Metraipolis › archive › dc_2f39fc3e1194
Human Behavior-Informed Crash Scenario Generation with Real-World Crash Priors for Autonomous Vehicle Safety Evaluation — arXiv:2610.04366
- Source
- arXiv
- Original
- https://arxiv.org/abs/2610.04366
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-06T05:26:10.542Z
- SHA-256 of the archived text
a6100304f2eb9e7717424263a4e6f4fb55160e78a965877f7faa7eb032123a5b- Stable URL of this page
https://metraipolis.com/documento/dc_2f39fc3e1194
How to cite
Human Behavior-Informed Crash Scenario Generation with Real-World Crash Priors for Autonomous Vehicle Safety Evaluation — arXiv:2610.04366 — arXiv, https://arxiv.org/abs/2610.04366 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_2f39fc3e1194 (Metraipolis archive dc_2f39fc3e1194, sha256 a6100304f2eb9e7717424263a4e6f4fb55160e78a965877f7faa7eb032123a5b)
BibTeX
@misc{dc2f39fc3e1194,
title = {Human Behavior-Informed Crash Scenario Generation with Real-World Crash Priors for Autonomous Vehicle Safety Evaluation — arXiv:2610.04366},
howpublished = {arXiv},
url = {https://arxiv.org/abs/2610.04366},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_2f39fc3e1194; sha256 a6100304f2eb9e7717424263a4e6f4fb55160e78a965877f7faa7eb032123a5b},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv, https://arxiv.org/abs/2610.04366. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Reliable safety evaluation of autonomous vehicles (AVs) is essential to improving road safety, yet it depends critically on realistic simulation of rare crashes. Existing crash scenario generation methods can increase collision occurrence, but often fail to realistically reproduce how crashes evolve before impact or the distribution of crash types observed in the real world. Here, we present CrashSim, a human behavior-informed crash scenario generation framework that uses real-world crash priors to guide generative multi-agent traffic simulation for more reliable AV safety evaluation. These priors capture how real-world crashes evolve before impact and how different crash types are distributed, allowing limited crash data to guide realistic and scalable scenario generation across naturalistic driving contexts. We evaluate CrashSim against competing methods, showing that it more closely reproduces real-world pre-impact behavior, collision dynamics, collision geometry and crash-type distributions. We further use CrashSim to construct nuCrash dataset, containing over 4,000 crash and near-crash scenarios. Closed-loop evaluation of five AV planners shows that nuCrash more effectively exposes differences in planner safety capabilities than nuScenes. An LLM-assisted evaluation agent further analyzes planner failures to provide capability-level diagnoses and targeted improvement guidance. Together, CrashSim enables realistic and scalable crash generation for more informative AV safety evaluation. 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/2610.04366 — 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 2026-10-06T05:24:05.841Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).