Teresa Escrig

News and oppinion about Cognitive AI & Robotics

Archive for the ‘Robotics’ tag

Willow Garage’ s PR2 robot giving the disable independence

leave a comment

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 >

 

Hanson Robokind unveils latest version of its Zeno humanoid robot

leave a comment

by 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.

 

Cognitive Robots includes Common-Sense Knowledge and Reasoning into their Robotics and Computer Vision solutions

5 comments

Representation, reasoning and learning are the basic principles of human intelligence. The emulation of human intelligence has been the aim of Artificial Intelligence since its origins in 1956.

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: Read the rest of this entry »

This Little Robot Could Totally Transform The Way Humanity Shops

leave a comment

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.”

Read more >

MIT creates intelligent car co-pilot that only interferes if you’re about to crash

leave a comment

By 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 >

More light about why Amazon acquired Kiva

3 comments

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.

Skippy is an internet-controlled robot that skips stones across a pond

leave a comment

We are going to be amazed of the number and variety of applications that people will came up with in service robotics…

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

By , July 11, 2012

Read more >

Biologically accurate robotic legs get the gait right

leave a comment

Very impressive video of the biologically accurate robotic legs in action.

By , July 10, 2012

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 >

Why Amazon acquired Kiva?

leave a comment

by Mark P. Mills, 3/23/2012

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 >

Automated robotic warehousing is a hot investment focus

leave a comment

Amazon just acquired Kiva Systems for $775 million and now Permira, a European private equity firm, announced that it was acquiring Intelligrated for an amount in excess of $500 million! The deal is expected to close after the summer.

Read more >