The invention discloses a vehicle track prediction method based on a graph convolutional neural network in a network connection environment, and the method comprises the steps: enabling a main vehicle to obtain the historical motion state data of a vehicle in a set scene range through the network connection environment, carrying out the preprocessing, and converting the preprocessed historical motion state data into a space graph based on a space interaction coefficient; converting the preprocessed historical motion state data into a time graph based on a time interaction coefficient, extracting space interaction features in a space graph and time interaction features in the time graph through a graph convolutional neural network, and fusing the space interaction features and the time interaction features to obtain space-time interaction features of vehicles in a set scene range; and finally, motion tracks of all vehicles in the set scene in a future period of time are decoded and output based on the convolutional neural network. According to the method, the space interaction coefficient and the time interaction coefficient are provided, so that the problem of insufficient time interaction modeling in the existing research is solved, and the prediction precision of vehicle trajectory prediction is improved.

    本发明公开了一种网联环境下基于图卷积神经网络的车辆轨迹预测方法,主车首先通过网联环境获取设定场景范围内车辆的历史运动状态数据并进行预处理,然后基于空间交互系数将预处理后的历史运动状态数据转换为空间图,基于时间交互系数将预处理后的历史运动状态数据转换为时间图,接下来通过图卷积神经网络提取空间图中的空间交互特征和时间图中的时间交互特征,融合两者获得设定场景范围内车辆的时空交互特征,最后基于卷积神经网络解码输出设定场景内所有车辆在未来一段时间的运动轨迹。本发明通过提出空间交互系数和时间交互系数,解决了现有研究中存在的时间交互建模不充分的问题,提高了车辆轨迹预测的预测精度。


    Zugriff

    Download


    Exportieren, teilen und zitieren



    Titel :

    Vehicle track prediction method based on graph convolutional neural network in network connection environment


    Weitere Titelangaben:

    一种网联环境下基于图卷积神经网络的车辆轨迹预测方法


    Beteiligte:
    GUO HONGWEI (Autor:in) / SON DONG-SEON (Autor:in) / HAN KEXIAN (Autor:in) / WANG WUHONG (Autor:in) / JIANG XIAOBEI (Autor:in) / YANG JINGCHAO (Autor:in) / GAO QIHANG (Autor:in)

    Erscheinungsdatum :

    2023-10-24


    Medientyp :

    Patent


    Format :

    Elektronische Ressource


    Sprache :

    Chinesisch


    Klassifikation :

    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



    Traffic jam prediction method based on tense graph convolutional neural network

    ZHANG HAO / ZHANG GE / HUA QIFAN et al. | Europäisches Patentamt | 2023

    Freier Zugriff


    Ship traffic flow prediction method based on improved graph convolutional neural network

    LIU WEN / ZHAN YANG / LIANG MAOHAN et al. | Europäisches Patentamt | 2022

    Freier Zugriff

    Multi-scale traffic flow prediction method based on graph convolutional neural network

    ZHANG MEIYUE / WANG SENZHANG / MIAO HAO et al. | Europäisches Patentamt | 2021

    Freier Zugriff

    Short-term traffic flow prediction method based on integrated graph convolutional neural network

    LIU LUYANG / LYU SHUAIQI / BAO XU | Europäisches Patentamt | 2024

    Freier Zugriff