HumanEgo: 人間の一人称視点動画数分からのゼロショットロボット学習
HumanEgo: Zero-Shot Robot Learning from Minutes of Human Egocentric Videos
人間の一人称視点動画からロボット操作スキルをゼロショットで転移するフレームワークを提案。手と物体の相互作用をエンティティレベルで表現し、フローマッチングポリシーと補助損失で学習することで、ロボットデータ不要で高効率な学習を実現した。
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: Zhi Wang, Botao He, Kelin Yu, Seungjae Lee, Ruohan Gao, Furong Huang, Yiannis Aloimonos
分類: cs.RO, cs.AI, cs.CV, cs.LG
原文アブストラクト
Human egocentric video captures rich manipulation demonstrations without any robot hardware, yet transferring these skills to robots remains challenging due to the embodiment gap between human and robot in both visual appearance and kinematics. We present HumanEgo, a framework that bridges the embodiment gap by lifting each human demonstration to an entity-level representation of hand-object interaction, and training a flow matching policy with dense auxiliary objectives that amplify supervision from every trajectory. HumanEgo is robot-data-free, hardware-agnostic, data-efficient, and zero-shot human-to-robot transferable. With only 30 minutes of human videos per task, HumanEgo achieves 92.5% average success across four real-world tasks (75% with just 15 minutes), outperforms matched-time robot teleoperation by 41%, and robustly transfers zero-shot across novel robots, cameras, and environments. We release HumanEgo as an easy-to-use, open-source framework for learning robot policies directly from human data: https://github.com/TX-Leo/HumanEgo
