Metraipolis › archive › dc_7f0e45e22dcc
Beyond Retrieval Relevance: Scene-Grounded Risk Entailment for Vision-Language Driving — arXiv:2609.34145
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.34145
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-08T00:17:17.030Z
- SHA-256 of the archived text
6a340ff56ef8235b41d1c379cff7879b5c9e810f160fb554b45e95d7af6ac05e- Stable URL of this page
https://metraipolis.com/documento/dc_7f0e45e22dcc
How to cite
Beyond Retrieval Relevance: Scene-Grounded Risk Entailment for Vision-Language Driving — arXiv:2609.34145 — arXiv (en), https://arxiv.org/abs/2609.34145 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_7f0e45e22dcc (Metraipolis archive dc_7f0e45e22dcc, sha256 6a340ff56ef8235b41d1c379cff7879b5c9e810f160fb554b45e95d7af6ac05e)
BibTeX
@misc{dc7f0e45e22dcc,
title = {Beyond Retrieval Relevance: Scene-Grounded Risk Entailment for Vision-Language Driving — arXiv:2609.34145},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.34145},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_7f0e45e22dcc; sha256 6a340ff56ef8235b41d1c379cff7879b5c9e810f160fb554b45e95d7af6ac05e},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.34145. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Retrieval-augmented generation (RAG) gives vision--language driving systems access to external safety knowledge, yet a retrieved risk rule may be relevant without applying to the current scene. A vision--language model (VLM) receiving such knowledge must ground objects, bind entities across time, and verify relations before deciding how to act, leaving the support for risk conclusions implicit. We address this relevance--applicability gap with a Driving-Risk Knowledge Graph (DRKG) and Semantic Web Rule Language (SWRL) reasoning stage before VLM decision-making. Structured perception instantiates scene facts, from which SWRL rules derive events and directed risk relations when their antecedents are jointly satisfied. Recognized events, bound risk relations, and semantic descriptions of activated rules form compact evidence that conditions the VLM and diffusion planner. In matched comparisons on nuReasoning, our method improved the nuReasoning planning score (NPS) by 1.30 points and the non-at-fault collision score (NC) by 2.76 points over the relevance retrieval-based baseline. These gains indicate that scene-applicable risk evidence improves safety-weighted planning relative to semantically retrieved risk knowledge. Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-29 in cs.RO). Categorie arXiv: Robotics (cs.RO). Pagina del lavoro: https://arxiv.org/abs/2609.34145 — 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 2026-10-07T23:52:16.514Z dalla pagina https://arxiv.org/catchup/cs.RO/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).