一句话：提出 SoVAR，从事故报告构建可泛化场景，以支持自动驾驶系统安全测试。
自动驾驶系统（ADS）已用于安全关键场景，但致命事故表明其安全性仍需更全面、有针对性的测试。真实事故报告中的场景包含关键场景和高质量种子，是 ADS 测试的重要资源。然而，现有从事故报告重建场景的方法在信息抽取上精度有限；同时，道路环境多样复杂，将当前事故信息与仿真地图数据匹配以完成重建面临显著挑战。为此，论文提出 SoVAR，旨在从事故报告构建可泛化场景，以增强 ADS 测试。摘要主要描述问题与动机，未展开具体方法与实验评估。
Autonomous driving systems (ADSs) have undergone remarkable development and are increasingly employed in safety-critical applications. However, recently reported data on fatal accidents involving ADSs suggests that the desired level of safety has not yet been fully achieved. Consequently, there is a growing need for more comprehensive and targeted testing approaches to ensure safe driving. Scenarios from real-world accident reports provide valuable resources for ADS testing, including critical scenarios and high-quality seeds. However, existing scenario reconstruction methods from accident reports often exhibit limited accuracy in information extraction. Moreover, due to the diversity and complexity of road environments, matching current accident information with the simulation map data for reconstruction poses significant challenges.
@inproceedings{paperbot8414,
title = {SoVAR: Build Generalizable Scenarios from Accident Reports for Autonomous Driving Testing},
author = {An Guo and Yuan Zhou and Haoxiang Tian and Chunrong Fang and Yunjian Sun and Weisong Sun and Xinyu Gao and Anh Tuan Luu and Yang Liu and Zhenyu Chen},
booktitle = {ASE},
year = {2024},
doi = {10.1145/3691620.3695037}
}