Towards semi-episodic learning for robot damage recovery

Konstantinos Chatzilygeroudis 1 Antoine Cully 2 Jean-Baptiste Mouret 1
1 LARSEN - Lifelong Autonomy and interaction skills for Robots in a Sensing ENvironment
Inria Nancy - Grand Est, LORIA - AIS - Department of Complex Systems, Artificial Intelligence & Robotics
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 lifetime autonomy and adaptivity. Preliminary experiments on a toy simulation and a 6-legged robot locomotion task show promising results.
Complete list of metadatas

Cited literature [16 references]  Display  Hide  Download

https://hal.inria.fr/hal-01376288
Contributor : Konstantinos Chatzilygeroudis <>
Submitted on : Tuesday, October 4, 2016 - 4:17:45 PM
Last modification on : Tuesday, December 18, 2018 - 4:40:22 PM
Long-term archiving on : Friday, February 3, 2017 - 4:08:28 PM

Files

ailta.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01376288, version 1
  • ARXIV : 1610.01407

Collections

Citation

Konstantinos Chatzilygeroudis, Antoine Cully, Jean-Baptiste Mouret. Towards semi-episodic learning for robot damage recovery. Workshop on AI for Long-Term Autonomy at the IEEE International Conference on Robotics and Automation (ICRA), Lars Kunze; Nick Hawes; Tom Duckett; Gabe Sibley, May 2016, Stockholm, Sweden. ⟨hal-01376288⟩

Share

Metrics

Record views

464

Files downloads

78