Towards semi-episodic learning for robot damage recovery

Published on Mar 31, 2016

"Towards semi-episodic learning for robot damage recovery"

Konstantinos Chatzilygeroudis, Antoine Cully and Jean-Baptiste Mouret

Paper submitted to "Artificial Intelligence for Long-Term Autonomy" (AILTA) workshop in ICRA 2016.

Abstract:

The recently introduced Intelligent Trial and Error algorithm (IT&E) enables robots to creatively adapt to damage in a matter of minutes by combining an off-line evolutionary algorithm and an on-line learning algorithm based on Bayesian Optimization. We extend the IT&E algorithm to allow for robots to learn to compensate for damages while executing their task(s). This leads to a semi-episodic learning scheme that increases the robot’s life-time autonomy and adaptivity. Preliminary experiments on a toy simulation and a 6-legged robot locomotion task show promising results.

This video shows a 6-legged robot performing locomotion tasks despite the left middle leg being removed using our technique.

This work was supported by the ERC project “ResiBots” (grant agreement No 637972), funded by the European Research Council.