The invention provides a vehicle lane changing trajectory prediction method based on a random forest and an improved Informer model, and relates to the technical field of traffic vehicle trajectory prediction, and the method comprises the following steps: collecting vehicle driving information based on a vehicle-mounted sensor and a disclosed natural driving data set; preprocessing the vehicle driving information to obtain preprocessed vehicle driving information; constructing a data set for the preprocessed vehicle driving information by adopting a random forest algorithm; and predicting a vehicle lane changing track through the training model according to the characteristics of the vehicle data and the vehicle lane changing track prediction demand. According to the method, the richness of training data is increased, the generalization ability of the model is improved, the influence of other attributes on the classification effect is avoided by adopting an attribute random selection technology, the robustness of the model is improved, the risk of over-fitting is reduced, and the time and resource consumption of model operation are reduced.

    本发明提供基于随机森林和改进的Informer模型的车辆换道轨迹预测方法,涉及交通车辆轨迹预测技术领域,包括如下的步骤:基于车载传感器和公开的自然驾驶数据集,采集车辆行车信息;对车辆行车信息进行预处理得到预处理车辆行车信息;对预处理车辆行车信息采用随机森林算法构建数据集;根据车辆数据的特点以及车辆换道轨迹预测需求通过训练模型预测车辆换道轨迹。本发明增加训练数据的丰富性,提高模型的泛化能力,采用属性随机选择技术避免了其他属性对于分类效果的影响,提高模型的鲁棒性,降低了发生过拟合的风险,降低模型运行的时间和资源消耗。


    Zugriff

    Download


    Exportieren, teilen und zitieren



    Titel :

    Vehicle lane changing trajectory prediction method based on random forest and improved Informer model


    Weitere Titelangaben:

    基于随机森林和改进的Informer模型的车辆换道轨迹预测方法


    Beteiligte:
    AN YISHENG (Autor:in) / YANG HAOQI (Autor:in) / LI TING (Autor:in) / LI YING (Autor:in) / XIAO YUKUN (Autor:in) / WEI YAXIN (Autor:in)

    Erscheinungsdatum :

    2024-04-02


    Medientyp :

    Patent


    Format :

    Elektronische Ressource


    Sprache :

    Chinesisch


    Klassifikation :

    IPC:    G06F ELECTRIC DIGITAL DATA PROCESSING , Elektrische digitale Datenverarbeitung / 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



    Lane changing trajectory planning method for autonomous vehicle

    WANG JIAN / HAN HAIYANG / PEI ZHONGHUI | Europäisches Patentamt | 2023

    Freier Zugriff

    Vehicle lane changing trajectory planning method based on cubic B-spline

    SHEN LEI / ZHA YUNFEI / LI ZHE et al. | Europäisches Patentamt | 2023

    Freier Zugriff

    Networked vehicle lane changing trajectory planning method based on accessibility analysis

    QU DAYI / LI AODI / WANG KEDONG et al. | Europäisches Patentamt | 2024

    Freier Zugriff

    Flight plan track prediction method based on informer + arima model

    CHEN YUMING / FENG JUN / DU JUNWEI et al. | Europäisches Patentamt | 2023

    Freier Zugriff

    Intelligent vehicle lane changing decision-making method and system for LSTM trajectory prediction

    YANG ZHENGCAI / SUN TIANJUN / GAO ZHENHAI et al. | Europäisches Patentamt | 2024

    Freier Zugriff