任务规划是无人机协同作战的关键技术之一。以压制敌方防空火力任务为背景, 考虑战场地形与威胁分布、击毁目标需要的火力以及无人机的战斗毁伤概率等因素, 建立了多架无人机协同攻击多个地面目标的任务规划模型, 并提出并行遗传粒子群优化算法(GAPSO)求解任务规划问题。通过具体的仿真算例验证了协同任务规划模型的合理性, 并比较分析并行GAPSO算法与标准GAPSO算法, 证明了并行GAPSO算法具有更好的收敛性且能避免陷入局部最优。

Mission planning is one of key technologies for Unmanned Aerial Vehicle (UAV) cooperative combat. For the task of suppressing the enemy's aerial-defense firepower, we established a mission planning model for multi-UAV cooperative attacking multiple ground targets by taking terrain and threat distribution, firepower resource needed to destroy the targets, and damage probability of UAVs into consideration. A parallel Genetic Algorithm and Particle Swarm Optimization (GAPSO) algorithm was proposed to resolve this multi-UAV cooperative mission planning problem. Simulation example verified the rationality of the mission planning model. The comparison between parallel GAPSO algorithm and traditional GAPSO algorithm showed that the parallel algorithm has better convergence performance and could avoid trapping in local optimum.