HumanoidUMI: Bridging Robot-Free Demonstrations and Humanoid Whole-Body Manipulation
FeaturedHongwu Wang, Chenhao Yu, Youhao Hu, Jiachen Zhang, Yuanyuan Li, Shaqi Luo · · 2026
Framework
JavaScript
License
N/A
Stars
0
Summary
High-quality demonstration data are essential for humanoid robot skill learning, especially for whole-body behaviors that require coordinated perception, locomotion, and manipulation. Existing data-collection methods largely rely on robot teleoperation, which is constrained by...
Abstract Summary
Key Points
- High-quality demonstration data are essential for humanoid robot skill learning, especially for whole-body behaviors that require coordinated percepti...
Abstract
High-quality demonstration data are essential for humanoid robot skill learning, especially for whole-body behaviors that require coordinated perception, locomotion, and manipulation. Existing data-collection methods largely rely on robot teleoperation, which is constrained by hardware accessibility, operator expertise, and limited efficiency. Inspired by the Universal Manipulation Interface (UMI), we propose HumanoidUMI, a portable and robot-free framework for humanoid whole-body data collection. HumanoidUMI uses lightweight VR devices and UMI-inspired grippers to collect sparse human keypoint trajectories, wrist-view observations, and gripper actions. These demonstrations train a high-level policy to predict future keypoints, which are retargeted to robot-native whole-body references and executed by a whole-body controller. Experiments in five real-world scenarios demonstrate the effectiveness of the proposed framework and validate the collected demonstrations for transferable humanoid whole-body skill learning.
Links
- Paper (PDF): 2606.27239v1
- arXiv: 2606.27239v1
Related Papers
Scalable Behavior Cloning with Open Data, Training, and Evaluation
Arthur Allshire, Himanshu Gaurav Singh, Ritvik Singh et al. · arXiv · Jun 2026
We introduce ABC, a fully open-source stack for manipulation with behavior cloning. At its core is ABC-130K: the largest open-source teleoperation dataset to date, featuring 3,500 hours of data spanning over 130K episodes across 195 diverse tasks. Furthermore, we open-source o...
LA4VLA: Learning to Act without Seeing via Language-Action Pretraining
Tao Lin, Yuxin Du, Yiran Mao et al. · arXiv · Jun 2026
Vision-Language-Action (VLA) models are commonly pretrained on robot demonstrations by jointly mapping visual observations and language instructions to actions. However, dense visual-action supervision can dominate the comparatively sparse language-action signal. As a result, ...
VibeAct: Vibration to Actions for Contact-Rich Reactive Robot Dexterity
Yuemin Mao, Uksang Yoo, Jean Oh et al. · arXiv · Jun 2026
Dexterous manipulation depends on contact events that are fast, local, and often visually occluded. Piezoelectric microphones offer a compact and high-bandwidth way to sense these interactions, but the resulting vibro-acoustic signals are difficult to simulate faithfully enoug...
E-TTS: A New Embodied Test-Time Scaling Framework for Robotic Manipulation
Wen Ye, Peiyan Li, Tingyu Yuan et al. · arXiv · Jun 2026
Recently, a few works have made early attempts to study test-time scaling for embodied tasks. However, two major challenges remain unsolved: (1) reasoning can effectively improve the performance of the policy, but its scaling mechanism has seldom been studied; (2) historical i...