Metraipolis › archive › dc_06a8b7fe7efc

HandMimicX: Learning Human-Like Dexterous Manipulation via an Object-Centric Policy from Egocentric Videos — arXiv:2610.41336

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.41336
License (as archived)
CC0-1.0
Archived
2026-11-03T05:47:21.705Z
SHA-256 of the archived text
c3b9ac65e14fdb1950e5799cf809c27d8a0ecadcf917fc26043ad3033560a45f
Stable URL of this page
https://metraipolis.com/documento/dc_06a8b7fe7efc

How to cite

HandMimicX: Learning Human-Like Dexterous Manipulation via an Object-Centric Policy from Egocentric Videos — arXiv:2610.41336 — arXiv (en), https://arxiv.org/abs/2610.41336 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_06a8b7fe7efc (Metraipolis archive dc_06a8b7fe7efc, sha256 c3b9ac65e14fdb1950e5799cf809c27d8a0ecadcf917fc26043ad3033560a45f)
BibTeX
@misc{dc06a8b7fe7efc,
  title = {HandMimicX: Learning Human-Like Dexterous Manipulation via an Object-Centric Policy from Egocentric Videos — arXiv:2610.41336},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.41336},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_06a8b7fe7efc; sha256 c3b9ac65e14fdb1950e5799cf809c27d8a0ecadcf917fc26043ad3033560a45f},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.41336. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Learning dexterous manipulation from human videos remains an open challenge, particularly in the context of transferring a single demonstration into a spatially generalizable robotic skill and maintaining physically plausible human-like interactions. Unlike prior works that emphasize hand-motion imitation, we introduce an object-centric framework for acquiring dexterous skills from egocentric human RGB-D videos. Within our framework, we formulate the reinforcement learning (RL) objective in terms of object motion to decouple the underlying skill from the specific hand trajectory and impose constraints on hand-object interaction states to promote more anatomically natural hand configurations. Extensive experiments in simulation and on real robots demonstrate that our method enables efficient learning from human videos and generalizable skill transfer across novel spatial configurations.

Tema degli esploratori: statistica e scienza dei dati (elenco arXiv cs.RO, nuovi lavori del giorno).
Categorie arXiv: Robotics (cs.RO).
Pagina del lavoro: https://arxiv.org/abs/2610.41336 — 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 2026-11-03T05:33:48.013Z dalla pagina https://arxiv.org/list/cs.RO/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).