The invention discloses a trajectory prediction method based on a digital twin platform. The method comprises the steps of collecting information such as the position, the speed, the driving state and the surrounding environment state of a vehicle in real time; after initial processing is carried out on the information, the vehicle transmits the processed information to a track prediction platform located at the cloud end by means of a built-in communication module of the vehicle; secondly, extracting data features of vehicles and roadside units through a multi-channel mechanism, and sending the extracted features to a Transform module to predict a future trajectory; and finally, the platform feeds back the prediction result to the vehicle, so that a driver can timely adjust the current track to avoid traffic accidents. Compared with other schemes, the method has the advantages that ADE and FDE indexes are the lowest, the model efficiency is the best, and in addition, the average reasoning delay is 11.83 ms within the trajectory prediction time step length of 5 seconds.

    本发明公开了一种基于数字孪生平台的轨迹预测方法,实时收集车辆的位置、速度、行驶状态、周围环境状态等信息;在对信息进行初始处理后,车辆依靠自身内置的通信模块将处理后的信息传输到位于云端的轨迹预测平台;然后,通过多通道机制来提取车辆、路边单元的数据特征,并将提取的特征发送给Transformer模块来预测未来的轨迹;最后,平台将预测结果反馈给车辆,以便驾驶员及时调整当前轨迹,避免交通事故。与其他方案进行对比,本发明的ADE与FDE指标最低,模型效率最好,此外,在5秒的轨迹预测时间步长内,平均推理延迟为11.83ms。


    Access

    Download


    Export, share and cite



    Title :

    Track prediction method based on digital twin platform


    Additional title:

    一种基于数字孪生平台的轨迹预测方法


    Contributors:
    XUN YIJIE (author) / ZHANG SIJIA (author) / LEI JIAHAO (author) / XUN ZHIJIE (author) / MAO BOMIN (author) / GUO HONGZHI (author)

    Publication date :

    2025-01-24


    Type of media :

    Patent


    Type of material :

    Electronic Resource


    Language :

    Chinese


    Classification :

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



    Vehicle driving track prediction method under highway traffic control based on digital twin tracking simulation

    LIU XINJIAN / LIU SHUANG / LI HENGKUN et al. | European Patent Office | 2025

    Free access

    Digital Twin of Vehicle-Track System for Integrated Track Condition Monitoring

    Shen, Chen / Dollevoet, Rolf / Li, Zili | Springer Verlag | 2024


    Twin Track Models

    Schramm, Dieter / Hiller, Manfred / Bardini, Roberto | Springer Verlag | 2014


    Twin Track Models

    Schramm, Dieter / Hiller, Manfred / Bardini, Roberto | Springer Verlag | 2017