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

TL;DR

EgoHumanoid leverages abundant human egocentric demonstrations combined with limited robot data to enable humanoids to perform loco-manipulation in diverse real-world environments, addressing the embodiment gap through a systematic alignment pipeline.

Contribution

This work introduces a novel framework that co-trains vision-language-action policies using human demonstrations and a new alignment pipeline for humanoid control.

Findings

Incorporating human data improves performance by 51% over robot-only baselines.

The alignment pipeline effectively bridges the embodiment gap between humans and robots.

Humans can transfer behaviors efficiently to humanoids in unseen environments.

Abstract

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.