WARPED: 手首視点レンダリングによる自己中心視点の人間デモからのロボットポリシー学習
WARPED: Wrist-Aligned Rendering for Robot Policy Learning from Egocentric Human Demonstrations
単眼RGBの自己中心視点動画から、手首視点の写実的な観測を合成してロボットポリシーを訓練するフレームワークを提案。遠隔操作デモと同等の成功率を5〜8倍短いデータ収集時間で達成した。
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: Harry Freeman, Chung Hee Kim, George Kantor
分類: cs.RO
原文アブストラクト
Recent advancements in learning from human demonstration have shown promising results in addressing the scalability and high cost of data collection required to train robust visuomotor policies. However, existing approaches are often constrained by a reliance on multiview camera setups, depth sensors, or custom hardware and are typically limited to policy execution from third-person or egocentric cameras. In this paper, we present WARPED, a framework designed to synthesize realistic wrist-view observations from human demonstration videos to facilitate the training of visuomotor policies using only monocular RGB data. With data collected from an egocentric RGB camera, our system leverages vision foundation models to initialize the interactive scene. A hand-object interaction pipeline is then employed to track the hand and manipulated object and retarget the trajectories to a robotic end-effector. Lastly, photo-realistic wrist-view observations are synthesized via Gaussian Splatting to directly train a robotic policy. We demonstrate that WARPED achieves success rates comparable to policies trained on teleoperated demonstration data for five tabletop manipulation tasks, while requiring 5-8x less data collection time.
