基于自适应粒子群优化算法的无人机三维航迹规划  

Three Dimensional Path Planning of UAV Based on Adaptive Particle Swarm Optimization Algorithm

作　　者：王磊 赵红超 王书湖 卢仁伟 WANG Lei;ZHAO Hongchao;WANG Shuhu;LU Renwei(Naval Aviation University,Yantai Shandong 264001,China;Yantai Nanshan College,Longkou Shandong 265713,China)

机构地区：[1]海军航空大学,山东烟台264001 [2]烟台南山学院,山东龙口265713

出　　处：《海军航空工程学院学报》2020年第3期241-247,共7页Journal of Naval Aeronautical and Astronautical University

基　　金：中国博士后科学基金特别资助项目(2016T90980)。

摘　　要：针对传统的粒子群优化算法容易陷入局部最优解的问题,提出了一种自适应粒子群优化算法,在迭代寻优过程中自适应地调节惯性权重和2个学习因子的数值。建立了无人机在山区环境执行勘察任务的航迹规划环境模型,分析了无人机自身约束条件。设计了自适应粒子群优化算法的适应度函数和航迹规划算法流程。分别采用自适应粒子群优化算法和传统粒子群优化算法开展了无人机三维航迹规划仿真实验。仿真结果对比表明,所提出的自适应粒子群优化算法比传统粒子群优化算法具有更高的全局搜索能力和搜索精度。Aiming at the problem of falling easily into local optimal solution of conventional particle swarm optimization al⁃gorithm,an adaptive particle swarm optimization algorithm is proposed,which adaptively adjusts the values of inertia weight and two learning factors in iterative optimization process.The environment model of path planning was built for un⁃manned aerial vehicle(UAV)to perform reconnaissance task in mountainous environment.The self-constraint conditions of UAV were analyzed.The fitness function of adaptive particle swarm optimization algorithm and flow chart of path plan⁃ning algorithm were designed.The simulation experiments of three dimensional path planning of UAV were carried out by adopting the adaptive particle swarm optimization algorithm and the conventional particle swarm optimization algorithm re⁃spectively.The contrast of simulation results show that the proposed adaptive particle swarm optimization algorithm has higher global search capability and search precision than the conventional particle swarm optimization algorithm.

关 键 词：自适应粒子群优化算法 航迹规划 约束条件 全局搜索 

分 类 号：V249[航空宇航科学与技术—飞行器设计]