Metraipolis › archive › dc_a4350089cdb4

PhysWAM: Physically Consistent World Action Model for Autonomous Driving — arXiv:2609.37970

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.37970
License (as archived)
CC0-1.0
Archived
2026-10-07T18:42:09.541Z
SHA-256 of the archived text
9271e1e93a7de906f24e2a6d4594acfded3b8e8dd0f3fe56c5118e7677a6c9a4
Stable URL of this page
https://metraipolis.com/documento/dc_a4350089cdb4

How to cite

PhysWAM: Physically Consistent World Action Model for Autonomous Driving — arXiv:2609.37970 — arXiv (en), https://arxiv.org/abs/2609.37970 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_a4350089cdb4 (Metraipolis archive dc_a4350089cdb4, sha256 9271e1e93a7de906f24e2a6d4594acfded3b8e8dd0f3fe56c5118e7677a6c9a4)
BibTeX
@misc{dca4350089cdb4,
  title = {PhysWAM: Physically Consistent World Action Model for Autonomous Driving — arXiv:2609.37970},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.37970},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_a4350089cdb4; sha256 9271e1e93a7de906f24e2a6d4594acfded3b8e8dd0f3fe56c5118e7677a6c9a4},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.37970. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

World-action models (WAMs) jointly predict how a scene will evolve and how an agent should act, however joint generation alone does not necessarily impose a shared geometric constraint on these predictions. We present PhysWAM, a unified world-action model for autonomous driving that co-denoises multiview video, metric depth, and ego motion within a single flow-matching transformer. To ground world and action generation in measured scene geometry, we introduce Coupled Point Projection (CPP) that unprojects the generated depth into 3D points, transforms them using the generated $\mathrm{SE}(3)$ ego motion, and minimizes their distance to LiDAR points transformed using the recorded ego motion. This geometric constraint promotes physical consistency with the measured scene by jointly supervising generated depth and motion alongside their standard flow-matching objectives. At inference, trajectory selection relies only on a simple label-free consensus rule, with no learned scorer or simulator feedback. We evaluate PhysWAM across NAVSIM v1 and v2 planning, zero-shot closed-loop transfer, and future video and metric-depth prediction. Despite PhysWAM's simple selection procedure, it achieves strong planning performance and transfers zero-shot to unseen driving environments. It also generates accurate metric depth and temporally coherent video, with CPP improving both planning and depth prediction. Together, these results demonstrate that the geometric relationship between scene depth and ego motion provides a direct way to couple world and action generation within a simple unified model.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-30 in cs.CV).
Categorie arXiv: Robotics (cs.RO) ; Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2609.37970 — 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 2026-10-07T18:04:24.982Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-30?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).