The invention discloses a flight path planning method based on multi-agent reinforcement learning in an opposite support scene. When the method is applied to real-time simulation deduction, the method comprises the following steps: initializing an opposite support simulation engine and instantiating an entity; acquiring current situation information of all entities and environments; performing situation conversion on the obtained situation information; based on the situation information converted to the relative coordinate system, a pre-trained reinforcement learning model decides the maneuvering direction of each airplane of the own side; according to the maneuvering direction of each airplane of the own side, performing action conversion by using a maneuvering model to generate position information of each airplane of the own side at the next moment; according to the position information of each airplane of the own side at the next moment, the situation information of all entities and environments at the next moment is obtained; and repeatedly executing until the opposite support task is completed, and outputting a complete route of each airplane of the own side containing the position information at each moment. According to the invention, the flight path planning efficiency and the environmental adaptability in an opposite support scene are improved.

    本发明公开了一种对面支援场景下基于多智能体强化学习的航迹规划方法,应用在实时仿真推演时包括:对面支援仿真引擎初始化并实例化实体;获取所有实体与环境当前的态势信息;将得到的态势信息进行态势转换;基于转换至相对坐标系下的态势信息,由预训练的强化学习模型决策出己方每架飞机的机动方向;根据己方每架飞机的机动方向,通过利用机动模型进行动作转换生成己方每架飞机下一时刻的位置信息;根据己方每架飞机下一时刻的位置信息,得到所有实体与环境下一时刻的态势信息;重复执行直至完成对面支援任务,输出己方每架飞机包含各个时刻的位置信息的完整航线。本发明提高了对面支援场景下的航迹规划的效率和环境适应性。


    Access

    Download


    Export, share and cite



    Title :

    Flight path planning method based on multi-agent reinforcement learning in opposite support scene


    Additional title:

    对面支援场景下基于多智能体强化学习的航迹规划方法


    Contributors:
    QU CHONGXIAO (author) / JIN HUIQUAN (author) / JIAO WENMING (author) / ZHU LIAOYUAN (author) / XIA SHAOJIE (author) / FAN CHANGJUN (author)

    Publication date :

    2022-12-09


    Type of media :

    Patent


    Type of material :

    Electronic Resource


    Language :

    Chinese


    Classification :

    IPC:    G08G Anlagen zur Steuerung, Regelung oder Überwachung des Verkehrs , TRAFFIC CONTROL SYSTEMS / G06N COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS , Rechnersysteme, basierend auf spezifischen Rechenmodellen



    Exploration of Multi-Agent Reinforcement Learning for ISR Flight Path Planning

    Xie, Lynphone Mark / Conway, Emily / Cheng, Huaining et al. | IEEE | 2024


    Multi-UAV Path Planning and Following Based on Multi-Agent Reinforcement Learning

    Xiaoru Zhao / Rennong Yang / Liangsheng Zhong et al. | DOAJ | 2024

    Free access

    Dynamic Scene Path Planning of UAVs Based on Deep Reinforcement Learning

    Jin Tang / Yangang Liang / Kebo Li | DOAJ | 2024

    Free access

    Deep Reinforcement Learning for Image-Based Multi-Agent Coverage Path Planning

    Xu, Meng / She, Yechao / Jin, Yang et al. | IEEE | 2023


    Reinforcement learning parking path planning method and system for non-structural scene

    CHEN SHITAO / QIU ZHUO / SHI JIAMIN et al. | European Patent Office | 2023

    Free access