In order to decide a safe and reliable trajectory for autonomous driving vehicles, the threat of surrounding vehicles need to be assessed quantitatively and consider the potential risk. This paper proposes a novel integrated threat assessment algorithm for the decision-making system. First, the motion of the surrounding vehicle is predicted probabilistic based on the interact multiple model (IMM) to consider the potential threat. Then, we build an integrated threat assessment function to assess the threat in each state quantitatively and objectively, which synthesizes the existing time-to-collision (TTC), time-headway (TH), and the original proposed time-to-front (TTF). Based on this, the decision-making system is established according to the Markov decision process (MDP) and the feedback value of each decision sequence is calculated by the integrated threat assessment function, thus the safest trajectory for the current moment can be determined by optimal search. Finally, the decision-making system is verified in the overtaking and cut-in scenario by Carsim and Simulink co-simulation. The results show that the proposed threat assessment algorithm for the decision-making system can help autonomous vehicles decide a safe trajectory in real-time and maintain good maneuverability.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    An Integrated Threat Assessment Algorithm for Decision-Making of Autonomous Driving Vehicles


    Contributors:
    Xu, Can (author) / Zhao, Wanzhong (author) / Wang, Chunyan (author)


    Publication date :

    2020-06-01


    Size :

    4959148 byte




    Type of media :

    Article (Journal)


    Type of material :

    Electronic Resource


    Language :

    English




    A Bootstrapped DQN-Based Decision-Making Method for Autonomous Driving Vehicles

    Wang, Yinglei / Liang, Jinhao / Lu, Yanbo et al. | IEEE | 2023


    Autonomous Driving Cars: Decision-Making

    Ramanathan, Prabhu / Kartik | Springer Verlag | 2020


    DeepAD: An integrated decision-making framework for intelligent autonomous driving

    Shi, Yunyang / Liu, Jinghan / Liu, Chengqi et al. | Elsevier | 2024


    Decision-making techniques for autonomous vehicles

    Villagra, Jorge ;Jiménez, Felipe | TIBKAT | 2023