Metraipolis › archive › dc_84442cfdf160

Weave: Learning Whole-Body Dexterous Loco-Manipulation from Human-Object Interactions — arXiv:2609.16683

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.16683
License (as archived)
CC0-1.0
Archived
2026-10-15T18:35:12.511Z
SHA-256 of the archived text
6a52ea89d5593b90aebc80e2c508e1e5b17cbad6234fc91e152686e1b1919177
Stable URL of this page
https://metraipolis.com/documento/dc_84442cfdf160

How to cite

Weave: Learning Whole-Body Dexterous Loco-Manipulation from Human-Object Interactions — arXiv:2609.16683 — arXiv (en), https://arxiv.org/abs/2609.16683 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_84442cfdf160 (Metraipolis archive dc_84442cfdf160, sha256 6a52ea89d5593b90aebc80e2c508e1e5b17cbad6234fc91e152686e1b1919177)
BibTeX
@misc{dc84442cfdf160,
  title = {Weave: Learning Whole-Body Dexterous Loco-Manipulation from Human-Object Interactions — arXiv:2609.16683},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.16683},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_84442cfdf160; sha256 6a52ea89d5593b90aebc80e2c508e1e5b17cbad6234fc91e152686e1b1919177},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.16683. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Learning humanoid-object interaction requires coordinating whole-body balance, locomotion, and dexterous hand contact to control both robot and object motion. Human demonstrations provide examples of coordinated interaction, but transferring these behaviors to humanoid robots requires learning how to establish and maintain effective contacts under different embodiments and dynamics. We present Weave, a unified framework for learning whole-body dexterous humanoid-object interaction from captured human demonstrations. Weave first converts captured human-object interactions into executable robot-object references through contact-aware retargeting and approach-motion completion. At its core is a contact- and geometry-aware policy that jointly commands 29 body joints and 12 actuated finger joints across multiple objects and interaction sequences. Evaluation across nine objects yields a 92.5% success rate on trained interactions and, without any additional training, 65.0% on sequences never seen during training. We additionally release ~9,000 physically executed rollouts spanning ~23 hours, providing robot-object trajectories with contact annotations for downstream interaction-policy learning and physically consistent HOI motion generation. Project website: this https URL

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-16 in cs.AI).
Categorie arXiv: Robotics (cs.RO) ; Artificial Intelligence (cs.AI); Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2609.16683 — 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 2026-10-15T18:03:09.679Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-16?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).