基于优化粒子群算法的无人机航路规划

针对粒子群优化(PSO)算法的无人机(UAV)航路规划问题,引入惯性权重和自然选择对粒子群算法进行优化,以提高基本粒子群算法收敛速度,防止陷入局部最优.算法分析惯性权重对粒子群算法的影响,进而调整惯性因子,提高算法的搜索能力;利用自然选择的便利性和规律性等特点,更新粒子群算法的粒子;同时通过对无人机的可行航向进行限定,缩小搜索范围.仿真实验表明:基于粒子群优化算法的无人机航路规划不仅缩短了最优航路,而且提高了搜索速度.

UAV route planning based on PSO algorithm

Aiming at unmanned aerial vehicle (UAV)route planning problem of particle swarm optimization (PSO)algorithm,introduce inertia weight and natural selection to optimize PSO,in order to improve convergence speed of basic PSO,prevent fall into part optimum. Algorithm analyze on influence of inertia weight on PSO algorithm,and then adjust inertial factor,improve search ability of algorithm;Using characteristics of convenience and regularity of natural selection update particle of PSO;At the same time through limiting practical course of UAV,narrow search range. Simulation results show that,UAV route planning based on optimized PSO algorithm not only reduces the optimal route,but also improve search speed.