cs.RONov 19, 2026

Awaken-HI: Scaling Humanoid Intelligence with Whole-Body Human Experience

Authors: EngineAI

Abstract

A central goal of humanoid robotics is for robots to perform the everyday work people do in homes and workplaces. Existing egocentric video datasets cover many of these activities but provide little synchronized whole-body motion data for learning loco-manipulation at scale. We build Awaken-Human, which pairs approximately 50,000 hours of egocentric stereo video with synchronized whole-body human motion and covers more than 100 skills. Building on this, we also introduce Awaken-HI (Humanoid Intelligence), a vision-language-action model for humanoid loco-manipulation that jointly predicts original human motion and retargeted robot actions through a shared action expert. We show that loco-manipulation skills transfer more effectively from people to humanoids when human trajectories directly supervise the shared action expert. Increasing human pretraining data reduces held-out robot action prediction error according to an empirical scaling law and raises the mean success rate on downstream real-robot tasks. After full-corpus pretraining and T800 adaptation, Awaken-HI achieves a mean success rate of 93.75% across eight individual tasks and outperforms GR00T N1.7 and π0.5π_{0.5} in both individual and long-horizon evaluations. The same policy generalizes to objects unseen during robot post-training and to new pairings of familiar objects and destinations.

Figures & tables

Explore similar work

CardsList
  1. Towards a General Humanoid Loco-Manipulation Model via Egocentric Whole-Body Human Data Pretraining

    Sep 30, 2026Chongyang Xu, Zhao Wu, Jin Chen +9Humanoid Loco-ManipulationCross-Embodiment Robot Learning

  2. Ψ0Ψ_0: An Open Foundation Model Towards Universal Humanoid Loco-Manipulation

    Mar 12, 2026Songlin Wei, Hongyi Jing, Boqian Li +12Egocentric Video Learning for RoboticsRobot Learning