Metraipolis › archive › dc_5ffee3f0852b
Learning Object-Centric Motion Priors from Human for Robotic Dexterous Manipulation — arXiv:2611.05979
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.05979
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-05T18:30:37.022Z
- SHA-256 of the archived text
a7d6b7d7f996c11c5bcedecda1315e26277ef5bd612308015edb89b15306f3fa- Stable URL of this page
https://metraipolis.com/documento/dc_5ffee3f0852b
How to cite
Learning Object-Centric Motion Priors from Human for Robotic Dexterous Manipulation — arXiv:2611.05979 — arXiv (en), https://arxiv.org/abs/2611.05979 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_5ffee3f0852b (Metraipolis archive dc_5ffee3f0852b, sha256 a7d6b7d7f996c11c5bcedecda1315e26277ef5bd612308015edb89b15306f3fa)
BibTeX
@misc{dc5ffee3f0852b,
title = {Learning Object-Centric Motion Priors from Human for Robotic Dexterous Manipulation — arXiv:2611.05979},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.05979},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_5ffee3f0852b; sha256 a7d6b7d7f996c11c5bcedecda1315e26277ef5bd612308015edb89b15306f3fa},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.05979. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Manipulating diverse objects with multi-fingered dexterous hands is challenging due to the high dimensionality and complex dynamics. Human-Object Interaction (HOI) datasets provide rich knowledge about task information and embodied interactions. Instead of solely imitating the human demonstrations, our method learns to holistically predict future hand-object states by leveraging these datasets. The predicted future states of the object can serve as a general-purpose reward term for reinforcement learning, reducing reliance on task-specific reward engineering and enhancing generalization across tasks. We conduct extensive experiments on three manipulation tasks in simulation and the real world. Our approach outperforms existing SOTA methods in both success rate and generalizability on novel objects. Furthermore, we validate the cross-embodiment compatibility of our methods by successfully deploying the skills on different robot hands. 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/2611.05979 — 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 2026-11-05T18:20:03.984Z dalla pagina https://arxiv.org/list/cs.RO/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).