EgoHumanoid: Unlocking In-the-Wild Loco-Manipulation with Robot-Free Egocentric Demonstration
For humanoid robotics, this work addresses the data scarcity problem by leveraging abundant human demonstrations, achieving significant performance gains in real-world loco-manipulation.
EgoHumanoid is the first framework to co-train a vision-language-action policy using egocentric human demonstrations and limited robot data, enabling humanoid loco-manipulation in diverse real-world environments. Incorporating human data improves performance over robot-only baselines by 51% in unseen environments.
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.