为自动驾驶场景测试建立统计基础，解决安全评估的科学性问题
On the Need for a Statistical Foundation in Scenario-Based Testing of Autonomous Vehicles
- 引入概率模型量化每种场景的失效风险（pfs）
- 证明场景测试与里程测试无绝对优劣，需结合条件选择
- 提出仿真与真实测试对齐的验证方法，支持可信安全声明
场景测试已成为自动驾驶汽车安全评估的常用方法，相比里程测试更高效，聚焦于高风险场景。然而，其停止规则、残余风险估计、调试有效性以及仿真保真度对安全结论的影响仍缺乏基础支撑。本文主张建立严谨的统计基础以应对这些挑战，实现可信赖的安全保障。通过类比软件测试中的成熟方法，识别出共性研究缺口并复用解决方案。我们提出了概念验证模型，用于量化每个场景的失效概率（pfs），并在不同条件下评估测试效果。分析表明，场景测试与里程测试并无普遍优劣之分。此外，我们给出一个关于合成数据与真实世界测试结果一致性的形式化推理示例，这是迈向基于仿真的可统计辩护安全声明的第一步。
原文摘要 · Abstract (English)
Scenario-based testing has emerged as a common method for autonomous vehicles (AVs) safety assessment, offering a more efficient alternative to mile-based testing by focusing on high-risk scenarios. However, fundamental questions persist regarding its stopping rules, residual risk estimation, debug effectiveness, and the impact of simulation fidelity on safety claims. This paper argues that a rigorous statistical foundation is essential to address these challenges and enable rigorous safety assurance. By drawing parallels between AV testing and established software testing methods, we identify shared research gaps and reusable solutions. We propose proof-of-concept models to quantify the probability of failure per scenario (\textit{pfs}) and evaluate testing effectiveness under varying conditions. Our analysis reveals that neither scenario-based nor mile-based testing universally outperforms the other. Furthermore, we give an example of formal reasoning about alignment of synthetic and real-world testing outcomes, a first step towards supporting statistically defensible simulation-based safety claims.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。