特権的批評家トレーニングによるセンサ不要のスラスタ故障適応：エンドツーエンド強化学習
Privileged Critic Training Enables Sensor-Free Thruster Fault Adaptation in End-to-End RL
スラスタ駆動ロボットの故障耐性ナビゲーションにおいて、訓練中にのみ真の故障状態を価値関数へ与える特権的批評家トレーニングにより、センサなしで故障適応を実現する手法RAFTを提案した。
著者: Ricard Marsal I Castan, Miguel A. Olivares-Méndez
分類: cs.RO
原文アブストラクト
Fault-tolerant navigation for thruster-actuated robots requires online adaptation to failures that are neither binary nor fully observable: thrusters may degrade continuously, fail dead, or jam stuck-open. Classical fault detection pipelines require dedicated sensors unavailable at deployment; oracle controllers that observe the true failure state are equally impractical. We show that privileged critic training is sufficient for sensor-free fault adaptation: giving the PPO value function access to the true degradation state dgt during training, while the actor receives only standard task observations, shapes a policy that compensates for failures at deployment without any dedicated fault sensing. We propose RAFT (Recurrent Asymmetric Fault Tolerant), a policy with recurrent memory trained with a privileged asymmetric critic. Evaluated on a floating-platform robot (8 thrusters, 1 reaction wheel) under up to four simultaneous thruster failures, RAFT achieves 70.2% success at four concurrent failures, closing 84% of the gap from a failure-naive baseline (4.8%) to an oracle policy that sees the full degradation state at deployment (82.4%). All code, checkpoints, and data are open-source.