Metraipolis › archive › dc_d31085e45df1
One Demonstration, Many Objects: Generalizing Manipulation via Local Contact Geometry — arXiv:2609.01938
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.01938
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-17T05:51:10.797Z
- SHA-256 of the archived text
0252871f187e0bd30412335df18fc3a56d4d2c9af4101b20dae1d86ab8c81e1e- Stable URL of this page
https://metraipolis.com/documento/dc_d31085e45df1
How to cite
One Demonstration, Many Objects: Generalizing Manipulation via Local Contact Geometry — arXiv:2609.01938 — arXiv (en), https://arxiv.org/abs/2609.01938 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_d31085e45df1 (Metraipolis archive dc_d31085e45df1, sha256 0252871f187e0bd30412335df18fc3a56d4d2c9af4101b20dae1d86ab8c81e1e)
BibTeX
@misc{dcd31085e45df1,
title = {One Demonstration, Many Objects: Generalizing Manipulation via Local Contact Geometry — arXiv:2609.01938},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.01938},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_d31085e45df1; sha256 0252871f187e0bd30412335df18fc3a56d4d2c9af4101b20dae1d86ab8c81e1e},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.01938. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Dexterous manipulation with multi-fingered robot hands promises human-level dexterity, but collecting large-scale dexterous robot hand data remains difficult. Learning from human demonstrations has emerged as a scalable alternative to robot teleoperation, providing strong priors on object interaction and contact strategies. Recent sim-to-real RL methods incorporate such priors, but often (i) omit rewards that explicitly incentivize precise contact, yielding weak real-world performance, and/or (ii) generalize poorly to unseen object instances. We propose DemoMimic (Dexterous Motion Mimic), a policy that manipulates objects by focusing on their geometry local to the contact points. Its contact-centric rewards encourage precise contact and improve sim-to-real consistency, yielding a single real-world policy that transfers across objects of varying shape, scale, mass, and friction wherever local contact structure is preserved. Real-world ablations show that DemoMimic achieves 71% success across 16 objects, four tasks, and two robot-hand embodiments, with the smallest sim-to-real drop compared to baselines. Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-03 in cs.RO). Categorie arXiv: Robotics (cs.RO). Pagina del lavoro: https://arxiv.org/abs/2609.01938 — 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 2026-10-17T05:39:02.666Z dalla pagina https://arxiv.org/catchup/cs.RO/2026-09-03?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).