Enhanced particle swarm optimization for path planning of unmanned aerial vehicles

Abstract

This paper presents an enhanced particle swarm optimization (PSO) for the path planning of un- manned aerial vehicles (UAVs). An evolutionary al- gorithm such as PSO is costly because every applica- tion requires different parameter settings to maximize the performance of the analyzed parameters. Peo- ple generally use the trial-and-error method or refer to the recommended settings from general problems. The former is time consuming, while the latter is usu- ally not the optimum setting for various speci c ap- plications. Hence, this study focuses on analyzing the impact of input parameters on the PSO performance in UAV path planning using various complex terrain maps with adequate repetitions to solve the tuning is- sues. Results show that inertial weight parameter is insigni cant, and a 1.4 acceleration coeffcient is opti- mum for UAV path planning. In addition, a popula- tion size between 40 and 60 seems to be the optimum setting based on case studies.