METIS: 多源自己中心データによる統合型巧みな視覚-言語-行動モデルの事前学習
METIS: Multi-Source Egocentric Training for Integrated Dexterous Vision-Language-Action Model
人間とロボットの自己中心視点データを統合した大規模データセットEgoAtlasと動作表現を用いて、巧みな操作のための視覚-言語-行動モデルを事前学習し、実世界タスクでの成功率と汎化性能を向上させた。
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: Yankai Fu, Ning Chen, Junkai Zhao, Shaozhe Shan, Guocai Yao, Pengwei Wang, Zhongyuan Wang, Shanghang Zhang
分類: cs.RO, cs.CV
原文アブストラクト
Building a generalist robot that can perceive, reason, and act across diverse tasks remains an open challenge, especially for dexterous manipulation. A major bottleneck lies in the scarcity of large-scale, action-annotated data for dexterous skills, as teleoperation is difficult and costly. Human data, with its vast scale and diverse manipulation behaviors, provides rich priors for learning robotic actions. While prior works have explored leveraging human demonstrations, they are often constrained by limited scenarios and a large visual gap between human and robots. To eliminate these limitations, we propose METIS, a vision-language-action (VLA) model for dexterous manipulation pretrained on multi-source egocentric datasets. We first construct EgoAtlas, which integrates large-scale human and robotic data from multiple sources, all unified under a consistent action space. We further extract motion-aware dynamics, a compact and discretized motion representation, which provides efficient and expressive supervision for VLA training. Built upon them, METIS integrates reasoning and acting into a unified framework, enabling effective deployment to downstream dexterous manipulation tasks. Our method demonstrates exceptional dexterous manipulation capabilities, achieving highest average success rate in six real-world tasks. Experimental results also highlight the superior generalization and robustness to out-of-distribution scenarios. These findings emphasize METIS as a promising step toward a generalist model for dexterous manipulation.
