Autonomous vehicles must undergo a comprehensive performance evaluation before being deployed in real-world traffic, and testing in safety-critical scenarios is essential for identifying scenarios that autonomous vehicles cannot handle. Given the rarity of safety-critical scenarios, it is necessary to investigate how to systematically generate these scenarios. In this paper, we propose an adversarial method to efficiently generate safety-critical scenarios through deep reinforcement learning. We first formulate the typical lane-change scenarios based on the Markov Decision Process and then train the background vehicles to aggressively interfere with the autonomous vehicle under test and create some risky situations. We also propose a reasonableness reward to avoid the extreme adversarial behavior of the background vehicles, making the scenarios reasonable and informative for the autonomous vehicle testing. Simulation results show that the generated scenarios are more critical in terms of safety than those in the naturalistic environment, significantly degrading the performance of the vehicle under test and providing a basis for improving the model.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Adversarial Generation of Safety-Critical Lane-Change Scenarios for Autonomous Vehicles


    Contributors:
    He, Zimin (author) / Zhang, Jiawei (author) / Yao, Danya (author) / Zhang, Yi (author) / Pei, Huaxin (author)


    Publication date :

    2023-09-24


    Size :

    2291694 byte





    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Adversarial Evaluation of Autonomous Vehicles in Lane-Change Scenarios

    Chen, Baiming / Chen, Xiang / Qiong, Wu et al. | ArXiv | 2020

    Free access

    Adversarial Evaluation of Autonomous Vehicles in Lane-Change Scenarios

    Chen, Baiming / Chen, Xiang / Wu, Qiong et al. | IEEE | 2022


    Adversarial scenarios for safety testing of autonomous vehicles

    HARI SIVA KUMAR SASTRY / FROSIO IURI / GHODSI ZAHRA et al. | European Patent Office | 2023

    Free access

    Adversarial scenarios for safety testing of autonomous vehicles

    HARI SIVA KUMAR SASTRY / FROSIO IURI / GHODSI ZAHRA et al. | European Patent Office | 2024

    Free access

    ADVERSARIAL SCENARIOS FOR SAFETY TESTING OF AUTONOMOUS VEHICLES

    HARI SIVA KUMAR SASTRY / FROSIO IURI / GHODSI ZAHRA et al. | European Patent Office | 2023

    Free access