In this research, a procedure based on GRU method has been proposed to predict the short-term trajectory of drones. First, historical trajectory data of various types of drones have been collected. Then, the GRU neural network has been constructed for data training. Several benchmark methods are selected to testify the prediction performance of the present method. The results indicated that the proposed approach achieved generally satisfactory performance over most of the scenarios of the testing datasets. Moreover, both the one-step and multi-step trajectory predictions are conducted. Comparison of MAEs for different speed sections are also provided. The results can provide technical support for UAV safety management in low altitudes.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Short-term Trajectory Prediction for Small Scale Drones at Low-attitude Airspace


    Beteiligte:
    Zhu, Renwei (Autor:in) / Yang, Zhao (Autor:in) / Chen, Jun (Autor:in) / Li, Na (Autor:in) / Zhang, Zhijie (Autor:in) / Song, Yilu (Autor:in)


    Erscheinungsdatum :

    12.10.2022


    Format / Umfang :

    1639046 byte




    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch




    An Airport Airspace Flow Control Method for Drones

    Zeng, Guoqi / Cui, Kai / Quan, Quan et al. | IEEE | 2019



    LAYER APPROACH TO MANAGING AIRSPACE OF LARGE GROUPS OF DRONES

    AUDRONIS TYRIS MONTE | Europäisches Patentamt | 2024

    Freier Zugriff

    Short-term trajectory prediction methods

    Chatterji, Gano | AIAA | 1999