The invention discloses a surrounding vehicle track prediction method and device, a medium and a product, and relates to the technical field of automatic driving, and the method comprises the steps: employing a Monte Carlo simulation method and a quintic polynomial method to generate a posterior track cluster for each path reference line in a historical track data set; determining a posterior trajectory distribution parameter of each path reference line according to the posterior trajectory cluster, and taking the posterior trajectory distribution parameter as label data; training a neural network by taking the time sequence of the starting point state in each path reference line as input and the posterior trajectory distribution parameter as output to obtain a trajectory distribution parameter prediction model; inputting the time sequence of the starting point state of the target vehicle into a trajectory distribution parameter prediction model to obtain a predicted trajectory distribution parameter of an adjacent vehicle of the target vehicle; and determining predicted trajectories of vehicles around the target vehicle according to the predicted trajectory distribution parameters. According to the invention, the accuracy of the predicted trajectory of the surrounding vehicle is improved, and the driving safety of automatic driving is further improved.

    本发明公开一种周车轨迹预测方法、设备、介质及产品,涉及自动驾驶技术领域,方法包括:对历史轨迹数据集中每条路径参考线,采用蒙特卡洛模拟法和五次多项式方法生成后验轨迹簇;根据后验轨迹簇确定每条路径参考线的后验轨迹分布参数,并将后验轨迹分布参数作为标签数据;以每条路径参考线中起点状态的时间序列为输入,后验轨迹分布参数为输出训练神经网络,得到轨迹分布参数预测模型;将目标车辆起点状态的时间序列输入轨迹分布参数预测模型,得到目标车辆的邻车的预测轨迹分布参数;根据预测轨迹分布参数确定目标车辆的周围车辆的预测轨迹。本发明提高了周围车辆的预测轨迹的准确性,进而提高了自动驾驶的行车的安全性。


    Access

    Download


    Export, share and cite



    Title :

    Peripheral vehicle track prediction method and device, medium and product


    Additional title:

    一种周车轨迹预测方法、设备、介质及产品


    Contributors:
    ZHANG LEI (author) / WANG ZHENPO (author) / YUAN HENG (author)

    Publication date :

    2024-06-25


    Type of media :

    Patent


    Type of material :

    Electronic Resource


    Language :

    Chinese


    Classification :

    IPC:    G06N COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS , Rechnersysteme, basierend auf spezifischen Rechenmodellen / G08G Anlagen zur Steuerung, Regelung oder Überwachung des Verkehrs , TRAFFIC CONTROL SYSTEMS



    Vehicle driving track prediction method, device, equipment, medium and product

    ZHANG ZHONGXU / LIU YUFENG | European Patent Office | 2024

    Free access


    Motion track prediction method, device, equipment, medium and product

    LIU HAICHAO / CHEN KAI / MA JUN | European Patent Office | 2024

    Free access

    Vehicle track prediction method and device, vehicle and storage medium

    RAN FUWEN | European Patent Office | 2023

    Free access

    Vehicle track prediction method and device, vehicle and storage medium

    ZHANG YANGHONG / LIU QIAN | European Patent Office | 2024

    Free access