EgoAVFlow: 人間の一人称視点動画から3Dフローを介した能動視覚によるロボット方策学習
EgoAVFlow: Robot Policy Learning with Active Vision from Human Egocentric Videos via 3D Flow
人間の一人称視点動画から3Dフロー表現を共有して操作と能動視覚を学習し、ロボット実演なしで視点制御と操作を実現する手法を提案。
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: Daesol Cho, Youngseok Jang, Danfei Xu, Sehoon Ha
分類: cs.RO
原文アブストラクト
Egocentric human videos provide a scalable source of manipulation demonstrations; however, deploying them on robots requires active viewpoint control to maintain task-critical visibility, which human viewpoint imitation often fails to provide due to human-specific priors. We propose EgoAVFlow, which learns manipulation and active vision from egocentric videos through a shared 3D flow representation that supports geometric visibility reasoning and transfers without robot demonstrations. EgoAVFlow uses diffusion models to predict robot actions, future 3D flow, and camera trajectories, and refines viewpoints at test time with reward-maximizing denoising under a visibility-aware reward computed from predicted motion and scene geometry. Real-world experiments under actively changing viewpoints show that EgoAVFlow consistently outperforms prior human-demo-based baselines, demonstrating effective visibility maintenance and robust manipulation without robot demonstrations.
