Metraipolis › archive › dc_c42da3125367

Reinforcing End-to-End Autonomous Driving Safety via Negative-Aware Planning in a Unified World-Action Model — arXiv:2611.08111

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.08111
License (as archived)
CC0-1.0
Archived
2026-11-06T14:53:52.983Z
SHA-256 of the archived text
955205edb40de05f6a70d1514982e00658eccd351c5f1e066262d9505c3b8037
Stable URL of this page
https://metraipolis.com/documento/dc_c42da3125367

How to cite

Reinforcing End-to-End Autonomous Driving Safety via Negative-Aware Planning in a Unified World-Action Model — arXiv:2611.08111 — arXiv (en), https://arxiv.org/abs/2611.08111 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_c42da3125367 (Metraipolis archive dc_c42da3125367, sha256 955205edb40de05f6a70d1514982e00658eccd351c5f1e066262d9505c3b8037)
BibTeX
@misc{dcc42da3125367,
  title = {Reinforcing End-to-End Autonomous Driving Safety via Negative-Aware Planning in a Unified World-Action Model — arXiv:2611.08111},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.08111},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_c42da3125367; sha256 955205edb40de05f6a70d1514982e00658eccd351c5f1e066262d9505c3b8037},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.08111. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

World-action models (WAMs) jointly model future traffic states and driving actions for end-to-end autonomous driving in intelligent transportation systems. However, their action learning remains dominated by expert-trajectory imitation, leaving unsafe alternatives close to expert trajectories insufficiently constrained. To improve WAM robustness in safety-critical scenarios, we propose NegWAM, a safety post-training framework for unified WAMs that learns explicit safety boundaries from near-expert failure trajectories. NegWAM constructs negative trajectories that are geometrically close to the expert trajectory yet carry safety risks, uses them as repulsive anchors to steer predictions away from dangerous behavior, and encodes them as scene-conditioned rider tokens to learn scene--trajectory compatibility. During training, NegWAM jointly optimizes the flow-matching and near-expert negative objectives, while the auxiliary rider branch is discarded at inference, incurring no additional overhead. On NAVSIM v2, NegWAM achieves 40.4 EPDMS on navhard, a 4.1% relative improvement over the strongest compared scorer-free WAM baseline, and achieves 93.3 EPDMS on navtest. These results demonstrate that NegWAM achieves strong performance in safety-critical scenarios while preserving routine-driving performance. Zero-shot closed-loop evaluation on HUGSIM further demonstrates cross-benchmark generalization. The code is available at this https URL .

Tema degli esploratori: statistica e scienza dei dati (elenco arXiv cs.CV, nuovi lavori del giorno).
Categorie arXiv: Robotics (cs.RO) ; Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2611.08111 — 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 2026-11-06T14:25:42.634Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).