With the rapid development of autonomous driving technology, ensuring the safety of Autonomous Vehicles (AVs) has become a paramount concern. To tackle these safety challenges and enhance testing efficiency, this study presents an innovative method for generating naturalistic simulation scenarios for AV testing. The proposed method perceives the actions of the driving model as a probability problem, thus enabling the construction of a probability description model for naturalistic interactive behavior. Utilizing Naturalistic Driving Data (NDD) from DiDi autonomous driving dataset, the Copula function is employed to establish a high-dimensional, multivariate joint distribution model of naturalistic behavior variables. This constructed model is designed to encapsulate the distribution characteristics of interactive behavior variables effectively. This approach allows for the generation of behaviors featuring naturalistic interactions and driving scenarios that are unbiased reflections of real-world conditions. Experimental validation corroborates the effectiveness of these constructed simulation scenarios in emulating real-world driving behaviors. A comparative analysis with simulation scenarios based on the Intelligent Driver Model indicates a substantial reduction in the Mean Squared Error of vehicle variable distribution relative to real data in the Copula-based simulation scenarios, thereby validating the superiority of our proposed model.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Copula-Based Interactive Behavior Modeling for Naturalistic Test Scenarios Generation


    Contributors:
    Gu, Xinyu (author) / Wu, Siyu (author) / Li, Boqi (author) / Wang, Hong (author) / Jiao, Xiaohong (author) / Wang, Zheng (author) / Lu, Wei (author) / Yu, Wenhao (author) / Chen, Liyang (author) / Hu, Jia (author)


    Publication date :

    2023-09-24


    Size :

    2309558 byte





    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Test Concrete Scenarios Extraction of Lane-Changing Scenarios Based on China-FOT Naturalistic Driving Data

    Yin, Qi / Fang, Xiaowei / Zhu, Xichan et al. | SAE Technical Papers | 2023


    Naturalistic Driving Behavior Analysis under Typical Normal Cut-In Scenarios

    Ma, Xuehan / Ma, Zhixiong / Zhu, Xichan et al. | British Library Conference Proceedings | 2019


    Naturalistic Driving Behavior Analysis under Typical Normal Cut-In Scenarios

    Yu, Feng / Cao, Jianyong / Zhu, Xichan et al. | SAE Technical Papers | 2019