Fast Damage Recovery in Robotics with the T-Resilience Algorithm

TL;DR

The paper introduces the T-Resilience algorithm enabling autonomous robots to rapidly discover compensatory behaviors after damage, significantly improving recovery speed and effectiveness with minimal testing.

Contribution

The T-Resilience algorithm is a novel damage recovery method that learns to find effective behaviors without prior damage knowledge, outperforming existing approaches.

Findings

T-Resilience achieves better recovery results than other methods.

It requires only 25 tests and 20 minutes to adapt.

The algorithm effectively handles various types of robot damage.

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.