METIS：多源自体训练用于集成的灵巧视觉-语言-动作模型
METIS: Multi-Source Egocentric Training for Integrated Dexterous Vision-Language-Action Model
AI总结：
METIS通过多源自体训练构建集成的视觉-语言-动作模型，提升灵巧操作的泛化能力和鲁棒性。
摘要：
构建一个能够跨多样任务感知、推理和行动的通用机器人仍是一个开放性挑战，尤其是对于灵巧操作。主要瓶颈在于缺乏大规模、动作标注的数据用于灵巧技能，因为远程操作困难且成本高。人类数据以其规模庞大和多样化的操作行为，为学习机器人动作提供了丰富的先验知识。尽管先前工作已探索利用人类演示，但往往受限于有限的场景和人与机器人之间的大视觉差距。为消除这些限制，我们提出了METIS，一种针对灵巧操作的视觉-语言-动作（VLA）模型，该模型在多源自体数据集上进行了预训练。我们首先构建了EgoAtlas，它整合了来自多个来源的大规模人类和机器人数据，所有数据都统一在一个一致的动作空间下。我们进一步提取了运动感知动态，一种紧凑且离散化的运动表示，为VLA训练提供了高效且表达丰富的监督。基于这些，METIS将推理和行动整合到统一的框架中，使有效部署到下游的灵巧操作任务成为可能。我们的方法在六个现实任务中展现了卓越的灵巧操作能力，实现了六项任务的最高平均成功率。实验结果还突显了方法在非分布场景中的优越泛化能力和鲁棒性。这些发现强调METIS是向通用灵巧操作模型迈出的重要一步。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
