Interacting Multiple Model (IMM) is a popular algorithm in trajectory prediction research field, and it can predict the Three-Dimensional (3D) position information about longitude, latitude and altitude, but it is difficult to accurately predict the time. In order to realize the prediction of time and improve the prediction accuracy of longitude, latitude and altitude, neural network is used to model the implicit relationship from historical data, and combining the Long and Short-Term Memory neural network (LSTM) with IMM algorithm, a short-term 4D trajectory prediction method based on LSTM-IMM is proposed. IMM algorithm is used to predict 3D trajectory information about the longitude, latitude and altitude while the LSTM neural network is used to achieve the prediction of time and compensate for the longitude, latitude, and altitude predicted by the IMM algorithm to improve the prediction accuracy. In terms of time, the time interval between adjacent trajectory points is used as a feature for prediction; in terms of longitude, latitude and altitude, LSTM neural network is used to predict the error values between the trajectory predicted by IMM algorithm and the actual trajectory, and these error values are used to compensate the 3D position information predicted by IMM algorithm. The performance of the algorithm is verified by the actual flight data, the results show that this method can well predict the time of trajectory points, significantly improve the prediction accuracy of all flight stages, and has faster response speed in case of trajectory mutation.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Short-Term 4D Trajectory Prediction Method Based on LSTM-IMM


    Beteiligte:
    Liu, Baichao (Autor:in) / Shi, Qingyan (Autor:in) / Han, Ping (Autor:in)


    Erscheinungsdatum :

    18.09.2022


    Format / Umfang :

    2014231 byte





    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Short-Term Target Maneuvering Trajectory Prediction Using DTW–CNN–LSTM

    Haifeng Guo / Jinyi Yang / Xianyong Jing et al. | DOAJ | 2025

    Freier Zugriff

    STG-LSTM: Spatial-temporal graph-based long short-term memory for vehicle trajectory prediction

    Daniela Daniel Ndunguru / Fan Xing / Chrispus Zacharia Oroni et al. | DOAJ | 2025

    Freier Zugriff

    Pedstrian Trajectory Prediction Based on LSTM

    Li, Shaosong / Jiang, Junchen / Zhou, Qingbin et al. | IEEE | 2023


    Transform and LSTM-based vehicle trajectory prediction method

    CHENG DENGYANG / GU XIANG / QIAN CONG et al. | Europäisches Patentamt | 2023

    Freier Zugriff

    Short-Term Traffic Flow Prediction: Using LSTM

    Poonia, Pregya / Jain, V. K. | IEEE | 2020