Abstract
Learning predictive models of contact-rich dexterous manipulation requires dense tactile interaction, but such data are costly to scale on real robots and remain tied to embodiment-specific sensors. We introduce DexTouch-WM, an action-conditioned world model that learns from scalable human touch to jointly predict future RGB observations and bilateral tactile dynamics. Our insight is that human and robot manipulation share transferable contact dynamics when their tactile observations and action spaces are made compatible. We deploy flexible piezoresistive arrays with a shared sensing layout on both human and dexterous robot hands, and retarget human motion into the robot action space so that human interaction can supervise the same dynamics model used for real-robot prediction. DexTouch-WM couples a pretrained video expert with a lightweight tactile expert using anatomy-aware tactile tokens and aligned action conditioning. In human-to-robot scaling experiments, we keep five hours of real-robot supervision fixed while increasing human interaction from 0 to 100 hours, and observe substantial improvements in held-out robot-domain visual, geometric, and contact prediction despite disjoint human and robot task sets. Beyond prediction, we evaluate the world models as surrogate environments for policy evaluation and as generators of synthetic trajectories for real-robot policy learning, showing that scalable human interaction provides a complementary data axis for learning dexterous robot world models.
Keywords
Subject
Publication details
- Journal
- Not available
- Open access
- Green open access
Cite this article
APA 7
Qin, Y., Chen, Y., Lin, W., Liu, S., Lyu, C., Su, K., Jin, W., Yu, C., Luo, P., Ding, W., Chen, T., & Xu, R. (2026). DexTouch-WM: Learning Action-Conditioned Tactile World Models from Human Touch for Dexterous Robot Manipulation. https://omanscience.com/en/articles/dextouch-wm-learning-action-conditioned-tactile-world-models-from-human-touch-for-dexterous-robot-manipulation
MLA 9
Qin, Yan, et al. "DexTouch-WM: Learning Action-Conditioned Tactile World Models from Human Touch for Dexterous Robot Manipulation." https://omanscience.com/en/articles/dextouch-wm-learning-action-conditioned-tactile-world-models-from-human-touch-for-dexterous-robot-manipulation.
Chicago (author–date)
Qin, Yan, Yue Chen, Wenwei Lin, Shujia Liu, Chuqiao Lyu, Kailun Su, Weiyang Jin, Chenze Yu, Ping Luo, Wenbo Ding, Tianxing Chen, and Renjing Xu. 2026. "DexTouch-WM: Learning Action-Conditioned Tactile World Models from Human Touch for Dexterous Robot Manipulation." https://omanscience.com/en/articles/dextouch-wm-learning-action-conditioned-tactile-world-models-from-human-touch-for-dexterous-robot-manipulation.
Harvard
Qin, Y., Chen, Y., Lin, W., Liu, S., Lyu, C., Su, K., Jin, W., Yu, C., Luo, P., Ding, W., Chen, T. and Xu, R. (2026) 'DexTouch-WM: Learning Action-Conditioned Tactile World Models from Human Touch for Dexterous Robot Manipulation', Available at: https://omanscience.com/en/articles/dextouch-wm-learning-action-conditioned-tactile-world-models-from-human-touch-for-dexterous-robot-manipulation.
Vancouver
Qin Y, Chen Y, Lin W, Liu S, Lyu C, Su K, et al. DexTouch-WM: Learning Action-Conditioned Tactile World Models from Human Touch for Dexterous Robot Manipulation. https://omanscience.com/en/articles/dextouch-wm-learning-action-conditioned-tactile-world-models-from-human-touch-for-dexterous-robot-manipulation
IEEE
Y. Qin, Y. Chen, W. Lin, S. Liu, C. Lyu, K. Su, W. Jin, C. Yu, P. Luo, W. Ding, T. Chen, and R. Xu, "DexTouch-WM: Learning Action-Conditioned Tactile World Models from Human Touch for Dexterous Robot Manipulation," https://omanscience.com/en/articles/dextouch-wm-learning-action-conditioned-tactile-world-models-from-human-touch-for-dexterous-robot-manipulation.