基于NAPPGA算法的无人机低空突防航迹规划  

Flight Path Planning for UAV Low-Altitude Penetration Based on Niche Adaptive Pseudo Parallel Genetic Algorithm

作　　者：任鹏[1] 高晓光[1] 

机构地区：[1]西北工业大学电子信息学院,陕西西安710072

出　　处：《计算机仿真》2014年第4期102-105,共4页Computer Simulation

基　　金：国家自然科学基金(60774064);高等学校博士学科点专项科研基金(20116102110026)

摘　　要：在无人机突防快速回避优化问题的研究中,无人机(UAV)低空突防航迹规划本质是复杂的多目标、多约束优化问题,求解的复杂性及难度高,常用的智能算法无法保证飞行航迹的最优性和可达性。针对UAV低空突防三维航迹规划问题的实际,利用基于角度量的变长度基因编码表示飞行航迹,将UAV飞行性能约束融入到算法中,保证物理航迹可飞;基于进化算法的原理,提出一种小生境伪并行自适应遗传算法(NAPPGA),综合利用多种群、伪并行计算和共享函数的小生境技术提高算法进化效率、防止"早熟"。通过大量仿真计算,结果表明:应用改进算法规划出的三维航迹能够有效实现威胁回避、地形回避和地形跟随,满足UAV低空突防要求,具有一定的实用性。The essential content of flight paths planning for UAV low altitude penetration is multi objective, multi constraint optimization problem. The method of solution is extremely complex and difficult. Using variable length gene encoding based on angle applied for the flight paths planning technologies of low altitude penetration, the constraints of flight performance was melt into algorithm. A Niche Adaptive Pseudo Parallel Genetic Algorithm （NAPPGA） against several limitations of the existing intelligent algorithms was presented. Using muhi populations, pseudo parallel computing and niche technology based on share function, this method improves evolutionary efficiency and prevents precocious. A lot of simulation studies show that the global optimal solutions of multi objective optimi zation problem can be obtained by NAPPGA and the solving three dimensional flight paths can meet the require ments of UAV low altitude penetration, efficient implementation of threat avoidance, terrain avoidance and terrain following. This method has a certain practicality.

关 键 词：小生境伪并行自适应遗传算法 无人机 低空突防 航迹规划 

分 类 号：V249[航空宇航科学与技术—飞行器设计]