Metraipolis › archive › dc_e46054db3d63

Dex-One2Many: Learning Dexterous Manipulation from a Single Human Demonstration — arXiv:2610.12470

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.12470
License (as archived)
CC0-1.0
Archived
2026-10-09T06:33:07.278Z
SHA-256 of the archived text
1c8ebce89d58f0f71dedbdf350f2187f5eaf4de029ebf3218c5e3d8b8c8c309b
Stable URL of this page
https://metraipolis.com/documento/dc_e46054db3d63

How to cite

Dex-One2Many: Learning Dexterous Manipulation from a Single Human Demonstration — arXiv:2610.12470 — arXiv (en), https://arxiv.org/abs/2610.12470 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_e46054db3d63 (Metraipolis archive dc_e46054db3d63, sha256 1c8ebce89d58f0f71dedbdf350f2187f5eaf4de029ebf3218c5e3d8b8c8c309b)
BibTeX
@misc{dce46054db3d63,
  title = {Dex-One2Many: Learning Dexterous Manipulation from a Single Human Demonstration — arXiv:2610.12470},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.12470},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_e46054db3d63; sha256 1c8ebce89d58f0f71dedbdf350f2187f5eaf4de029ebf3218c5e3d8b8c8c309b},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.12470. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

While learning dexterous manipulation from a single human video offers a promising alternative to costly robot demonstrations, many recent methods predominantly imitate demonstrated motions. Such strict motion matching often limits generalization to initial object poses, goal poses, and grasps not shown in the video. Alternatively, discovering a policy via reinforcement learning (RL) allows for broad generalization, but without prior guidance, it struggles with high-dimensional exploration in complex, multi-stage tasks. To address these coupled generalization and exploration challenges, we present Dex-One2Many, a real-to-sim-to-real framework that learns a generalizable dexterous manipulation policy from a single human video. Our key insight is to abstract the video into sequential scene graphs that guide RL, enabling efficient exploration while preserving broad generalizability. The graphs serve as generative constraints for sampling diverse reset states and provide dense rewards for each stage. Because the graphs constrain relations rather than exact poses, these reset states cover object poses and grasps beyond the video, while initializing each stage from them with dense rewards keeps exploration short and guided. Trained entirely in simulation, Dex-One2Many transfers zero-shot to a real multi-fingered hand. Across five tool-use and manipulation tasks, Dex-One2Many exceeds baselines by 6.5% in seen configurations, while its robust generalization widens this gap to 71% in unseen scenarios.

Tema degli esploratori: statistica e scienza dei dati (elenco arXiv cs.CV, nuovi lavori del giorno).
Categorie arXiv: Robotics (cs.RO) ; Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2610.12470 — 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 2026-10-09T05:55:07.895Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).