UCAV Path Planning Based on Improved Chaotic Particle Swarm Optimization

Abstract

This paper presents an improved particle swarm optimization (PSO) algorithm based on the chaos of Zaslavskii to solve the path planning problem of Uninhabited Combat Air Vehicle (UCAV) in the threat battlefield. The proposed method uses the characteristics of traditional particle swarm optimization algorithm, such as fast convergence speed, ergodicity, randomness of chaotic motion and sensitivity to initial value. The chaos mapping formula of Zaslavskii is used to generate chaotic sequence and improves the inertia weight and random variables of PSO algorithm. The improved PSO algorithm is applied to bear on the problem of path planning of UCAV. It gradually escapes from the local optimal path and find the global optimal path in the complex and changeable battlefield environment. The simulation results show that the improved PSO algorithm can effectively accelerate the convergence speed and improve the optimal trajectory.