力発揮型ヒューマノイドの移動操作のための運動学を考慮したマルチポリシー強化学習
Kinematics-Aware Multi-Policy Reinforcement Learning for Force-Capable Humanoid Loco-Manipulation
上半身・下半身・差分コマンドの3段階に分けた強化学習で、ヒューマノイドが移動しながら環境に力を加える操作を可能にした研究。
詳しい要約
1. どんなもの?
2. 先行研究と比べてどこがすごい?
3. 技術・手法の肝は?
4. どうやって有効だと検証した?
5. 議論はある?
6. 次に読むべき論文は?
※ AIが要旨から生成した要約です。正確性は原文をご確認ください。
著者: Kaiyan Xiao, Zihan Xu, Cheng Zhe, Chengju Liu, Qijun Chen
分類: cs.RO
原文アブストラクト
Humanoid robots, with their human-like morphology, hold great potential for industrial applications. However, existing loco-manipulation methods primarily focus on dexterous manipulation, falling short of the combined requirements for dexterity and proactive force interaction in high-load industrial scenarios. To bridge this gap, we propose a reinforcement learning-based framework with a decoupled three-stage training pipeline, consisting of an upper-body policy, a lower-body policy, and a delta-command policy. To accelerate upper-body training, a heuristic reward function is designed. By implicitly embedding forward kinematics priors, it enables the policy to converge faster and achieve superior performance. For the lower body, a force-based curriculum learning strategy is developed, enabling the robot to actively exert and regulate interaction forces with the environment.
