基于改进人工蜂群算法的多无人作战飞机协同航迹规划

Path planning for multiple unmanned combat aerial vehicles based on improved artificial bee colony algorithm

针对多无人作战飞机(UCAV)航迹规划约束条件复杂、不确定因素多、实时性要求高的特点,提出一种基于改进的人工蜂群算法求解多UCAV协同航迹规划模型。首先构建战场空间的改进Voronoi图生成航迹优化可飞区域;然后采用混沌搜索算法来初始化航迹集合作为算法的蜜源,使其初始航迹集合能以有限的数据充分表示航迹优化可飞区域;最后对多UCAV在多种威胁环境下的航迹空间寻优进行仿真验证。仿真结果证明改进的人工蜂群算法提高了蜜源多样性和算法的收敛速度,增强了UCAV的动态战场适应能力和突发威胁应对能力。

Due to the complex constraints, many uncertain factors and critical real-time demand of path planning for multiple Unmanned Combat Aerial Vehicle （multi-UCAV）, an Improved Artificial Bee Colony （1-ABC） algorithm was proposed to solve the model of path planning for muhi-UCAV. First, the Voronoi diagram of battle field space was conceived to generate the optimal area of UCAV＇s paths. Then the chaotic searching algorithm was used to initialize the collection of paths, which was regarded as foods of ABC algorithm. With the limited data, the initial collection could search the optimal area of paths perfectly. Finally simulations of the muhi-UCA~ path planning under various threats were carried out. The simulation results verify that I-ABC can improve the diversity of nectar source and the convergence rate of algorithm, and it can increase the adaptability of dynamic battlefield and unexpected threats for UCAV.