cs.ROFeb 6, 2026

HuMI: Humanoid Whole-Body Manipulation from Humanoid-Free Demonstrations

Authors: Ruiqian Nai, Boyuan Zheng, Junming Zhao, Haodong Zhu, Sicong Dai, Zunhao Chen, Yihang Hu, Yingdong Hu, 

Organizations: Tsinghua University · Shanghai Qi Zhi Institute · Shanghai Jiao Tong University

Abstract

Current approaches for humanoid whole-body manipulation, primarily relying on teleoperation or visual sim-to-real reinforcement learning, are hindered by hardware logistics and complex reward engineering. Consequently, demonstrated autonomous skills remain limited and are typically restricted to controlled environments. In this paper, we present the Humanoid Manipulation Interface (HuMI), a portable and efficient framework for learning diverse whole-body manipulation tasks across various environments. HuMI enables humanoid-free data collection by capturing rich whole-body motion using portable hardware. This data drives a hierarchical learning pipeline that translates human motions into dexterous and feasible humanoid skills. Extensive experiments across five whole-body tasks--including kneeling, squatting, tossing, walking, and bimanual manipulation--demonstrate that HuMI achieves a 3x increase in data collection efficiency compared to teleoperation and attains a 70% success rate in unseen environments.

Figures & tables

Appendix figures & tables10 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. HumanoidUMI: Bridging Robot-Free Demonstrations and Humanoid Whole-Body Manipulation

    Jun 25, 2026Hongwu Wang, Chenhao Yu, Youhao Hu +3Robot Skill LearningRobotic Data Collection

  2. HoMMI: Learning Whole-Body Mobile Manipulation from Human Demonstrations

    Mar 3, 2026Xiaomeng Xu, Jisang Park, Han Zhang +6Mobile ManipulationWhole-Body Robotic Manipulation

  3. BifrostUMI: Bridging Robot-Free Demonstrations and Humanoid Whole-Body Manipulation

    May 5, 2026Hongwu Wang, Chenhao Yu, Youhao Hu +3Robotic Data CollectionHumanoid Robot Control