基于改进多维粒子群的多无人机任务分配方法  

An improved multi-dimensional particle swarm-based approach to multi-UAV mission assignment

作　　者：彭鹏菲[1] 龚雪 姜俊 郑雅莲 PENG Pengfei;GONG Xue;JIANG Jun;ZHENG Yalian(School of Electronic Engineering,Naval University of Engineering,Wuhan 430033,China;Department of Operational Research and Planning,Naval University of Engineering,Wuhan 430033,China;State Key Laboratory of Water Resources and Hydropower Engineering Science,Wuhan University,Wuhan 430072,China)

机构地区：[1]海军工程大学电子工程学院,武汉430033 [2]海军工程大学作战运筹与规划系,武汉430033 [3]武汉大学水资源与水电工程科学国家重点实验室,武汉430072

出　　处：《兵器装备工程学报》2023年第7期227-236,共10页Journal of Ordnance Equipment Engineering

基　　金：国家重点研发计划项目(2017YFC1405205);海军工程大学科研发展基金自主立项项目(425317S107)。

摘　　要：针对复杂战场环境下的多无人机任务规划解空间维度不确定、任务需求随时间变化等问题,提出了一种基于改进多维粒子群算法的多无人机任务分配方法。该方法构建了适应度函数集,应用多个适应度函数来限制种群趋向,同时采用基于时变目标价值的映射变量,建立目标价值随时间变化的多无人机目标决策模型;而后引入整数编码机制,构建面向任务序列的多维粒子,利用改进的自适应多维粒子群算法,得到最优维度下多无人机的任务分配优化方案。仿真实验结果表明:基于改进多维粒子群算法的多无人机任务规划方法可在最优解空间下,获得更好的任务动态分配效果,收敛速度更快,具有良好的推广应用前景。This paper proposes a multi-UAV mission assignment method based on an improved multi-dimensional particle swarm algorithm to address the problems of uncertainty in the spatial dimension of multi-UAV mission planning solutions and the change of mission requirements with time in complex battlefield environments.The method constructs a set of fitness functions and applies multiple fitness functions to restrict the population tendency,while using mapping variables based on time-varying target values to establish a multi-UAV target decision model with time-varying target values.Then,it introduces an integer coding mechanism to construct multi-dimensional particles oriented to the task sequence,and uses the improved adaptive multi-dimensional particle swarm algorithm to obtain multi-UAV mission planning optimization scheme under the optimal dimension.The simulation results show that the multi-UAV mission planning method based on the improved multi-dimensional particle swarm algorithm can obtain a better dynamic mission assignment effect in the optimal solution space with a faster convergence speed,which has good prospects for application.

关 键 词：空间维度 多维粒子群算法 整数编码 多无人机任务分配 适应度函数集 

分 类 号：V279[航空宇航科学与技术—飞行器设计] TP18[自动化与计算机技术—控制理论与控制工程]