The trajectory prediction model of traditional weapon control algorithm cannot effectively predict the complex trajectory of drones. Besides, the single UAV is usually considered in current research on complex trajec-tory prediction, which has huge amount of calculation. To predict the trajectory of UAV drone swarm quickly and accurately, a method of trajectory prediction for UAVs is proposed. After obtaining the trajectory of drone swarm,the clustering is conducted firstly based on DBSCAN(density-based spatial clustering of applications with noise)method to judge the category of each UAV in drone swarm. Then the trajectory complexity of UAV is judged based on fractal algorithm. Finally, Kalman filter is used for simple trajectory prediction, and the long short-term memory (LSTM) network method is used for complex trajectory prediction. The results show that the prediction error of the proposed trajectory prediction method for UAVs is less than that of Kalman filter, and the prediction time is less than that of LSTM network method, which can predict the trajectory of different swarm UAVs in drone, and provide scientific basis for anti-UAV swarm calculation.


    Access

    Download


    Export, share and cite



    Title :

    Research on trajectory prediction of UAV drone swarm


    Contributors:
    ZHANG Genyuan (author) / LIN Zhiwei (author) / TANG Xu (author) / LEI Kaiwen (author)


    Publication date :

    2023




    Type of media :

    Article (Journal)


    Type of material :

    Electronic Resource


    Language :

    Unknown





    FireFly - Autonomous Drone Swarm

    Nemirovsky, Meir / Yavnai, Arik / Alfandari, Liran et al. | British Library Conference Proceedings | 2019


    CABLE-CONNECTED DRONE SWARM

    NOHMI MOTOHIKO / SEKINO YUMIKO | European Patent Office | 2018

    Free access

    FLYING DRONE TRAJECTORY SYNCHRONIZATION

    VERMEULEN KOERT / BUYS KOEN | European Patent Office | 2024

    Free access

    Artificial intelligence swarm drone control system for drone defense

    LEE KI OH | European Patent Office | 2025

    Free access