Global path planning algorithm based on the IPSO algorithm for USVs
Jingjing Zhang, Xiao Chen, Hongning Hu, Jianqiang Zhang, Wang Lian · 2018
The global path planning problem of the USV in marine environment has been discussed, a path planning algorithm for USVs based on modeling in polar coordinate system and the improved particle swarm optimization algorithm is proposed. Firstly, considering the global exploration and local development ability of the particle swarm optimization algorithm, the population is initialized by the beta distribution, and the inertia weight is updated by the inverse incomplete function Γ . Then, according to the characteristics of particle swarm optimization algorithm, the learning factors of asynchronous changing are designed and the new operator is introduced based on the idea ofdifferential evolution to realize the updating of particle's velocity and position. Finally, the boundary symmetric mapping strategy is used to deal with the transboundary problem of particles. Simulation results show that the improved algorithm is superior to the differential evolution algorithm, artificial bee colony optimization algorithm and ordinary particle swarm optimization algorithm. And then the IPSO algorithm is introduced into the path planning for the USV, the current position of the USV, the expected position and the distance between the obstacle position are used to determine whether the path planning algorithm should be performed, when the obstacle is encountered, the improved PSO algorithm for path planning is resorted to obtain a feasible, shortest and absolutely safe polyline path. Simulation results verify the effectiveness ofthe algorithm.