RoboEarth

Connecting Robots Worldwide

 

At its core, RoboEarth is a World Wide Web for robots: a giant network and database repository where robots can share information and learn from each other about their behavior and their environment. Bringing a new meaning to the phrase “experience is the best teacher”, the goal of RoboEarth is to allow robotic systems to benefit from the experience of other robots, paving the way for rapid advances in machine cognition and behaviour, and ultimately, for more subtle and sophisticated human-machine interaction.

For more information please see http://www.roboearth.org

Sharing articulation models

One of the first demonstrators of RoboEarth illustrates how robots can benefit from sharing articulation models to successfully open doors and drawers.

The video below shows how a compliant robot arm with accurate sensing capabilities can learn articulation models for the drawers and doors of a cupboard. This was done by generating a reference trajectory for the robot arm based on an initial guess for the unknown articulation model. In subsequent steps, measurements of the compliant arm's deviation from this reference trajectory were used to continuously refine the model estimate in a closed-loop control structure. At the end of this learning stage, the learned articulation model of a specific door instance was attached to the door's object description and uploaded to the RoboEarth database.

Second, a service robot with less accurate sensing capabilities downloaded the stored articulation model and its parameters (in this case, the door radius and axis of rotation) from the RoboEarth database. Using this knowledge, this second robot was able to generate an open-loop trajectory and successfully open the cupboard's door.

This demonstration illustrates that robots with different hardware and control architectures can use a common database to share knowledge. It also shows how robots can create knowledge that is useful across different robot platforms and how robots benefit from the experience of other robots to interact with objects.