TY  - JOUR
PY  - 2023//
TI  - A dynamic test scenario generation method for autonomous vehicles based on conditional generative adversarial imitation learning
JO  - Accident analysis and prevention
A1  - Jia, Lulu
A1  - Yang, Dezhen
A1  - Ren, Yi
A1  - Qian, Cheng
A1  - Feng, Qiang
A1  - Sun, Bo
A1  - Wang, Zili
SP  - e107279
EP  - e107279
VL  - 194
IS  - 
N2  - Autonomous vehicles must be comprehensively evaluated before deployed in cities and highways. However, most existing evaluation approaches for autonomous vehicles are static and model environmental vehicles with predefined trajectories, which ignore the time-sequential interactions between the ego vehicle and environmental vehicles. In this paper, we propose a dynamic test scenario generation method to evaluate autonomous vehicles by modeling environmental vehicles as agents with human behavior and simulating the interaction process between the autonomous vehicle and environmental vehicles. Considering the multimodal features of traffic scenarios, we cluster the real-word traffic environments, and integrate the scenario class labels into the conditional generative adversarial imitation learning (CGAIL) model to generate different types of traffic scenarios. The proposed method is validated in a typical lane-change scenario that involves frequent interactions between ego vehicle and environmental vehicles. <br><br>RESULTS show that the proposed method further test autonomous vehicles' ability to cope with dynamic scenarios, and can be used to infer the weaknesses of the tested vehicles.<p />  <p>Language: en</p>
LA  - en
SN  - 0001-4575
UR  - http://dx.doi.org/10.1016/j.aap.2023.107279
ID  - ref1
ER  -