The invention provides an automatic driving protection-free left turn method and system, and relates to the technical field of artificial intelligence, and the method comprises the steps: S1, obtaining the interaction information of all obstacle lanes in the current frame and an own vehicle lane, screening out opposite straight obstacles, and enabling the obstacles to be motor vehicles and non-motor vehicles; and S2, performing clustering processing on the motor vehicles and the non-motor vehicles at the intersection, judging whether the motor vehicles and the non-motor vehicles are part of the traffic flow or not, and performing processing according to different conditions. According to the invention, the challenge problem of unprotected left turn can be solved, the ADV can smoothly carry out unprotected left turn, and the safety and efficiency are ensured at the same time.

    本发明提供了一种自动驾驶无保护左转方法及系统,涉及人工智能技术领域,包括:步骤S1:获取当前帧所有障碍物车道与自车车道的交互信息,筛选出对向直行的障碍物,所述障碍物为机动车和非机动车;步骤S2:对路口的机动车和非机动车进行聚类的处理,判断机动车和非机动车是否是车流的一部分,根据不同情况分别进行处理。本发明能够解决无保护左转的挑战问题,让ADV能够顺利地进行无保护左转,同时保证安全性和效率。


    Access

    Download


    Export, share and cite



    Title :

    Automatic driving unprotected left turning method and system


    Additional title:

    自动驾驶无保护左转方法及系统


    Contributors:
    LIAO WENLONG (author) / MAO LIDONG (author) / HE TAO (author) / ZHANG RUNXI (author)

    Publication date :

    2023-06-02


    Type of media :

    Patent


    Type of material :

    Electronic Resource


    Language :

    Chinese


    Classification :

    IPC:    B60W CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION , Gemeinsame Steuerung oder Regelung von Fahrzeug-Unteraggregaten verschiedenen Typs oder verschiedener Funktion



    Unprotected left-turn driving control method based on deep reinforcement learning

    ZHAO MIN / SUN DIHUA / CHEN JIN | European Patent Office | 2021

    Free access




    Autonomous vehicles’ intended cooperative motion planning for unprotected turning at intersections

    Zhou, Donghao / Ma, Zian / Zhang, Xiaohui et al. | Wiley | 2022

    Free access