Fast Damage Recovery in Robotics with the T-Resilience Algorithm
This addresses the challenge of long-term autonomous operation for robots by providing a fast and efficient recovery method, though it is incremental as it builds on existing self-modeling approaches.
The paper tackles the problem of autonomous damage recovery in robots by introducing the T-Resilience algorithm, which enables robots to quickly discover compensatory behaviors in unanticipated situations without identifying damaged parts, resulting in substantially better performance than other methods using only 25 tests and 20 minutes of running time.
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.