With the rapid development of new infrastructure and a strong transportation country, China’s road infrastructure has been upgraded with intelligent systems. A comprehensive testing and evaluation system is necessary to promote the development of vehicle-road cooperative systems. Traditional testing tools and methods for conventional vehicles cannot meet the needs of cooperative vehicle-road testing. Scenario-based virtual testing methods have significant technical advantages in testing efficiency and cost and are becoming an essential means of testing and verification in the future autonomous driving field. Therefore, this paper proposes a scenario-based method for evaluating the efficiency of vehicle-road cooperative perception. First, a data-driven construction method based on generative adversarial networks (GANs) is used to automatically generate structured test cases for the selected operational design domains (ODDs) to solve the problem of rare event long tails in the testing process. Then, we perform performance tests on multiple visual perception algorithms, such as YOLO, SSD, and Faster R-CNN, on a vehicle-road cooperative simulation platform. Finally, we establish a quantitative evaluation system of testing scenarios and multidimensional test requirement metrics to evaluate the results of the testing stage. The results show that the proposed method can efficiently and rapidly generate critical testing scenarios for evaluating vehicle-road cooperative perception efficiency, thereby improving the testing efficiency of cooperative sensing systems.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    A Scenario-Based Method for Evaluating the Efficiency of Vehicle-Road Cooperative Perception


    Beteiligte:
    Li, Ruifen (Autor:in) / Liu, Zhanwen (Autor:in) / Xiao, Fangwei (Autor:in) / Wang, Di (Autor:in) / He, Yi (Autor:in) / Fang, Fan (Autor:in)


    Erscheinungsdatum :

    04.08.2023


    Format / Umfang :

    1472709 byte





    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Vehicle motion intention reasoning using cooperative perception on urban road

    Liu, Wei / Kim, Seong-Woo / Marczuk, Katarzyna et al. | IEEE | 2014


    Cooperative Perception using Cellular V2X in Mixed Traffic Scenario

    Hidayatullah, Muhammad Rony / Juang, Jyh-Ching / Zheng, Zhao-Shun et al. | IEEE | 2021


    Cooperative Perception System And Cooperative Perception Method

    LEE JUN HYUNG / KIM HYOUNG SOO / YANG IN CHUL | Europäisches Patentamt | 2024

    Freier Zugriff

    Vehicle-road cooperative road traffic system

    ZHANG KUN / ZHU XIAOLONG / WANG HAO | Europäisches Patentamt | 2021

    Freier Zugriff