基于改进PSO算法的无人机路径规划OA

The efficiency of path planning and obstacle avoidance capabilities of unmanned aerial vehicles(UAV)in complex environments directly determine the reliability and safety of their mission execution.Traditional optimization algorithms are prone to getting stuck in local optima,resulting in high planning costs,poor adaptability,and an inability to meet the requirements for efficient flight.This paper proposes a genetic-chaotic particle swarm optimization(G-CPSO)algorithm,constructing a comprehensive objective drone path planning model based on distance,obstacle avoidance cost,and smoothness.It integrates the genetic algorithm(GA)and adopts a tent mapping chaotic perturbation strategy,introducing nonlinear adaptive inertial weights to enhance the optimization capability in the solution space,significantly improving path planning quality.Simulation results show that in a two-dimensional multi-obstacle complex terrain obstacle avoidance problem,compared with the traditional particle swarm optimization(PSO)algorithm,G-CPSO is more efficient,with a total cost reduction of 87.14％and better smoothness.The effectiveness of this method is further verified in a three-dimensional obstacle environment.This method improves the reliability and practicality of path planning in actual applications and can provide support for subsequent research on complex dynamic task-path coordination strategies.