DexCtrl: 適応的コントローラ学習によるsim-to-real器用さの実現
DexCtrl: Towards Sim-to-Real Dexterity with Adaptive Controller Learning
軌道とコントローラの履歴から行動と制御パラメータを同時に学習し、実行中に制御パラメータを自動調整することで、手動調整なしにシミュレーションから実機への転移ギャップを軽減する枠組みを提案した。
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: Shuqi Zhao, Ke Yang, Yuxin Chen, Chenran Li, Yichen Xie, Xiang Zhang, Changhao Wang, Masayoshi Tomizuka
分類: cs.RO, cs.SY, eess.SY
原文アブストラクト
Dexterous manipulation has seen remarkable progress in recent years, with policies capable of executing many complex and contact-rich tasks in simulation. However, transferring these policies from simulation to real world remains a significant challenge. One important issue is the mismatch in low-level controller dynamics, where identical trajectories can lead to vastly different contact forces and behaviors when control parameters vary. Existing approaches often rely on manual tuning or controller randomization, which can be labor-intensive, task-specific, and introduce significant training difficulty. In this work, we propose a framework that jointly learns actions and controller parameters based on the historical information of both trajectory and controller. This adaptive controller adjustment mechanism allows the policy to automatically tune control parameters during execution, thereby mitigating the sim-to-real gap without extensive manual tuning or excessive randomization. Moreover, by explicitly providing controller parameters as part of the observation, our approach facilitates better reasoning over force interactions and improves robustness in real-world scenarios. Experimental results demonstrate that our method achieves improved transfer performance across a variety of dexterous tasks involving variable force conditions.
