Energy-based USV maritime monitoring using multi-objective evolutionary algorithms

This study addresses the monitoring mission problem using an USV equipped with an on-board LiDAR allowing to monitor regions inside its coverage radius. The problem is formulated as a bi-objective coverage path planning with two conflicting objectives : minimization of the consumed energy and maximi...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:Ocean engineering Ročník 253; s. 111182
Hlavní autori: Ouelmokhtar, Hand, Benmoussa, Yahia, Benazzouz, Djamel, Ait-Chikh, Mohamed Abdessamed, Lemarchand, Laurent
Médium: Journal Article
Jazyk:English
Vydavateľské údaje: Elsevier Ltd 01.06.2022
Elsevier
Predmet:
Chromosome size
Computer Science
Covering Path Planning
Embedded Systems
MOEA
Operations Research
USV
Way-points
Covering Path Planning
Chromosome size
USV
MOEA
Way-points
ISSN:0029-8018, 1873-5258
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Popis
Shrnutí:This study addresses the monitoring mission problem using an USV equipped with an on-board LiDAR allowing to monitor regions inside its coverage radius. The problem is formulated as a bi-objective coverage path planning with two conflicting objectives : minimization of the consumed energy and maximization of the coverage rate. To solve the problem, we use two popular multi-objective evolutionary algorithms : Non-Dominated Sorting Genetic Algorithm II (NSGA-II) and Pareto Archived Evolution Strategy (PAES). First, we compare the efficiency of these two algorithms and show that PAES allows to find solutions allowing to save more energy as compared to those provided by NSGA-II. Then, we propose a new method which improves the performance of evolutionary algorithms when solving covering path planning problems by reducing the chromosome size. We have applied this method on the used algorithms and simulation results shows a significant performance enhancement both PAES and NSGA-II. •Unmanned maritime surface drones for performing surveillance tasks.•Coverage area and energy consumption optimization.•Global covering path planning.•New methodology to enhance problem solving performance.•Performance and solution quality comparison with conventional methods.
ISSN:0029-8018
1873-5258
DOI:10.1016/j.oceaneng.2022.111182