*Result*: 基于改进人工蜂群算法的无人飞行器路径协同规划.

*To solve the path planning problem of high-subsonic unmanned aerial vehicles (UAVs) in air combat scenarios, an improved artificial bee colony algorithm (IABC) is proposed. Firstly, by comprehensively considering the obstacles in three-dimensional space and the coordination problem of UAV’s path planning, a combat scenario model and an objective function are established. Secondly, in the employed bee stage, the particle swarm optimization (PSO) algorithm is introduced to reduce the blindness while searching and enhance the search ability of the algorithm. Finally, in the onlooker bee stage, local smoothing processing is carried out on the food sources in the early stage of iteration based on the dynamic greedy criterion, which further improves the convergence speed of the algorithm. In order to verify the effectiveness of the algorithm, a simulation comparison experiment on the algorithm is conducted. The simulation experiment shows that the IABC algorithm inherits the search advantages of the ABC and PSO algorithms. Compared with the ABC algorithm, the average convergence speed of the algorithm is increased by 47.83%, and the average convergence accuracy of the algorithm is increased by 53.49%. [ABSTRACT FROM AUTHOR]*

*为解决空战场景下的高亚声速无人飞行器 (Unmanned aerial vehicle, UAV) 的路径规划问题, 提出一种改 进的人工蜂群 (Improved artificial bee colony, IABC) 算法. 综合考虑三维空间障碍与无人飞行器路径规划的协 同问题, 建立作战场景模型与目标函数; 在雇佣蜂阶段引入了粒子群算法 (Particle swarm optimization, PSO) 降 低搜索的盲目性, 增强算法的搜索能力; 在观察蜂阶段基于动态贪婪准则对迭代初期的蜜源进行局部平滑处理, 进一步提升算法的收敛速度. 为了验证算法有效性, 对算法进行了仿真对比实验. 仿真实验表明, IABC 算法继 承了 ABC 与 PSO 算法的搜索优点, 相较 ABC 算法, 平均算法收敛速度提升 47.83%, 算法收敛精度平均提升 53.49%. [ABSTRACT FROM AUTHOR]*