Metraipolis › archive › dc_ff801f366f71

Jev with Foresight: Safe Language-Guided Autonomous Driving via a Language World Model — arXiv:2611.05448

Source: arXiv (en)
Original: https://arxiv.org/abs/2611.05448
License (as archived): CC0-1.0
Archived: 2026-11-05T18:17:21.936Z
SHA-256 of the archived text: a05ebb5c57a8d3d99526142f457d3d6468f42612aacbb85e15ff5d27c1e9c0e6
Stable URL of this page: https://metraipolis.com/documento/dc_ff801f366f71

How to cite

Jev with Foresight: Safe Language-Guided Autonomous Driving via a Language World Model — arXiv:2611.05448 — arXiv (en), https://arxiv.org/abs/2611.05448 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ff801f366f71 (Metraipolis archive dc_ff801f366f71, sha256 a05ebb5c57a8d3d99526142f457d3d6468f42612aacbb85e15ff5d27c1e9c0e6)

BibTeX

@misc{dcff801f366f71,
  title = {Jev with Foresight: Safe Language-Guided Autonomous Driving via a Language World Model — arXiv:2611.05448},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.05448},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ff801f366f71; sha256 a05ebb5c57a8d3d99526142f457d3d6468f42612aacbb85e15ff5d27c1e9c0e6},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.05448. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Large language models understand passengers' driving commands, but as driving agents they reason in generated text for seconds and must infer each action's consequences implicitly from the scene. We present Jev-AD, which pairs Jev, a typed decision model that answers predefined questions with probabilities, not generated text, with a language world model that predicts for every candidate action how nearby vehicles move over the next two seconds. Code turns these predictions into foreseen consequences, which Jev compares instead of inferring them from coordinates. In simulated highway merging (500 car-episodes), this foresight lowers the same decision model's collision rate from 26.0% to 2.4% at 0.25 seconds per decision, and Jev-AD achieves the passenger's intent in 93% of free-form command trials. In 500 replayed real-world NGSIM episodes, foresight lowers the collision rate from 48.2% to 2.8%, and the world model, learned from this traffic, foresees 93% of dangerous actions. Project page: this https URL .

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/2611.05448 — 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 2026-11-05T18:12:49.026Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).