EgoScale：利用多样化的视点人类数据进行规模化灵巧操作
EgoScale: Scaling Dexterous Manipulation with Diverse Egocentric Human Data
AI总结：
EgoScale通过大规模视点人类数据训练视觉语言动作模型，实现高效的灵巧操作转移，提升机器人任务成功率54%。
摘要：
人类行为是学习物理智能最可扩展的数据源之一，但如何有效地利用它来实现灵巧操作仍不清楚。尽管先前的工作展示了在受限环境下的人类到机器人的转移，但不清楚大规模的人类数据是否能支持精细的、高自由度的灵巧操作。我们提出了EgoScale，一个基于大规模视点人类数据的人类到灵巧操作转移框架。我们训练了一个视觉语言动作（VLA）模型，使用超过20,854小时的动作标注视点人类视频进行训练，比先前的努力大了20多倍，并揭示了人类数据规模与验证损失之间的对数线性缩放定律。这种验证损失与下游真实机器人性能有很强的相关性，确立了大规模人类数据作为可预测的监督源。除了规模之外，我们引入了一个简单的两阶段转移配方：大规模人类预训练后跟轻量级对齐的人机中等训练。这使能够实现强大的长周期灵巧操作和一次任务适应，只需最小的机器人监督。我们的最终策略在使用22自由度灵巧机械手的基准上将平均成功率提高了54%，并且能有效转移到自由度较低的手机器人上，表明大规模人类运动提供了可重用、与身体无关的运动先验。
英文摘要：
Human behavior is among the most scalable sources of data for learning physical intelligence, yet how to effectively leverage it for dexterous manipulation remains unclear. While prior work demonstrates human to robot transfer in constrained settings, it is unclear whether large scale human data can support fine grained, high degree of freedom dexterous manipulation. We present EgoScale, a human to dexterous manipulation transfer framework built on large scale egocentric human data. We train a Vision Language Action (VLA) model on over 20,854 hours of action labeled egocentric human video, more than 20 times larger than prior efforts, and uncover a log linear scaling law between human data scale and validation loss. This validation loss strongly correlates with downstream real robot performance, establishing large scale human data as a predictable supervision source. Beyond scale, we introduce a simple two stage transfer recipe: large scale human pretraining followed by lightweight aligned human robot mid training. This enables strong long horizon dexterous manipulation and one shot task adaptation with minimal robot supervision. Our final policy improves average success rate by 54% over a no pretraining baseline using a 22 DoF dexterous robotic hand, and transfers effectively to robots with lower DoF hands, indicating that large scale human motion provides a reusable, embodiment agnostic motor prior.
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。
