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

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Nai, Ruiqian, Zheng, Boyuan, Zhao, Junming, Zhu, Haodong, Dai, Sicong, Chen, Zunhao, Hu, Yihang, Hu, Yingdong, Zhang, Tong, Wen, Chuan, Gao, Yang
Formato: Preprint
Publicado: 2026
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866911442977947648
author Nai, Ruiqian
Zheng, Boyuan
Zhao, Junming
Zhu, Haodong
Dai, Sicong
Chen, Zunhao
Hu, Yihang
Hu, Yingdong
Zhang, Tong
Wen, Chuan
Gao, Yang
author_facet Nai, Ruiqian
Zheng, Boyuan
Zhao, Junming
Zhu, Haodong
Dai, Sicong
Chen, Zunhao
Hu, Yihang
Hu, Yingdong
Zhang, Tong
Wen, Chuan
Gao, Yang
contents 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 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.
format Preprint
id arxiv_https___arxiv_org_abs_2602_06643
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Humanoid Manipulation Interface: Humanoid Whole-Body Manipulation from Robot-Free Demonstrations
Nai, Ruiqian
Zheng, Boyuan
Zhao, Junming
Zhu, Haodong
Dai, Sicong
Chen, Zunhao
Hu, Yihang
Hu, Yingdong
Zhang, Tong
Wen, Chuan
Gao, Yang
Robotics
Artificial Intelligence
Machine Learning
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 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.
title Humanoid Manipulation Interface: Humanoid Whole-Body Manipulation from Robot-Free Demonstrations
topic Robotics
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2602.06643