Han, Qingwen (Chongqing University), Fan, Duowen (Chongqing University), Zeng, Lingqiu (Chongqing University), Qi, LingFeng (Chongqing University), Ye, Lei (Chongqing University)

The Extraction and Generation of Complex Critical Scenarios for Demonstration Area-Oriented C-V2X Test

Scheduled for presentation during the Regular Session "Communications and Protocols in ITS" (WeAT11), Wednesday, September 25, 2024, 11:50−12:10, Salon 19/20

2024 IEEE 27th International Conference on Intelligent Transportation Systems (ITSC), September 24- 27, 2024, Edmonton, Canada

This information is tentative and subject to change. Compiled on October 3, 2024

Abstract

The C-V2X demonstration area, which could provide testing and evaluation services, is considered as an ideal field test road section. One key points of demonstration area-oriented test is the reliability of test scenarios, which should be extracted from the traffic features of corresponding area. Therefore, in this paper, a criticality-complexity-based test scenario generation method is proposed to construct a demonstration area-oriented exclusive test scenario library. Two new concepts, critical vehicle pairs and complex driving backgrounds, are defined and employed as the basic elements to generate complex critical test scenarios. To address the issue of insufficient sample size, an attention-RGAN network is designed to fulfill data augmentation. Then, a method for generating complex critical test scenarios is proposed. Simulation results and on-road test results verify the effectiveness of the proposed method, while the generated test scenario library was deployed in the Yongchuan demonstration area in Chongqing, China.