@inproceedings{260b0680b8054ecdbb3b9d70cae89a64,
title = "Research on screening methods of autonomous driving dangerous test cases based on Carmaker",
abstract = "Autonomous driving vehicle is the mainstream trend of the development of the automotive industry at home and abroad. In the process of its research and development, many safety problems are frequently exposed. Therefore, the safety test of autonomous driving vehicles is particularly important. Autonomous driving vehicle testing can be carried out in three aspects: virtual simulation test, proving ground test and real road test. Among them, proving ground test, as a kind of real vehicle test, mainly tests typical dangerous scenarios. Based on the simulation software Carmaker, a method of automatic generation of simulation test cases is proposed in this paper. The method defines different parameter variables and parameter boundary, realizes the automatic combination of parameters through the editing and running of the code, and improves the efficiency of simulation test and the coverage of test cases. Through the high-efficiency and high-coverage hardware-in-the-loop simulation test, the dangerous test cases of typical scenarios are screened out for the proving ground test, so as to make the proving ground test more targeted and improve the efficiency of the proving ground test. Meanwhile, combination of virtual simulation and proving ground in actual test is able to ensure simulation result effectiveness.",
keywords = "Autonomous driving, Carmaker, Dangerous test cases, Proving ground test, Simulation test",
author = "Zhiqiang Zhang and Shaohua Liu and Cheng Zhang and Li, \{Hong Fei\}",
note = "Publisher Copyright: {\textcopyright} 2021 SPIE.; International Conference on Smart Transportation and City Engineering 2021 ; Conference date: 26-10-2021 Through 28-10-2021",
year = "2021",
doi = "10.1117/12.2613892",
language = "English",
series = "Proceedings of SPIE - The International Society for Optical Engineering",
publisher = "SPIE",
editor = "Zhengliang Li and Fengjie Cen",
booktitle = "International Conference on Smart Transportation and City Engineering 2021",
address = "United States",
}