Metraipolis › archive › dc_ef017fabcb0e
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
- 2026-11-03T08:23:45.001Z
- SHA-256 of the archived text
beb6d442ccd792f63e1b698a67951d5e0d5c99021bdbce0d556f0f1b16f40dab- Stable URL of this page
https://metraipolis.com/documento/dc_ef017fabcb0e
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_ef017fabcb0e (Metraipolis archive dc_ef017fabcb0e, sha256 beb6d442ccd792f63e1b698a67951d5e0d5c99021bdbce0d556f0f1b16f40dab)
BibTeX
@misc{dcef017fabcb0e,
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_ef017fabcb0e; sha256 beb6d442ccd792f63e1b698a67951d5e0d5c99021bdbce0d556f0f1b16f40dab},
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 2026-11-03T08:06:53.851Z dalla pagina https://arxiv.org/list/cs.RO/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).