Performance evaluation of particle swarm intelligence based optimization techniques in a novel AUV path planner

Over years of development, many optimizationtechniques have been proposed for the path planning of theAutonomous Underwater Vehicle (AUV). The development inswarm intelligence optimization, particularly the particle swarmoptimization (PSO), has significantly improved the performanceof the AUV path planner. This study presents 12 variants ofparticle swarm intelligence (PSI)-based algorithms, which wereapplied to evaluate their performances in solving the optimal pathplanning problem of an AUV operating in 2D and 3D oceanenvironments with obstacles and non-uniform currents.Throughout the structure of the optimization problem, thepracticability of the path planning algorithms were considered bytaking into account the physical limitations of the AUV actuations.To compare the performances of these PSI-based algorithms,extensive Monte Carlo simulations were conducted to evaluatethese algorithms based on their respective solution qualities,stabilities and computational efficiencies. Ultimately, the strengthsand weaknesses of these algorithms were comprehensivelyanalyzed, in order to identify the most appropriate optimizationalgorithm for AUV path planning in dynamic environments