Metraipolis › archive › dc_aeadfab7e978

Learning Safe Humanoid Navigation from Reduced Order Models — arXiv:2609.19272

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.19272
License (as archived)
CC0-1.0
Archived
2026-10-10T05:25:19.538Z
SHA-256 of the archived text
5b91cffc24964eac3b9b816ecee77c2c44d23e53ccd3bc93bb1e60c5e134e905
Stable URL of this page
https://metraipolis.com/documento/dc_aeadfab7e978

How to cite

Learning Safe Humanoid Navigation from Reduced Order Models — arXiv:2609.19272 — arXiv (en), https://arxiv.org/abs/2609.19272 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_aeadfab7e978 (Metraipolis archive dc_aeadfab7e978, sha256 5b91cffc24964eac3b9b816ecee77c2c44d23e53ccd3bc93bb1e60c5e134e905)
BibTeX
@misc{dcaeadfab7e978,
  title = {Learning Safe Humanoid Navigation from Reduced Order Models — arXiv:2609.19272},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.19272},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_aeadfab7e978; sha256 5b91cffc24964eac3b9b816ecee77c2c44d23e53ccd3bc93bb1e60c5e134e905},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.19272. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Research in humanoid robotics has achieved rapid progress in locomotion, and recent results have pushed the boundary on autonomous navigation. We demonstrate that a standard single-stage RL navigation pipeline struggles to scale to multi-level and multi-story terrain, limited by the difficulty of complex humanoid terrain interactions such as stairs. To overcome this challenge, we decompose the navigation problem into two pieces. First, we train a policy operating on the reduced order dynamics but with full 3D LiDAR observations to navigate complex, multi-story terrain. We then utilize this navigation knowledge to kickstart a policy operating on the full-order humanoid dynamics, with a frozen locomotion policy in the loop. Additionally, we demonstrate that applying a Poisson safety filter to the navigation policy output recovers safety in the presence of out-of-distribution obstacles, without dropping navigation success rate. We demonstrate the resulting RoM-Nav policy on a Unitree G1, accomplishing mapless multi-floor navigation covering trials with over 10m of vertical displacement and over 100m of path length. Project page with videos this https URL .

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-18 in cs.RO).
Categorie arXiv: Robotics (cs.RO).
Pagina del lavoro: https://arxiv.org/abs/2609.19272 — 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 2026-10-10T04:47:38.804Z dalla pagina https://arxiv.org/catchup/cs.RO/2026-09-18?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).