Abstract
Learning contact-rich dexterous manipulation from human demonstrations provides a scalable source of interaction data, yet transferring such skills to robots remains challenging due to unreliable human--robot correspondence. Existing human-to-robot transfer methods typically rely on visual appearance or motion similarity, which may associate similar motions with different contact states and force patterns. Tactile dynamics provide interaction-aware cues to distinguish manipulation processes with similar motions but different contact states. We introduce tactile-guided optimal transport (TacOT), a framework for human-to-robot contact-rich manipulation. TacOT leverages action--tactile dynamic time warping to identify human--robot demonstration correspondences with consistent interaction dynamics and uses these correspondences to guide soft optimal transport alignment in a shared policy representation space. This enables human demonstrations to provide contact-rich supervision for robot policy learning without requiring predefined frame-level human--robot pairing. Across four real-world dexterous manipulation tasks, TacOT improves closed-loop success rates over action-guided OT by up to 17 points on in-distribution tasks and 20 points under targeted human-to-robot out-of-distribution transfer. Further analyses show that tactile-guided correspondence selects demonstration pairs with more consistent contact dynamics and produces latent representations that better reflect interaction-state evolution. These results demonstrate that tactile dynamics provide an effective semantic signal for establishing reliable human-to-robot correspondence in contact-rich dexterous manipulation.
Keywords
Subject
Publication details
- Journal
- Not available
- Open access
- Green open access
Cite this article
APA 7
Li, X., Han, Y., Lin, Z., Hou, W., Lyu, C., Li, S., & Ding, W. (2026). TacOT: Learning Contact-Rich Dexterous Manipulation from Human Demonstrations via Tactile-Guided Optimal Transport. https://omanscience.com/en/articles/tacot-learning-contact-rich-dexterous-manipulation-from-human-demonstrations-via-tactile-guided-optimal-transport
MLA 9
Li, Xingting, et al. "TacOT: Learning Contact-Rich Dexterous Manipulation from Human Demonstrations via Tactile-Guided Optimal Transport." https://omanscience.com/en/articles/tacot-learning-contact-rich-dexterous-manipulation-from-human-demonstrations-via-tactile-guided-optimal-transport.
Chicago (author–date)
Li, Xingting, Yifan Han, Zijian Lin, Wei Hou, Chuqiao Lyu, Shoujie Li, and Wenbo Ding. 2026. "TacOT: Learning Contact-Rich Dexterous Manipulation from Human Demonstrations via Tactile-Guided Optimal Transport." https://omanscience.com/en/articles/tacot-learning-contact-rich-dexterous-manipulation-from-human-demonstrations-via-tactile-guided-optimal-transport.
Harvard
Li, X., Han, Y., Lin, Z., Hou, W., Lyu, C., Li, S. and Ding, W. (2026) 'TacOT: Learning Contact-Rich Dexterous Manipulation from Human Demonstrations via Tactile-Guided Optimal Transport', Available at: https://omanscience.com/en/articles/tacot-learning-contact-rich-dexterous-manipulation-from-human-demonstrations-via-tactile-guided-optimal-transport.
Vancouver
Li X, Han Y, Lin Z, Hou W, Lyu C, Li S, et al. TacOT: Learning Contact-Rich Dexterous Manipulation from Human Demonstrations via Tactile-Guided Optimal Transport. https://omanscience.com/en/articles/tacot-learning-contact-rich-dexterous-manipulation-from-human-demonstrations-via-tactile-guided-optimal-transport
IEEE
X. Li, Y. Han, Z. Lin, W. Hou, C. Lyu, S. Li, and W. Ding, "TacOT: Learning Contact-Rich Dexterous Manipulation from Human Demonstrations via Tactile-Guided Optimal Transport," https://omanscience.com/en/articles/tacot-learning-contact-rich-dexterous-manipulation-from-human-demonstrations-via-tactile-guided-optimal-transport.