基于DAMPSO算法的USVs集群攻击任务规划研究  

Research on cluster attack mission planning of USVs based on DAMPSO algorithm

作　　者：李杰[1] 孙尧[1] 

机构地区：[1]哈尔滨工程大学自动化学院,哈尔滨150001

出　　处：《计算机工程与应用》2013年第20期1-4,51,共5页Computer Engineering and Applications

基　　金：国家自然科学基金(No.61075113);中央高校基本科研业务费重大专项(No.HEUCFZ1029);黑龙江省杰出青年科学基金(No.JC201212)

摘　　要：现代防御技术的迅速发展使得水面舰艇的攻击效果大大下降,水面无人舰艇自主编队集群攻击技术已经成为未来海战的关键技术之一,多水面无人舰艇之间的任务规划是保证无人舰艇顺利、高效完成任务的关键。将水面无人舰艇集群攻击任务规划问题看成是多约束的任务分配过程,建立任务规划模型,提出了基于分布式拍卖机制的粒子群优化算法,该算法结合分布式拍卖机制对粒子群优化算法的粒子初始化和寻优过程进行改进,使得粒子既符合任务的约束条件,又保持了多样性,避免粒子在寻优过程中陷入局部最优。仿真结果表明应用分布式拍卖机制粒子群优化算法得到的方案不仅完全满足水面无人舰艇集群攻击任务的要求,而且比传统粒子群优化算法和其他群体智能算法具有更好的收敛性。The rapid development of modem defense technology decreases the USVs＇ attacking effect greatly, autonomous for mation cluster attack technique of USVs has become one of the key technologies of future naval warfare, mission planning among USVs is the key for them to complete tasks smoothly and efficiently. It regards the cluster attack mission planning problem as multi-constrained task allocation process, builds mission planning model. A PSO optimization algorithm based on distributed auction is proposed, this algorithm improves particle initialization and optimization process combined with distributed auction mechanism to make partial meet mission constrain condition and maintain diversity, this will avoid PSO optimization falling into a local optimum. Simulation result indicates that the program achieved with distributed auction mechanism particle swarm opti mization could fully meet the requirements of U SV s＇ cluster attack missions, and shows better convergence compared with tradi tional particle swarm optimization and other swarm intelligence algorithms.

关 键 词：多水面无人舰艇 任务规划 分布式拍卖机制 粒子群优化 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]