arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2606.08107cs.ROcs.AI

Ego-Pi: 面向自我中心人类与机器人数据的VLA微调

Ego-Pi: VLA Fine-Tuning for Ego-Centric Human and Robot Data

Stanford University(斯坦福大学);Meta

Ji Woong Kim, Ke Wang, Zipeng Fu, Sirui Chen, Cong Zhao, Jeff Lai, Chelsea Finn

AI总结:

为解决机器人数据稀缺问题,利用自我中心人类数据,基于π₀.₅模型微调,使机器人学习新任务语义并组合现有技能,无需对应机器人数据。

摘要:

机器人技术面临数据稀缺的根本挑战。与语言或视觉研究不同,机器人操作没有互联网规模的数据集。一个有前景的途径是利用自我中心人类数据,这类数据更容易收集、范围更广且规模更大。为此,我们研究了跨人类和配备灵巧五指手的类人机器人实体学习的关键设计选择,以$π_{0.5}$模型为基础。我们的结果表明,人类数据使机器人能够学习新的任务语义,并将现有技能组合成新颖的行为,而无需相应的机器人数据。论文网站:https://egopipaper.github.io/

英文摘要:

Robotics faces a fundamental challenge of data scarcity. Unlike language or vision research, there is no internet-scale dataset for robotic manipulation. A promising path forward is to leverage egocentric human data, which can be collected more easily, with greater breadth, and at a larger scale. Towards this end, we investigate key design choices for learning across human and humanoid embodiments equipped with dexterous five-finger hands, using the $π_{0.5}$ model as a foundation. Our results show that human data enables robots to learn new task semantics and compose existing skills into novel behaviors without corresponding robot data. The paper website is here: https://egopipaper.github.io/

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。

↑