Research On UAV Path Planning Based On Intelligent Algorith

The application areas of UAVs are becoming more and more extensive,and the tasks they perform are becoming more complex and diverse.During the actual flight of UAVs,it is necessary to calculate the safe path based on its own location,environment,obstacles and other information.Due to the complex and changing scenarios and environments in which UAVs perform their tasks,it becomes important to choose a suitable UAV path planning algorithm.This thesis focuses on the offline path planning algorithm for UAVs,and focuses on the following elements.(1)The UAV path planning model is established based on the structural characteristics of the UAV and the map modeling principle.It contains a two-dimensional map model,a threedimensional map model,a UAV manoeuvrability constraint model and a UAV path planning evaluation model.The map model is designed with corresponding simulated radar and terrain obstacles,the performance constraint model is designed with maximum range constraint,minimum turn radius constraint,flight altitude constraint,maximum yaw angle constraint and maximum pitch angle constraint,and the path planning cost assessment model is designed with flight fuel consumption threat,altitude threat,radar threat and terrain collision threat.(2)An improved artificial bee swarm algorithm based on Zaslavskii chaos is proposed for the two-dimensional path planning problem of UAVs in simulated threat battlefields.Based on the two-dimensional path planning model,the characteristics of the faster convergence of the swarm algorithm and the ergodic and random nature of chaotic motion are used to improve the nectar source selection and search strategy of the swarm algorithm,solving the problems that the algorithm is prone to fall into local optimum and slow solving.Finally,the improved swarm algorithm is applied to solve the UAV two-dimensional path planning problem.The simulations show that the algorithm can get rid of the local optimal path and find the global optimal path quickly in the complex and changing battlefield environment.(3)For the path planning problem of single UAV in 3D environment,an integrated improved particle swarm algorithm based on UAV 3D path planning algorithm is proposed,which uses chaotic sequences and adaptive inertia weights to improve the initial distribution of particles,enhance the optimality of the solution and accelerate the convergence speed of the algorithm.Finally,the comprehensive improved chaotic particle swarm algorithm is applied to the UAV three-dimensional path planning problem,and the simulation results verify the effectiveness of the method.(4)For the path planning problem of multiple UAVs in complex 3D environments,an improved genetic particle fusion algorithm is proposed based on the study of(3)to ensure that multiple UAVs reach the mission location from different angles.Taking the genetic algorithm as the main body,the improved particle swarm algorithm is used to optimize the screened excellent chromosomes twice,and adaptive dynamic crossover probability and fixed variation rate are designed to reduce the operational difficulty of the algorithm and improve the solution speed and solution accuracy of the algorithm.Finally,the improved genetic particle fusion algorithm is applied to the multi-UAV complex 3D path planning problem,and the simulation results show that the multi-UAV complex 3D environment path planning based on the improved genetic particle fusion algorithm can meet the reliability and safety of the planning requirements.