The invention discloses a multi-traffic-participant trajectory and speed prediction method based on vehicle-road cooperation. The method comprises the following steps: S1, carrying out data acquisition on a complex traffic scene containing multiple types of traffic participants from a vehicle end and a road end; s2, modeling a complex traffic scene through a space-time diagram method, quantifying the interaction strength among different traffic participants in the scene through a kernel function according to the relative displacement and relative speed information among the traffic participants, and constructing an adjacent matrix for measuring the interaction relationship among the traffic participants based on the quantification result, the time-space diagram scene modeling is completed; s3, on the basis of the space-time diagram, a trajectory and speed prediction model is constructed through a diagram convolutional neural network and a time convolutional neural network, and trajectory and speed prediction of traffic participants is carried out; and S4, completing optimal state estimation of multi-category traffic participant trajectory and speed prediction based on the vehicle-road cooperation V2X technology. The method can be competent for track and speed prediction tasks of multiple traffic participants at the same time, and adaptability and prediction accuracy are improved.

    一种车路协同的多交通参与者轨迹与速度预测方法,包括如下步骤:S1:从车端和路端对含有多类别交通参与者的复杂交通场景进行数据采集;S2:通过时空图方法进行复杂交通场景的建模,其中,针对交通参与者之间的相对位移和相对速度信息,通过核函数来量化场景中不同交通参与者之间的交互强度,并基于量化结果构建出度量交通参与者间的交互关系的邻接矩阵,来完成时空图场景建模;S3:基于所述时空图,通过图卷积神经网络和时间卷积神经网络构建轨迹与速度预测模型,进行交通参与者的轨迹与速度预测;S4:完成基于车路协同V2X技术的多类别交通参与者轨迹与速度预测的最优状态估计。本方法同时可以胜任多交通参与者的轨迹与速度预测任务,提高了适应性和预测准确性。


    Zugriff

    Download


    Exportieren, teilen und zitieren



    Titel :

    Trajectory and speed prediction method for multiple traffic participants based on vehicle-road cooperation


    Weitere Titelangaben:

    一种车路协同的多交通参与者轨迹与速度预测方法


    Beteiligte:
    NIU LING (Autor:in) / CHEN BOKUI (Autor:in)

    Erscheinungsdatum :

    26.07.2024


    Medientyp :

    Patent


    Format :

    Elektronische Ressource


    Sprache :

    Chinesisch


    Klassifikation :

    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 collision early warning method based on vehicle-road cooperation trajectory prediction

    SONG LIANG / HU XING / NI WEI et al. | Europäisches Patentamt | 2023

    Freier Zugriff

    Road occupancy prediction of traffic participants

    Althoff, Matthias / Hess, Daniel / Gambert, Florian | IEEE | 2013


    Multi-time scale traffic flow speed prediction method based on vehicle-road cloud cooperation

    XIE HUI / LI FANGXUAN / SONG KANG | Europäisches Patentamt | 2024

    Freier Zugriff

    METHOD FOR LONG-TERM TRAJECTORY PREDICTION OF TRAFFIC PARTICIPANTS

    VELKEY GEZA / KIS KORNEL ISTVAN / KOROSI-SZABO PETER | Europäisches Patentamt | 2021

    Freier Zugriff