基于真实碰撞先验的人类行为感知碰撞场景生成方法用于自动驾驶车辆安全评估
Human Behavior-Informed Crash Scenario Generation with Real-World Crash Priors for Autonomous Vehicle Safety Evaluation
浏览论文内容
中文总结 AI 辅助
针对现有碰撞场景生成不真实的问题，提出CrashSim框架，利用真实碰撞先验指导生成式多智能体仿真，生成超4000个场景的nuCrash数据集，更真实再现碰撞并有效评估AV规划器安全能力。
中文摘要 AI 辅助
自动驾驶车辆（AV）的可靠安全评估对于改善道路安全至关重要，但这关键依赖于对罕见碰撞的真实模拟。现有的碰撞场景生成方法可以增加碰撞发生频率，但往往无法真实再现碰撞在撞击前如何演变，或无法再现现实世界中观察到的碰撞类型分布。在此，我们提出CrashSim，一个基于人类行为感知的碰撞场景生成框架，利用真实碰撞先验来指导生成式多智能体交通仿真，以实现更可靠的自动驾驶车辆安全评估。这些先验捕捉了真实碰撞在撞击前的演变过程以及不同碰撞类型的分布，使得有限的碰撞数据能够指导在自然驾驶情境下进行真实且可扩展的场景生成。我们将CrashSim与竞争方法进行评估，结果表明它更接近地再现了真实世界的撞击前行为、碰撞动力学、碰撞几何形状和碰撞类型分布。我们进一步使用CrashSim构建了nuCrash数据集，包含超过4000个碰撞和近碰撞场景。对五个自动驾驶规划器的闭环评估表明，nuCrash比nuScenes更有效地暴露了规划器安全能力的差异。一个基于大语言模型的评估智能体进一步分析规划器故障，以提供能力层面的诊断和有针对性的改进指导。总之，CrashSim能够实现真实且可扩展的碰撞生成，从而进行更具信息量的自动驾驶车辆安全评估。
英文摘要
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.
发表机构
- The Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州））
- Institute of Automation Chinese Academy of Sciences（中国科学院自动化研究所）
- The University of Hong Kong（香港大学）
- Shenzhen University（深圳大学）
机构由 AI 辅助整理，请以论文原文为准。
