Phantom: 人間の動画だけでロボットを訓練する
Phantom: Training Robots Without Robots Using Only Human Videos
人間の動画デモから手の姿勢推定と視覚編集でロボット用の観測・行動ペアを生成し、ロボットデータなしで操作方策を訓練するフレームワーク。実機で最大92%の成功率を達成。
著者: Marion Lepert, Jiaying Fang, Jeannette Bohg
分類: cs.RO
原文アブストラクト
Training general-purpose robots requires learning from large and diverse data sources. Current approaches rely heavily on teleoperated demonstrations which are difficult to scale. We present a scalable framework for training manipulation policies directly from human video demonstrations, requiring no robot data. Our method converts human demonstrations into robot-compatible observation-action pairs using hand pose estimation and visual data editing. We inpaint the human arm and overlay a rendered robot to align the visual domains. This enables zero-shot deployment on real hardware without any fine-tuning. We demonstrate strong success rates-up to 92%-on a range of tasks including deformable object manipulation, multi-object sweeping, and insertion. Our approach generalizes to novel environments and supports closed-loop execution. By demonstrating that effective policies can be trained using only human videos, our method broadens the path to scalable robot learning.
