Skip to Main content Skip to Navigation
Journal articles

Fast Damage Recovery in Robotics with the T-Resilience Algorithm

Abstract : Damage recovery is critical for autonomous robots that need to operate for a long time without assistance. Most current methods are complex and costly because they require anticipating each potential damage in order to have a contingency plan ready. As an alternative, we introduce the T-Resilience algorithm, a new algorithm that allows robots to quickly and autonomously discover compensatory behaviors in unanticipated situations. This algorithm equips the robot with a self-model and discovers new behaviors by learning to avoid those that perform differently in the self-model and in reality. Our algorithm thus does not identify the damaged parts but it implicitly searches for efficient behaviors that do not use them. We evaluate the T-Resilience algorithm on a hexapod robot that needs to adapt to leg removal, broken legs and motor failures; we compare it to stochastic local search, policy gradient and the self-modeling algorithm proposed by Bongard et al. The behavior of the robot is assessed on-board thanks to a RGB-D sensor and a SLAM algorithm. Using only 25 tests on the robot and an overall running time of 20 minutes, T-Resilience consistently leads to substantially better results than the other approaches.
Document type :
Journal articles
Complete list of metadatas

Cited literature [91 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-00932862
Contributor : Antoine Cully <>
Submitted on : Friday, January 17, 2014 - 7:34:50 PM
Last modification on : Thursday, December 10, 2020 - 12:32:21 PM
Long-term archiving on: : Friday, April 18, 2014 - 11:53:48 AM

File

resilience.pdf
Files produced by the author(s)

Identifiers

Citation

Sylvain Koos, Antoine Cully, Jean-Baptiste Mouret. Fast Damage Recovery in Robotics with the T-Resilience Algorithm. The International Journal of Robotics Research, SAGE Publications, 2013, 32 (14), pp.1700-1723. ⟨10.1177/0278364913499192⟩. ⟨hal-00932862⟩

Share

Metrics

Record views

226

Files downloads

591