Metraipolis › archive › dc_00dcda1eead0

ROOF: Learning Humanoid Fall Recovery under Overhead Constraints — arXiv:2610.42097

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.42097
License (as archived)
CC0-1.0
Archived
2026-11-02T05:05:53.218Z
SHA-256 of the archived text
790b31fadd140ebf7cb5414527bb3470cfb40860979ee2103359da0eaca7a3c3
Stable URL of this page
https://metraipolis.com/documento/dc_00dcda1eead0

How to cite

ROOF: Learning Humanoid Fall Recovery under Overhead Constraints — arXiv:2610.42097 — arXiv (en), https://arxiv.org/abs/2610.42097 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_00dcda1eead0 (Metraipolis archive dc_00dcda1eead0, sha256 790b31fadd140ebf7cb5414527bb3470cfb40860979ee2103359da0eaca7a3c3)
BibTeX
@misc{dc00dcda1eead0,
  title = {ROOF: Learning Humanoid Fall Recovery under Overhead Constraints — arXiv:2610.42097},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.42097},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_00dcda1eead0; sha256 790b31fadd140ebf7cb5414527bb3470cfb40860979ee2103359da0eaca7a3c3},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.42097. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

A fallen humanoid beneath an overhead obstacle faces a coupled recovery problem. It must create clearance while organizing support for a stable rise, since attempting to stand before making room can further increase obstruction. We introduce a reinforcement learning method with contact-supported geometric escape guidance, which rewards incremental reduction of robot-obstacle overlap without prescribing an escape path. To achieve this, a learned motion prior, together with posture-dependent support and joint-stall costs, is proposed to shape a single policy that learns when to clear the obstacle, how to establish support, and when to complete the rise, all using proprioception alone. In simulation, it recovers in 88.5% of trials beneath plates that can only be lifted, compared with 18.9% without geometric guidance, and in 98.6% of trials beneath free plates with randomized size, mass and placement. On a Unitree G1, the deployed policy recovered in 95 of 150 attempts across seven real-world obstacle scenes, including furniture and multi-object arrangements absent from training. Project page: this https URL

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/2610.42097 — 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 2026-11-02T04:49:28.242Z dalla pagina https://arxiv.org/list/cs.RO/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).