The invention is suitable for the technical field of vehicle trajectory prediction, provides a vehicle trajectory deep learning prediction method considering physical constraints, and establishes a constant yaw velocity and variable acceleration vehicle kinematics model by considering vehicle kinematics characteristics of a vehicle in a lane changing scene on the basis of a classical constant steering velocity and acceleration model. Meanwhile, a long-short-term memory network is selected as a basic data model. The method comprises the following steps: embedding a constant yaw velocity and variable acceleration automobile kinematic model as a physical constraint into a long-short-term memory network, and building the physical constraint long-short-term memory network; simulation results show that the trajectory prediction method is suitable for long-term prediction of vehicle trajectories, and compared with a traditional trajectory prediction method based on deep learning, the interpretability of the prediction process and the reliability of prediction results are enhanced on the premise that the prediction accuracy is guaranteed.

    本发明适用于车辆的轨迹预测技术领域,提供了一种考虑物理约束的车辆轨迹深度学习预测方法,在经典恒转向速度和加速度模型的基础上,考虑换道场景下的车辆的汽车运动学特点,建立了恒横摆角速度、变加速度汽车运动学模型。同时,选取长短时记忆网络作为基础的数据模型。将恒横摆角速度、变加速度汽车运动学模型作为物理约束嵌入长短时记忆网络中,搭建物理约束长短时记忆网络。仿真结果表明,本发明提出的轨迹预测方法适用于车辆轨迹的长期预测,相较于传统基于深度学习的轨迹预测方法,在保证预测准确性的前提下,增强了预测过程的可解释性和预测结果的可靠性。


    Access

    Download


    Export, share and cite



    Title :

    Vehicle track deep learning prediction method considering physical constraint


    Additional title:

    一种考虑物理约束的车辆轨迹深度学习预测方法


    Contributors:
    XU FANG (author) / HAN SHUAI (author) / GUO ZHONGYI (author) / QU TING (author) / CHEN HONG (author)

    Publication date :

    2023-07-28


    Type of media :

    Patent


    Type of material :

    Electronic Resource


    Language :

    Chinese


    Classification :

    IPC:    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



    Hybrid electric vehicle prediction energy management method considering SOC track

    ZENG XIAOHUA / WANG YUNYE / SONG DAFENG et al. | European Patent Office | 2023

    Free access

    Vehicle track prediction method and system considering multiple target points

    REN HONGBIN / ZHAO SHIYUAN / ZHOU GAOLI et al. | European Patent Office | 2023

    Free access

    Vehicle track detection method based on deep learning

    ZHANG ZHONG / SUN GUANLONG / HUANG JUNJIE | European Patent Office | 2022

    Free access

    Vehicle track reconstruction method considering overtaking behavior

    CAO QI / DENG YUE / REN GANG et al. | European Patent Office | 2023

    Free access