Risk Assessment of Roundabout Scenarios in Virtual Testing Based on an Improved Driving Safety Field
Author:
Chen Wentao1, Li Aoxue2, Jiang Haobin1ORCID
Affiliation:
1. Automotive Engineering Research Institute, Jiangsu University, Zhenjiang 212013, China 2. School of Automotive and Traffic Engineering, Jiangsu University, Zhenjiang 212013, China
Abstract
With the advancement of autonomous driving technology, scenario-based testing has become the mainstream testing method for intelligent vehicles. However, traditional risk indicators often fail in roundabout scenarios and cannot accurately define dangerous situations. To accurately quantify driving risks in roundabout scenarios, an improved driving safety field model is proposed in this paper. First, considering the unique traffic flow characteristics of roundabouts, the dynamic characteristics of vehicles during diverging or merging were taken into account, and the driving safety field model was improved to accurately quantify the driving risks in roundabout scenarios. Second, based on data from the rounD dataset, the model parameters were calibrated using the social force model. Finally, a DENCLUE-like method was used to extract collision systems, calculate vehicle risk degree, and analyze these risks for both the temporal and the spatial dimensions, providing guidance for virtual testing. The proposed method significantly improves detection efficiency, increasing the number of identified dangerous scenarios by 175% compared to the Time to Collision (TTC) method. Moreover, this method can more accurately quantify driving risks in roundabout scenarios and enhance the efficiency of generating dangerous scenarios, contributing to promoting the safety of autonomous vehicles.
Funder
National Natural Science Foundation of China Project of Philosophy and Social Science Research in Colleges and Universities in Jiangsu Province Public Open Project of Automobile Standardization
Reference40 articles.
1. Zhang, Y., Wang, J., Lv, J., Gao, B., Chu, H., and Na, X. (2022). Computational efficient motion planning method for automated vehicles considering dynamic obstacle avoidance and traffic interaction. Sensors, 22. 2. He, J., Cheng, Z., Li, C., Xiang, W., Chen, B., Luo, B., Geng, Y., and Xie, X. (2023, January 19–25). Damo-streamnet: Optimizing streaming perception in autonomous driving. Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence(IJCAI-23), Marco, China. 3. Automatic virtual test technology for intelligent driving systems considering both coverage and efficiency;Gao;IEEE Trans. Veh. Technol.,2020 4. Parallel vision for long-tail regularization: Initial results from IVFC autonomous driving testing;Wang;IEEE Trans. Intell. Veh.,2022 5. Thorn, E., Kimmel, S.C., Chaka, M., and Hamilton, B.A. (2018). A Framework for Automated Driving System Testable Cases and Scenarios, DOT HS 812 623.
|
|