Metraipolis › archive › dc_e4abc6ba4cd6
Safety-Critical Scenarios Emerge from Initial Scenes — arXiv:2609.20103
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.20103
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-10T05:25:39.968Z
- SHA-256 of the archived text
8136e1f22cd45322a7d2f425a5995ba79a21cafa431c61171872e980bb1eb90b- Stable URL of this page
https://metraipolis.com/documento/dc_e4abc6ba4cd6
How to cite
Safety-Critical Scenarios Emerge from Initial Scenes — arXiv:2609.20103 — arXiv (en), https://arxiv.org/abs/2609.20103 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_e4abc6ba4cd6 (Metraipolis archive dc_e4abc6ba4cd6, sha256 8136e1f22cd45322a7d2f425a5995ba79a21cafa431c61171872e980bb1eb90b)
BibTeX
@misc{dce4abc6ba4cd6,
title = {Safety-Critical Scenarios Emerge from Initial Scenes — arXiv:2609.20103},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.20103},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_e4abc6ba4cd6; sha256 8136e1f22cd45322a7d2f425a5995ba79a21cafa431c61171872e980bb1eb90b},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.20103. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Safety-critical driving scenario generation has largely focused on manipulating the behavior of surrounding agents while starting from an initial scene from driving data. This assumption can limit the space of discoverable failures, since driving data can provide little opportunity for meaningful interaction. For example, in the Waymo Open Motion Dataset, 20.44% of recorded slices feature a stationary ego vehicle that never moves, and 30.39% of initial frames contain no nearby traffic participants within 10 meters. We instead study safety-critical scenario generation as an initialization problem: given agnostic black-box driving policies, we learn to generate realistic initial scenes that are more likely to evolve into critical interactions. We propose AdvScene, a conditional latent diffusion model that is trained in two stages. Starting from pretraining on naturalistic driving data, we post-train the adversarial-agent generation branch using reinforcement learning with feedback from closed-loop simulator rollouts. Conditioning on ego driving displacement prevents the ego from remaining static, and RL finetuning induces criticality directly with non-differentiable safety-critical metrics. Experiments on the Waymo dataset across 12 combinations of ego and traffic policies show that our AdvScene substantially increases the rate of ego-fault collision events and TTC<3s events. Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-18 in cs.RO). Categorie arXiv: Robotics (cs.RO). Pagina del lavoro: https://arxiv.org/abs/2609.20103 — 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 2026-10-10T04:47:38.882Z dalla pagina https://arxiv.org/catchup/cs.RO/2026-09-18?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).