Metraipolis › archive › dc_8249808a29df
DA-WAM: Decision-Aligned Future Latents for Driving World Models — arXiv:2608.19085
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.19085
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-18T13:45:33.599Z
- SHA-256 of the archived text
9bceeb9e57b7b992d6e02c8cfb4fcdd0dbb1ede5d943bb049572bfd1823bb0c1- Stable URL of this page
https://metraipolis.com/documento/dc_8249808a29df
How to cite
DA-WAM: Decision-Aligned Future Latents for Driving World Models — arXiv:2608.19085 — arXiv (en), https://arxiv.org/abs/2608.19085 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_8249808a29df (Metraipolis archive dc_8249808a29df, sha256 9bceeb9e57b7b992d6e02c8cfb4fcdd0dbb1ede5d943bb049572bfd1823bb0c1)
BibTeX
@misc{dc8249808a29df,
title = {DA-WAM: Decision-Aligned Future Latents for Driving World Models — arXiv:2608.19085},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.19085},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_8249808a29df; sha256 9bceeb9e57b7b992d6e02c8cfb4fcdd0dbb1ede5d943bb049572bfd1823bb0c1},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.19085. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Anticipating how scenes evolve under ego actions is fundamental to safe autonomous driving, yet the full potential of world models for decision-making remains unrealized. The critical challenge lies in ensuring that future modeling is not merely predictive, but decision-informative: the predicted future must directly shape which trajectory is selected. Existing approaches decouple future representation learning from planning optimization, or share predicted states across trajectory candidates, thereby diluting the action-specific consequences that ought to guide selection. To bridge this gap, we propose DA-WAM, a framework that unifies predictive representation learning, action-conditioned future modeling, and trajectory scoring under a single decision-making objective. DA-WAM maintains predictive supervision throughout planner optimization via an online encoder and a stable momentum target, allowing future representations to co-evolve with the driving task. An action-conditioned predictor generates a distinct future latent state per trajectory candidate, which is then evaluated by a future-latent-conditioned factorized scorer. For the expert-matched trajectory, the predicted future latent is supervised by the observed future representation, while safety-critical hard negatives provide additional supervision near planning boundaries. Extensive experiments on NAVSIM-v1 and NAVSIM-v2 demonstrate state-of-the-art performance, while ablations and diagnostic analyses validate the key components. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-20 in cs.AI). Categorie arXiv: Robotics (cs.RO) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2608.19085 — 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 2026-10-18T13:41:17.998Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-20?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).