The invention discloses a communication unmanned aerial vehicle trajectory optimization control method based on deep intensity learning, and the method comprises the following specific steps: S1, enabling an unmanned aerial vehicle to take off from a base station to reach a geometric center point of a service range before the unmanned aerial vehicle starts to serve; s2, the unmanned aerial vehicle issues a radar signal to detect a ground mobile user, and the received radar echo is analyzed to obtain user coordinate information; and S3, inputting the coordinates of the user at several past moments as the initial state of reinforcement learning into the trained SAC network, selecting a corresponding action from an action space by an action network in the SAC network according to the input initial state, calculating to obtain the coordinate information of the user at the next time slot according to the selected action, and updating the state information. According to the method, the SAC architecture is adopted to train the network to realize the mobile tracking of the user, the pilot frequency overhead is reduced, the communication efficiency is improved, the deep expansion network is adopted to optimize the beam forming and the hovering position of the unmanned aerial vehicle, and the maximization of the communication throughput rate is realized with relatively low calculation complexity.

    本发明公开了基于深度强度学习的通信无人机轨迹优化控制方法,具体步骤如下:S1:无人机开始服务前,无人机从基站起飞到达服务范围的几何中心点;S2:无人机下发雷达信号探测地面移动用户,接收到雷达回波解析得到用户坐标信息;S3:将用户过去几个时刻的坐标作为强化学习的初始状态输入训练好的SAC网络,SAC网络中的动作网络根据输入的初始状态从动作空间中选取对应的动作,根据选择的动作计算得到下一时隙用户的坐标信息,并更新状态信息。本发明采用SAC架构来训练网络实现对用户的移动追踪,降低导频开销,提升通信效率,并且采用深度展开网络优化波束赋形和无人机悬停位置,以较低的计算复杂度实现通信吞吐率的最大化。


    Zugriff

    Download


    Exportieren, teilen und zitieren



    Titel :

    Communication unmanned aerial vehicle track optimization control method based on deep intensity learning


    Weitere Titelangaben:

    基于深度强度学习的通信无人机轨迹优化控制方法


    Beteiligte:
    YIN RUI (Autor:in) / PENG JINGWEI (Autor:in) / YUAN JIANTAO (Autor:in) / LIU SHENGLI (Autor:in) / HE XIN (Autor:in)

    Erscheinungsdatum :

    2024-04-30


    Medientyp :

    Patent


    Format :

    Elektronische Ressource


    Sprache :

    Chinesisch


    Klassifikation :

    IPC:    G08G Anlagen zur Steuerung, Regelung oder Überwachung des Verkehrs , TRAFFIC CONTROL SYSTEMS / H04B TRANSMISSION , Übertragung / H04W WIRELESS COMMUNICATION NETWORKS , Drahtlose Kommunikationsnetze



    Unmanned aerial vehicle track flight system

    ZHU NI / HU QIANG | Europäisches Patentamt | 2022

    Freier Zugriff

    Multi-unmanned aerial vehicle communication rate optimization method

    WANG JIN / WANG YUJING / WEI XIANGYUAN et al. | Europäisches Patentamt | 2024

    Freier Zugriff

    Unmanned aerial vehicle track and power optimization method with optimal relay communication energy efficiency

    GUO LILI / ZHANG SHIBING / JI XIAODONG et al. | Europäisches Patentamt | 2023

    Freier Zugriff


    UNMANNED AERIAL VEHICLE, UNMANNED AERIAL VEHICLE CONTROL SYSTEM, AND UNMANNED AERIAL VEHICLE CONTROL METHOD

    ISHIKAWA NAOHIRO / TESHIMA TAKESHI | Europäisches Patentamt | 2024

    Freier Zugriff