arXiv 2602.101062026-06-04cs.RO

EgoHumanoid: 通过无机器人眼示范解锁真实场景中的移动- manipulation

EgoHumanoid: Unlocking In-the-Wild Loco-Manipulation with Robot-Free Egocentric Demonstration

University of California, Berkeley（加州大学伯克利分校）；Tsinghua University（清华大学）

Modi Shi, Shijia Peng, Jin Chen, Haoran Jiang, Tianyu Li, Di Huang, Ping Luo, Hongyang Li, Li Chen

备注：: Project page: https://opendrivelab.com/EgoHumanoid

AI总结：

本文提出EgoHumanoid框架，通过结合大量眼示范数据和少量机器人数据共同训练视觉-语言-动作策略，使机器人能够执行多样化的现实环境中的移动- manipulation任务，实验表明无机器人数据显著提升了性能，尤其在未见过的环境中表现更优。

摘要：

人类示范提供丰富的环境多样性，并能自然扩展规模，使其成为机器人远程操作的有吸引力替代方案。尽管这一范式已促进了机器人手臂操作的发展，但其在更具挑战性且数据需求高的问题——人形机器人移动- manipulation方面的潜力仍 largely未被探索。我们提出了EgoHumanoid，这是首个框架，通过大量眼示范数据和少量机器人数据共同训练视觉-语言-动作策略，使机器人能够执行多样化的现实环境中的移动- manipulation任务。为弥合人类与机器人之间的身体差距，包括形态和视角的差异，我们引入了一个系统化的对齐流程，涵盖从硬件设计到数据处理的各个方面。开发了一种便携式系统用于可扩展的人类数据收集，并建立了实用的收集协议以提高可迁移性。我们的核心人类到人形机器人对齐流程包含两个关键组件。视图对齐减少了由相机高度和视角变化引起的视觉领域差异。动作对齐将人类动作映射到一个统一的、在人形机器人控制中可行的动作空间。广泛的现实世界实验表明，结合无机器人眼数据显著优于仅机器人数据的基线，提高了51%，特别是在未见过的环境中。我们的分析进一步揭示了哪些行为能够有效迁移以及人类数据扩展的潜力。

英文摘要：

Human demonstrations offer rich environmental diversity and scale naturally, making them an appealing alternative to robot teleoperation. While this paradigm has advanced robot-arm manipulation, its potential for the more challenging, data-hungry problem of humanoid loco-manipulation remains largely unexplored. We present EgoHumanoid, the first framework to co-train a vision-language-action policy using abundant egocentric human demonstrations together with a limited amount of robot data, enabling humanoids to perform loco-manipulation across diverse real-world environments. To bridge the embodiment gap between humans and robots, including discrepancies in physical morphology and viewpoint, we introduce a systematic alignment pipeline spanning from hardware design to data processing. A portable system for scalable human data collection is developed, and we establish practical collection protocols to improve transferability. At the core of our human-to-humanoid alignment pipeline lies two key components. The view alignment reduces visual domain discrepancies caused by camera height and perspective variation. The action alignment maps human motions into a unified, kinematically feasible action space for humanoid control. Extensive real-world experiments demonstrate that incorporating robot-free egocentric data significantly outperforms robot-only baselines by 51\%, particularly in unseen environments. Our analysis further reveals which behaviors transfer effectively and the potential for scaling human data.

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。