Metraipolis › archive › dc_97ff53bd242f

BrainWAM: Action-Space Coordination of Semantic Priors and Predictive Dynamics for Autonomous Driving — arXiv:2608.12854

Source: arXiv (en)
Original: https://arxiv.org/abs/2608.12854
License (as archived): CC0-1.0
Archived: 2026-10-19T04:18:12.757Z
SHA-256 of the archived text: 591c5e4c6aaf979d09a7336f84c4c383f8c379fa5d60e37420919b81d9b9b442
Stable URL of this page: https://metraipolis.com/documento/dc_97ff53bd242f

How to cite

BrainWAM: Action-Space Coordination of Semantic Priors and Predictive Dynamics for Autonomous Driving — arXiv:2608.12854 — arXiv (en), https://arxiv.org/abs/2608.12854 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_97ff53bd242f (Metraipolis archive dc_97ff53bd242f, sha256 591c5e4c6aaf979d09a7336f84c4c383f8c379fa5d60e37420919b81d9b9b442)

BibTeX

@misc{dc97ff53bd242f,
  title = {BrainWAM: Action-Space Coordination of Semantic Priors and Predictive Dynamics for Autonomous Driving — arXiv:2608.12854},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.12854},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_97ff53bd242f; sha256 591c5e4c6aaf979d09a7336f84c4c383f8c379fa5d60e37420919b81d9b9b442},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.12854. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Autonomous driving requires planning under both semantic constraints and predictive dynamics. Existing end-to-end driving approaches, however, typically emphasize only one side of this requirement: Vision-Language-Action (VLA) models exploit VLM priors for semantic reasoning, while World Action Models (WAMs) provide future-aware prediction through generative world modeling. This naturally motivates a unified planner that can leverage both semantic priors and predictive dynamics. However, we find that a naive combination through joint token-level attention suffers from an attention-allocation mismatch, where semantic shortcuts dominate the shared attention space and suppress predictive dynamics. Inspired by neuroscience evidence that complex behavior arises from coordination among functionally specialized systems, we propose BrainWAM, a structured action-space coordination framework that converts semantic reasoning and predictive world modeling into two specialized action-oriented pathways, and aligns them at the level of compact action representations. We further introduce an asynchronous rectified-flow inference strategy with decoupled video and action denoising, which shortens inference latency while preserving planning-relevant predictive context. BrainWAM reaches state-of-the-art performance on both NAVSIM v1 (89.5 PDMS) and NAVSIM v2 (89.6 EPDMS), consistently outperforming VLA-only or WAM-only methods, highlighting BrainWAM as a practical and promising direction for autonomous driving systems.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-14 in cs.AI).
Categorie arXiv: Robotics (cs.RO) ; Artificial Intelligence (cs.AI); Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2608.12854 — 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 2026-10-19T04:13:06.713Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-14?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).