Open AccessGenetic algorithm‐based multiple moving target reaching using a fleet of sailboats
Author(s) -
Christophe Viel,
Ulysse Vaultier,
Jian Wan,
Luc Jaulin
Publication year - 2019
Publication title -
iet cyber‐systems and robotics
Language(s) - English
Resource type - Journals
ISSN - 2631-6315
DOI - 10.1049/iet-csr.2019.0029
Subject(s) - genetic algorithm , propulsion , travelling salesman problem , computer science , marine engineering , task (project management) , algorithm , simulation , engineering , aerospace engineering , machine learning , systems engineering
This study addresses the problem of Dynamic Travelling Salesman Problem for a multi‐agent system using a fleet of sailboats. A genetic algorithm (GA) is proposed, which attributes to each agent a varying number of targets to be collected. GA allows obtaining a suboptimal solution in the shortest time possible. Moreover, this study adapts it to the specific problem involving a fleet of sailboats, which is a challenging task with comparison to autonomous underwater vehicles or motorised vehicles in terms of the propulsion. Therein motors can be flexibly controlled while sailboat movements are constrained by available wind direction and speed. Thus the method takes into account wind conditions at various locations of the sailboat. Simulation results demonstrate the effectiveness of the proposed approach.