[
    {
        "id": "osp-18425",
        "type": "article-journal",
        "title": "TacOT: Learning Contact-Rich Dexterous Manipulation from Human Demonstrations via Tactile-Guided Optimal Transport",
        "author": [
            {
                "family": "Li",
                "given": "Xingting"
            },
            {
                "family": "Han",
                "given": "Yifan"
            },
            {
                "family": "Lin",
                "given": "Zijian"
            },
            {
                "family": "Hou",
                "given": "Wei"
            },
            {
                "family": "Lyu",
                "given": "Chuqiao"
            },
            {
                "family": "Li",
                "given": "Shoujie"
            },
            {
                "family": "Ding",
                "given": "Wenbo"
            }
        ],
        "URL": "https://omanscience.com/en/articles/tacot-learning-contact-rich-dexterous-manipulation-from-human-demonstrations-via-tactile-guided-optimal-transport",
        "language": "en",
        "issued": {
            "date-parts": [
                [
                    2026
                ]
            ]
        },
        "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."
    }
]