関節トルク空間への摂動注入によるヒューマノイド歩行ポリシーのsim-to-real
Sim-to-Real of Humanoid Locomotion Policies via Joint Torque Space Perturbation Injection
シミュレーション訓練時に、順動力学計算に用いる関節トルクへ状態依存の摂動を加えることで、従来のドメインランダム化より広い現実ギャップに頑健なヒューマノイド歩行ポリシーを獲得する手法を提案した。
著者: Junhyeok Rui Cha, Woohyun Cha, Jaeyong Shin, Donghyeon Kim, Jaeheung Park
分類: cs.RO
原文アブストラクト
This paper proposes a novel alternative to existing sim-to-real methods for training control policies with simulated experiences. Prior sim-to-real methods for legged robots mostly rely on the domain randomization approach, where a fixed finite set of simulation parameters is randomized during training. Instead, our method adds state-dependent perturbations to the input joint torque used for forward simulation during the training phase. These state-dependent perturbations are designed to simulate a broader range of reality gaps than those captured by randomizing a fixed set of simulation parameters. Experimental results show that our method enables humanoid locomotion policies that achieve greater robustness against complex reality gaps unseen in the training domain.
