Humanoid Manipulation Interface: Humanoid Whole-Body Manipulation from Robot-Free Demonstrations

Ruiqian Nai, Boyuan Zheng, Junming Zhao, Haodong Zhu, Sicong Dai, Zunhao Chen, Yihang Hu, Yingdong Hu, Tong Zhang, Chuan Wen, Yang Gao

Keywords: robot learning, humanoid, data acquisition

TL;DR: We present Humanoid Manipulation Interface (HuMI), a portable and efficient framework for learning diverse humanoid whole-body manipulation tasks from robot-free demonstrations.

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 **Hu**manoid **M**anipulation **I**nterface (**HuMI**), a portable and efficient framework for learning diverse whole-body manipulation tasks across various environments. HuMI enables robot-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.

Email Sharing: We authorize the sharing of all author emails with Program Chairs.

Data Release: We authorize the release of our submission and author names to the public in the event of acceptance.

Submission Number: 2