Metraipolis › archive › dc_8934fcb2d332
CrashDiffuser: VLM-Guided Collision Intent Reasoning for Fine-Grained Safety-Critical Traffic Scenario Generation — arXiv:2609.02270
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.02270
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-17T03:37:34.135Z
- SHA-256 of the archived text
42114bef252bfd9d134b2a298c644d1254e47b5d3f9a7b08e848a8b09abd908c- Stable URL of this page
https://metraipolis.com/documento/dc_8934fcb2d332
How to cite
CrashDiffuser: VLM-Guided Collision Intent Reasoning for Fine-Grained Safety-Critical Traffic Scenario Generation — arXiv:2609.02270 — arXiv (en), https://arxiv.org/abs/2609.02270 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_8934fcb2d332 (Metraipolis archive dc_8934fcb2d332, sha256 42114bef252bfd9d134b2a298c644d1254e47b5d3f9a7b08e848a8b09abd908c)
BibTeX
@misc{dc8934fcb2d332,
title = {CrashDiffuser: VLM-Guided Collision Intent Reasoning for Fine-Grained Safety-Critical Traffic Scenario Generation — arXiv:2609.02270},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.02270},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_8934fcb2d332; sha256 42114bef252bfd9d134b2a298c644d1254e47b5d3f9a7b08e848a8b09abd908c},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.02270. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Generating safety-critical scenarios is essential for evaluating autonomous driving systems. However, existing generators primarily focus on inducing collisions and offer limited control over where contact occurs on the target vehicle. In this paper, we study fine-grained safety-critical scenario generation, where success requires both a target collision and a specified head, rear, or side contact region. We propose CrashDiffuser, a closed-loop VLM-guided diffusion framework that decouples semantic collision reasoning from continuous trajectory synthesis through a hierarchical collision-intent interface derived from the requested target contact region. At initialization, the VLM extracts reusable scene-level context; at each replanning step, it predicts a structured action tuple describing speed change, turning behavior, and collision stage. This intent conditions a diffusion model to generate executable adversarial trajectories, while collision-guided sampling, candidate selection, and short-horizon replanning adapt generation to the target vehicle's evolving behavior. On WOMD-derived closed-loop scenarios, CrashDiffuser achieves a target-collision rate of 50.33% in a single attempt and 67.98% after three attempts, together with a contact-region control success rate of 40.05% and competitive trajectory naturalness. Component ablations further support the proposed design. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-03 in cs.AI). Categorie arXiv: Robotics (cs.RO) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2609.02270 — 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 2026-10-17T03:13:12.524Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-03?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).