MPCからの安全な移動スキル学習
Safe Learning of Locomotion Skills from MPC
モデル予測制御(MPC)を専門家として活用し、安全なデータ集約手法により移動スキルを安全に学習するフレームワークを提案。訓練中の失敗を大幅に削減し、外乱に対するロバスト性も向上させる。
著者: Xun Pua, Majid Khadiv
分類: cs.RO
原文アブストラクト
Safe learning of locomotion skills is still an open problem. Indeed, the intrinsically unstable nature of the open-loop dynamics of locomotion systems renders naive learning from scratch prone to catastrophic failures in the real world. In this work, we investigate the use of iterative algorithms to safely learn locomotion skills from model predictive control (MPC). In our framework, we use MPC as an expert and take inspiration from the safe data aggregation (SafeDAGGER) framework to minimize the number of failures during training of the policy. Through a comparison with other standard approaches such as behavior cloning and vanilla DAGGER, we show that not only our approach has a substantially fewer number of failures during training, but the resulting policy is also more robust to external disturbances.
