ContactMimic: 接触制御によるヒューマノイドの物体インタラクション
ContactMimic: Humanoid Object Interaction via Contact Control
キーポイント追跡だけでは不十分な物体インタラクション(椅子に座る、黒板を拭くなど)に対し、接触コマンドを明示的に追跡する学習フレームワークを提案。接触追従報酬と軌道拡張により接触行動をキーポイント幾何から分離し、実世界で接触制御を実現した。
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: Xinyao Li, Xialin He, Runpei Dong, Saurabh Gupta
分類: cs.RO
原文アブストラクト
Keypoint tracking alone is insufficient for object interaction tasks such as sitting on a chair, wiping a board, or pushing furniture, where the robot can reach the correct pose without making meaningful physical contact with the object. We present CONTACTMIMIC, a learning framework that tracks explicit partlevel binary contact commands alongside keypoint trajectories. CONTACTMIMIC is made possible through the use of contact-following rewards and a trajectory augmentation scheme aimed at breaking the correlations between keypoint trajectories and contact labels. The resulting policy successfully decouples contact behavior from keypoint geometry, and achieves precise physical contact as well as contact-controllability (produce or suppress contact during deployment as desired). Simulation experiments across 10 diverse human-object interaction motions confirm that CONTACTMIMIC exhibits contact controllability that enables it to complete manipulation tasks without task-specific rewards, while also outperforming keypoint-only trackers on contact-relevant tasks. Ablations confirm the necessity of the proposed trajectory augmentation scheme and sim2real deployment validates contact controllability in the real world across 5 different motions. Video results are available on https://lixinyao11.github.io/contactmimic-page/.
