Teresa Escrig

News and oppinion about Cognitive AI & Robotics

Cognitive Robots’ Cognitive Brain for Service Robotics has been successfully incorporated into Robosoft’s Kompai companion robot

leave a comment

Last week the results of the ECHORD C-Brain experiment was presented at IROS’12 conference in Portugal.

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!

Leave a Reply