关键词: 无人机, 航迹规划, 粒子群算法, 混沌, 精英反向学习策略

Abstract: In order to solve the problem that the classical particle swarm optimization (PSO) has insufficient global search ability and is easy to fall into local optimality in the course of UAV 3D flight path planning, a multi-dimensional enhanced particle swarm optimization (MDEPSO) algorithm is proposed. Firstly, by introducing improvement factors, the algorithm dynamically adjusts the inertia weights in each stage of particle optimization, which improves the group adaptability and overcome the local optimal ability Secondly, the dynamic constraint equation is used to enhance the learning factor, which makes the information sharing between particles more efficient and improves the self-learning ability of the algorithm. Then the orderly integration of chaos initialization and elite reverse learning evolution strategy advantages, re-planning the particle swarm evolution process, enhance the balance and diversity of particles in the iterative process. In the experiment, through horizontal comparison of test functions and vertical application in complex three-dimensional battlefield environment, MDEPSO algorithm has improved UAV track planning ability compared with PSO algorithm in the new multidimensional objective function index, showing better effectiveness and competitiveness among the five comparison algorithms.

Key words: unmanned aerial vehicle, path planning, particle swarm optimization, chaos, elite backward learning strategy