Robots bootstrapped through learning from experience

Published on Jul 28, 2016

This video shows an integrated demonstration of central results of the Xperience project. In the example task of preparing a salad
and setting a table together with a human, the robot ARMAR-III uses its knowledge gained from previous experience to plan and execute
the necessary actions towards its goal. The demonstration highlights the aspects of the realization of integrated complete robot systems,
and emphasizes the concept of structural bootstrapping on the levels of human-robot communication and physical interaction, sensorimotor
learning, learning of object affordances, and planning in robotics.

The scenario integrates several scientific methods developed in the project:
- Execution of complex manipulation tasks and plans based on the developed architecture and its implementation
- Automatic generation of domain descriptions for planning based on the robots experience
- Replanning on the fly in case of missing objects
- Replacing missing objects by employing different bootstrapping (replacement) strategies
- Replacing actions by adapting previously learnt actions to new context
- Human-robot communication in natural language including the robot's understanding of spoken commands, world descriptions, and feedback as well as the robot's ability to ask the human for help and information
- Handing over objects between the robot and the human