Premium
Two‐dimensional optimal path planning for autonomous underwater vehicle using a whale optimization algorithm
Author(s) -
Yan Zheping,
Zhang Jinzhong,
Yang Zewen,
Tang Jialing
Publication year - 2020
Publication title -
concurrency and computation: practice and experience
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.309
H-Index - 67
eISSN - 1532-0634
pISSN - 1532-0626
DOI - 10.1002/cpe.6140
Subject(s) - mathematical optimization , computer science , motion planning , cuckoo search , particle swarm optimization , robustness (evolution) , underwater , ant colony optimization algorithms , sonar , convergence (economics) , harmony search , algorithm , mathematics , artificial intelligence , robot , geology , biochemistry , chemistry , oceanography , economic growth , economics , gene
Abstract This paper presents a whale optimization algorithm (WOA) based on forward looking sonar to achieve two‐dimensional optimal path planning for an autonomous underwater vehicle. The purpose of path planning is not only to effectively avoid threat regions and safely reach the intended target with minimum fuel cost but also to obtain an optimal or near‐optimal path in a complex ocean battlefield environment. The WOA, based on the bubble‐net attacking behavior of humpback whales, mimics encircling the prey, attacks with a bubble‐net method, and search for prey to effectively determine the global optimal solution in the search space. The WOA not only has fast convergence speed and high calculation accuracy but can also effectively balance exploration and exploitation to avoid falling into a local optimum and obtain the global optimal solution. Five sets of experiments are applied to verify the superiority and stability of the WOA. Compared with other algorithms, such as artificial bee colony, bat algorithm, cuckoo search, flower pollination algorithm, moth‐flame optimization algorithm, particle swarm optimization, and water wave optimization, the WOA exhibits better optimization performance and stronger robustness. The experimental results reveal that the WOA can find the shortest path compared with all the other algorithms, and it is an effective and feasible method for solving the path planning problem.