UAV Path Robustness Optimization Based on Improved PSO and Hopfield Neural Network
Nowadays,drone path planning is achieved through the fusion of machine learning,deep learn-ing,evolutionary algorithms and intelligent algorithms.For the problem of path robustness optimization of UAVs between different cities,the existing single neural network model cannot reach the optimal solution to a certain extent,and local optimization will occur,resulting in the optimization effect can not be maxi-mized.In this paper,an improved particle swarm optimization algorithm combined with the continuous Hopfield neural network model is studied.By improving the inertia weight in the particle swarm optimiza-tion algorithm,the particle motion speed is controlled.In the process of updating all particles,each indi-vidual particle has an independent search and optimization ability.The results show that IPSO-CHNN neural network model can effectively avoid local optimal solutions,and has better optimization effect on UAV path robustness than traditional HNN.
万方数据
维普
