The invention relates to an intelligent vehicle highway ramp convergence decision-making method based on reinforcement learning, relates to the field of intelligent vehicles, and is used for improving the convergence success rate of the intelligent vehicles and reducing traffic accidents. The method comprises the following steps: setting an intersection of a highway ramp and a main road as a confluence point, and setting the ramp and a main road positioned at a position S1 m behind the confluence point and a position S2 m in front of the confluence point as control areas; in the control area, the intelligent vehicle is projected to a target lane of the main road, and the distance between the projected intelligent vehicle and the confluence point is equal to the distance between the intelligent vehicle on the ramp and the confluence point; vehicles in front of and behind the projection intelligent vehicle are determined, and the speeds and positions of the vehicles are obtained as environmental vehicle information; obtaining the distance between the intelligent vehicle and the confluence point and the speed and acceleration of the intelligent vehicle as intelligent vehicle information; and according to the intelligent vehicle information and the environmental vehicle information, acceleration and front wheel rotation angle adjustment is carried out by adopting a reinforcement learning DDPG model, and successful convergence is gradually realized.

    本发明涉及一种基于强化学习的智能车辆高速公路匝道汇入决策方法,涉及智能车辆领域,用于提高智能车辆汇入成功率,减少交通事故。该方法将高速公路匝道与主路的交叉点设置为合流点,将匝道以及位于合流点后S1米处和合流点前S2米处的主干道设置为控制区域;在控制区域内,将智能车辆投影到主路的目标车道上,投影智能车辆到合流点距离和匝道上智能车辆到合流点距离相等;确定投影智能车辆前面车辆和后面车辆,获取它们的速度和位置作为环境车辆信息;获取智能车辆与合流点距离、智能车辆速度和加速度作为智能车辆信息;根据智能车辆信息、环境车辆信息,采用强化学习DDPG模型进行加速度和前轮转角调整,逐步实现成功汇入。


    Zugriff

    Download


    Exportieren, teilen und zitieren



    Titel :

    Intelligent vehicle highway ramp convergence decision-making method based on reinforcement learning


    Weitere Titelangaben:

    基于强化学习的智能车辆高速公路匝道汇入决策方法


    Beteiligte:
    HAN GUANGDE (Autor:in) / ZHU WENTAO (Autor:in) / XIE XIANYI (Autor:in) / LIU GUOFENG (Autor:in) / JIN LISHENG (Autor:in) / GUO BAICANG (Autor:in)

    Erscheinungsdatum :

    2023-10-13


    Medientyp :

    Patent


    Format :

    Elektronische Ressource


    Sprache :

    Chinesisch


    Klassifikation :

    IPC:    G08G Anlagen zur Steuerung, Regelung oder Überwachung des Verkehrs , TRAFFIC CONTROL SYSTEMS



    Reinforcement Learning-Based On-Ramp Merging Decision-Making for Autonomous Vehicles

    Ma, Ning / Zhang, Ying / Cai, Wangze et al. | IEEE | 2023


    A decision making approach at an air highway ramp

    Li-li, Wang / Yue, Wu / Wan-le, Wang | IEEE | 2015


    HIGHWAY TRAFFIC MODELING AND DECISION MAKING FOR AUTONOMOUS VEHICLE USING REINFORCEMENT LEARNING

    You, Changxi / Lu, Jianbo / Filev, Dimitar et al. | British Library Conference Proceedings | 2018



    Learning Highway Ramp Merging Via Reinforcement Learning with Temporally-Extended Actions

    Triest, Samuel / Villaflor, Adam / Dolan, John M. | IEEE | 2020