EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Constraint- and Risk-Driven Search for Safety-Critical Scenarios in Autonomous Driving Simulation

Deng Pan, Bin Lu, Xiaoji Zhou, Yuyang Mao, Lipeng Cao

Vehicles · 13.08.2026 · 8 (8) · 188

DOI: 10.3390/vehicles8080188 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Vehicles, online erschienen am 13.08.2026. Verfasst von Deng Pan und 4 weiteren Autor:innen. Die Arbeit nennt 17 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Chongqing Municipal Science and Technology Bureau, Information Intelligence Business Division, China Automotive Engineering Research Institute Co., Ltd..

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Efficient discovery of safety-critical scenarios is a central problem in autonomous-driving simulation because safety-critical events are rare and the scenario parameter space is often high-dimensional. Direct random sampling can spend most of the simulation budget on samples that are weakly relevant, physically unreachable, or behaviorally inconsistent. This study proposes a constraint- and risk-driven framework for safety-critical scenario discovery. The framework first constructs a valid scenario space using physical reachability, behavioral consistency, and traffic-feasibility constraints. It then evaluates valid simulated samples with a hierarchical scenario-value model that combines kinematic criticality, longitudinal controllability risk, and scenario diversity. Finally, a risk-feedback probabilistic search updates the sampling distribution using high-value samples. The method is evaluated primarily in a lead-vehicle hard-braking scenario and additionally in a cut-in scenario. In the lead-vehicle hard-braking scenario, the proposed method improves the discovery rate from 0.68% for Random Sampling to 49.62% under a budget of 1000 evaluations. In the cut-in scenario, the discovery rate improves from 5.28% to 67.68% under the same budget. Ablation results show that constraint-aware construction reduces potentially invalid samples, while the full hierarchical scenario-value model improves coverage of discovered safety-critical samples.

Förderung

  • Chongqing Municipal Science and Technology Bureau
  • Information Intelligence Business Division, China Automotive Engineering Research Institute Co., Ltd.

Zitieren

APA

Pan, D., Lu, B., Zhou, X., Mao, Y., & Cao, L. (2026). Constraint- and Risk-Driven Search for Safety-Critical Scenarios in Autonomous Driving Simulation. Vehicles, 8(8), 188. https://doi.org/10.3390/vehicles8080188

Vancouver

Pan D, Lu B, Zhou X, Mao Y, Cao L. Constraint- and Risk-Driven Search for Safety-Critical Scenarios in Autonomous Driving Simulation. Vehicles. 2026;8(8):188. doi:10.3390/vehicles8080188

BibTeX
@article{Pan2026,
  author = {Pan, Deng and Lu, Bin and Zhou, Xiaoji and Mao, Yuyang and Cao, Lipeng},
  title = {Constraint- and Risk-Driven Search for Safety-Critical Scenarios in Autonomous Driving Simulation},
  journal = {Vehicles},
  year = {2026},
  volume = {8},
  number = {8},
  pages = {188},
  doi = {10.3390/vehicles8080188}
}
Kostenlos starten →