Enhanced PSO with adaptive weights and Gaussian mutation based 3D path planning for UAVs

Abstract

Path planning is an indispensable part of the autonomous control system for unmanned aerial vehicles (UAVs). In addition, UAVs mission planning has been proven to be an NP-hard problem. This paper systematically analyzes the state-of-the-art intelligent optimization algorithms for UAVs path planning. Considering that traditional particle swarm optimization (PSO) and adaptive weight particle swarm optimization (AWPSO) easily converge to local optima, this work develops an enhanced PSO with adaptive weight and Gaussian mutation (EPSO-AWGM). The introduction of adaptive weight factors and Gaussian mutation operators helps the algorithm escape local optimum solutions. Moreover, cubic spline method is utilized to smooth the UAVs flight paths. Simulation results show that the proposed EPSO-AWGM can obtain shorter and higher-quality flight paths. It therefore has great application potential in practical UAVs path planning scenarios.