用可信度加权模型，解决自动驾驶事故责任定价难题。
Credibility-Weighted Pricing of Autonomous Vehicle Liability Under Operational Design Domain Shift
- 构建分层贝叶斯框架，通过学习的ODD相似核跨城市、版本聚合数据。
- 实测显示城市级可信度权重在0.12至0.46之间，部分聚合显著优于无聚合。
- 适用于保险精算与自动驾驶监管，尤其适合多城市部署系统评估。
自动驾驶系统部署带来核心精算挑战：事故样本稀疏、运行设计域（ODD）变化频繁，且软件更新导致风险非平稳。本文提出一种分层贝叶斯可信度框架，通过学习的ODD相似核，在城市、软件版本和区域间进行数据聚合，其可退化为Buhlmann-Straub模型的极限情形。基于美国四座城市共648起经验证的Waymo碰撞事件（来自NHTSA通用令数据库）与1.16亿匹配里程的数据，结果显示城市聚合的可信度权重处于0.12至0.46之间；部分聚合效果显著优于无聚合；幂分析表明，当部署城市数达到约12个时，学习核的优势即可被检测到。
原文摘要 · Abstract (English)
Automated Driving System deployments create a foundational ratemaking challenge: sparse experience, shifting operational design domains, and non-stationary risk across software releases. We propose a hierarchical Bayesian credibility framework pooling across cities, software versions, and territories via a learned ODD-similarity kernel, nesting Buhlmann-Straub as a limiting case. Demonstrated on 648 verified-engaged Waymo crashes across four U.S. metros from the NHTSA Standing General Order database against 116 million matched miles, city-aggregate credibility weights are moderate (0.12-0.46), partial pooling decisively outperforms no pooling, and a power analysis shows the learned kernel's advantage becomes detectable at approximately twelve deployed cities.
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。