Metraipolis › archive › dc_27132288bfce

World-Model-Augmented Visual Locomotion for Humanoids on Foothold-Constrained Terrain — arXiv:2609.02542

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.02542
License (as archived)
CC0-1.0
Archived
2026-10-17T05:51:16.797Z
SHA-256 of the archived text
f298e86a0c697e56c37bd2052c38d9679dfc750baa1298e5514187f2515472ab
Stable URL of this page
https://metraipolis.com/documento/dc_27132288bfce

How to cite

World-Model-Augmented Visual Locomotion for Humanoids on Foothold-Constrained Terrain — arXiv:2609.02542 — arXiv (en), https://arxiv.org/abs/2609.02542 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_27132288bfce (Metraipolis archive dc_27132288bfce, sha256 f298e86a0c697e56c37bd2052c38d9679dfc750baa1298e5514187f2515472ab)
BibTeX
@misc{dc27132288bfce,
  title = {World-Model-Augmented Visual Locomotion for Humanoids on Foothold-Constrained Terrain — arXiv:2609.02542},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.02542},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_27132288bfce; sha256 f298e86a0c697e56c37bd2052c38d9679dfc750baa1298e5514187f2515472ab},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.02542. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Foothold-constrained terrain is characterized by sparse, discontinuous, or geometrically restricted feasible foot contacts, as encountered on stepping stones, across gaps, and on narrow stair treads. On such terrain, a single misstep often leaves little room to recover, so policies that base foot-placement decisions primarily on the immediately visible terrain are prone to failure. We ask whether a learned predictive summary of near-future observations and rewards can provide the anticipatory information required in such settings. We present World-Model-Augmented Visual Locomotion (WM-LOCO), which jointly trains a recurrent world model and a PPO policy. Conditioned on proprioception and a single onboard depth image, the world model produces a predictive recurrent feature that guides the policy, without explicit foothold labels. In simulation, WM-LOCO succeeds on gaps and stepping stones where a matched baseline fails completely, and matches the baseline's success rate on stairs while improving stride efficiency and reducing pelvis acceleration. We deploy the same policy onboard a physical Unitree G1 humanoid using onboard proprioception and a single depth stream; it traverses all three terrain classes with an average success rate of 93.3%.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-03 in cs.RO).
Categorie arXiv: Robotics (cs.RO).
Pagina del lavoro: https://arxiv.org/abs/2609.02542 — 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 2026-10-17T05:39:02.690Z dalla pagina https://arxiv.org/catchup/cs.RO/2026-09-03?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).