Wh0: 生成的世界モデルによるスケーラブルな自己中心視点の人間手操作データ生成
Wh0: Generative World Models as Scalable Sources of Egocentric Human Hand Manipulation Data
生成ビデオ世界モデルを用いて、ロボット学習に使える自己中心視点の人間手操作ビデオデータを大量生成し、実ロボットデータと組み合わせて器用な操作VLAモデルの性能を大幅に向上させる手法を提案した。
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: Yangtao Chen, Zixuan Chen, Peiyang Wang, Yong-Lu Li, Jing Huo, Jieqi Shi, Yang Gao
分類: cs.RO
原文アブストラクト
Scaling dexterous manipulation requires generalization across objects, scenes, and tasks, yet existing data sources face a trade-off between scale and scene/embodiment alignment: teleoperation data is well aligned with robot deployment but expensive to collect; simulation is scalable but limited by the sim-to-real gap; and real egocentric videos scale effectively but remain misaligned with robot deployment. We propose Wh0, a framework that uses generative video world models as scalable and controllable sources of egocentric human-hand manipulation data to unlock the manipulation capabilities of pretrained dexterous VLA models. Conditioned on language, objects, and scenes, Wh0 uses a generative world model to produce WM-H, a 50k-episode dataset of egocentric human-object interaction videos. Wh0 then converts the generated videos into robot-trainable supervision through hand motion reconstruction and visual editing. Co-trained with a limited amount of real robot data, WM-H adapts pretrained VLA models to dexterous manipulation deployment. Across 18 real-world dexterous manipulation tasks, compared with a model post-trained only on robot data, Wh0 improves zero-shot success on unseen tasks from 8.3% to 38.9%. Ablation studies further show that scalable generation and scene/embodiment alignment are key drivers of performance gains. Videos and open-source code can be found on our project website: https://chenyt31.github.io/wh0.github.io/.
