面向多无人机任务分配的二维编码粒子群算法  

Two-dimensional Code PSO Algorithm for Multi-UCAV Task Assignment Problem

作　　者：陈侠[1] 胡永新[1] 徐光延[1] 

机构地区：[1]沈阳航空航天大学自动化学院,沈阳110136

出　　处：《系统仿真学报》2013年第12期3045-3049,3056,共6页Journal of System Simulation

基　　金：航空科学基金资助项目(2008ZG54023);辽宁省自然科学基金资助项目(20092053)

摘　　要：任务分配问题一直是多UCAV任务规划系统的重要研究课题。粒子群优化算法具有结构简单和寻优能力较强等特点,它是目前解决无人机任务规划问题比较常用的算法。在应用该算法来解决此问题时,采用一维的向量形式的编码方式的粒子群算法较为常见,采用二维的矩阵形式的编码方式较为少见,而后者能更直接且更容易符合问题的要求,采用了二维的编码方式,将粒子表示为矩阵形式,并根据粒子群算法思想,设计了对应的矩阵元素操作作为其信息交流方式,进而提出了一种新的离散粒子群优化算法。并通过仿真验证所提出的算法应用于无人机的任务规划问题是可行的和有效的。Task allocation problem has always been an important research topic of the multi-UCAV mission planning system. Because the particle swarm optimization algorithm is characteristic of simple structure and strong optimization capability; it is a commonly used algorithm for solving the problem of UCAV task assignment. When using the algorithm to solve the problem, the encoding of one-dimensional vector structure is common, and the encoding of two-dimensional matrix form is rare, but the latter is more directly and more easily to meet the requirements of the problem. Using the two dimensional code, each particle was expressed as a matrix form. According to the standard particle swarm optimization algorithm, the corresponding matrix operation was designed as the way of the particle to exchange information. Then the discrete particle swarm optimization algorithm was proposed. Simulation results show that the algorithm is feasible and effective to solve the UCAV task allocation problem.

关 键 词：UCAV 任务分配 粒子群优化算法 二维编码 

分 类 号：TP391.9[自动化与计算机技术—计算机应用技术]