一句话：提出基于CARLA的DNN自动驾驶测试平台ADEPT，结合事故报告NLP与闭环对抗攻击生成测试场景。
本文面向基于DNN的自动驾驶系统（ADS）的质量保障问题，提出了一个名为ADEPT的测试平台。ADEPT构建在虚拟仿真器CARLA之上，提供场景构造、ADS导入、测试执行与记录等较为完整的测试设施。其核心特色是两种面向自动驾驶的测试场景生成策略：一是利用真实事故报告，通过自然语言处理技术构造大量驾驶场景；二是考虑ADS的反馈来合成物理鲁棒性较强的对抗攻击，从而生成闭环测试场景。实验验证了该平台在自动驾驶系统测试中的有效性。
Effective quality assurance methods for autonomous driving systems ADS have attracted growing interests recently. In this paper, we report a new testing platform ADEPT, aiming to provide practically realistic and comprehensive testing facilities for DNN-based ADS. ADEPT is based on the virtual simulator CARLA and provides numerous testing facilities such as scene construction, ADS importation, test execution and recording, etc. In particular, ADEPT features two distinguished test scenario generation strategies designed for autonomous driving. First, we make use of real-life accident reports from which we leverage natural language processing to fabricate abundant driving scenarios. Second, we synthesize physically-robust adversarial attacks by taking the feedback of ADS into consideration and thus are able to generate closed-loop test scenarios. The experiments confirm the efficacy of the platform.
@inproceedings{paperbot7352,
title = {ADEPT: A Testing Platform for Simulated Autonomous Driving},
author = {Sen Wang and Zhuheng Sheng and Jingwei Xu and Taolue Chen and Junjun Zhu and Shuhui Zhang and Yuan Yao and Xiaoxing Ma},
booktitle = {ASE},
year = {2022},
doi = {10.1145/3551349.3559528}
}