The invention discloses an expressway automatic driving commercial vehicle trajectory prediction and decision-making method and system based on a complex network theory, and the method comprises the steps: coding a high-definition map and an intelligent agent context into node codes of a directed weighted complex network through employing a complex network encoder in a prediction model, and obtaining the reachable condition of each node; a target point predictor predicts target points of all agents according to historical trajectory information of the agents and local road features, and joint distribution of reference trajectories is obtained by combining the reachability of lane nodes and the criticality of the nodes of the agents. And the trajectory decoder is used for inputting a historical trajectory of the intelligent agent and kinematics or dynamics constraint decoding to generate a predicted trajectory and optimizing the predicted trajectory under the condition of the reference trajectory. The decision model inputs a navigation route provided by the upstream global path planning layer, judges whether there is a lane changing demand and determines the priority of a lane. And then a cost function is designed by combining the joint distribution probability of the reference trajectory, the complex network risk value and the lane priority, and an optimal trajectory is selected as a decision result.

    本发明公开了基于复杂网络理论的高速公路自动驾驶商用车轨迹预测与决策方法与系统,利用预测模型中复杂网络编码器将高清地图和智能体上下文编码为有向加权复杂网络的节点编码,得出各节点的可达情况。目标点预测器根据智能体历史轨迹信息和局部道路特征预测各智能体目标点,并结合车道节点可达性和智能体节点关键性获得参考轨迹的联合分布。轨迹解码器以参考轨迹为条件,输入智能体历史轨迹和运动学或动力学约束解码生成预测轨迹并优化。决策模型输入上游全局路径规划层提供的导航路线,判断是否有变道需求并确定车道的优先级。然后结合参考轨迹的联合分布概率、复杂网络风险值和车道优先级设计代价函数,挑选最优轨迹作为决策结果。


    Access

    Download


    Export, share and cite



    Title :

    Expressway automatic driving commercial vehicle trajectory prediction and decision-making method and system based on complex network theory


    Additional title:

    基于复杂网络理论的高速公路自动驾驶商用车轨迹预测与决策方法与系统


    Contributors:
    ZHAO GAOSHI (author) / CAI YINGFENG (author) / CHEN LONG (author) / TENG CHENGLONG (author) / WANG HAI (author) / SUN XIAOQIANG (author) / LIU QINGCHAO (author)

    Publication date :

    2023-05-02


    Type of media :

    Patent


    Type of material :

    Electronic Resource


    Language :

    Chinese


    Classification :

    IPC:    G06F ELECTRIC DIGITAL DATA PROCESSING , Elektrische digitale Datenverarbeitung / 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 / G06N COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS , Rechnersysteme, basierend auf spezifischen Rechenmodellen



    Expressway automatic driving safety decision-making system

    WANG YONGJIE / NIU YUCHEN / ZHU WENYING et al. | European Patent Office | 2024

    Free access

    Decision-making and planning method for network-connected automatic driving vehicle in expressway shunting area

    CHENG ZEYANG / ZHU JINYANG / ZHANG WEIHUA et al. | European Patent Office | 2024

    Free access


    Reinforcement learning automatic driving decision-making method and device based on trajectory prediction

    FU MINGJIAN / GUO FUQIANG / CHEN GUANGYONG et al. | European Patent Office | 2024

    Free access

    Commercial vehicle overtaking decision-making method, device and equipment on expressway and storage medium

    WANG YU / XU JIN / LIAO XINYU et al. | European Patent Office | 2024

    Free access