Metraipolis › archive › dc_9d75e2d2f47d

Dexterous Robot Manipulation from Human Demonstrations via Contact-Anchored Retargeting and Residual Policy Learning — arXiv:2609.24093

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.24093
License (as archived)
CC0-1.0
Archived
2026-10-09T22:24:15.007Z
SHA-256 of the archived text
23a88b1fa6558b8b20b0df0f23ba4bec373bbe9bc7053897ef7f9910df3f94a5
Stable URL of this page
https://metraipolis.com/documento/dc_9d75e2d2f47d

How to cite

Dexterous Robot Manipulation from Human Demonstrations via Contact-Anchored Retargeting and Residual Policy Learning — arXiv:2609.24093 — arXiv (en), https://arxiv.org/abs/2609.24093 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_9d75e2d2f47d (Metraipolis archive dc_9d75e2d2f47d, sha256 23a88b1fa6558b8b20b0df0f23ba4bec373bbe9bc7053897ef7f9910df3f94a5)
BibTeX
@misc{dc9d75e2d2f47d,
  title = {Dexterous Robot Manipulation from Human Demonstrations via Contact-Anchored Retargeting and Residual Policy Learning — arXiv:2609.24093},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.24093},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_9d75e2d2f47d; sha256 23a88b1fa6558b8b20b0df0f23ba4bec373bbe9bc7053897ef7f9910df3f94a5},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.24093. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Learning dexterous manipulation from demonstrations is bottlenecked by data: the contact forces that determine whether a grasp succeeds are absent from every scalable source of human demonstrations. This paper builds on two observations. First, what survives the change from a human hand to a robot hand is the contact structure of a demonstration - which finger regions touch which object locations, and in what order - rather than its joint motion. Second, physical consistency need not be engineered per task: a single residual reinforcement learning (RL) policy, trained once across diverse demonstrations, can repair kinematic recordings into physically consistent, contact-annotated trajectories, and the same residual formulation restores dynamic feasibility after retargeting. These observations yield a three-stage pipeline that converts human motion-capture recordings into dexterous robot policies with no real-robot training data: physics refinement with a simulated MANO hand recovers contacts and forces, contact-anchored retargeting transfers the demonstrated contact structure through an objective independent of hand morphology, and residual policy learning adapts the result to robot actuation. The pipeline reconstructs 25,454 single-hand trajectories (success 7.3% -> 59.3%) and 25 dual-hand tasks (16.0% -> 62.4%) with one shared policy per setting, transfers one human dataset to four morphologically distinct robot hands (+62.4 pp), and executes four contact-rich bimanual tasks on physical hardware with zero real-robot training data.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-22 in cs.RO).
Categorie arXiv: Robotics (cs.RO).
Pagina del lavoro: https://arxiv.org/abs/2609.24093 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-09T21:59:59.675Z dalla pagina https://arxiv.org/catchup/cs.RO/2026-09-22?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).