TY - JOUR AB - 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 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 behavior in unanticipated situations. This algorithm equips the robot with a self-model and discovers new behavior 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 behavior that does 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 an RGB-D sensor and a SLAM algorithm. Using only 25 tests on the robot and an overall running time of 20 min, T-resilience consistently leads to substantially better results than the other approaches. AU - Koos,S AU - Cully,A AU - Mouret,J-B DO - 10.1177/0278364913499192 EP - 1723 PY - 2013/// SN - 0278-3649 SP - 1700 TI - Fast damage recovery in robotics with the T-resilience algorithm T2 - The International Journal of Robotics Research UR - http://dx.doi.org/10.1177/0278364913499192 UR - http://hdl.handle.net/10044/1/50400 VL - 32 ER -