Metraipolis › archive › dc_cc81bb8ff3c2
OpenNWM: A Generalist Navigation World Model with Latent Action Pretraining — arXiv:2611.01844
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.01844
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-03T18:18:13.493Z
- SHA-256 of the archived text
ee90b51a83cac54634d884f1ca51ec813e442c19f7c78267bfa1d531e2e8187a- Stable URL of this page
https://metraipolis.com/documento/dc_cc81bb8ff3c2
How to cite
OpenNWM: A Generalist Navigation World Model with Latent Action Pretraining — arXiv:2611.01844 — arXiv (en), https://arxiv.org/abs/2611.01844 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_cc81bb8ff3c2 (Metraipolis archive dc_cc81bb8ff3c2, sha256 ee90b51a83cac54634d884f1ca51ec813e442c19f7c78267bfa1d531e2e8187a)
BibTeX
@misc{dccc81bb8ff3c2,
title = {OpenNWM: A Generalist Navigation World Model with Latent Action Pretraining — arXiv:2611.01844},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.01844},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_cc81bb8ff3c2; sha256 ee90b51a83cac54634d884f1ca51ec813e442c19f7c78267bfa1d531e2e8187a},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.01844. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Navigation world models predict future observations conditioned on navigation actions to support planning, but their generalization across real-world environments remains constrained by the limited coverage of action-labeled data. Action-free navigation videos provide diverse visual experience, yet lack the recorded actions required for action-conditioned training. We introduce OpenNWM, a generalist navigation world model with latent action pretraining. It learns universal latent actions from large-scale action-free videos through visual prediction pretraining, and further aligns them with physical motions via action-conditioned post-training. To support video pretraining, we curate NavAnywhere, a large-scale action-free navigation video dataset comprising 17.5 million visual observations from 15 heterogeneous sources. It captures navigation by ground robots, humans, and drones, with diverse viewpoints and motion patterns across five broad scene types: residential areas, public and commercial spaces, urban settings, parks, and natural landscapes. Experiments demonstrate improved visual prediction on in-domain and out-of-domain benchmarks, together with improved navigation performance. These results show that latent-action pretraining enables diverse, action-free videos to improve dynamics learning and generalization for open-world navigation. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Robotics (cs.RO) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2611.01844 — 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 2026-11-03T18:09:53.631Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).