基于MAX-MIN自适应蚁群优化的无人作战飞机航路规划

UCAV Path Planning Based on MAX-MIN Self-adaptive Ant Colony Optimization

为了保证无人作战飞机(UCAV)以最小的被发现概率和最优的航程到达目标点,在敌方防御区域内执行任务前必须进行航路规划。蚁群优化(ACO)算法的并行实现机制适合于复杂作战环境下的UCAV航路规划,但是基本ACO算法有易陷于局部最优解的缺点。在对基本ACO算法采用精灵策略保留每次迭代最优解的基础上,提出了一种适用于航路规划的MAX-MIN自适应ACO算法,并给出了改进后ACO算法的实现流程,最后采用改进前后的ACO算法对某UCAV的任务态势分别做了仿真实验。实验结果表明改进后的ACO算法可更加有效地应用于UCAV航路规划。

To ensure unmanned combat aerial vehicle （UCAV） to reach the destination with an optimal path and a minimum rate to be found, UCAV path planning must be made before mission execution. The parallelism of ant colony optimization （ACO） is feasible in UCAV path planning under complicated combat environments, but the basic ACO algorithm has the limitation of stagnation, and is easy to fall into local optimum trouble. Elitist strategy is adopted to preserve the best solution in each iteration, and a novel type of MAX-MIN self-adaptive ACO algorithm is put forward in this paper. The flowchart of the improved ACO algorithm is also presented. Finally, with UCAV mission posture data, series simulation experiments using basic ACO algorithm and improved ACO algorithm are conducted. The experimental results show that the improved ACO algorithm is more feasible and effective in UCAV path planning than the basic ACO algorithm.