有人—无人机协同空战机动决策研究  

Research on MAV-UAV cooperative air combat maneuver decision

作　　者：刘波 魏潇龙 屈虹[2] 甘旭升[2] 刘飞 LIU Bo;WEI Xiaolong;QU Hong;GAN Xusheng;LIU Fei(Department of Management Technology,Xijing University,Xi’an 710123,China;Air Traffic Control and Navigation School,Air Force Engineering University,Xi’an 710051,China)

机构地区：[1]西京学院管理技术系,西安710123 [2]空军工程大学空管领航学院,西安710051

出　　处：《航空工程进展》2023年第6期63-72,共10页Advances in Aeronautical Science and Engineering

摘　　要：目前,有关无人机空战的研究主要考虑无人机的完全自主决策机动算法,关于有人机有限监督决策下的空战机动决策的研究鲜有报道,更缺乏对有人—无人机协同作战的研究。为实现无人机协同空战过程中的自主机动,设计一种基于路径规划技术的有人—无人机协同空战机动决策模型。首先,引入动态栅格环境,自适应调整栅格规模和分辨率,以弥补静态栅格环境规划空间越大规划效率越低的缺陷;然后,将A star算法规划路径作为参考路径,提出ACO-A star混合路径规划算法,以提升ACO算法的寻优效能;最后,基于均值聚类算法设计有人—无人机协同空战机动决策算法。进行空战对抗仿真模拟,结果表明:所提出的算法具有更好的决策正确性,可有效提升空战胜率。At present,the research on UAV air combat mainly considers the fully autonomous decision-making maneuver algorithm of UAV,and the research on the air combat maneuver decision-making under the limited supervision decision of UAV is rare,let alone the research on manned aerial vehicle and unmanned aerial vehicle(MAVUAV)cooperative combat.In order to realize the autonomous maneuver of UAV in the process of cooperative air combat,a maneuver decision model for MAV-UAV cooperative air combat is designed on the basis of path planning technology.First,the dynamic grid environment is introduced to adaptively adjust the grid scale and resolution,so as to make up for the defect that,the larger the static grid environment planning space is,the lower the planning efficiency will be.Then,by taking the path planned using A star algorithm as the reference path,the ACO-A star hybrid path planning algorithm is proposed to improve the optimization efficiency of ACO algorithm.Finally,based on the mean clustering algorithm,a maneuver decision algorithm for MAV-UAV cooperative air combat is designed.The air combat simulation result shows that the proposed model has better decision correctness and can effectively improve the air combat victory rate.

关 键 词：无人机 空战对抗 协同决策 蚁群算法 A star算法 

分 类 号：V271.4[航空宇航科学与技术—飞行器设计] E926.3[军事—军事装备学]