completely silent unless you come close to breaking one of these constraints — which might be as simple as a car in front braking quickly, or as complex as taking a corner too quickly. When this happens, a ton of robotics under the hood take over, only passing back control to the driver when the car is safe.

Read more >

In this brilliant TED talk, Kiva‘s CEO, Mick Mountz, explains how they revolutionized the way warehouses pack and ship their inventory by using robots, mobile shelving, and algorithms based on complexity theory. What used to take hours of tedious tasks is transformed into fun, 15-minute, click-to-ship order processing.

Kiva’s CEO, Mick Mountz, had a front row seat when internet pioneer Weban failed to deliver online fulfillment services in a cost effective manner.

The system is absolutely brilliant and effective. That is a very good reason for Kiva System being acquired by Amazon for $775 M.

Can you imagine how it could be if the robots would not need to have wires to direct their trajectory under the floor? That is the next step for automation which will require intelligence.

Comments:

by Dan Kara (LinkedIn): Robotics Trends International Network

Kiva Acquisition Has Huge Implications for Businesses and Society

Teresa, I analyzed the Kiva purchase for Robotics Business Review (www.roboticsbusinessreview.com). It is important to note that Kiva Systems is not the only robotics company that Amazon CEO Jeff Bezos has exhibited interest in. Bezos Expeditions, the firm that manages the personal investments of Bezos, participated in equity rounds for Rethink Robotics (formally Heartland Robotics), the Boston based start-up founded by Rod Brooks, noted roboticist and co-founder of iRobot. Rethink, I believe, is developing a class of low cost, dexterous robotic systems capable of working directly with humans.

For all of the billions that Amazon has invested in automating its fulfillment processes, it is still dependent on large numbers of people to get the job done. The Kiva system succeeds largely because it reduces the number of humans that must traverse the distribution center collecting products to ship. But what if the model was extended even further, to include the humans who actually “pick” individual items out of the robotically delivered storage containers? In theory, a dexterous robotic system capable of fine manipulation and using vision in combination with touch sensors (much like its human “picker” counterpart) could perform the last, unautomated leg of the Kiva fulfillment process.

Kiva MPS represents a paradigm shift in the way in which ecommerce companies go about fulfilling orders. The long term ramifications of the purchase are not clear, but in the end Amazon could become an architecture provider for ebusiness order fulfillment (own the architecture, win the war). It could also develop fulfillment and distribution centers that for all purposes contain no people. Furthermore, it would make the holy grail of “same day shipping” possible. That’s more than a paradigm shift, it is a seismic change and one with profound implications for businesses and society.

by Thomas Ciesielka (LinkedIn): Robotics Trends International Network

Dan, You are spot on. Robotics, in this configuration, will lead the way for economic revitalization and evolution. Combining it with a “cognitive brain” that Teresa has championed, is the future.

With the ultimate goal of designing completely autonomous robots that can navigate and map cloudy underwater environments without any prior knowledge of the environment and detect mines as small as 10 cm in diameter, researchers at HoverGroup (MIT) have came up with algorithms to program a robot called the Hovering Autonomous Underwater Vehicle (HAUV).

To provide a detailed sweep of a ship’s hull, the researchers took a two-stage approach. Firstly, the robot is programmed to swim in a square around the ship’s hull at a safe distance of 10 meters (33 ft), using its sonar camera to gather data that is used to produce a grainy point cloud. Although a ship’s large propeller can be identified at this low resolution, it isn’t detailed enough to make out a small mine.

Additionally, the point cloud may not necessarily tell the robot where a ship’s structure begins and ends – a problem if it wants to avoid colliding with a ship’s propellers. To generate a three-dimensional, “watertight” mesh model of the ship, the researchers translated this point cloud into a solid structure by adapting computer-graphics algorithms to the sonar data.

Once the robot has a solid structure to work with, the robot moves onto the second stage. This sees the robot programmed to swim closer to the ship, with the idea of covering every point in the mesh at spaces of 10 centimeters apart.

Read more >

US Navy is also developing autonomous underwater hull-cleaning robots. The Robotic Hull Bio-inspired Underwater Grooming tool, or Hull BUG, is being developed by the US Office of Naval Research (ONR) and SeaRobotics.

The Hull BUG has four wheels, and attaches itself to the underside of ships using a negative pressure device that creates a vortex between the BUG and the hull. Much like a robotic vacuum cleaner, lawnmower or floor cleaner, the idea is that once it’s put in place, it can set about getting the job done without any outside control.

Onboard sensors allow it to steer around obstacles, and a fluorometer lets it detect biofilm, the goop in which barnacles and other greeblies settle. Once it detects biofilm, powerful brushes on its underside are activated, and the film is scrubbed off. In this way, it is intended more for the prevention of barnacles, than for their removal. Initial tests have shown it to be very effective.

Read more >

Whatch this TED talk where Chris Gerdes (Director, Center for Automotive Research at Stanford (CARS)) reveals how he and his team are developing robotic race cars that can drive at 150 mph while avoiding every possible accident. And yet, in studying the brainwaves of professional racing drivers, Gerdes says he has gained a new appreciation for the instincts of professional drivers.

Instincts as well as common sense knowledge have always been the most difficult knowledge to capture by Artificial Intelligence. That has been the job of the team of  Cognitive Robots for over 20 years. The results are included in its Cognitive Brain for Service Robotics, which is able to capture commonsense knowledge by qualitative representation and reasoning.

The global service robotics market in 2011 was worth $18.38 billion. This market is valued at $20.73 billion in 2012 and expected to reach $46.18 billion by 2017 at an estimated CAGR of 17.4% from 2012 to 2017.

The market is driven by factors like:

• Ageing population,
• Value enhancement by robots,
• Increasing grants and funds by governments,
• Increasing venture capital investments in service robotics companies,
• Enhancements in complementary technologies and
• Integration of robotics with mobile technologies, other smart products, and appliances.

The key market players in service robotics industry are:

• HONDA MOTORS (Japan)
• IRobot (USA)
• AB Electrolux (Sweden)
• SONY (Japan)
• Fujitsu (Japan)
• Toyota (Japan)
• Yujin Robot (South Korea)

You can find the full service robotics market research report in the next link. It is not free, but we can already see very important information here.

Read more >

Look at this video of Skippy, an internet-controlled robot that skips stones across a pond.

Read more >

The machine comprises simplified versions of the human neural, musculoskeletal and sensory feedback systems.

The robotic legs are unique in that they are controlled by a crude equivalent of the central pattern generator (CPG) – a neural network located in the spinal cord at the abdominal level and responsible for generating rhythmic muscle signals. These signals are modulated by the CPG as it gathers information from different body parts responding to external stimuli. As a result, we are able to walk without ever giving the activity much thought.

The most basic form of a CPG is called a half center and is made up of two neurons rhythmically alternating in producing a signal. An artificial version of a half center produces signals and gathers feedback from sensors in the robotic limbs, such as load sensors that notice when the angle of the walking surface has shifted.

Read more >

Amazon’s enormous, automated and well-organized warehouses are the stuff of legend, as are their path-breaking joint ventures with vendors, repair operations and UPS shipping. Still, physical order fulfillment reportedly costs nearly 9 percent of their $40 billion in global revenues.

Amazon was amongst the first to build data centers at Cloud scale – a scale that Google engineers labeled “warehouse scale computing.”   But to disrupt traditional retail Amazon had to do more than create a customer-friendly Web interface for their warehouse-scale computers.  They had to solve the old-fashioned physical warehouse problem in order to distribute the objects they sold.

Enter Kiva’s robots, and their inevitable progeny; the logical connection between the cyber and physical worlds. Think of Kiva bots as the hands and feet of the Cloud. They are not autonomous Star-Trek-like agents, but are wirelessly connected to and controlled by the Cloud in real-time.

When you tap “place your order” on your iPad’s touch-screen you are literally reaching through the Cloud to become one with Kiva to grab a box in the warehouse. Such robots are practical today because of a confluence of enabling technologies; cheap and powerful processing and communications, advanced electro-motive power, and clever software. All this is the domain of computing and square in Amazon’s wheelhouse.

Amazon needs to own Kiva for the same reason they own computing.

Read more >

Amazon

Read more >

The entire process will be executed completely autonomously, managed not by human intervention.

The technology behind the landing is an interplay of hardware and software. On the software side, the computer algorithms that guide each part of the craft can be tested from Earth, simulations can be run, and new software updates can be installed – the final stable version was uploaded in the last few days of May.

Testing the hardware was not nearly as easy, since the right conditions can’t be recreated on Earth…

Read more >

The future of robotics goes totally towards the incorporation of more intelligence.
Intelligence includes, among other things, perception (interpreting the environment and extracting the most relevant information from it), reasoning (inferring new knowledge from the one we perceive, i.e. if we know that A implies B, and B implies C, then we can infer that A implies C); learning (as many people have pointed out in this thread already); and decision making to implement solutions to particular applications (such as security, companion, tele-presence robots, autonomous scrubber machines, vacuum cleaners, etc).

At Cognitive Robots, we have developed the first embryonic brain called “Cognitive Brain for Service Robotics” -CR-B100-, which integrates all these four aspects, in a patent pending software.
We have tested the “brain” in several “bodies” with great results.

Please, check this post (http://wp.me/p2hKFw-8U) for more information.

We are actively looking for partnerships and investment capital to bring our company Cognitive Robots to the next level.
If you know some visionary mind with capital to invest, please, pass the person my email: mtescrig@c-robots.com

By Frank Tobe May 1, 2012.

“Pure play” is an investment term that refers to a company which is exclusively focused on a particular product or service. An investor buys stock in pure play companies in order to obtain a market share in the industry as well as in the company. Robotics, to many, are just a tool to accomplish business tasks in an efficient way. To me, making robots to achieve those goals is an industry in itself and deserving of consideration for investment because of good prospects for the future. Hence the need to find pure play companies in the industry.

For example, iRobot (IRBT:US) and KUKA (KU2:GR) are pure plays while Boeing (BA:US) and John Deere (DE:US) are not; yet all four companies are involved with robotics. In the case of Boeing and John Deere, robotics is not their primary business and represents just a tiny fraction of their operating profits. Boeing designs and manufactures UAV’s for defense agencies and John Deere produces a line of AGV’s including a new robotic lawn mower, and also provides autonomous navigation modules for tractors; but neither is truly a robotics company.

Consequently, if you believe that the robotics industry is ready for you to invest in, you wouldn’t purchase either Boeing or John Deere — they aren’t representative of the industry and their stocks move to the beat of a different drummer than robotics. Instead, you would pick from a list of pure play robotic stocks (if such a list existed).

Read more >

Researchers at Georgia Tech’s Center for Music Technology have developed a one-foot-tall (30 cm) smartphone-enabled robot called Shimi, which they describe as an interactive “musical buddy.”

Shime is going to be unveiled tomorrow (June the 28th 2012) at the Google I/O conference in San Francisco.

Shimi can analyze a beat clapped by a user and scan the phone’s musical library to play the song that best matches the rhythm and tempo. The robot will then dance, tapping its foot and moving its head in time with the beat. With the speakers positioned as Shimi’s ears, the robot can also use the connected phone’s camera and face-detection software to move its head so that the sound follows the listener around the room.

Future apps in the works will allow users to shake their head when they don’t like the currently playing song and tell Shimi to skip to the next track with a wave of a hand. Again, these gestures are picked up using the phone’s built in camera. Shimi will also be able to recommend new music based on the user’s song choices.

Shimi was created by Professor Gil Weinberg, director of Georgia Tech’s Center for Music Technology, who hopes third party developers will get on board to expand Shimi’s capabilities further by creating their own apps. He developed the robot in collaboration with Professor Guy Hoffmann from MIT’s Media Lab and IDC in Israel, entrepreneur Ian Campbell and robot designer Roberto Aimi.

“We’ve packed a lot of exciting robotics technology into Shimi,” says Weinberg. “Shimi is actually the product of nearly a decade of musical robotics research.”

Read more >

However, when the driving process requires less of our active attention, it becomes boring to just observe how the semi-autonomous device is operating our car.

Self-driving features are moving from concept vehicles to the production line. The 2013 models of the Cadillac XTS and ATS sedans will include a Driver Assist Package, which includes features such as full-speed range adaptive cruise control and automatic emergency braking.

“Driver assist features such as adaptive cruise control and automatic emergency braking are paving the way to self-driving automobiles,” says Salinger. “Some things are coming out this year that are basically the precursors to allowing cars to drive themselves.” These technologies focus on safety features, warning systems and crash avoidance and are the stepping stones that will allow future cars to drive autonomously.

Read more >

Marina Gorbis is the Executive Director of Institute for the Future.

Marina’s biography – During her tenture at IFTF, and previously with SRI International, Marina has worked with hundreds of organizations in business, education, government, and philanthropy, bringing a future perspective to improve innovation capacity, develop strategies, and design new products and services. A native of Odessa, Ukraine, Marina is particularly suited to see things from a global perspective. She has worked all over the world and feels equally at home in Silicon Valley, Europe, India, or Kazakhstan. Before becoming IFTF’s Executive Director in 2006, Marina created the Global Innovation Forum, a project comparing innovation strategies in different regions, and she founded Global Ethnographic Network (GEN), a multi-year ethnographic research program aimed at understanding daily lives of people in Brazil, Russia, India, China, and Silicon Valley. She also led IFTF’s Technology Horizons Program, focusing on interaction between technology and social organizations. She has been a guest blogger on BoingBoing.net and writes for IFTF and major media outlets. She is a frequent speaker on future organizational, technology, and social issues. Marina holds a Master’s Degree from the Graduate School of Public Policy at UC Berkeley.

Sewing is a very complex task. I would love to know how they are going to do it!

Read more >

With remote control of rovers on Mars out of the question due to radio signals taking up to 40 minutes to make the round trip to and from the Red Planet, the European Space Agency (ESA) has developed a vehicle that is able to carry out instructions fully autonomously.

With Mars lacking any GPS satellites to help with navigation, the rover must determine how far it has moved relative to its starting point. However, as ESA’s Gianfranco Visentin points out, any errors in this “dead reckoning” method can “build up into risky uncertainties.”

To minimize any uncertainties, the team sought to fix the rover’s position on a map to an accuracy of one meter (3.28 ft). To build a 3D map of its surroundings, assess how far it had traveled and plan the most efficient route to avoid obstacles, Seeker relied on its stereo vision.

“We managed 5.1 km (3.16 miles), somewhat short of our 6 km goal, but an excellent result considering the variety of terrain crossed, changes in lighting conditions experienced and most of all this was ESA’s first large-scale rover test – though definitely not our last.”

“The difficulty comes with follow-on missions, which will require daily traverses of five to ten times longer,” he says. “With longer journeys, the rover progressively loses sense of where it is.”

Read more >

Intelligence includes, among other things, perception (interpreting the environment and extracting the most relevant information from it), reasoning (inferring new knowledge from the one we perceive, i.e. if we know that A implies B, and B implies C, then we can infer that A implies C), learning (as many people have pointed out in this thread already) and decision making to implement solutions to particular applications (such as security, companion, tele-presence robots, autonomous scrubber machines, vacuum cleaners, etc).

At Cognitive Robots, we have developed the first embryonic brain called “Cognitive Brain for Service Robotics” -CR-B100-, which integrates all these four aspects, in a patent pending software.

We have tested the “brain” in several “bodies” with excellent results.

Please, check this post for more information.

We are actively looking for partnerships and investment capital to bring our company Cognitive Robots to the next level.

If you know of a visionary mind with capital to invest, please, pass that person my email: mtescrig@c-robots.com

We are planning on going to crowdfunding resources like KickStarter and offering our own robotic platform (brain and body) for research and a smaller version for education. What are your thoughts on that?

Indego takes about 20 minutes to mow each 200 sq m – this is actually up to four times quicker than other robotic mowers, claims the company. Every 20 minutes the robotic mower needs to recharge the battery. It is able to find that charger on its own, and takes 90 minutes to fully recharge.

It mows in orderly sequential rows. By contrast, some other robotic mowers move more or less randomly all over the place, the idea being that they’ll eventually get the whole lawn done. It is also able to sense obstacles or “no-mow” surfaces such as gravel, and automatically figures out how to adjust its mowing pattern in order to avoid those. Certain other mowers must be programmed with the location of such areas, or require them to be cordoned off with wire.

So far, it appears that the mower is only available in Sweden and other parts of Scandinavia, although presumably a wider release is in the works. Its suggested retail price is 14,995 Krona (US$2,121).

Read more >

The intent behind the improvement of the Kompai platform is to better serve the users – the elderly.

We have identified 3 aspects of the Kompai’s functionality to be improved in this project:

• Autonomous MAP creation was the first aspect identified to improve. Previously when a new user purchased a Kompai and it arrived to its new home, a Robosoft technician needed to spend an entire day creating the map for Kompai. No furniture could be moved in the house without the technician spending another day for the robot to re-learn the map.

• The second thing to improve was decision making. Kompai wasn’t making any decisions by itself, the user pressed buttons on the GUI screen or gave verbal orders to ask the robot to act. The robot was not pro-active.

• And third, we added cleaning functionality to the robot as a plus for the elderly.

The most significant visual changes in the Kompai platform have been the addition of three buttons in the  Kompai’s GUI screen (MAP, CLEAN, and BEHAVIOUR) (Figure 1) and the incorporation of the vacuum cleaner device at the bottom of Kompai and the 3D Kinect sensor (in the front of the Kompai) (Figure 2).

Figure 1. a) Kompai’s original GUI; b) Extended functionalities provided by C-Brain for the project.

Figure 2. New hardware features added to the Kompai platform for the project: the vacuum cleaner and the 3D Kinect sensor.

We are almost at the end of the project. The software development from C-Robots is basically finished. The benefits of incorporating the Cognitive Brain for Service Robotics ® – CR-B100  from Cognitive Robots into Robosoft’s Kompai platform are the following:

1-  Autonomous map creation (Figure 1 b). With the C-Brain, the Kompai will create the new map by itself, not only the first time it arrives to a new home, but every single time the owner changes the layout of the home – without the need to call a technician again.

2-  Obstacle avoidance in 3D. Before the incorporation of C-Brain, the Kompai was only able to perceive a line in the environment at the height of the laser sensor, which was very dangerous in a home environment, with a lot of obstacles at different heights. Thanks to the incorporation of the Kinect sensor, Kompai is able to perceive obstacles in 3D around the home.

3-  Landmark perception/detection. Both with the laser and the Kinect sensors, the distances collected from these sensors are processed to extract the most significant landmarks of the environment (qualitative information), which will allow the robot to reason and make decisions. This is part of the patent pending, proprietary software of the “Cognitive Brain for Service Robotics” from Cognitive Robots.

4-  The navigation system by Robosoft has been substituted by a more sophisticated one, which applies the ‘landmark perception/detection system’ (above) allowing the robot to reason and make further decisions.

5-  Vacuum cleaning algorithms using the ‘landmark detection system’ allows the robot to know what it has done and what still needs to be done.

6-  Decision making. Before the incorporation of C-Brain, Kompai has been a static robotic platform waiting for a ‘call to action’ by the user. With the incorporation of C-Brain, Kompai will be proactive and will start actions by itself to engage the user.

We are now working towards the final demonstration of the project in France in July.

Cognitive Robots will be in France next week (11-15 of June).

We will be uploading videos soon.

Researchers from RMIT in Melbourne, Australia have developed a flying running companion called Joggobot. The system uses the built-in camera on a commercially-available Parrot AR Drone quadrocopter to track the position of a jogger, and fly a few feet out in front. While the current version has some serious limitations, there is huge potential for the development of a fully interactive training partner or coach in the very near future.

Read more >

Robots can work in a macro-scale as well as in a micro-scale.

Published on May 23, 2012 by mashable

The Georgia Tech Research Institute’s (GTRI) has developed an Intelligent Cutting and Deboning System. Using 3D imaging technology, this robot can debone an entire chicken with the skill of a human butcher and has the potential of saving the poultry industry millions of dollars by reducing costs and waste.

No very idyllic, but very practical.

Read more >

A new trend has emerged in the past few years and has led to the development of technologies like Siri, iPhone’s “personal assistant.” It entails using mathematical tools, namely probability and statistics, to try and model how people use language to communicate in social situations. The work at Stanford builds directly on this branch of research.

Although statistics provide an initial solution to problems, in my opinion it is very primitive and has considerable limitations. It uses the brute force of the computer and no cognition. Other techniques, like qualitative models, have been demonstrated to be much more useful for extracting relevant information from any system, and then processing that information to make decisions. That is the technology being used in the “Cognitive Brain for Service Robotics (R)” of Cognitive Robots. You can find a link to my book that explains the basics here.

Our Cognitive Brain incorporates four aspects of human intelligence: perception (object recognition), reasoning, learning and decision-making. This advanced level of artificial intelligence enables adaptation when uncertainty and unknown situations occur.

We’re actively seeking technical partnerships and investment capital.

Here you can see our corporate video:

Current accomplishments and activities of Cognitive Robots include:

• CR-B100 has been adapted to commercial floor scrubbers (beta state).
• CR-B100 has been fully incorporated into a Pioneer (Adept) research platform to prove out the full capabilities of the brain.
• CR-B100 is currently being incorporated into Robosoft’s companion robot Kompai to enhance the Kompai’s capabilities with intelligence. This allows it to perceive the landmarks in the environment, automatically create its own map, avoid obstacles in 3D, clean the home intelligently, and make decisions to engage the elderly.
• Cognitive Robots is about to launch its own Service Robotics platform using the CR-B100.
• Another product of Cognitive Robots, the CR-B50 – Manual Assisted Driver- has been successfully incorporated into commercial forklifts, to increase security.
• CR-B50 is now being incorporated into commercial buses.

The World Economic Forum‘s (WEF’s) Global Agenda Council on Emerging Technologies has compiled a list of the top 10 emerging technologies it believes will have the greatest impact on the state of the world in 2012, in order from lowest to highest in terms of the potential to provide solutions to global challenges.

1. Informatics for adding value to information
2. Synthetic biology and metabolic engineering
3. Green Revolution 2.0 – technologies for increased food and biomass
4. Nanoscale design of materials
5. Systems biology and computational modelling/simulation of chemical and biological systems
6. Utilization of carbon dioxide as a resource
7. Wireless power
8. High energy density power systems
9. Personalized medicine, nutrition and disease prevention
10. Enhanced education technology

Read more>

Part-funded by the European Commission, SARTRE is a joint venture between Ricardo UK Ltd, Applus Idiada, Robotiker, Institut für Kraftfahrzeuge Aachen (IKA), SP Technical Research Institute, Volvo Technology and Volvo Car Corporation. It works by using a high-tech suite of cameras, radar and laser sensors to enable a wirelessly linked “platoon” of cars to travel autonomously in a road train behind a lead vehicle operated by a professional driver.

The project started in 2009 and the technology was successfully demonstrated at the Volvo Proving Ground near Gothenburg, Sweden, back in 2010. In the latest milestone, the SARTRE platoon took to the motorways of Spain amidst other road users in a journey that saw a Volvo XC60, a Volvo V60, a Volvo S60 and one truck drive automatically behind the lead vehicle at 85 km/h (53 mph) separated by a distance of as little as five meters (16.4 feet). Using Ricardo’s autonomous control system, each of the vehicles was able to accelerate, brake and turn in exactly the same fashion as the lead vehicle.

“People think that autonomous driving is science fiction, but the fact is that the technology is already here,” says Linda Wahlström, project manager for the SARTRE project at Volvo Car Corporation.

Read more >

“It detects objects and people who move within the visual field that a person with no visual pathologies would have,” said Professor Vergaz, leader of the research team who has developed the “intelligent” goggles. “Very often the patient does not detect them due to problems of contrast. The information regarding depth is what is most missed by patients who use this type of technical aid.”

Read more >

Humantenna uses the human body as an antenna to pick up the electromagnetic fields — generated by power lines and electrical appliances — found in indoor and outdoor spaces. Users wear a device that measures the signals picked up by the body and transmits them wirelessly to a computer. By studying how the signal changes as users move through the electromagnetic fields, the team was able to program the system to identify 12 gestures, such as a punching motion or a swipe of the hand, with more than 90 percent accuracy.

Humantenna requires users to wear a sensor. They are still working in its robustness.

SoundWave relies on an inaudible tone generated by a laptop’s loudspeaker. When a hand moves in front of the laptop, it changes the frequency of the tone, which the computer’s microphone picks up. By matching characteristic frequency changes with specific hand movements, SoundWave can detect certain gestures with an accuracy of 90 percent or more, even in noisy environments such as a cafeteria.

Human-[robot/computer/machine] interaction can get huge benefits from these two new sensors.

Read More >

While Robonaut 2 has been busy testing its technology in microgravity aboard the International Space Station, NASA and General Motors have been working together on the ground to find new ways those technologiescan be used.

The two groups began working together in 2007 on Robonaut 2, or R2, which in 2011 became the first humanoid robot in space. NASA and GM now are developing a robotic glove that auto workers and astronauts can wear to perform their respective jobs, while reducing the risk of repetitive stress injuries. Officially, it’s called the Human Grasp Assist device, but generally it’s called the K-Glove or Robo-Glove.

In this image, Robonaut and a spacesuit-gloved hand are extended toward each other to demonstrate the collaboration between robots and humans in space.

Image Credit: NASA

How this robotic glove can be used for other apps?

Is it a threat to Roomba?

By Sarah Berlow, May 8, 2012.

Cocorobo’s many gadgets make iRobot’s popular Roomba look like it should be sold alongside Easy Bake ovens. Voice recognition technology enables Cocorobo’s vacuum to respond to greetings or commands — in multiple languages or dialects.  (So far, though, its vocabulary is limited to about 30 phrases, such as “I understand.”)

Cocorobo dances around in reply to commands, resembling the Jetson housekeeper’s friendly compliance. A camera also enables Cocorobo to watch the pet left at home, sending photos via cloud technology to the owner’s iPhone or other smartphone. It can vacuum for up to an hour before requiring a recharge. It does so by linking itself at a port, and has a USB port installed in the vacuum to download updates, such as an expanded vocabulary.

With so much technology heaped onto it, Cocorobo’s vacuuming capability seems almost an afterthought, though Sharp claims it also has an extra-powerful vacuuming system.

Read more >

I was thinking that Google couldn’t change or improve because it was so big, well-established and essentially a monopoly. Perhaps it still can offer new solutions…

by Laurie Sullivan, Thursday, May 17, 2012

Google began rolling out a feature that gives searchers in the United States the potential to access more relevant and in-depth responses to answers without leaving the page. The concept is built on something the company calls “knowledge graph,” which ties together words to create relationships.

There are a multitude of sources behind this data. The search results page displays a variety of content related to keyword queries, bringing up a list of facts, photos, and landmarks, as well as quick links to other popular uses for the search term. Think of a Web beneath the user interface layer of the Internet that ties together all information across the Web.

Rob Garner, vice president of strategy at agency iCrossing, said Google’s knowledge graph takes another step in the company’s long transition to develop an artificial intelligence engine — semantic search. “It’s something Google’s doing in parallel to Schema.org in terms of relating object, places and people,” he said. “Looking at the schema for a person you can actually define the relationship with other people using schema vocabulary.”

For example, someone looking for information on Marie Curie will see her birth and death dates, but also details on her education and scientific discoveries. The search engine understands much more…

Read more >

• It flies vertically and horizontally, like a humming-bird.
• It’s unmanned.
• It can land in any attitude because it’s round
• It can also move along the ground
• It can fly 8 minutes continuously, from 0 to 60 Km/h
• It was build from commercially available parts with a total cost of $1400 USD
• Applications: rescue and recognizance

Source
Spherical Flying Machine – Watch More Funny Videos

Dear Teresa, My name is Paul Doyle and I am Head of Access R&D at Hereward College in Coventry. Hereward is a residential college that supports disabled students. We have for some years developed a keen interest in the use of robotics as an assistive technology.

by Panvadee (Bua) CHUASRITRAKUL (LinkedIn Group: Robotics Guru) – Agree with Craig. To have a bit of control can increase the level of safety and will make kids feel more comfortable with the feeding machine. It could be one of their buddy at school.
We could also use computer vision to recognize face, locate the mount, and also be a switch for the next feed. The machine can see when they turn their face away or lean forward to get more food. I’m not a computer vision expert, so I would like to hear from an expert whether it is practical or not.
The next questions would be what type of disability and food we are talking about here. In the email said there are a variety of physical disabilities, so it could be more types of feeding machines. If so, we can start from the easiest one or the majority type of disabilities.

by Demetrescu (LinkedIn Group: Robotics Guru) – Iulian@Panvadee there are some libraries and tools like OpenCV that can ease the burden of face recognition. More important is the communication between the disabled person and the machine. How and when one needs to be fed, how much, what happens when something goes wrong (choking,sneezing,etc).

by Panvadee (Bua) CHUASRITRAKUL (LinkedIn Group: Robotics Guru) – Thanks for your response, Demetrescu. I heard about OpenCV. Sorry I was not clear about my question. Is the computer vision practical/possible in this application in term of processing capacity and respond time (how fast the machine can react from what it see). We would not want to put a super computer in every feeding machine.
The communication between the user and the feeding machine and how we gonna feed them bring us back to the question “what type of disabilities and what type of food we want to work on here”. I think the machine should be able to recognize when someone is choking or sneezing (capture quick movement for example), and may need to let the carer know when there is a problem. The carer should be able to observe around the room and see when there is a problem while they are feeding other students or doing other tasks. By the way, I don’t want it to be too complicated now, simplest is the best. We should start from a physical switch as Craig’s suggestion together with remote and local emergency stop switches

by Demetrescu Iulian (LinkedIn Group: Robotics Guru) – So in theory we have the basic “effector”. A robotic arm coupled to a SBC. A moderate resolution camera will capture the subject reaction, eventually interaction with the subject can be provided by the means of a standard LCD panel and audio speakers, wireless or wired action switches connected to the effector SBC.
But we are a little ahead of this project. We should establish somehow a project , a website, some hardware requirements, etc in order to proceed further.

by Demetrescu Iulian (LinkedIn Group: Robotics Guru) – I propose the name “RAFE”. Stands for Robotic Aided Feeding Equipment. We can setup a website and start.

by Teresa Escrig  – Hi all, I really appreciate your contributions and enthusiasm. I asked directly to Paul Doyle, the Head of Access R&D at Hereward College in Coventry about your questions and he will respond to them. He has been out of office.  I am not going to be able to lead that web site that you are talking about, but I can certainly lead the research and provide our Cognitive Brain to the project. I can happily be an adviser, a contributor.  I would not start something unless I know that we are able to accomplish something (but that’s just me).

by Paul Doyle (LinkedIn Group: Robotics Guru) – Thank you. I am really excited to see there is so much interest in our plight. I wholly endorse the idea of a vehicle to facilitate this discussion and a project site is certainly a good idea I am not sure we have the capacity to develop such a site but am more than happy to support the the development of the project by bringing the real needs of physically disabled individuals and those who care for them to the table.
What I have suggested to Teresa is that a site amongst other uses could also serve as a means of bringing the user and the developer together, in order to best capture the needs and aspirations of young disabled people.
I stress young as so often the development of assistive technologies focus on older users,but our students will hopefully be the using a range of robotics technologies for many decades so the y have a vested interest in their development.
I think feeding is an essential activity as well as accessing hydration and these activities of daily living serve as a realistic starting point for the development of useful cost effective personal robotics. Again I emphasise cost effective as to be of practical use such technologies need to have a sound financial model underpinning their provision. Needles to say safety is at the core of the project too.
If you would like to know more about the needs of our student population please do not hesitate to contact me directly.
Lets see where this goes. Many thanks. Paul

by Paul Doyle (personal email) – Perhaps we could link our students up to the group of experts?
A virtual discussion, or even a Skype session? I think the idea of a project site would be fantastic, if students were able to use it to communicate their needs directly it would help break down some of the barriers and misconceptions that have traditionally arisen when technical experts try to visualize the issues encountered by the disabled community. Getting to know real users will help contextualize some of the issues we have raised. Kind regards, Paul

by Teresa Escrig – Paul, that would be absolutely great! It can change the way things are going in technology in many ways: first users and technicians will be closer, so we can solve what it’s really needed; and second, we might attract some investor who likes the synergy created and get funded to make it really happen.
Please, ask your students if they would like to get involved.
I will post this communication to LinkedIn and my blog.
Thanks, Teresa

by Demetrescu Iulian (LinkedIn Group: Robotics Guru) – Teresa, Thank you for the reply. I was personally interested in your opinion regarding the entire project. I agree with you that we first have to hear from Paul, the actual problem issuer if he is willing to embark in such a project. As far as i understood from the letter Paul wrote to you, we are talking mainly about children or young people, who have the greatest chance to recover from their condition. Personally i am willing to put up the website providing space, domain registration, storage, maintenance and collaboration tools in order to move this project ahead. Also i have some expertise in embedded systems, electronics design, embedded programming, skills that can be of great help in such an endeavor.
Of course we can use any resource and knowledge you can share and we could at least outline some directions and sketches before committing to something. If we can reach a theoretical model that can work, i think we can risk a PoC system that can be minimal in terms of hardware requirements but with the core features present.
If Panvadee steps in, it will be great because he has also experience in robotics and can help with the hardware part also. As a side note, I will move to Australia in the next month and i will be closer to him, so we could meet either in Sydney or Canberra in order to test and debate over hardware/software issues .
As for the accomplishment, if we understand each other, if we debate all the facets of the project and reach a conclusion, we can accomplish what we want. All we have to do is to really want to help.

by Teresa Escrig (LinkedIn Group: Robotics Guru) – @Demetresku, I really appreciate your passion and enthusiasm.
I have been directing many big projects and teams to solve real problems including cutting-edge technology, like this one. As I know what it takes to make this kind of things happen, i want to make sure we have or can have all we need to succeed, before we start to dedicate time to this project.

by Craig Hines (LinkedIn Group: Robotics Guru) – From what I can gather from the web site, Hereward College is for the 18 year old and up group (“College” has different meanings in different countries.) Disability at Hereward could mean any condition from autism, blindness, to MS or spinal injury. From my experience in customizing power chair drive and powered seating systems and electronics, disabled people come in all shapes and forms. You can’t count on their head being in centre position or even facing forwards or in an upright position in their natural relaxed state. Some conditions make people so weak it literally takes a minute for them to get their hand to push a button. Others can’t do fine movements, when they do their muscles spasm and break equipment – this condition is a permanent workout, their muscles can be surprisingly strong. Some conditions come with a childish irresponsibility, though not intellectually handicapped – the sort of person that shouldn’t have been left in charge of an automotive air horn in a supermarket (it happened!)
What I am getting at is, I think the feeder needs to be adaptable to a variety of positions and external equipment that might get in the way. It needs actuator force to be applied by spring loaded mechanisms so that a lurch forwards does no harm to the user or equipment. Each user may need their own settings, and if there are several machines, a networked profile lookup could help so that any machine can work with any user. Caregivers and teachers probably aren’t technicians, if the machine doesn’t do what they expect, it will end up in the broom cupboard. Industrial robotics these days is more user programmable. If the caregivers can train the machine by physically moving the arm and feeder mechanism they will be more confident about using it. Some users may be able to do this for themselves, so the machine simply assists them where they wouldn’t normally be able to hold their hand still enough to self feed.
On a practicality point, it seems that possibly parallel prototypes could be built in Sydney and in the UK (Coventry), maybe at a certain point a media release could drum up some funding.
It is so encouraging to see so many experts being inspired by this challenge. I don’t know if I can contribute much to the technical development, but I hope to learn from it.

by Demetrescu Iulian (LinkedIn Group: Robotics Guru) – @Craig, your experience in customization can bring a great deal of inside information in the behaviour and different needs of each case you encountered over the years. Please don’t minimize your work since, as I see it, is a valuable source of information. For the identification issue I was thinking at a comfortable wrist RF-ID tag similar to those used in some hospitals. That tag can carry patient information and also can be used in future home-friendly appliances ( intelligent house,etc), I’m dreaming yes i know…
Also a great deal of information will have to come from some specialized doctors that can give us a medical view of the problems we are facing, risks associated with each disease we are trying to manage. We have to be aware of the fact that we are ( or at least we think of) creating a complex device that will interact at an intimate level with human beings. Our conception will have to pass a huge set of safety rules and regulations due to the fact that it will be perceived as a medical equipment. We need a close relationship with the medical environment if we want to have a chance to make this work.
It’s not important where the device/devices hardware will be created. We will share the bits and pieces of hardware and software ( despite the great distance between UK and New Zealand, India, Australia,etc). We have to ask Teresa to lead the way and eventually at some point let’s have a conference over skype to set some things up.
Also we have to attract more developers and robotic technicians because ” more eyes have a bigger picture “.
In order to attract some of the funds we most probably need, we can try first at the humanitarian organizations. These associations can help us buy at least the more expensive items that for sure will not be donated. Of course at some point we can have a press conference and if we can achieve at least a limited working prototype until the next year, we can enroll a talk on TED (www.ted.com) which will for sure attract more developers and founders.

by Panvadee (Bua) CHUASRITRAKUL (LinkedIn Group: Robotics Guru) – Please count me in. My experience is around developing cost-effective robots and bespoke devices (mostly Defense projects). Having a clear scope and requirements of a product will reduce the cost from unnecessary and/or expensive solutions. One of the most important factor for a successful product is the interaction between the end users and the developers (and we will have that). If we have a limited budget, we will need to narrow the scope down and try to maintain the must functions. It does not sound great, but it is a reality. In the car industry, we have affordable car and luxury car. Same here.
I think I understand Teresa’s point. At the moment, we still have many holes in the project. I think we can start small, and I will promote this project among my connections as well. My skill set is technology integration, system design, mechatronic design, electronic and PCB design, logistic and manufacturing. I hope that I could help more or less. My next step would be to summarize the requirements from what we have so far.
@Demetrescu, I can help you with the website if you want. I’m not a programmer, but I can help with words and design (and if you need a second opinion). Good news that you are moving to Australia, how’s convenient. We can arrange a meeting when you are here. BTW, I’m a she not he.

by Panvadee (Bua) CHUASRITRAKUL (LinkedIn Group: Robotics Guru) – @Demetescu,
>>For the identification issue i was thinking at a comfortable wrist RF-ID tag similar to those used in some hospitals. That tag can carry patient information and also can be used in future home-friendly appliances ( intelligent house,etc), i’m dreaming yes i know…
No, it is real now. It has already been used in home automation. RFID solution is not expensive, we should be able to use it.

by David McMillan (LinkedIn Group: Robotics Guru) – As a professional user of heavy industrial robots, I have to confess that the idea of putting robots into direct contact with young people, especially disabled ones, makes me extremely aprehensive. Safety for a RAFE system would would be absolutely critical, but also difficult to achieve.
Some of this can be addressed at the design level, by making the manipulator low-powered and compliant (a bit like Willow Garage’s PR1), but even that has limits — a robot capable of putting a small spoonful of food into someone’s mouth is easily capable of sticking that spoon in their eye. And errors *will* happen.
In an industrial environment, general practice is for anyone working within reach of a robotic manipulator to carry a “deadman switch”. This multi-stage switch must be held partially closed (first stage) in order for the manipulator to have power. Releasing the switch or squeezing it too tightly (ie, a panic reaction) kills power to the manipulator, freezing it in place. For the proposed RAFE system, I imagine that some equivalent would be absolutely necessary, but given that we are dealing with disabled persons, and a wide variety of disabilities, creating such a safety presents a serious ergonomic challenge. This is one of those areas where the design engineers would need to work closely with the people experienced with the physical disabilities in question. For example, I’m having a very difficult time envisioning a safety-qualified “deadman” for a person whose disability leaves them only able to manipulate suck-and-puff controls. But the Hereward staff, being experienced in this area, might well be able to provide the critical insights necessary to create a functional safety interlock.
Getting the right food to the right people could also be a safety-critical item. I once was peripherally involved in a case where an elderly man whose swallow reflex was impaired after a severe stroke was accidentally fed something other than thin, clear fluids, and who developed severed respiratory complications as a result, which probably hastened his eventual demise. This is another area where the Hereward staff would bring absolutely critical knowledge to the endevour.

by Paul Doyle (LinkedIn Group: Robotics Guru) – David, I agree safety should be at the heart of the project. Managing risk is something we all do on a daily basis and this will apply to Hereward students too. The designing out of risk is an issue that the powered wheelchair industry have years of experience of but accidents still happen. You are right to point out that getting the balance right (balancing risk against benefit) is an outcome worthy of consideration.

by Paul Doyle (LinkedIn Group: Robotics Guru) – I would be interested in the safety protocols adopted during this experiment!
http://www.bbc.co.uk/news/health-18092653

by Craig Hines (LinkedIn Group: Robotics Guru) – These are definitely interesting times for emerging technologies for the disabled and the cross over with robotics and bionics. But even once this technology, and exo skeletons become more mainstream, it will be a long wait till it is affordable for most. Powered wheelchairs have been around for decades but are out of reach for many who don’t quite fit funding criteria in NZ.
Back on safety and economy. Both could be addressed to some extent by just focusing on people who can move their heads towards the spoon for the final gulp. A simple collision avoidance IR distance detector could freeze the robot arm about 30mm in front of the user’s mouth, and when their head moves back again the arm retracts for another spoonful, food ball or whatever.
Let humans handle the trickier cases.

by Demetrescu Iulian (LinkedIn Group: Robotics Guru) – From my point of view, spoons and forks are out of the question in our system. Serving liquids hot or cold from spoons can lead to unpredictable results( spills, burns, etc) if the patient moves unexpectedly and the robot arm decides to abruptly stop the move. Better go on the already paved road with a recipient and a straw. It’s already verified and works. Also the robot arm must be provided with protection against accidental collision with human body parts because the shear brute force of an uncontrolled human arm or head slaming into the robotic arm can cause severe injuries. Maybe some sort of IR proximity sensors that can trigger a swift retract of the entire robotic arm when such a human move is encountered. Since i have dealt with MS i can tell you that sometimes muscles can contract or extend uncontrollably generating hieratic movements of the limbs, head, torso, etc. For reference we can try to observe the feeding process of a small child that refuses food. His head and upper limbs move unpredictably but the person feeding the child in most cases is able to avoid any fatal collision between the feeding arm holding the spoon and the child. Then we can build avoidance patterns that can be programmed inside the AI of the robot in order for this to react when sensors are triggered.
If we are talking about solid food, here the problem is even more difficult to attack. Different diets, type of food, consistency, etc will generate a whole load of types of effectors that can grab and serve that kind of food. But if we look at the problem from another angle, we might get away with just one kind. Reverting back to the feeding process of a child, i recalled the times when my son was young and also the times when i was taking care of my Ex. In both situations the solid food was server directly with the hand in form of small portions, enough to be eaten comfortably without the risk of choking or producing injuries. I think that by creating an end effector with a general shape of human hand ( not the entire hand, just three fingers counting from the big one which are the most used) elastic enough to bend if forced gently but stiff enough to hold and direct food, can be a real success, again from my point of view. This can be unappealing to many including the patient but i think that the human hand holds the answer to this issue. It is used to feed ourselves on a daily basis from ancient times and rarely fails if handled correctly.

by Paul Doyle (LinkedIn Group: Robotics Guru) – Demetrescu, We need to be careful not to neglect the emotional needs of the individual/user in a pursuit of functionality. I say this because having worked with disabled people for some years I have found some technology is not used not because of what it does but instead of what it means. We have used the following device for many years http://www.neater.co.uk/products.htm but a lot of our students still prefer a human feeder for a host of reasons even though technically this device and others like it can enable them to feed themselves. I think there is a kind of subtle emotional transaction taking place whereby the user needs to want to sacrifice the benefits of interacting with a human carer for the ability to do something unaided. In an ideal world there would be space enough for both choices but as we are in difficult financial times and the reservoir of carers is diminishing whilst the cared for population grows this is not the case.

by Panvadee (Bua) CHUASRITRAKUL (LinkedIn Group: Robotics Guru) – Have you seen “Luke” arm?
http://www.wired.com/gadgetlab/2008/05/dean-kamens-rob/
It is a bit old, but relevant here. The test pilot and engineers look happier in the video

As we all seem to relate the solution to a feeding robotic arm, I am just curious.
@Paul, any other processes apart from feeding will be worth looking at? You wrote about asking the student what they want from the menu and bring the food from the counter. If we automated that process first, will it help a lot? I can imagine that feeding would take the longest and would be a bottle neck here, but the other processes will be easier and will take less time to develop.
We can also work with food scientists to develop a easy-feed-and-taste-good food for the machine.

by Demetrescu Iulian (LinkedIn Group: Robotics Guru) – @Paul, i would never neglect such an important issue. That is why i think it is imperative to involve the students into the development process. Any idea, even a crazy idea that can make them feel safe and confident in using this device can be adapted to our system. The student have the most crucial impact to this project. They will teach us how to help them not the other way around, us teaching them to eat or dress or use the facilities. We have to keep in mind that their main goal is not to live in a “special world” they want to live and share what we call our “normal world”. They will agree to change their food consistency to some degree but in order to be successful they have to be able to eat “normal” food as well.
Maybe the greatest idea of this project is actually the deep involvement of the students in it. We should ask them what features they want inside, we should put their minds at work in designing some or all of it. I’m sure they will com up with some idea that can be put to practice.
@Bua for sure we will ask them once we have the occasion what other processes can be robotized but Paul can give us an insight on the day by day activity in the college.

by Wolfgang Heller (LinkedIn Group: Personal Robotics) – Take a look at Bestic http://www.bestic.se/en/home/ a nice solution from Sweden. Links to other meal-assistance devices can be found at http://webbrain.com/u/135I

by Craig Hines (LinkedIn Group: Personal Robotics) – We had a speaker at a company meeting who was an ex client, power chair user with muscular dystrophy. He had to make the transition from mobility scooter to power chair, as insisted by his occupational therapist. Once he had his power chair he left it sitting in the corner for about six months. To use it, he said in afterthought, was to accept that his condition had worsened, but also, the power chair meant that he was “disabled”, unable to use his old mobility scooter. Finally, he had a crash on his scooter and was unable to raise a hand to fend off the ground and gravel or protect his head. When he finally accepted the power chair he wondered why it had taken him so long – it actually gave him more freedom and more ability.
Along the lines of what Bua said, if the arm could perform other tasks and become a personal piece of equipment rather than the shop feeder maybe it would be accepted more widely. Send txts, operate iPad for speech assistance, iArm. Probably getting too complex with this though.

by Panvadee (Bua) CHUASRITRAKUL (LinkedIn Group: Personal Robotics) – If the kids can play games, watching kid’s programs or some interaction activities while being fed, it may make them want to be fed by the machine. It would be a plus if we can add some of these functions into the machine.

by Demetrescu Iulian  (LinkedIn Group: Personal Robotics) – @Craig & Bua i couldn’t agree more. we should’t limit to the feeding exercise but expand the capabilities of the device. This is why i think it’s imperative to talk to the students. Eventually Paul can try and start some sort of brain storming with the students in order to gather some thoughts and ideas from them.
Last evening i was reviewing the entire discussion and it appears to me that the route of some impersonal cold metallic robot arm will not be so appealing to anybody. We have to think out of the box and come up with a solution. In my wildest dreams i would go as far as building something around the human body not external to it. I mean a partial exo-skeleton to smooth/enhace/correct/revive an arm for example. I know it souds SF but looking at the movies and products presented so far, the most successful solutions tend to be the direct replacement foR the missing limbs with their robotic counterpart. If we can conceive and exo skeleton capable of controlling the student’s arm, for example, i think we can have a lower rejection figure from the ancients. This is not so far from the original idea but it’s another angle of approaching the problem. If we go this way the students will be able to feed themselves, and do many other things they couldn’t do until now.

by Demetrescu Iulian (LinkedIn Group: Personal Robotics) – @Bua, my thought was more on the line of an exo skeleton like http://www.theverge.com/2012/5/9/3008979/paralyzed-woman-bionic-suit-marathon
but designed to be concealed under the clothes. Very light builds from aluminum with carbon fiber, maybe using muscle wire, that was the idea…

by Panvadee (Bua) CHUASRITRAKUL (LinkedIn Group: Personal Robotics) – The video showed that the students want a personal robot (RoboBuddy) rather than just a feeding machine; however, to come up with all of those requirements in one go would take us forever. In my opinion, we should separate those requirements into sub-systems; for example, AI module, robotic arm (manual), vision system (integrated with other sub-systems to create a smart system), physical movement (including exo skeleton), Speech assistance, etc. Targeting a shorter goal and creating a usable equipment as soon as possible will bring the advantage to both the students and our group. The student will have a reliable user-friendly equipment for the most needed task sooner, while we will have some success to attract more people to get involved.
Our group is still too small comparing to the tasks ahead. First of all, I think we should help Teresa promoting this campaign. She prefers to use Tweeter. I will start from getting a Tweeter account and help re-tweet hers. Secondly, I want to finalize the requirements and get the specification for the first device which has a possibility to have a prototype within a couple years. We can start with a device that involve only one sub-system or two and add it up step by step; for example, a robotic arm (just feeding or pick up things) with AI module or a speech help with AI module. At the end of the day, we will have to consider developing a device that suite the team’s skills and budget as well. Then, I would like to hear from the group what do you think we should develop for the first step, based on students’ needs and your skills. In the future, if we can get other companies or people to help out, we would have many sub-systems developing at the same time.
I am a system (mechatronic) engineer. This is what I do; develop requirements, create the product specs, benchmark, choose to develop in house or using off-the-shelf technologies, design the whole system (hardware and software) with the team, assign tasks, design E&E system, design electromechanical system, system integration, electronic design, building prototype and test, engineering commercialization and manufacturing. I can help designing a robotic arm, vehicle, or a device, and basically anything but the high level programming (I know how it work. I can edit and understand the code, but I have never written the code myself). I usually do C in micro-controller. If we have something solid, I can also talk to my employer about this project. They are a bunch of investors.

by Teresa – @Bua, your way of approaching the project is the one that makes more sense.
I know we want to help, therefore the effort, the goals and the resources (both human and financial) need to be in place to succeed. Being backed up by investors would help a lot Bua!
The solution the students were talking about in the video is very challenging for the current state of robotics nowadays.
The questions were very vague to make sure that if we provide something similar to what they are asking, they are not going to get bored very easily. The survey was a starting point, but in my opinion, not enough to justify the project yet.
Let’s continue working, talking and getting clearer.
MIT researchers have created a robotic elephant trunk that could be useful to pick up things from the floor: http://www.gizmag.com/universal-jamming-gripper-trunkbot/22610/

by Panvadee (Bua) CHUASRITRAKUL (LinkedIn Group: Personal Robotics) – Below is my draft requirements for the first version robot. From this requirements, we will do the brainstorming, to collect possible solutions, to create the specification (product’s requirements in details) and then we will have a product concept and proposal to ask for funding. As always, I am open for feedback and opinions.

RAFE V1 (Robotic Aided Feeding Equipment version 1) Requirements Summary:
[We need a new name because now the aim is not just feeding]

1. An equipment/machine that help users with disabilities (age 18+) to be able to feed themselves and help pick up a small thing from the floor or on the shelf as closest as the majority of people can do. The users can be: any wheelchair users with various physical disabilities except vision impairment; must not be a person with cognitive/emotional issues, refers to medical personnel.
2. User interface should be vary depends on the users’ abilities. There are two groups of users: (1) users with muscle-control difficulty and (2) users without muscle-control difficulty.
3. The machine should be able to interact with users while feeding them. In another word, the machine has to make the user feel that they are not alone or forget that they are alone.
4. The machine needs to look friendly and to make users feel safe and comfortable around it.
5. The machine has to be extremely safe and robust for the users. For example; it has to be soft-touch and able to handle an unexpected force. [need more details]
6. The machine has to be cost effective and reasonably comparable with the stuff rate [required stuff rate and number of students per staff], may be a break-even within .. years.
7. The machine has to be easy to operate and to perform minor-maintenance by non-technical staff.

In Silicon Valley (SRI), the most effective, least invasive surgical treatment option available today was created.

You might be interested to learn that:

• Of $29 billion of venture capital raised by companies in 2011, only about $160 million went to robotics companies.

• There are currently 17 million robots at large in the world. At the current rate, the number of robots doubles approximately every 2.5 years.

• About 80 robotics companies have been tracked in Boston compared with fewer than 40 in Silicon Valley.

• In March, Amazon.com acquired Kiva for $775 million and plans to use its system to overhaul the online retail giant’s order fulfillment centers. Kiva started in Silicon Valley but moved to the Boston area where the investors were ready.

• The USA east coast has natural assets like the Massachusetts Institute of Technology, which churns out leading robotics graduates. And several years ago, people in the robotics industry began to gather on a regular basis, holding regular robotics summits, educating VCs, lobbying state legislatures for research grant funding and educational funding. That was key in their leadership.

By Chris O:Brien, Mercury News Columnist, Posted:   05/05/2012 03:00:00 PM PDT

Attention, Silicon Valley: We are losing the robot war!

Not the apocalyptic one where robots rise up and enslave humans or wipe us out or turn us into cute pets. As far as I can tell, that one hasn’t started. Yet.

No, I’m talking about the battle to be the world’s capital of the emerging robotics industry. On Thursday, I attended a forum at SRI in Menlo Park called “The Future of Robotics in Silicon Valley and Beyond.” Given the growing chatter I hear, I assumed Silicon Valley was leading the robotics revolution as it does in, well, just about every other area of technology. I know that sounds like I’m being a valley snob, but it does have the merit of usually being true.

Usually, but not in this case. The robotics forum delivered a sobering message: Silicon Valley is sucking on the fumes of such regions as Boston and Pittsburgh, which have become the leading robotic regions. In general, much of the day felt like I had entered a Bizarro-alternative universe where the valley was a high-tech also-ran, the Des Moines of robotics, and other people came to lecture us about how to become a technology cluster, the importance of networking to drive innovation, and the need for venture capital to fund big ideas.

In other words, they were quoting from the playbook that Silicon Valley wrote!

“Robotics is one of those rare fields where rather than leading, Silicon Valley needs to play catch up,” said Wade Roush, editor of the

Read more >

James Falasco – I am curious about the comment that the SICK sensor is mandatory . How so ?

Teresa – Jim, The SICK laser sensor is still mandatory for robots or vehicles that need to show intelligence because:

• it’s the most reliable distance sensor for medium-long distances, much more than sonar or infrared (which is basically useful for very short distances)
• it’s necessary to perceive the boundaries of the environment to autonomously build the map of it. The map is necessary for the robot to know where things are.
• The linear laser, such as SICK, has also drawbacks. The main one is that it only perceives one line.
• The best way to go would be to have all the information needed and interpreted from a camera, which would be much less expensive, and with richer information.
• Although we have developed a cognitive vision system which gives meaning to the objects of an image, with two cameras you can get distances to objects, yet we still need further development and some integration to use only camera.
• We have also integrated into the Cognitive Brain the Kinect sensor with great success. It gives us depth in a conical area in front of the robot, although with short reach (we can’t see the limits of the rooms) and very sensitive to light changes (not good in exterior settings yet).

Summary: We use laser, Kinect and camera sensors. We can’t avoid the laser yet, which is the most expensive component of the whole robot, by far.

I am sure that with more development we can make the camera work to completely substitute the laser. I would love to do it.

Comments of other experts on the subject are very welcome. Thanks.

Read the comments.

Comments:

by Adel Djellal (LinkedIn Group: IEEE Robotics and Automation Society (IEEE RAS)) – yes it is very mandatory, it helps the robot to perceive the entire environment. but the problem is that it is very expensive, so we have to search other techniques less expensive, because if we need to design cheaper robots in commercial dimension. we need to minimize the expenses as possible as we get.

by Jim Falasco (LinkedIn Group: IEEE Robotics and Automation Society (IEEE RAS)) – One of the reasons the robotics niche has never fully matured is we continue to debate technology and not talk what people are really willing to pay for and fund. See The Ten Top Reasons Why The Market has never developed at : http://falascoj.blogspot.com/
Here is a teaser :
10.Pervasive Internet
With the all encompassing reach of the Internet old ideas resurface and morph into a reflection of the current environment . With all the attention paid to drones and other related technology people have rediscovered robotics and using the connectivity of the Internet building a worldwide community. This factor gives some glue to the movement that didn’t exist when the last crazes hit.

by Seth Kaufman (LinkedIn Group: Robotics Trends Professional Network) – While Lidar in general is a common, useful sensor, SICK is not the only brand. Hokuyo makes an IP 67 rated Lidar unit, for example.

by Harri Vartiainen (LinkedIn Group: Robotics Guru) – Robert, Google Street View cars has at least two Sick scanners. Compare yourself:
http://ekstreme.com/images/google-streetview-camera-1.jpg
https://mysick.com/partnerPortal/ProductCatalog/DataSheet.aspx?ProductID=33772#
It might not be exactly the same model, but body is same.

by Bryn Wolfe (LinkedIn Group: Robotics Guru) – There seems to be some confusion here about what “Google car” means. The StreetView car is what Google uses to generate street views for google maps. That’s what Harri V shows having the SICK sensors on it.
The self-driving car from google has a Velodyne HDL-64E S2 sensor (shown here
http://www.youtube.com/watch?v=YaGJ6nH36uI ), which costs about $70K.
SICK used to be the only player in the Lidar market, but there are plenty of alternatives now. Unfortunately, these sensors from any vendor are still going to cost you around $5000.

by David McMillan (LinkedIn Group: Robotics Guru) – One large driver for the cost is the fact that this is safety-related hardware. The test and certification for these units is much more expensive than for components that do not directly impact human safety. There’s also the legal liability issue, especially in the US market — it’s bad enough that I’ve worked on systems inside the USA where the safety certification had to be performed by someone hired from the EU, specifically b/c there was no US company willing to accept the legal liability involved.
One side effect of the legal liability issue is that a very high barrier to entry is created, limiting innovation; only entities with very deep pockets and large R&D&T resources will try to get into the safety-hardware market, and even those entities will tend to settle on a “if it’s not broke, don’t tinker with it” policy as soon as they have a product that works well enough.

by Arnout Appelo (personal email) – One of my findings is that for correct navigation you do need something like a laser range scanner, but the thing is way too expensive to make a viable business case for the cleaning industry. But perhaps there will be new solutions within short that will enable the case.

by R. Martin Spencer (LinkedIn Group: Cognitive Modeling) – That’s not really true. We used sensor fusion quite a bit to eliminate the high cost SICK indoors. We have fused short range IR on a scanning array with fixed long range IR and sonar and gotten “loose crowd” levels of autonomy.
Here is an example from our elder care personal robot alpha trials:
http://www.geckosystems.com/timeline/?year=2010
Now outdoors, the SICK does dominate. But we believe our CSA technology can be migrated outdoors. But again use sensor fusion and not rely on any single sensor system to achieve “actionable situation awareness.”

by Hudhaifa Jasim (LinkedIn Group: IEEE Robotics and Automation Society (IEEE RAS)) – Currently, I’m working on an Intelligent Ground Vehicle – I’m glad to reach the level that we can do obstacle avoidance using only machine vision. I admit, the accuracy is not yet enough – but it’s a mater of time (and hard work).

by Ronald Howell (LinkedIn Group: Robotics Guru) – I’ve used the Leuze sensor and had only one problem. (I had a false reflection problem which was corrected by turning up the time delay to about 50 mSec. The factory defaults are set very low, probably for liability reasons). The software is logical but not all that intutive (German). The price was a little less the Sick. I have also used the Keyance and liked that unit for the price we got. We bought a couple of dozen and got them at about half the price of the Sick. Sick does not like to negotiate.

by Meysar Zeinali (LinkedIn Group: IEEE Robotics and Automation Society (IEEE RAS)) – I think we can do the job with vision,and more intelligence. Nature is a good example to learn. Almost all of the animals uses vision system and intelligence (although some animal like Bat uses ultrasonic sounds). Vision can provide more feature of the obstale and surronding environment.
I have developed a data analysis and control systems that has two components. These two components of the control system can also be interpreted as the integration of the fast reaction to immediate feedback information and the reaction based on the knowledge that has already been built into the knowledge base of the controller, i.e., the information encapsulated in the fuzzy rules. So, we even do not need high density data streams to make a decision. The built in knowledge can be updated and modified based on the long-term observation. My point is that use prediction and data stream. on high denstiy data stream cost more.

We’ve successfully developed the worlds first truly autonomous Cognitive Brain, and have focused our efforts on Service Robotics.

We’re actively seeking both working partnerships and investment capital.

Highlights to-date include:

• A part of the Cognitive Brain for Service Robotics has been successfully incorporated into a commercial floor scrubber machine, as well as a Pioneer research platform (investment from different sources).

• Our ‘Manual Assisted Driver’ has been successfully incorporated into forklifts and buses (funded by the Spanish government).

• We have integrating the Cognitive Brain into our own service robotics platform.  This will be launched in the next few months, and can be used for a variety of applications, including companion, security, marketing, air contamination detection, etc. (funded by Spanish government).

• The Cognitive Brain is being incorporated into Robosoft’s companion robot Kompai of (funded by a European Project).

If you’d like further information, we’ve prepared a .pdf document that explains in detail what we have and are offering.

If you are interested, please, contact me at mtescrig@c-robots.com

Kind Regards, Teresa Escrig, PhD, CEO Cognitive Robots

Another incredible TED talk about the power of believing in ourselves and understanding that every single individual possesses a Genius Mind that can be unlocked. I truly believe so. And I very strongly support any example where we can demonstrate it to ourselves and eliminate doubt.

Published on: April 30, 2012 By Angie Chang (Co-Founder & Editor-in-Chief, Women 2.0)

Meredith Perry is the founder and CEO of Wireless recharging startup uBeam. She is not an engineer by training or a expert. She knows how to use Google, and she knows how to think differently.

In her TEDxNashville talk “How to be a technology innovator – without an engineering degree or Asperger’s”, Meredith argues for non-experts to broach innovative solutions and learn new technology with the help of Google, Wikipedia and by consulting with college professors and such “experts”. She found that said “experts” often have contradictory and different opinions.

In her talk she says,

“But because I already learned not to trust one person’s opinion, I become immune to the naysayers.

For each technological hurdle deemed insurmountable by the experts, I would spend just a few hours thinking about the problem from a variety of sources. As Steve Jobs said, I had to think differently – so I found solutions based on the acoustics of musical instruments, based on other technologies, from authoritative sources such as Wikipedia and when I would present my progressto engineers, they say, yeah that could work. So I was able to solve problems when the Ph.D experts couldn’t with just a few hours of really simple research.

Every single argument why the technology couldn’t’t work has been indisputably wrong and for every objection that has been raised I have found a solution. This was another very important lesson for me to learn. Engineers are inherently linear thinkers and tend to take a very binary approach to solving problems.

When faced with a problem, they think can this work, can this not work. I think – how can I make this work? As a non expert I had an advantage because I could look at the problem from different angles because I just didn’t know what was possible. Being naive is sometimes a good thing. Because without constraints the world is literally your oyster…

My experience also made me wonder, how many game-changing brilliant ideas out there thought of by laypeople, teenagers, store clerks, paleobiologists have been squashed by experts that said it wouldn’t work? I know that if I weren’t as stubborn as I am I would have chucked this entire idea 8 months ago because I was told my idea wasn’t possible.

But by thinking differently, by thinking outside the box, by thinking around corners you can outthink the top thinkers. They say that the most revolutionary ideas in the world were considered crazy until the point where they became revolutionary.

Dream out loud, ask questions, take risks, never give up, keep pushing and believe in yourself even when no one else is.”

22 year old Meredith Perry was recently featured in Forbes “30 Under 30? for her energy startup uBeam.

It’s very obvious that the service robotics field is very much in its infancy.  Basically toys (with the exception of the tele-presence robot), these represent what are currently considered, the top most useful robots. It is clear we can do much, much better.

The technology, is much more advanced, not only in the academic world but also in the industrial one, and can provide much more service to humanity. I guess it takes time to arrive to the market.

Another completely different picture would be if we could say that the 7 top useful robots are for:

•  Autonomous scrubber machines
•  Semi-autonomous and autonomous fork-lifts
•  Security robots
•  Companion robots
•  Autonomous robots for ware houses
•  Autonomous lawn mowers
•  Autonomous tractors

As I see it, there are two basic obstacles that hinder real world market application:

• The security SICK laser sensor is currently mandatory for autonomous robots – if we want the ability to perceive the world, and therefore show a bit of intelligence. It costs almost 3000 euros. While not without its drawbacks, this sensor represents the  state of the art and is the most expensive component in a current autonomous robot.   If we produce robots as prototypes, not on a large scale, we can not provide inexpensive robots yet.
• The technology is developed but not integrated completely yet, and therefore not completely tested.

The solution for these problems are:

• By decreasing the price of the SICK laser, service robots would be would be more affordable, the resulting growth and popularity should in-turn result in greater unit sales.
• To infuse funds to integrate and test the technologies which used in corporations and the academic world.

Our experience in both the academic (20 years) and corporate world (5 years), at Cognitive Robots is allowing us to provide this integration to bring the service robotics into the next stage.

We are actively looking for partnerships and investors. If you are interested in positioning yourself at the leading edge of service robotics with us, please contact me at mtescrig@c-robots.com

Dr. Michio Kaku is a theoretical physicist, best-selling author, and popularizer of science. He’s the co-founder of string field theory (a branch of string theory), and continues Einstein’s search to unite the four fundamental forces of nature into one unified theory.

In this incredibly well done movie, he explains how Artificial Intelligence is affecting our lives now.  How our kids are spending more time in virtual worlds, such as “War of World Craft”,  than with their real friends. And how this will affect our lives in the near future.

It is an amazing review, of some of the scientific research that is taking place on the planet, related with Artificial Intelligence.

There is at least one thing that I do not agree with at all: that humans are going to have incorporated into their bodies more robotic parts than human parts in the near future.  To me, this final idea is nonsense.

One of my research lines a few years ago, was to create a ‘General Model’ to describe the behavior of all qualitative models based on intervals, also named – “naming” qualitative models. “Naming” qualitative models are the ones that help us to express spatial-temporal concepts such as “That horse is really fast” (velocity); “That boy is really tall” (size); “My favorite restaurant is close” (distance).  The other way we reason with qualities is by comparing:  “The black horse is faster than the brown one”; “My son is taller than yours”; “The pizzeria is closer to the Thai restaurant”.

The basis of the qualitative reasoning process is defined very easily (in fact, it’s easier than it seems when you try to explain it with words, as I am doing).  If you have the relationship (any of the spatial-temporal concepts that you are interested in applying) between the object b and the reference system RS1, and we have the relationship between the object c and another reference system RS2, and object b is included into the RS2, the basic reasoning model will obtain the relationship between object c and RS1.  As an example: given two distances between three spatial objects, a , b and c, that is Dab and Dbc, we want to find the distance which is not initially given, i.e. Dac.

I can hear the voices of those asking… “and why is this important”?  “What is this useful for”?  The general model will allow us to create a unique algorithm to be able to represent and reason with all different spatial-temporal qualitative naming concepts.

We corrected this article so many times, that we finally obtained the Practical Applications of Agent and Multi-Agent Systems’ 2012 AWARD OF SCIENTIFIC EXCELLENCE.  Congratulations Esther!

If you want to read the whole article, paperDCAI-2012_red

What would it need to do?

What would they call it?

How would it change the life of the elderly?

I asked those questions to my colleges at the LinkedIn groups related with Artificial Intelligence and Robotics.

I will be posting their answer here. Thank you very much for all your contributions!  Keep an eye to it…

by Elad Inbar (LinkedIn Group: IEEE Robotics and Automation Society (IEEE RAS))

Check out this new movie… I think it will gove you many answers.

http://singularityhub.com/2012/02/24/new-robot-and-frank-movie-looks-like-a-realistic-portrayal-of-the-not-too-distant-future/

I post the trailer below: Frank Langella and Liv Tyler on their Sundance hit ‘Robot and Frank,’ about an elderly man living with a home health aid robot. (March 23)

by Huma Shah (LinkedIn Group: Robotics and Machine Intelligence)- Okay, if it were to assist an elderly lady a companion robot could be shaped like a handbag. It should have speech recognition with an ability to verbally remind about medication times, appointments, as well as act like a personal assistant, like the all-knowing virtual librarian in Neal Stephenson’s Snow Crash. The handbook should also be an e-book reader and audio book. Not sure what design a male would prefer in a companion robot!

by Jim Falasco (LinkedIn Group: IEEE Robotics and Automation Society (IEEE RAS)) – Posts on http://surveillance-securityinanasymmetricalera.com address some aspects of the robotics market past and present. A companion robot is a very different market space then today’s UGV’s that deal with EOD’s, HAZMAT and ISR. Anything used by the elderly would need to be simple to control, cost effective, appear non threatening and most of all perform essential services vs. gimmick. The dream of companion robots has been around since the SCI-Fi craze of the 1950′s. It is possible with the enabling technology of today to achieve this goal if it is done in a business vs. cute technology model. A companion robot could really change elder care. With a huge part of the population moving into that demographic depending on human caregivers just won’t get it done.

by Craig Hines (LinkedIn Group: Robotics Guru) – Primary functions of general health monitoring, emergency reporting, cleaning. Communications medium for the blind with speech recognition benefits. If it were to attempt to hold a conversation it could become an annoyance unless artificial intelligence makes a huge leap forwards. Dogs and cats make good companions and they barely have any words to speak.

by Mick Walters ( LinkedIn Group: Human Robot Interaction (HRI)- Our group has done quite a lot of work on what people’s expectation are regarding companion robots. The idea of consistency of appearance, behaviour and functionality is important for how people perceive robots. E.g. if the robot looks human-like to some degree, then people (unconsciously?) assume that it will have the same degree of human-like capabilities and behaviour. If their expectations are not met, i.e the robot looks the part, but fails to deliver, then people asses it as inconsistent or dishonest. In the worst case the effect becomes eerie or repulsive (Mori’s Uncanny Valley) – some useful links to our work:

• K. Dautenhahn (2004). Robots We Like to Live With? – A Developmental Perspective on a Personalized, Life-Long Robot Companion. . In Proceedings of the 13th IEEE International Workshop on Robot and Human Interactive Communication (RO-MAN 2004), Kurashiki, Okayama Japan. pp. 17-22 IEEE Press http://homepages.feis.herts.ac.uk/~comqkd/DautenhahnRoman-4-Invited.pdf

• K. Dautenhahn, S, N. Woods, C. Kaouri, M, L. Walters, K, L. Koay & I.Werry (2005). What is a Robot companion – Friend, Assistant or Butler?. In Proceedings of IEEE RSJ International Conference on Intelligent Robot Systems (IROS’05), Edmonton, Canada. pp. 1488-1493 http://homepages.feis.herts.ac.uk/~comqkd/Cogniron-IROS-Dautenhahnetal.pdf
• M, L. Walters, D, S. Syrdal, K. Dautenhahn, R. te Boekhorst & K, L.Koay (2008). Avoiding the Uncanny Valley – Robot Appearance, Personality and Consistency of Behavior in an Attention-Seeking Home Scenario for a Robot Companion. Journal of Autonomous Robots, 24(2). pp. 159-178 https://uhra.herts.ac.uk/dspace/bitstream/2299/3388/4/906071.pdf

by Jean-Gabriel GAUTIER CPP-EMBA-EDHEC (LinkedIn Group: Robot Business On Line) - Another and final point. As Pricing Manager, one of my objective is to identify customers insight to create value for both the customers and a company. Having say that, I don’t think this is key to add all the available technical features to your companion robot but to bring the ones you’re customer is expecting and ready to pay for ! I Robot is capabale to save time. Do you really think their robots costs as much as they price it ? I don’t think so…

by Jean-Gabriel GAUTIER CPP-EMBA-EDHEC (LinkedIn Group: Robot Business On Line) – Hi Teresa, this is a simple but very good question… For children: to be capable to sing music, to make animal noise, to make light during the night, to tell story, to dance, to react to child emotion such like smiling… To be robust but without any risk for my children. To generate cold or warm if my children are warm or cold. To keep secret: special box within to store toys. To follow my child and be capable to stop based on voice orders; A webcam and a Skype function to call family…. To be customized ! the children are not only looking for their own application but also style!  For my house: security & cleaning, but the market segment is pretty well fulfilled, except if you can install a Tazer on the robot or at least a an aggressive sound signal and visual recognition with SMS alert ;0). For me the next step is an integrated solution of robot : house-garden-swimming pool that can be managed with a tool on my computer. For grand parents: “Assistance”. Voice recognition and be capable to transform orders in tangible action such like: “call Doctor”. To be capable to assist / help them if they fall down. To remind today’s actions or medicament to be taken. Fire detection and alarm system.

The look has to be different vs the segments as the price, as the value for the different companion robot will be different.

by saurabh datta (LinkedIn Group: Human Robot Interaction (HRI)) - A robot should look like a robot, may it be designed for elders or for kids. But now-a days it is seen that japan Is really taking some hard steps in developing human alike bots .. But that may bring in some hardcore complications in the future . (everybody has his/her own point of view).. It should be optimum & chic when it comes to it’s size. A cute smart bot will be perfect that reflects the enthuse for the design. As you are mentioning it for elders so it should be user friendly & voice controlled as otherwise it would take some hard time for our elders to get well acquainted with the controls of the bot. About the functions- It should be custom built according to the needs. And then you’ll see whether the changes that you are expecting does meet them.

by Michael Will (LinkedIn Group: Robotics and Machine Intelligence) – I’d make sure it had some sort of laws embedded in to ensure and prioritize no harm to humans, obey humans, no harm to itself. I’d probably name it Robbie . Seriously, I’d make sure that it was intelligent enough to surprise skeptics and thus make immediate dismissal of the concept difficult. Helping the elderly is easy – memory assistance.

by M. Anthony Lewis (LinkedIn Group: Robotics Consultants) – Good question! I think people are split on using a humanoid form versus something completely not like a human but still creature like. The third option is to make something that is completely utilitarian.
The first option, it is argued, makes sense because only a humanoid can do all of the tasks in a home. Human structured environment have affordances specific to human beings. Also, a human like face (or even a cartoon of a human face) can display some emotion and facilitate non-verbal communication.
The danger is: 1 it would be big and heavy, would therefore be expensive. Yet, it could be viable for the elderly if it were leased say on a monthly basis. If it were really competent it would be well worth the lease price. However, we are not there yet in terms of competence.
The second option is a “creature.” I am thinking that the elderly are old, not demented. They have not become child-like. Old people can be very computer savvy. A creature option makes sense only as a pet-replacement— a robot might give you percentage of the love and affection of a dog or cat but with zero percent of the effort. But, I am not sure if it fills all the needs of the elderly.
The third option is the utilitarian option. Make it look nothing like a human or animal.
If this option is adopted, then you have a model where something like a wii or cell phone would encourage people to socialize and exercise. A very intelligent agent might also manage the finances of the elderly (pay bills on time, move money around as necessary) to make life less complex. Who needs to deal with bills at 80!
Also, facilitating communication with family members. In the US as elsewhere family usually live apart and the elderly persons grown children may be far away.
The magic trick would be an agent that would get the elderly person “into the day” of family members or vice-versa. Facebook does this to some extent, but robotic telepresence, if spun correctly, might be better.
Note that this third option may turn into a system of devices. Think of a kitchen with a fridge, dishwasher, stove etc. Independent islands performing specific functions very well. This is an easier market to delve into, I think, because you only need to demonstrate a value proposition for one specific task.
So in summary, help with socializing, finances, exercise (and health and diet). Basically allow the elderly to be happier in their old age. They deserve it.

Jim Falasco (LinkedIn Group: IEEE Robotics and Automation Society (IEEE RAS)) – If you were going to design a companion robot, what would it look like? Multiple models : Just as in packaging of “Barbie’s” it will be key to project multiple styles. A traditional nurse , rock star, sports star, etc.
What would it need to do? The cleaning is already done by Roomba and Scoba. Focus on tasks that will enhance elder life such as assiting in movement skills, going to get things and bring them back,picking up clothing ,etc.
What would they call it? Again the name would depend on the task models and country. Pedro would not play in Tokyo but could in Dallas.
How would it change the life of the elderly? As an extension of the owner’s personality the effect would be profound.

by Robert Howell (LinkedIn Group: IEEE Robotics and Automation Society (IEEE RAS)) – I believe it should make sure they can live at home as long as they want to the stage they begin putting their health at risk. So..
What would it need to do?
- Plug and play compatibility for quick and easy monitoring.
- Touch screen and voice commands so the elderly and disabled can use the user interface.
- Reports uploaded to doctor or family members for inspection through wireless home network.
- Assist in Elderly Mobility (Provide walking support and simple object detection)
- Check daily medication, meals etc. have been taken especially important with those with early-mid stages of dementia.
- Mobility handle bars could provide simple cardio data
- VoIP with emergency services and family members.
- Temperature sensors to ensure correct heating of the house in the summer or winter. So many elderly die per year by freezing to death or overheating.
- Light sensors to ensure proper sleep routines.
- Perhaps navigation and object recognition to recognize suspected collapses. Then call for help.
I think they are the most essential and yet realistic capabilities with today’s technology.
What would they call it?
Care Bear…
How would it change the life of the elderly?
- Ensure medication is taken and that they eating correctly.
- Reports would provide a variety of data useful for family members and doctors to track onset of disease, disability or change in routine.
- Aided mobility around the home.
- Indication of whether additional care and support is needed or a specialist care home.

Some extra functionality:
Notify the regular care-worker/carer via mobile phone application of activity: “Mrs Miggins has not signed off her regular evening meal” / “Mr Jones has possibly collapsed” Then provide webcam access for inspection.

by Sergei Grichine (LinkedIn Group: Robotics Guru) – an old shepherd was once asked how did he manage to live to 120; he responded: “you see that sheep? when I am upset I can curse it and kick it, and it never curses or kicks back”. I guess there is a robot-related moral of this story…

by Mika Saaranen (LinkedIn Group: Human Robot Interaction (HRI)) – I do not think we have a single solution here. I would doubt that human like bots would be really convenient or needed yet. I think that if a robot resembles a human being, it needs to also behave like a human being. Otherwise it would give awkward feeling to people it interacts with. I think it will take considerable time before we reach that level of sophistication. However, I think this is an important area of development both for robotics, but also neurological and psychological research.
In my opinion, a companion robot should have excellent speech responses and interface. Actual physical form should be optimized for services the bot provides.

by Philippe Kervizic (???) (LinkedIn Group: IEEE Robotics and Automation Society (IEEE RAS)) – We should care to not mix what we want for our parents (then WE feel less guilty/worry to leave them alone) and what they want for themselves.
As often as possible I talk to old people about robots and what they can/will offer. Almost all don’t want robot at home, they often say: I prefer to live shorter but quiet.
Yet, there are things to do in the future, for sure!

by Craig Spanza (LinkedIn Group: IEEE Robotics and Automation Society (IEEE RAS)) – They should not be called robots (the whole idea is threatening and isolating), just Capable Appliances that allows them to take care of their health and homes so they don’t have to move into a care facility.
eg.
A lawnmower – that just happens to cut the grass itself as well as tidy up the yard, pick dandelions and water the plants
A snowblower – that takes care of the driveway and sidewalk shovelling as well as salt and sanding the slippery spots
A clothes washer – that sorts, washes, dries, folds and irons
A laundry basket – that gathers dirty cloths and put clean clothes in the dresser
A fridge – that cleans itself, orders food for delivery, prepares cold meals like cereal and sandwitches
A stove – that prepares hot meals, cleans itself and gets the fridge to order more food.
A dishwasher – that gathers dishes and loads itself as well as delivers clean dishes back to the fridge and the stove.
A phone – that answers, puts the caller on hold, and comes to the owner wherever he/she might be and wakes them up if necessary or takes a message and follows the owner around until it is delivered.
A dog – that fetches things the owner asks for like keys, hobby items, the remote control as well as refilling the toilet paper dispenser and cleaning the toilet. Could also bring fresh sheets to the bed so it can make itself and give the dirty sheets to the laundry basket.
A cat – that monitors health, dusts, wipes the counter waters the inside plants and catches bugs
A subscription to a maintenence plan where a nice young man/lady comes and services the appliances.
I could go on but the idea is simple taking the objects we all grew up with that makes life easier and heavily upgrade their function. not replace the person, augment the persons capabilities like a mobility scooter does.

by Michael Zeldich (LinkedIn Group: Cognitive Modeling) – The RoboCareGivers should behave as a live person educated for that kind of duties, with expanded set of sensors, so they will have the ability to see the patient problems mach earlier than human personnel can.

by Angelica Lim (LinkedIn Group: IEEE Robotics and Automation Society (IEEE RAS)) -  Social contact is an important factor for quality of life among the elderly. It ranks up there with health status (cf. Elderly people’s definitions of quality of life, Social Science & Medicine, Volume 41, Issue 10, Pages 1439-1446, Morag Farquhar).
In my view, robots could provide two social companionship roles: a) day-to-day interactions through telling the news, jokes, etc. b) facilitating social contact with friends.
The former is criticized by some, including MIT’s Sherry Turkle: are we replacing a person’s human contact by a machine’s? And is that healthy?
The latter hasn’t been explored much, but I think it’s a great research frontier. For example, the robot could be used a messenger to give news or gifts from friends around a retirement home, or as a way for family members to visit via telepresence. Social contact *via* robots, not *with* robots.
I think this would also be a great question to ask groups comprised of caregivers or nurses. I’m now visiting with a relative that is bed-ridden; one fundamental thing she needs is a way to sit up from the supine position. I’m sure that simple functions like this (“helps to sit up”!) would go a long way, but they’re only obvious to those working in close contact with the target group.

by Brad Morantz PhD (LinkedIn Group: Cognitive Modeling) – OK, how do we teach humans to treat our elderly respectfully and with care. Go and visit a senior citizen center, you will rarely find family coming to visit, and the care givers move as slowly as postal employees. What care? Only the doctors run to empty to coffers of medicare.

by Tony Ellis (LinkedIn Group: Personal Robotics Group) – For me a companion robot would look like this:

Its called AIMEC “Artificially Intelligent Mechanical Electronic Companion”
What does it do? This is shown in the four page article in “Robot” magazine which is a bit to much to copy here!
We are already working on advanced Ai to help the elderly and disabled.

by Mykola Rabchevskiy (LinkedIn Group: Personal Robotics Group) – Many of “robots” intended to be useful as companions are actually toys or health watching devices.
Real companion robot should provide physical help. For example it can be “smart” replacement for wheelchair – some (legged?) platform with ability to safe move over stairs and ability to rise (to provide access to upper shelf) and lower (up to floor level) your owner. Of course it should autonomously control self charging and will come to owner when called. I well know real elderly needs: my father and my wife parents are around 90…
Humanoid design definitely does not suit such needs, and most complicated part of development is not an human-robot interaction but mechanical design and movement control. Robot should also have a lot of tactile sensors to detect contacts with environment items at any side and any level. But it is not requires to be quick (in most cases pseudo-static approach to movement analysis will be ok).

by Gavin Graeaves (LinkedIn Group: Robotics Guru) – I have in previous discussions stated that android or any robot that could replace human/human interaction should not be around for at least 100 years while people work out the new social paradigms about these devices who without AI will have alimited understanding of how to deal with their emotions and that it was too soon for doom sayers to allow AI.
The case of the elderly or completely infirm raises different questions though about the need for social interactions, the present usual lack of them and how then do we want people to “feel” about such a device.
Obviously health and well being are one of the foremost functions so medical monitoring and being able to feed and otherwise deal with the persons physical function. Apart from that such a device should be limited knowledge wise in parameters to speak to person about in their direct lines of interest, it should not at any time be seen to be in anyway superior on a mental level than a human even if the persons brain is dysfunctional like altimeters.
Its far too big a question Teresa to answer in a thread I find. But I guess thats getting at the key points.The robot should always be a submissive character to the human no-matter whether the Robot has a cognitive AI of Mensa level.

by Dr. Paolo Di Prodi (LinkedIn Group: Robotics Guru) – Yes I a gree on the submissive attitude and also on the android question: it’s very easy to get into the uncanny valley. There are some good examples of humanoid faces with rubber skin etc. but you can achieve the same result with a simple display.
I would say the most important factor is to have a robot which can safely operate in the human environment and don’t care much about the human likeness.
For instance I am really really afraid of Teletubbies, I would recomend avoid anything that resemble by any mean a Teletubbie!

by David Buckley (LinkedIn Group: Robotics Guru) – I am glad somebody else thinks that way about Teletubbies, I asked around and it appeared to be just me. Regarding the uncanny valley, it is not how things look but how they act. Many people who program robots and animatronics seem to be so enthralled that they have got something to move that they fail to see the moves are creepy or weird and unexpected. I am confident that I can make almost anything (apart from things which resemble Teletubbies) move in a pleasing and friendly way. However, that said, something looking like a decapitated road accident victim is going to be very difficult. On the other hand I have had my walking robots at many science fairs and other exhibitions and they have been handled and interacted with by children of all ages and non of them have been frightened because the actions of the robots are not frightening. The worst reaction was one small child in a pushchair who initially made a cry and then two seconds later was leaning over to pat Condor. The adults often feign fear just to damage their children’s minds like they do with spiders.
http://davidbuckley.net/DB/YouTubeVideos.htm

by Dr. Paolo Di Prodi (LinkedIn Group: Robotics Guru) – Ah yes that is correct, the movements you don’t want to see a fully 360 rotating face (also from some horror movies).
The human psyche is asymmetric: on one side we project antromorphic properties to objects, on the other side we are afraid of human-like objects.
Xenophobia is also another factor but is a cultural learned factor.
I remember the last theory about the uncanny valley is that could be rooted in the bonding with infants wherebe the parents are subconsciously checking if the infant is still alive or not. My opinion is that to be on the safe side make something look like an animal peraphs a Meerkat which is becoming quite popular now in the UK advertising space.
Jokes a part we should hire more psychologist or sociolgists in the future but only if they don’t start analysing robots and making them guilty of sinking too much current from the sockets.
David I like your biped!

by David Buckley (LinkedIn Group: Robotics Guru) – Paolo – Thank you.
Unfortunately psychologists and sociologists are the last people to hire because they don’t really have a clue as to what they expound on when it comes to robots. All they have is some meagre ill thought out experiments with preconceived results.
Some years ago I created three Cycler presentation robots which have a little personality program and act on high level commands from a handler. These robots operated by Waste-Watch have performed in schools in front of about one and a half million (yes 1.5 MILLION) children presenting 3/4 hour show/lectures on recycling. When the robots are talking the children listen attentively and when given a chance will crowd round and hug them. The handlers report that maybe once a month a child has to be taken out of a presentation but the teachers always say that particular child has to be taken out of everything and it has nothing to do with the robots. I think when you consider that in general a Cycler is much taller than one of the children that says something.
http://davidbuckley.net/FR/Cycler/CyclerPresentationRobot.htm
The TecFoot bipeds Condor and Wild-Eagle have interacted with about 1500 people, they have been seen by many more, maybe 10,000, but they have interacted with about 1500. The Amblers have also been played with and interacted with several hundred people. The girls like to shepherd the robots about, especially Condor, and spend much more time with them than do the boys. About 70% of the girls want to interact with the robots as opposed to about 30% of the boys and that has nothing to do with adult intimidation as often they have been twenty feet or more away leaving the children free. A girl will also spend about three times as long with a robot as will a boy and often after twenty minutes they have to be dragged away by their parents. I now let Condor wander free amongst people and most of the time I have no idea where it is. The FabLab Manchester had its 2nd birthday party on Thursday and I was asked to take the robots, there were about 150 people from business and organisations all stood up drinking and talking. Condor was away in amongst all the people just aiming for the gaps and seemingly never in anybody’s way. Dogs in similar situations often get their toes trodden on but not Condor, I think adults have some sort of built in awareness for toddlers.
http://davidbuckley.net/DB/RobotOutings.htm

by Bill Leweywould (LinkedIn Group: Consumer Robotics) – look more like and robot appliance and less like a human or fuzzy pet. I think more toward the whimsical and not so much utilitarian. Simple. It would help the elderly be free and independent. It would not cease to function when called for, not even momentarily. I don’t want to name it yet.

by Keith Rowell (LinkedIn Group: Robotics Guru) – Human likeness is only important for navigating the human scale environment. Stairs are the most difficult obstacle. If a device with wheels like Dean Kamen’s wheel chair could satisfactorily navigate stairs “without spilling the drinks” that would be superior to anthropomorphic legs. I predict domestic robot design to evolve toward multiple legs “probably 6″ and wheels, combined. For now, we expect an appliance, like a very sophisticated dishwasher. i.e. it won’t always get every dish clean, it will require attention to maintain, we will come to rely on it, and it will fail, but ultimately we will re-arrange our lives to fit it’s foibles rather than go back to life without it. All of course, only if it provides a service we value for an affordable price. Austerity pushes that day further into the future.

by Keith Rowell (LinkedIn Group: Robotics Guru) – Humanoid shape is only important for navigating the human scale environment. Stairs are the most difficult obstacle. If a device with wheels like Dean Kamen’s wheel chair could satisfactorily navigate stairs “without spilling the drinks” that would be superior to anthropomorphic legs “computationally and mechanically”. I predict domestic robot design to evolve toward multiple legs “probably 6″ combined with wheels. This provides redundancy. But if a ball could climb stairs, there’d be no reason not to emulate “Rosie” from the Jetsons and have only one “wheel”.
In 100 years, expectations will be different, But for now, we expect an appliance, like a very sophisticated dishwasher. i.e. it won’t always get every dish clean, it will require attention to maintain, we will come to rely on it, and it will fail, but ultimately we will re-arrange our lives to fit it’s foibles rather than go back to life without it. All of course, only if it provides a service we value for an affordable price. Austerity pushes that day further into the future.

by Gavin Graeaves (LinkedIn Group: Robotics Guru) – True David, when it comes to footprint we have the technology now to design a device with some functions like the Karman chair and other devices that have had some very good idea’s but have been limited by the technology.
Now there has been a significant amount of development $$ thrown into single or Personal Transport Vehicles that a number of fantastic components are available off the shelf and its the software that requires the work for each functional enhancement.
I am working on a project right now with several local Universities one of who has a “Development Workshop” that they share technology development between themselves, Helsinki and Stanford to put the technology in place.
So I am very excited about the outcomes and the development of a base platform that has the most mechanical functionality with the software to drive it and can be used from people to developed into other machines.

by David Buckley (LinkedIn Group: Robotics Guru) – Nothing wrong with Personal Transport Systems having smarts but they are not what I would call companion robots and I think that goes for all the general public too. Companion robots will be inside houses, next to people, they will be company for people, not tools or equipment people use even though they may indeed perform tasks.

by Mykola Rabchevskiy (LinkedIn Group: Robotics Guru) – @David, companion robot can’t replace social networks and video calls which are widely available just now because we can’t make robot as smart as human (now and in nearest future). It also can’t replace pets because much higher ownership cost. But it can help to increase mobility, and many people are ready to pay for such service because lack of mobility is a root cause of many other problem. You’re right, such robot should operate in very narrow space – but such design is possible and is much less expensive than typical humanoid. Human-like exterior is similar to bumper stickers: some people is very excited but most not need

by David Buckley (LinkedIn Group: Robotics Guru) – @Mykola – I agree with you but this topic is about companion robots not mobility devices. Self parking and self driving wheelchairs are not, and unless we manage to build real Transformers never will be IMO, companion robots. Mixing up the two types of robot we end up in Ron Goulart’s world of “What’s Become of Screwloose? and Other Inquiries,” where your can opener chats to you and the dishwasher jumps out of the window.

by Mykola Rabchevskiy (LinkedIn Group: Robotics Guru) – @Sergey, fully automated house is not an alternative to mobility.

by David Buckley (LinkedIn Group: Robotics Guru) – I have spent time over the last 30 years hearing people talk about the automated house. It is all nonsense. It would be impossible to retrofit existing houses with all the services and conveyors and lifts and storage systems, and new builds would have to be twice the size of existing house just to fit in all the required gubbins. Then there is the problem of maintenance access and cleaning, of course the maid or mother or wife does that don’t they, either that or it is not even considered, Hey, have you ever looked inside air conditioning ducts? You are breathing that stuff.  Elderly people are not looking for a robot with a futuristic look. Instead, the robot tends to drive back the person due to its alleged technical complexity. Therefore, the first step to work on is the acceptance of the robot by the elderly.
The value of pets for the lonesome elderly has been demonstrated. We must therefore rely on these results to bring the benefits of the animal to the robot that will strengthen its effect and will not be perceived as complicated to use.
Having the general appearance of an animal, a soft texture and behaviors expressing emotions are therefore indicated. These feature will help the elderly to personify the robot and then to take care of it (see the interesting results of the robot Paro).

by Jerome Laplace (LinkedIn Group: Robotics Guru) – The game seems to me to be a nice feature for a companion robot. The idea is to entertain but also intellectually stimulate the elderly. Appropriate games can be designed.
In addition, two robots, each with a different person, can communicate with each other and thus provide a link between people who know each other but can not necessarily meet. The robot then acts as an avatar and each robot plays instead of the remote person.
In return, the robot will take care of the person by being able to contact family or a rescue team if needed.

by Gavin Graeaves (LinkedIn Group: Robotics Guru) – @david – its no wonder you see a wheeled robot as anything but a robot when you are designing a bi-ped device but that is where you and I diverge on what will and will not be socially acceptable and able to be a companion to the example of the elderly or even the infirm given the question posed by Teresa. Personally I think you are qualifying and android type device only as a robot and not wheeled devices. The working Biped is years of hardware development away, the wheeled robot is here, now and is only software programming away. A chair/combination or wheeled robot is only the developers imagination and budget away. When you say you dont think a wheelchair would be visually endearing you think in 100 year old technology when in todays example a chair could transform and appear and disappear inside the shell of a robot. You seem to take a very narrow view of what a wheeled robot could do.
You’re dogmatic comments against wheeled robots when so many people are willing to see so many more different examples of robots from Ipads to wheeled robots and other companion devices seems to be a very limited response to the question. I myself have stated why I believe the general public should not have access to a device that is able to engender human emotions leading to companionship bu.t that these elderly and infirm people require this emotional connection but I disagree that the robot should take humanoid or android like form again, these devices as yet do not engender positive feelings in the community as a whole and your limited responses from children are not representative of community views and value. Its a long STRETCH from a kid shaking hands with a robot to people making a commitment to having one look after a person and be their companion.
I hope that iterates the differences in our points of view more clearly.

by Nikolaos Spanoudakis (LinkedIn Group: Artificial Intelligence & Robotics) – Hi Teresa, We have recently worked on projects for ambient intelligence for the elderly (especially those with dementia) and I have some clues. I think it is very important for the robot to look and sound like a familiar person, especially for dementia. It would be great if it could start conversations about the past based on family photos. It should learn the habits of the elderly and identify changes in daily chores that probably indicate a problem and react. Also remind the person about his/her medication and assist in decision making taking into account the context in which decisions are made.
It is a very interesting area for our team too.
Best, Nikos

by David Buckley (LinkedIn Group: Robotics Guru) – @Gavin – You are not perchance an architect or a psychologist or do you work in air conditioning? Ah.. you are working on personal transport systems, that is it isn’t it!
I think you need to re-read the posts.
For the foreseeable future companion robots will either be immobile or have wheels. That still doesn’t make a wheelchair a companion robot. And regardless of what you see in films Transformer robots are not real and generally have to exist in a world where the laws of physics don’t apply. It is easy to prove me wrong, just make one.
As for people getting emotionally attached, they already do, they get attached to their cars, they get attached to their TV, they get attached to the house they live in, even the project they are working on, that’s the way it is. Like it or not you are not going to stop it.
Now, seemingly you are trying to force the word companion to have a meaning other than that which is normal and generally understood in English, it may indeed be different in other languages, but here we are using English.
I wouldn’t call the response from 1.5 million children limited, that’s about 2.5% of the population of Britain and in a few years they will be the ones running things. They are going to be the ones making decisions on care of old and disabled folk, they are the ones going to be placing orders (or not) for robots.
It is not going to be the people running things now for the simple reason the robots are not available now, they are still just ideas whi3A

by Gavin Graeaves (LinkedIn Group: Robotics Guru) – @David I didn’t realise how much idiocy or slander suited you until you tried it on, now I see its your reason for existence. I have read all the posts dont need to re-read them, you could perhaps do yourself the favor though. I didn’t say a wheelchair would be a companion robot that is your view and your view alone and I was telling you exactly that.
Transforming Robots are very real in the world today such as the chair the moves from 4 wheels to balancing on 2, thats the level of transformation I’m talking about not your simpleton view of movie transformers.
By the time your 1.5 million children become users or influences they will have seen every scary movie scenario we have made about AI which they haven’t at the moment and they will be in the same position that people now are in and I think you should open your eyes to that.
For every point you have I have a rebuke and its pointless to bring it to this thread because its not contributing to the discussion and your post could not be more worthless.

by Sergei Grichine (LinkedIn Group: Robotics Guru) – May I suggest a book closely related to the topic – “Love and Sex with Robots: The Evolution of Human-Robot Relationships” by David Levy. Surprisingly, not much there about sex with robots, but a lot about what bond and companionship means to humans, and how we develop relationship to other-than-human subjects.

by Ryan Anderson (LinkedIn Group: Robotics and Machine Intelligence) – Hmm, its probably best to ask the elderly what they want! I’d spend the time getting insight from as many potential users as I can sit down with. I know I’d learn more about what a companion needs to do for them FROM them, than anything else.

by Ifat Yaakobi (LinkedIn Group: Silicon Valley Robotics) – I think that the old age is characterized by the feeling of losing independence (Physical and Cognitive) and feeling of loneliness. In general I think that different ages requires different solutions. The more independent the elderly the more the robot should have the features of a tool. The less independent the elderly the robot should take more features of a caregiver.
Features that can help the elderly to feel independent:
They can take walks (using physical support if required) without getting lost (using navigation abilities if required). I would make an interface from the robot to an “Electric Mobility Scooter” for the time walking becomes hard.
Go shopping on its own (while possible) or using interface that allows the elderly to control the content of the shopping (if going on his own is not possible).
Control house chores by asking if this is ok to clean this and do that.
In general to restore feeling of independence the elder needs to feel in control on the robot and not the opposite way.
Features that can help the elder feel less lonely:
I would enable the platform to act as a communication tool to the outer world (e.g. family, friends and doctors) easily using voice commands (e. g. “Call Beth”).
Improve the state of the brain by playing chass and crossword puzzle with friend and the computer.
I would enable the elder to record their life story to keep for next generations. This give a sense of meaning.

by Ray Scully (LinkedIn Group: Robotics and Machine Intelligence) – The elderly have a few past times that a companion bot could fill nicely. Bingo caller, small dog walker, and it should fold out to become an adhoc portable bench during daily excerise rests. The bot should have a sympathetic ear for listening intently to stories about the war and how everything was better when they were young. The bot should look vaguely human, but have irregular features or a blemish or a limp to complain about so as to allow the owner the opportunity to give vent to his many illnesses, syndromes and general greviences about getting old. The bot should have an emergency alert circuit to activate when the client has fallen and cannot rise under their own power. Also perhaps a clap on, clap off switch. The bot will need to be waterproof and made sturdy enough to survive falls down stairwells and being hit by canes, walkers and other companion bots. If a mobility scooter add on is contemplated, a nice drink holder and basket wouldn’t be am iss.

by Craig Hines (LinkedIn Group: Robotics Guru) – Thanks Ifat, very practical and empathetic ideas. The client should always feel they control their destiny and their robot.
At least one major powerchair electronics company has made the first steps towards integrating an iPhone into the wheelchair electronics, albeit only as a display at this stage.
http://www.dynamiccontrols.com/iportal
Others are looking at similar interfaces. Getting apps approved by the likes of Apple would be an uphill battle if you were to attempt to get a device to drive their electronics due to liability concerns.
There are simpler ways to interface with drive electronics, such as 4 switch drive. I think that auto drive and GPS would be a most useful companion robot, especially if it came from a tablet type device that also provides communication, games, and at least a semblance of intelligence in that they are quite capable of automatically learning daily routines, preferences, and can be a speech machine with predictive input, for those that have to spell out every sentence. I have seen power chair trials go out that were doomed to fail as the client was legally blind, or incapable of operating a switch to drive, yet could speak well enough for voice commands.
Give someone more independence so they can get out into the community for companionship.

by Darlene Pantaleo (LinkedIn Group: Robotics and Machine Intelligence) – It is not just the elderly who would benefit from a companion robot. My son is in a power chair and cannot get meals or drinks for himself. He cannot reach for things and needs both hands to hold most things. A companion robot would make his life incredibly more independent.

by Keith Rowell (LinkedIn Group: Robotics and Machine Intelligence) – 1. Assuming I’m mentally aware but physically disabled, a senior care bot needs to be able to carry me, lift me from my bed, carry me to the bath. I’d like the dignity of autonomy even when I’m an invalid. Reach and carry and basically be my surrogate body. If it’s an “invisible friend” reminding me of my medications, there’s no physical robotic requirement there. If it’s a service robot, cleaning the house, my age is irrelevant.
2. Assuming I’m mentally compromised, my “companion” bot would help me stay grounded in reality; supplement my personality like a wiser alter ego. This “synthetic personality” would have to evolve and grow to match my cognitive level, or compensate for the lack there of. So compromised, when I asked “where is my robe?” I might not be able to discern if the answer came from without or within.
Navigation of the muddy waters of my own tenuous grip on reality, by software that can have only a simulation of reality, sounds like the blind leading the blind. But what an interesting exercise!
You are quite specific that it’s a “companion” though. That means remembering and recounting our conversations and understanding their meaning. I can picture that at some point, there will be more of my personality in the software than in my physical body. Is this the singularity?

by Mykola Rabchevskiy (LinkedIn Group: Robotics Guru ) – @David, no objections against such definition of companions. But it actually means that very different objects. For you phone can’t be companion, for many programmers computer can be – really! And many drivers speaking witch his cars… Embodiment can be quite different, but it probably should be presented in past environment of companion owner. I have cat and lathe – so for me both cat and lathe can be companion but not a dog or teddy bear Some non-presented before can be very attractive to one and very repulsive for another; it is pure psychology.. So when I describes potential “robot companion” I placed utility functions on the first place; this approach is more universal but of course it is different area. Our approaches are not mutually exclusive, there are just different things.
A couple words about your “pure companions”: there are at least two problems that should be resolved before such robots (independently on embodiment) become available and affordable:
[1] robot should distinct your owner from other people
[2] each robot should have a lot of differences from other, i.e. should have personality including personal exterior and should be easily recognisable by owner.
Both are very real problem (first is non-resolved technical problem, second is technological and financial problem: individual production has obvious drawbacks).
But when these problems will be solved utility robots (at least in some cases) can be “pure companion” too.
And last: my opinion about what robot can be useful is just generalised opinion of a few senior people.

by Gavin Graeaves (LinkedIn Group: Robotics Guru ) – I add to that there is no point the companion being left at home even if it is just the ability take the memory of the companion with you for integration into other more suitable devices.

by Craig Hines (LinkedIn Group: Robotics Guru ) – If your robot psyche were cloud based, then a taxi, bus, wheelchair, cinema would all act the same way around you and know your needs. A cloud companion. You wouldn’t need your own robot, just dial a robot to help you out of bed, feed etc. At home alone? Your big screen or phone still links you up to face book, linked in or club penguin.

by Mike Marzetta (LinkedIn Group: Personal Robotics Group) – All of the above are great ideas; but I would first automate all of the day to day tasks that humans perform. Some of these technologies exist, but haven’t really ever made it to the mainstream. Just a few examples are vaccuming, auotmatic lights on/off with dimmer, door opener, no touch home water faucet, combined (one touch) laundry shoot-washer-dryer-de-wrinkle (even handles the soap), automatic lawn mower, garage vaccumer, key and phone finder (for when you can’t find them…I could really use one of these), weed puller/poisoner, varuious automated pet feeders, auto-remote car starter, gas-pumper, auto in shower full body blow dryer, etc.

by Mark Worsdall (LinkedIn Group: Robotics Guru) – The first model would just follow me around carrying items like remotes, phones, emergency chords. I am in a w/chair and remembering to carry this stuff around is critical but a real pain. So I would want it to follow the w/chair but stay out of my way, automatically recharge via induction charging.
It would also be good if it could sense via weight that the items it should carry are not on it or just been taken by my, then go on a discovery mission to locate missing items.
Webcam and Skype is a must but the video should be available at same time to other apps on it.
It would also like it to have the ability to carry a glass of booze that it can pass to me when transferred into bed. It could do this via extending a tray to me.
I think it should be about 24inches high but the tray would raise up and towards me.
It must talk for verbal feedback.
It must also have a smart phone app for direct control.
I would like it be able to parked it against my wheelchair so while I am transferring the w/chair would not be able to slide away. No, breaks on w/chairs are just to stop the wheels moving, not the chair
That’s all for version 1.

by Michael Grant (LinkedIn Group: Robotics Guru) – My design would include voice and visual command recognition and be wirelessly connected to hospitals, EMTs etc. It would be low to the ground for stability, maybe even have four legs(?) and be able to lift and carry it’s owner. For the visually impaired, it would have an adaptive surface coating to help it to be located (or seen) and various light conditions and, of course, be waterproof.

by Craig Hines (LinkedIn Group: Robotics Guru) – Mark’s “LittleFriend” – it is good to have identified version 1, you can’t really make version 2 until 1 is proven. It is also a product that would serve the masses as well if the price was right. The technology is not really ground breaking, but making it affordable would require mass production. Why carry remotes? It can learn remote codes to control the house, or does the house control it? It needs a fairly smart vision, guidance and mapping system to figure out how to get around objects that dropped on the floor. Old fashioned lead acid batteries for stability when the liquor ballast has run low for some reason. The screen folds up from the tray no doubt, and however the tray folds down it would have to be sturdy as a support for transfer. Stability legs (RE Michael) could wind down as mid drive wheels won’t be stable. The Android control system has voice recognition app already. Lifting it’s owner might be for version 2??

by R. Martin Spencer (LinkedIn Group: Human Robot Interaction (HRI)) – Mika, Well said. I agree with you. Hers’s what we think is viable:
http://www.geckosystems.com/markets/personal_assistance.php

We got some surprising and unexpected benefits for the elderly during our alpha trials.

Another interesting article regarding how robot can help the elderly: “More useful than a cat: How robots could help the elderly”.

by Adil Shafi , President, ADVENOVATION, Inc.

Originally posted 04/04/2012 on Robotics Online

No army can stop an idea whose time has come ~ Victor Hugo

In 2011, the International Federation of Robotics commissioned a report on how robots create jobs. http://www.ifr.org/robots-create-jobs/. The findings report that, “One million industrial robots currently in operation have been directly responsible for the creation of close to three million jobs… A growth in robot use over the next five years will result in the creation of one million high quality jobs around the world.”

Further, the market research firm Metra Martech wrote, “In world terms three to five million jobs would not exist if automation and robotics had not been developed to enable cost effective production of millions of electronic products from Phones to PlayStations.” The report actually covers several markets in the automotive, electronics, food and beverage, plastics, chemicals and pharmaceutical industries and focuses on countries like Brazil, China, Germany, Japan, Republic of Korea and USA. The complete report is available at ifr.org .

Read more: http://roboticsonline.wordpress.com/2012/04/09/how-robots-create-jobs/

The increasingly popular field of soft robotics is set to have an enormous impact on the service and manufacturing industries.

And there is no need to be concerned that automation will put people out of work – the reverse is true as jobs that would otherwise be outsourced to China can be protected. …  As John Dulchinos, the chief executive of Adept, the largest US-based manufacturer of industrial robots, argued in a recent interview, the US has lost several million jobs in manufacturing to China because they did not automate their production lines but outsourced them to cheap labor countries.  …  moving people from dull or unhealthy jobs to more interesting ones, according to Foxconn founder and chairman Terry Gou.

We expect soft robotics to have an enormous impact on the service robotics industry because we will share our living space with these machines, and we will closely interact and cooperate with them.

The European Commission is doing an outstanding job at supporting basic research and development in the area of robotics and related fields with the 7th framework programme, and in the future with Horizon 2020. Examples of soft robotics basic projects include ECHORD, the European Clearing House for Open Robotics Development, which has the aim of bringing industry and academia – basic research – together.

Cognitive Robots is leading one of the ECHORD research projects, C-Kompai. The objective of the project is to enhance the companion robot Kompai by Robosoft with the cognitive capabilities provided by the Cognitive Brain for Service Robotics of Cognitive Robots.

Read the full article by professor Rolf Pfeifer (11 April 2012) – deputy director of the Swiss National Centre of Competence in Research Robotics and director of the artificial intelligence laboratory at the University of Zurich-: http://www.publicserviceeurope.com/article/1772/time-to-wake-up-and-invest-heavily-in-robotics-technology

Since February 2011, Cognitive Robots and Robosoft have been working together to enhance the “intelligence” of the Kompai companion robotics platform.  The project is funded by the European Commission as part of a set of demonstrations, of the current capabilities of the robots (ECHORD Project called C-Kompai).

The Kompai’s capabilities prior to  incorporating our ‘ Cognitive Brain for Service Robotics’ into the platform is shown in the current GUI control panel.  The robot is controlled using a push button interface as well as voice commands.

The main functions that Robosoft asked Cognitive Robots to improve with the Cognitive Brain were:

• Previously when a robot was purchased, the Robosoft technician needed to go to the elderly persons home and spend most of the day creating a map of the space that the robot would operate in.  Unfortunately, due to the maps limitations, the elderly couldn’t move any furniture around without the technician coming back again and remapping the environment.  This is a problem that remains in industrial applications as well.
• Kompai had a limited perception of the plane provided by the laser sensor at a certain height. That was a big problem because any house could have plenty of obstacles that would remain unseen by Kompai.

Cognitive Robots proposed to include two new features:

• The robot would vacuum the house.
• To include a more dynamic and proactive behaviour by the robot, than merely waiting to be called to do something.

The Kompai’s capabilities after the Cognitive Brain is fully incorporated will be:

• Automatic map creation.  Any furniture can be moved around without any technical assistance.
• 3D obstacle detection using the Kinect sensor
• ‘Autonomous vacuum cleaner’ capability
• Proactive behaviour: Kompai will engage actions and interaction with the elderly.

These enhanced capabilities are summarized with the addition of the following three new buttons to the GUI control panel.

The scope of this particular project doesn’t go further, but we’re curious to learn your thoughts on how the behaviour of the Kompai could be further enhanced?

Comments are welcome to contribute to the development of the companion robots industry!

by Bennett Brumson , Contributing Editor
Robotic Industries Association Posted 04/05/2012

Mobility promises to be the next frontier in flexible robotics. While fixed robots will always have a place in manufacturing, augmenting traditional robots with mobile robots promises additional flexibility to end-users in new applications. These applications include medical and surgical uses, personal assistance, security, warehouse and distribution applications, as well as ocean and space exploration.

Read more: http://www.robotics.org/content-detail.cfm/Industrial-Robotics-Feature-Article/New-Applications-for-Mobile-Robots/content_id/3362

Slowly but progressively, with 51 years and many man-hours of research effort, the results are not very impressive.

I agree with the comment that Stanford U. ‘emeritus professor’ Edward Feigenbaum said to me last year: “It is not that AI is so difficult that it can not be solved by humans, the problem is humans”.  The way research has been imposed on professors – you need to have a certain amount of publications a year to “measure” your production – has worked against going after the big problems, even when the solutions don’t arrive immediately. We are “forced” to choose a research area where we can reach publication requirements.  Sad but true.  I wish we could choose research goals without results expectations and obligations, so we could break the status quo to reach quantum leaps. It would help human progression.

The following is a very interesting video showing a big advance in the artificial reproduction of the human body. Some AI researchers, as professor Marcus du Sautoy is telling us in this video, believe that the study of intelligence in the same shape of a human body will help us to understand more intelligence.  I don’t see the relevance in this thinking.  We can provide the same intelligence to different body shapes.  And we can also have intelligence without a body.

2 April 2012 by BBC News Technology
Is it possible to create true artificial intelligence and, if so, how close are we to doing so, asks mathematician Professor Marcus du Sautoy.

It was while I was making my last BBC TV series, The Code, that I bumped into a neuroscientist I knew.

“Have you heard the news about Watson?” he asked me.

I wasn’t quite sure what he was referring to. A new release of Sherlock Holmes? I looked confused.

“Watson beat the world champions at Jeopardy last night,” he added.

Jeopardy is an American television quiz show which tests general knowledge. But I could not understand why a professor of the brain was interested in it.

But then he revealed that Watson was not a person, but a computer…

Full article: http://www.bbc.com/news/technology-17547694

What would you attempt to do if you knew you could not fail?” is the bottom line of this amazing talk by Regina Dugan, the director of DARPA, the Defense Advanced Research Projects Agency, about people who do not decide their next step based on the fear to fail, but beside the fear to fail, they do it any way.

In this breathtaking talk she describes some of the extraordinary projects — a robotic hummingbird, a prosthetic arm controlled by thought, and, well, the internet — that her agency has created by not worrying that they might fail.

I personally would dedicate more thoughts to the actual use of the results of the research.  She could not give a straight answer to that question to TED’s director Chris Anderson.

It is absolutely worthwhile to watch.

By: David Arnouts on 3/26/2012

A vehicle that drives itself has been a fantasy for many drivers since they encountered their first traffic jam. While a fully autonomous car is not quite here, Continental—yes, the same company that makes tires—has an experimental semiautonomous vehicle that will eclipse the magical 10,000-miles-on-road mark this month.

Its unassuming Volkswagen Passat is fitted with a plethora of safety and technology systems that the company has been developing and tweaking over the course of the project.

Read more: http://www.autoweek.com/article/20120326/CARNEWS/120329871?utm_source=DailyDrive20120327&utm_medium=enewsletter&utm_term=missedarticle7&utm_content=20120326-Continental_developing_experimental_semiautonomous_vehicle&utm_campaign=awdailydrive

Updated March 22, 2012, 8:43 a.m. ET by Ben Rooney. The Wall Street Journal. Tech Europe

“Robots should be smaller, it should be helpful, it should be subordinate, it should be making sure that you are the master and not the robot,”. And above all it must not look too human. Our acceptance of robots increases as robots get more human-like but only up to a point. In a phrase first coined by the Japanese roboticist Masahiro Mori, get too human and they fall into the “Uncanny Valley”, that point on a graph that plots acceptance against how human like a robot is where acceptance falls through the floor. “If it gets too human-like, people are very fearful”.

By far the most engaging robot on display at InnoRobo conference hold this week in Lion, France) looked nothing like a human and an awful lot like a baby seal. Called Paro, it is designed to help patients suffering from dementia.

In a video shown by the inventor, Takanori Shibata of the Intelligent System Research Institute of Japan’s AIST, U.S. President Barack Obama is shown interacting with a couple of robots. The first is a humanoid one and it is clear he doesn’t really know what to do. Then he meets Paro.

While talking to Mr. Shibata, who is holding the pup, Mr. Obama almost subconsciously reaches out to stroke it. When we do that with all our robots, then we will be living in the future.

Read more: http://online.wsj.com/article/SB10001424052702304724404577295802833627644.html

by Staff Writers, Brussels, Belgium (SPX) Mar 15, 2012

THE European Robotics Forum, the largest Robot industry and academia gathering in the EU, was held this year at Odense, Denmark. Delegates heard a renewed commitment to Robotic R and D from the European Commission.

Khalil Rouhana, director for digital content and cognitive systems in DG INFSO in the European Commission, told the 350 delegates that Horizon 2020, a projected 80 euro billion research fund which is planned for the period from 2014 to 2020, will be one of the largest research and innovation budgets in the world.

March 6th, 2012 – by Kent Bottles
IBM’s Watson is moving on from conquering “Jeopardy” to aiding health care providers by scanning the entire medical literature to help make diagnoses more accurate. A computer named Dr. Fill is even entered in the American Crossword Puzzle Tournament and expected to do well. Recent articles have speculated on what kind of physicians will soon be replaced by computer programs and robots, and artificial intelligence experts predict that medical diagnoses kiosks will soon be triaging patients in the third world.

Read the article: http://www.hospitalimpact.org/index.php/2012/03/06/p4009#more4009

By Kevin C. Tofel Mar. 12, 2012, 8:29am PT

The chips that power today’s smartphones and tablets are expanding to robots as Texas Instruments and iRobot announced a new partnership on Monday. TI’s OMAP platform will be used by iRobot — maker of the Roomba and Scooba service robots — to help develop new robotic technologies.

The partnership is a fitting match. Between its home and government service robots, iRobot has sold more than 7.5 million units, helping to move the robotics market forward. Clearly, it’s a leader in this space. And Texas Instruments is no slouch in the chip department. The company’s OMAP platform powers a number of currently popular mobile devices, such as the Samsung Galaxy Nexus, Motorola’s Droid Razr and the Amazon Kindle Fire.

Read more: http://gigaom.com/2012/03/12/why-texas-instruments-and-irobot-are-working-together/

NEW YORK — A University of California, Los Angeles professor is the winner of a $250,000 computing prize for his work in artificial intelligence.

Judea Pearl was named winner of the 2011 A.M. Turing Award on Thursday, one of the most prestigious honors in computing.

Pearl, 75, contributed to the field of artificial intelligence by developing mathematical formulas that factor in uncertainty. That allows computers to find connections between millions of pieces of data, even when the information is incomplete or vague. His work has made it possible for computers to think more like humans, as humans often have to make inferences in decision making.

The award, named after the British mathematician Alan Turing, is given annually by the Association for Computing Machinery. Intel (INTC) and Google (GOOG) provide funding.

http://www.mercurynews.com/business/ci_20182769/ucla-professor-wins-250k-computing-prize-ai?source=email

While quick and precise, this technology was available 20 years ago, for autonomous forklifts in warehouses: following wires on the floor.

What remains missing is the addition of intelligence to the robots so that:

- The whole infrastructure of the warehouse floors – a costly investment in itself – wouldn’t be necessary.

- Any change in the environment or in the robots performance wouldn’t need to redefine the whole system.

http://techland.time.com/2012/03/21/amazons-775-million-acquisition-of-kiva-systems-could-shift-how-businesses-see-robots/

The origins of Artificial Intelligence are attributed to the philosophers of antiquity. Plato (428 BC) wanted to know the characteristics of piety to determine if action could be regarded as pious.  This could be the first algorithm.  Aristotle conceived an informal system of syllogistic reasoning by which one could draw conclusions from premises, which became the precursor of reasoning.

Philosophers delineated the most important ideas related to artificial intelligence, but also needed a formalization of mathematics in three areas: computer science, logic and probability.  The idea of expressing a calculation with a formal algorithm is due to the 9^th century Arab mathematician, al-Khwarizmi, who also introduced Arabic numerals and algebra in Europe.

From the XIII century the first legend of the talking head of Friar Roger Bacon, indicated how to build a wall of brass – to surround England – to protect it from invaders.  The medieval physician Paracelsus described a recipe based on the alchemical tradition to create a homunculus, like a living child although smaller.  In the second half of XIV century came the legend of the golem, a being created from clay and deformed magic, with supernatural physical powers, who defended the Jews in Prague.

Parallel to this set of legends and stories, there is a prehistory of the robot as a machine.  The gears and cams of mechanical technology developed in the Middle Ages, were used in windmills and water wheels for grinding grain.  The first pipe organs were built of air springs.  The first mechanical men were figures of church towers in the late Middle Ages.  The first robots were built to be offered as toys to monarchs: Leonardo da Vinci built a lion (1500); Gianello de la Torre a girl playing a lute (1540), Isaac and Salomon de Caus built Ornamental fountains with moving figures (1600), Descartes built a robot (1640).  The art of watchmaking also boosted the development of robotics, in fact Jackes Vaucanson (1738) constructed a duck  and two very realistic droids using this technology.  Each duck wing contained over four hundred articulating pieces.  The androids were musicians (flute and drum) emitting the sounds of instruments directly, without being recorded.  In 1740 David Hume proposed what is now known as the principle of induction: whose general rules are obtained by repeated contact with associations among elements.  Wolfgang von Kempelen (1769) invented an android that played chess.  You never knew if it was a fraud, with a person inside the box, that moved the hands of the android to move the chess pieces – it played well and properly – but it was the first time that the distinction between man and machine was blurred.  Between 1770 and 1773, Pierre and Henri-Louis Jaquet-Droz built three androids, the scribe, the artist and the musician, made of clockworks and cams.  Setting levers on a control dial, the writer could write any text, the cartoonist could draw a few predetermined pictures, and the musician truly played the organ.  The three androids had very precise movements and imitated – very realistically – human behavior in these areas.

Industrial robots today are direct descendants of these three automata, with three differences: 1) The adoption of a functional form rather than a human form; 2) the use of hydraulics and other sources of energy, instead of springs and clock movements; 3) using other programming methods more sophisticated than the cams.

In 1788, James Watt designed the first feedback control mechanism for maintaining the set speed on a steamboat.  To solve the problem of processing the census data of the United States of America, the statistician Herman Hollerith elaborated, in 1989 an Electric Tabulating System to encode and transfer the data into punch cards.  The cards went through a surface of mercury.  A set of wires then came down on the cards, a thread touching the hole made an electrical contact with a counter, which then advanced one unit.  Data was read on a meter.

During the Industrial Revolution, which created great strides in science and engineering, there was a big gap in the evolution of robotics, that lasted for a century and a half (1790-1940).  It was necessary for the machine to be able to store information and make decisions, which was not possible until the beginning of World War II.  Charles Babbage (19th century) had the idea of a general-purpose digital computer with a stored program.  He created it with the clockwork technology of his time, but the accuracy obtained was not enough.

In science fiction at that time, writer Mary Shelley, took the idea of the golem from the 14th century, and added a set of physical laws, to create Frankenstein (1817).  The play by Karel Capek, R.U.R. (1920) defined a world in which robots were used as laborers and soldiers of war.  When pain and emotions were installed in the robots, they rebelled, facing humans and virtually exterminated the human race – their creators.

In 1937, Alan Turing declared that with a simple set of basic operations using toggle switches, open or closed, the machine could perform any mathematical calculation that could be completed in a finite number of steps.

The automatic controls developed in the Second World War, such as radar, jet propulsion, the V-2 rocket (where the destination could be set), the B-29 heavy bomber and the atomic bomb, led to the post-war programmable robots which are in use today.  During World War II the Enigma encoder was developed by the Germans.  Turing and his research team developed Colossus, a computer that was reading valve data from a punched tape, which deciphered the Enigma code – and marked a turning point in the war.

In literature, to counter the pessimistic ideas put forth in R.U.R., the science fiction writer Isaac Asimov in 1942, defined the three laws of robotics:

1. A robot may not injure a human being nor through inaction cause a human being to be harmed.
2. A robot must obey the orders received by human beings except where such orders conflict with the First Law.
3. A robot must protect its own existence, except where this conflicts with the first two laws.An example of robots in science fiction that followed Asimov’s laws were R2D2 and C3PO in The Star Wars Trilogy (1977).

In 1847, George Boole introduced a formal language to make logical inferences.  In 1879, Gottlob Frege constructed predicate logic first order, which is currently used as the basic system of knowledge representation.

The programmable computer appears next.  In 1941, the German Konrad Zuse invented the computer Z-3 and Plankalkül – the first high level programming language.  The first electronic computer – the ABC – was assembled between 1940 and 1942 is the United States by John Atanasoff and Clifford Berry.  The first digital, electronic and programmable computer was ENIAC – Electronic Numerical Integrator and Calculator – (1946).  Two differences separate computer ENIAC from the current computer: the decimal system, rather than binary; one that could only be programmed by making connections in a box, sticking pins, one by one in plugs, and only allowing a rigid set of orders.

John von Neumann had the idea that the computer should store your program using the same electronic code that manipulated data.  The program did not contain a fixed sequence of steps, but included conditions that allowed choosing the new sequence of steps to execute.  The next computer, built by von Neumann in 1947, EDVAC, had binary arithmetic with the program stored in an electronic memory – such as computers today.  The most significant improvement to occur with computers was with the IBM 701, built in 1952 by Nathalniel Rochester and his team.

At that time, the idea of what would later be known as Artificial Intelligence was introduced.  The first task in AI was developed by Warren McCulloch and Walter Pitts in 1943.  It consisted of a model of artificial neurons, which could be enabled or disabled as sufficient stimulation of neighboring neurons, which allowed calculating any computable function.  Donald Hebb in 1949 modified the model, including intensities between connections that neurons could learn.  In 1951 Marvin Minsky and Dean Edmonds built the first neural network computer.  In 1962, Frank Rosenblatt proved the convergence theorem of the perceptron, which indicated that the learning algorithm could adjust the connection strengths of a perceptron to correspond to any input data, provided that such correspondence was feasible.

In 1956, a group of researchers, McCarthy, Shannon and Marvin, coined the term Artificial Intelligence.  The first ‘intelligent’ program, called Logic Theorist, could prove theorems from Russell and Whitehead’s, Principia Mathematica.  In fact, one of the demonstrations provided to the program was shorter and more satisfactory than that provided by Russell and Whitehead.  The next step was a program called General Problem Solver, based on ‘means-end’ analysis and planning.  The ‘means-end’ analysis consisted in seeing where we are, comparing it to the place where we want to go and look for ways to reduce the difference.  Planning means identifying several goals on the road, monitoring which could bring us closer to the desired state.  This program had pretensions of generality, and worked well for logical problems and puzzles.  Meanwhile McCarthy was working on a program, which sought to use new knowledge while it was running the program, combined with what was already known.  This approach proved very difficult to implement, but originated the concept of timeshare, a computer used simultaneously by a large number of people.  In 1958 McCarthy defined the high-level language LISP, which would become the oldest programming language – and is still in use today.  McCarthy dedicated all of his efforts to the representation and reasoning in formal logic, which was integrated in the late 1960′s with Shakey the Robot at Stanford University.

The initial successes in the field of Artificial Intelligence set expectations among researchers who soon realized they could not be achieved.  The programs that worked for simple examples, failed miserably when they were used in real problems, because the complexity of the problems that AI was trying to solve grew exponentially with the size of the problem, i.e. the number of variables considered.

At the same time the first industrial robot, was introduced – called Unimates – which had a feedback control system and computer memory.  A user guided the robot through a sequence of steps, which the robot would then repeat.  The first task of Unimate was to control a die-casting.  With this industrial process metal parts were manufactured by injecting molten zinc or aluminum into a steel die – an unpleasant task for people and even dangerous to their health.

In the late 60′s, Stanford University and the Massachusetts Institute of Technology (MIT) developed a system in which a manipulator arm was guided by images received from a television camera located next to the arm, its task was to build a water pump from car parts distributed on a table.  The problem was not at all trivial. The robot had to understand the order of assembling the pump, while identifying the parts, handle any possible errors and make corrections.  At SRI International, a second version of Shakey was built, which exceeded the previous one in mobility.  It combined learning capabilities, pattern recognition software, that processed information from images, parts of the general problem solver, and programs to represent information about the outside world.

In 1978 the company that commercialized the Unimation, took out a smaller manipulator arm, called PUMA – Programmable Universal Machine for Assembly – specifically designed to handle smaller parts in the assembly of instruments and engines.  The company sold more than 50 robots per month.  These robots helped revolutionize the automotive industry.  For example, in a Detroit Chrysler plant, 50 robots working in two shifts performed the work previously done by two hundred human welders.  In a Texas factory, a robot selected bits from a tool rack, and drilled holes with a tolerance of 0.1mm.  The robot manufactured parts five times faster than a skilled person without wasting any parts.

The census conducted in 1980 counted 10,000 robots in Japan, 3,000 in the U.S.A., 850 in Germany, 300 in Sweden, 500 in Italy, 360 in Poland, 200 in France, 200 in Norway, 200 in England and 85 in the Soviet Union.  The large number of robots made by Japanese companies was due to a national strategy.  One company purchased a large number of robots to lease to manufacturers.  Business owners could rent robots and test their results without the risk of having to buy them, only to find that they didn’t serve their needs.

By 1980 the U.S. was producing 1,500 robots per year, while Japan was producing 7,500 robots per year.  In a television factory near Osaka, 80% of the parts of each unit were assembled by robots.  Quality was so high that there was only one checkpoint at the end of production!  Intermediate checkpoints were removed after realizing that they were unnecessary.  In the U.S. there were no businesses doing that.

All these robots were ‘blind’, performing tasks without the use of intelligence. They received parts corresponding to each stage in the assembly process in an exact position and then had to be placed in a predefined position.  If something changed an inch of the set position, the robot did not work.  Even today, most robots in the industry have these limitations.

Much effort has been devoted to artificial vision.  It is easy to take a video image, fragment it into small elements and convert it to numbers.  What is still an open research issue is the interpretation of the scene, recognizing objects that appear in it, even when partially hidden.

Much effort has also been devoted to reading and processing printed text.  For many years we have worked on machine translation between languages.  In 1949 Warren Weaver used methods to decipher codes developed during the war by Turing and his colleagues.  According to legend a researcher who worked with Weaver asked his computer to translate into Russian and from Russian into English the phrase – “The spirit is willing but the flesh is weak” – the result was “The vodka is nice, but the steak is rotten”.  The first translation programs offered even worse results.

Another early linguistic program was ELIZA, created in 1966 by Weitzenbaum at MIT.  ELIZA skipped an understanding of language by using a clever system of fixed responses.  The system identified key words and created questions for the interlocutor using those key words.

During the 1980s, expert systems were developed, programs including specialized knowledge of a particular subject and reasoning with it, issuing diagnoses: an expert system DENDRAL interpreted data from chemical instruments and provided advice on the structure of unknown compounds; MACYMSA carried out complex calculations and symbolic manipulations of higher mathematics; PROSPECTOR for geology, identified the location of deposits of molybdenum; MYCIN diagnosed meningitis and blood infections.  MYCIN incorporated an explanation of the deductions it was obtaining, the management of uncertainty, and the separation of the reasoning process from the knowledge.

The first expert system to be marketed, R1, was used by Digital Equipment Corporation to customize orders for new communication systems – which in turn provided a substantial cost savings for the company.

In 1981 the Japanese announced the “fifth generation” project, which lasted 10 years.  Intended to achieve intelligent computers, they would execute the programming language PROLOG, another AI language, along with LISP, commonly used in Artificial Intelligence, based on ‘first-order predicates formal logic’, instead of machine code (running normally on a computer).  The computer would take a huge amount of rules that would represent the knowledge of a part of reality, through millions of inferences per second.  The human and financial resources that the Japanese devoted to this project was matched by European and American efforts in fear that the Japanese would dominate the field.  The project was ultimately considered a huge failure and abandoned without satisfactory results.

Since the late 1980′s, Artificial Intelligence has made changes in methodology: it has gone from trying to solve general problems to addressing specific problems, using real-world applications instead of toy examples, and taking as its theoretical basis, mathematical theorems or solid experiments.

For example, in the field of natural language understanding, they were using hidden Markov models based on rigorous mathematical theory, and generated through learning processes based on a large volume of real data.  More recently, this area has been transitioning to industrial applications.

In 1986 the notion of normative expert systems was introduced, which act rationally according to the laws of decision theory, without attempting to imitate human experts.  That same year, Brooks developed the reactive architecture for autonomous agents.  In artificial vision there was a connection between perception and action, usually associated to a robot.

During the 1990′s there were advances in the connectionist paradigm, fuzzy logic, genetic algorithms, and qualitative models.  New methodologies such as KADS knowledge acquisition appeared.  Newell, Laird and Rosenbloom in 1990 introduced the idea of a complete agent architecture, which studied the behavior of agents engaged in real environments with continuous sensory inputs.

This work raised the awareness of the need to link all the fields of artificial intelligence to fully define the concept of agent (virtual) or robot (physical).

The origins of Cognitive Robots and the development of the first Cognitive Brain for Service Robotics are in the 1990′s with the development of qualitative models originally applied to simulated robots, and then, when the technology was ready, to real robots.

I have dedicated my entire professional life, almost 20 years of research, to developing a Cognitive Brain, which can be installed in almost any vehicle to transform it into an autonomous robot. One designed to serve individuals, commerce and industry in a variety of ways, without any human intervention. I clearly envisioned this future and had such passion that I created a whole research group to pursue that dream.

What does that future look like? Imagine that the floors of our workplaces, where we shop, airports, hospitals, schools, even our own homes were never again cleaned by a person, but by an autonomous cleaning machine controlled by this Cognitive Brain.

Imagine how cool it would be if that same Cognitive Brain were installed into a companion robot, a 3 foot tall, friendly helper for the elderly, that would remind them to take their pills every day, watch their safety, call their relatives and friends through teleconferences, keep them cognitively active and motivated, and at the same time keep the house clean.

What if that same Cognitive Brain were installed into a 3 foot tall security robot, patrolling garages, shopping malls, airports, any work environment, even at home, with autonomous image processing to distinguish anomalies in their environment which would then trigger a security protocol.

And if the same Cognitive Brain could be installed into lawn mowers, Zamboni machines for ice skating arenas, forklifts, excavators, concrete tampers and polishers, land machinery. The list is endless and it will grow as more vehicles become autonomous. All those repetitive tasks will be performed for us.

A simple version of the Cognitive Brain could also be installed into a tele-presence robot, used by doctors and other specialists from a central location, allowing them to perform their work remotely without the need to travel. The commands to the robot would be more sophisticated than now, where the robot is moved with a joystick. For example, “go to the conference room”, or “say hello to all my colleagues”.

A part of that Cognitive Brain could also be used to enhance the personal marketing provided by search engines.

Another part of the Cognitive Brain – Cognitive Vision – could be used in mobile applications. One example might be – you take your ‘smart phone’ with you to go mushroom hunting, the application tells you, on-site, if the mushroom in front of you is edible or not, or the plant in front of you is medicinal or not. How many applications can we think of if we had a Cognitive Vision system that could really identify objects and connect their name with a full concept of the object and its relationship with other objects?

If I told you that the Cognitive Vision System extracts only the most significant information from images, transforming thousands of pixels without meaning into dozens of tags with semantics, can you imagine how much we could improve the speed in transferring images through the Internet? Astronauts exploring other worlds would not have to wait 20 minutes to receive an image from Earth when they are on Mars, or vice-versa.

If we could provide meaning to the objects included in pictures, our Internet image search would become more precise.

The amount of applications and consequences of such a Cognitive Brain are infinite.

Such a Cognitive Brain is definitely going to open the service robotics market.

Even more it could be a natural transition from the Information Revolution, where we are right now, into the Service Robotics Revolution.

At Cognitive Robots we have developed and tested the embryonic of the Cognitive Brain. And we have all the pieces together to continue developing it to its maturity.

Other people have had the vision of robots at the service of humans. Bill Gates wrote an article for Scientific American in 2006 “A Robot in Every Home”. However this is not a reality in the market yet, because although physically robots have been beautifully developed, they have not been intelligent enough to adapt to new circumstances in a changing environment, they are not able to perceive and interpret their environment well enough, nor are they able to infer new information from the one already known, or they have not integrated all the aspects needed into the same hardware.

The uncertainty existing in a real environment, where robots are near people to serve us has been traditionally solved using stochastic or probabilistic methods. Those methods are a type of brute force with little if any cognitive intelligence, which in my opinion is the reason why service robotics has been stuck in the same stage for so long.

Coming from another area of research, artificial intelligence, instead of robotics, we saw the problem and therefore the solutions from another point of view that set us apart. This has been the use of Qualitative Reasoning, Cognitive Vision and a Learning process. Beside these 3 preparatory, very innovative basic components of our Cognitive Brain, we have also developed the rest of the components to provide the full behavior as a Brain. All the components have been developed in a highly modular way, so that they can be improved, changed, or added, without disturbing the other components. The Cognitive Brain can grow and evolve easily. It has also been integrated into hardware, which provides the Brain with the sensorial information and the capacity of thinking and deciding. And it is independent of the “body”, therefore it can be installed in many different vehicles, or even run virtually through the Internet.

We can be witnesses to a world with robots liberating people from repetitive tasks progressively in the next 5 years if this technology is supported and developed to its full potential.

Definition of Artificial Intelligence

Artificial Intelligence (AI) could be defined as the science that creates computer programs that simulate intelligent processes normally done by people.

There is no general accepted definition for AI. There are two basic positions being confronted among researchers working in the field [Russell & Norvig 96]: the human-behavior-centered approach, and the rational approach.

Approaches to AI based on what we think is intelligence

The human-behavior-centered approach has two slightly different definitions of intelligence. It will be defined as intelligent, that which “acts” as a human, or that which “thinks” as a human. This approach is an empirical science and will need the definition of hypothesis and its confirmation with experiments.

For the defenders of intelligence as “that which acts as a human”, in 1950 Alan Turing defined the well-known Turing Test, which consisted of a human, asking questions to a computer. The test would be passed if the human could not determine if the answer came from a computer or another human at the other end of the terminal. To pass the test, the computer should be able to fulfill the following tasks (which are still open research fields inside Artificial Intelligence):

• Natural language processing to establish a satisfactory communication in any human language.
• Representing the knowledge before and during the test.
• Automatically reasoning, using the correct knowledge for the situation and inferring new knowledge from the one stored.
• The process of learning to be able to adapt to new circumstances.

For this test, it was not necessary to physically simulate a human. However, for what was known as the Turing Total Test, the machine needed to grasp objects and recognize them. To be able to pass the Turing Total Test, it was necessary to develop other fields: artificial vision and robotics.

The Turing Test has still not been completely or partially passed. Although great advances have been accomplished in each one of the areas, all of them remain open research fields, with a tremendous number of researchers working on these themes.

For those that think that intelligence is “that which thinks as a human”, the research activity is centred first in the way the human brain functions, by introspection, neuroscience discoveries, or through psychological experiments. Once a new theory of how our brain works is discovered, it can be written in a computer program. Therefore, it is an interdisciplinary approach were Computer Science meets with Neuroscience and Psychology.

On the other hand, the rational approach defends the idea that the intelligent system must be rational, which means doing the correct thing, without mistakes, which is not necessarily what happens to human beings. This approach is based in the use of mathematics (in particular the use of logic) and engineering. They argue that it is not necessary to reproduce in a machine, human errors. If we want the machine to help us do repetitive or risky tasks, they should be done in the best way possible. However, the information that we have from situations or challenges is not always complete or accurate, and therefore it cannot always be expressed in the formal terms required by the logic. Moreover, the time required finding the best logical solution might be bigger that the time we have. To solve that problem, the heuristic methods were discovered. Heuristic methods are strategies that allow approaching the solution, although they do not obtain the correct answer, in practice the result is good enough.

Definition of Intelligent Machine

A controversy has always existed with respect to the definition of ‘intelligent machine’. Would it be possible some day to build an intelligent machine? This remains a current question in the mind of researchers in the area.

In 1950, a few years after the term Artificial Intelligence was officially established (1945), Alan Turing defined a list of things that a machine would never be able to do: “be polite, multifaceted, beautiful, friendly, have initiative, have a sense of humor, distinguish between good and bad, make errors, fall in love, taste strawberries with ice cream, make someone fall in love with them, learn from experience, use words correctly, be the object of their own thoughts, have as diverse behavior as humans, do things really new”.

More that 60 years have passed since Turing defined this list, and many things have changed. Although some of the subjects remain in a borderland between science and science fiction, I would say now, based on my own personal research, and that of my peers, that:

• A machine will be able to be polite (sometimes more that some humans), when natural language processing with semantics is completed. Emotional responses can be programmed.
• They will be multifaceted, i.e., they will be experts in several branches of knowledge.
• They will be capable of being friendly, i.e., we could have a nice and fluid conversation with them.
• They will be able to have sense of humor, understanding and creating sentences with double sense.
• With respect to distinguishing between bad and good, we can have a philosophical discussion here: Are human beings able to distinguish between both concepts? In general and superficially, people are able to distinguish both concepts if they have an exterior dogma of some religion or ethic from a particular culture. The same thing could be included into a machine, which could answer: “according to this dogma, that a behavior or action is a good one, or a bad one”. Simulating the individual feeling with respect to an action, without following any dogma, would be much more difficult, that is, the deep feeling that an action provokes in a person, based on past experiences and the personal interpretation of them.
• Machines are very good at making mistakes, particularly if the input data is incorrect, uncertain or imprecise. In fact, there is a very important branch in the Artificial Intelligence field that is in charge of this problem, i.e. when the knowledge of the environment is incomplete, partial or imprecise, the machine needs to be able to react in the environment and do some action, even if it is not the best for the particular situation.

And when the information from the environment is reliable and complete, why would we need the machine to make errors? Nowadays the machines learn from their own experience, there exist different learning techniques, although these still can be improved.

• The natural language processing, still an open research field, has already delivered several workable solutions. A time will arrive when the machines use the language correctly.
• With respect to testing strawberries with ice cream, I do not have any knowledge of any research group developing an electronic mouth, but I would say it is possible. There are research groups working on electronic noses to distinguish odors. We could develop an electronic mouth to analyze the chemical components of food. I am sure they will become better than humans in defining the composition of the food they’ve tried.

There are still several concepts that are more complicated to program in a machine: to be beautiful (although as creators of the programs or machines, we see them as beautiful); to have initiative; to fall in love; to make someone fall in love with the machine; be the object of your own thoughts; to have a behavior as diverse as a human being; and to do really new things. Perhaps in several years (less that 50) someone can say, that the machines can also do that.

In fact, a machine will be able to do everything we will be able to program in a computer. And it depends on our own genius and creativity, how we can program cognitive process (representation, reasoning and learning) and creative process.

During more that 60 years of life of Artificial Intelligence, we have demonstrated that the most specialized knowledge is the easiest one to program. Proof of that is evidenced in the Expert Systems programs that have been developed (in perhaps the only research line finished in AI at the moment): medical doctors can access programs that help them in the diagnosis of some illness, taking into account all the data available and similar clinical cases, without ever being tired or having a bad day, as human beings experience. There exists a program that plays chess better that the best human chess player. There are online law firms that respond to simple questions by using a program. There are programs that demonstrate mathematical theorems and others that design integrated circuits. The success of these programs is because they are specialists, they work only in the context they were design for, and they do not give satisfactory results in any other context.

Processes where we use common sense – those that everybody knows how to do, those that we perform everyday almost mechanically – are the ones that are still a challenge to be simulated by a machine. Some of them we can’t image how to program.

I will give you an example – cooking an omelet, which is a very basic dish even for those who don’t like to cook. Every action involved in cooking an omelet is still very difficult for a robot. For instance, cracking an egg into a plate and separating the content from the shell. If the egg falls and breaks on the floor, would the robot be able to respond successfully? We should be able to program the robot so that when we drop the egg into a pan with oil and there is fire underneath it, the egg goes from a liquid state to a solid state. But if the time passed is too long, the egg goes to the burned state, and both liquid and burned states are not edible. The number of eggs, the size of the pan, and the amount of fire underneath the pan, influence the time of exposure of the egg to the fire – although the egg is not completely solid in the upper part, it does not mean that it cannot be burned on the other side. Moreover, when we learn how to cook eggs, basically by observation and practice, we can also use the knowledge as analogy, when we drop any other liquid into a pan on top of the fire, which starts transforming into a solid state, such as crepes. Programming the mental process to establish analogies is a passionate open research area.

Why is it so difficult to program common sense? Here are some hints: 1. We need several years to acquire those abilities since we are born; 2. We still do not know well enough the internal mechanisms and processes that happen with them; 3. We need knowledge from many different sources.

Robot arm manipulators have been very successful in many production lines for the last 50 years, repeating the same sequence of steps mechanically, without being aware of the processes they are doing, but they cannot adapt to unexpected changes in the environment. Even the most spectacular humanoid robots (such as QRIO from SONY or NAO from Aldebaran) are still basically in this stage of evolution.

Science fiction movies and media have put out the idea that the robotics area is more advanced that it really is. We still do not have robots at home because they are not intelligent enough to react in an unpredictable environment.

During more than 20 years I have been leading research in the area of cognition to include real intelligence to robots. We have developed the first Cognitive Brain for Service Robotics® in the market, an embryonic artificial brain which incorporates the basics of human intelligence.

To learn more visit our web site: www.c-robots.com

Next topics coming soon in this blog:

What robots are really going to be able to do and when?

What is necessary for the service robotics market to take off?