Abstract
Mobile bimanual dexterous manipulation requires continuous coordination of locomotion, whole-body motion, and finger-level dexterity within a single trajectory, creating a severe robot demonstration bottleneck. Egocentric human demonstrations offer a scalable alternative, but prior approaches ease the transfer by simplifying human motion, discarding exactly the fine-grained, coupled structure such tasks depend on. We present DexRoam, a complete system for learning mobile bimanual dexterous manipulation from human demonstrations, in which whole-body motion remains continuous and coupled throughout the human-to-robot transfer process. To enable scalable collection of whole-body human manipulation demonstrations, we develop a tracker-free capture system using only a consumer VR headset and a head-mounted stereo camera, without external cameras or motion trackers. We then perform three explicit alignment stages---embodiment, action-semantic, and temporal---to map captured motion into the robot action space, preserving fine-grained whole-body motion and allowing human and robot demonstrations to be jointly learned by standard VLA policies. Real-world experiments with different VLA backbones show that human demonstrations consistently improve policy learning across training paradigms, raising average success from 29% to 56% on GR00T N1.7 and from 32% to 57% on pi0.5, while matching robot-only training with half the robot demonstrations. Ablations confirm that each alignment stage is necessary. These results highlight the potential of human demonstrations for scalable whole-body mobile manipulation with preserved fine-grained motion structure.
Keywords
Subject
Publication details
- Journal
- Not available
- Open access
- Green open access
Cite this article
APA 7
Zhou, R., Yuan, Y., Zhao, J., Zhao, F., Zhao, X., Zhang, S., & Han, S. (2026). DexRoam: Learning Mobile Bimanual Dexterous Manipulation from Egocentric Whole-Body Human Demonstrations. https://omanscience.com/en/articles/dexroam-learning-mobile-bimanual-dexterous-manipulation-from-egocentric-whole-body-human-demonstrations
MLA 9
Zhou, Rui, et al. "DexRoam: Learning Mobile Bimanual Dexterous Manipulation from Egocentric Whole-Body Human Demonstrations." https://omanscience.com/en/articles/dexroam-learning-mobile-bimanual-dexterous-manipulation-from-egocentric-whole-body-human-demonstrations.
Chicago (author–date)
Zhou, Rui, Yibo Yuan, Junkai Zhao, Fangyuan Zhao, Xiaoguang Zhao, Shanghang Zhang, and Sirui Han. 2026. "DexRoam: Learning Mobile Bimanual Dexterous Manipulation from Egocentric Whole-Body Human Demonstrations." https://omanscience.com/en/articles/dexroam-learning-mobile-bimanual-dexterous-manipulation-from-egocentric-whole-body-human-demonstrations.
Harvard
Zhou, R., Yuan, Y., Zhao, J., Zhao, F., Zhao, X., Zhang, S. and Han, S. (2026) 'DexRoam: Learning Mobile Bimanual Dexterous Manipulation from Egocentric Whole-Body Human Demonstrations', Available at: https://omanscience.com/en/articles/dexroam-learning-mobile-bimanual-dexterous-manipulation-from-egocentric-whole-body-human-demonstrations.
Vancouver
Zhou R, Yuan Y, Zhao J, Zhao F, Zhao X, Zhang S, et al. DexRoam: Learning Mobile Bimanual Dexterous Manipulation from Egocentric Whole-Body Human Demonstrations. https://omanscience.com/en/articles/dexroam-learning-mobile-bimanual-dexterous-manipulation-from-egocentric-whole-body-human-demonstrations
IEEE
R. Zhou, Y. Yuan, J. Zhao, F. Zhao, X. Zhao, S. Zhang, and S. Han, "DexRoam: Learning Mobile Bimanual Dexterous Manipulation from Egocentric Whole-Body Human Demonstrations," https://omanscience.com/en/articles/dexroam-learning-mobile-bimanual-dexterous-manipulation-from-egocentric-whole-body-human-demonstrations.