Artificial Neural Network for Improving the Motion Control Quality of Underwater Remotely Operated Vehicle
Naše more · 2025-09 · 72 (2) · 39-48
DOI: 10.17818/nm/2025/2.1 ↗Kurz gefasst
Fachartikel in der Zeitschrift Naše more, 2025-09. Verfasst von Xuan-Kien Dang und 4 weiteren Autor:innen. Die Arbeit wurde bisher 3-mal zitiert (Crossref).
Abstract (Originalsprache)
The Remotely Operated Vehicle (ROV) plays a crucial role in underwater surveys but faces challenges in complex environments with unmeasured variables, leading to inefficiencies in navigation. This paper develops a motion control solution for ROVs that utilizes Artificial Neural Networks (ANNs) to enhance control quality in response to environmental impacts. Firstly, the authors develop an Adaptive Fuzzy Control (AFC) to control ROV movements under varying environmental conditions, allowing for the collection of operational datasets. Next, the ROV motion controller is designed based on the ANN architecture to enhance control quality. Finally, experimental scenarios using MATLAB demonstrated that ANNs markedly improve control accuracy and overall performance for ROVs when following predetermined trajectories. This emphasizes their substantial potential in advancing autonomous marine applications.
Zitieren
APA
Dang, X., Koboević, Ž., Phan, N. L., Do, V., & Ly, S. (2025). Artificial Neural Network for Improving the Motion Control Quality of Underwater Remotely Operated Vehicle. Naše more, 72(2), 39-48. https://doi.org/10.17818/nm/2025/2.1
Vancouver
Dang X, Koboević Ž, Phan NL, Do V, Ly S. Artificial Neural Network for Improving the Motion Control Quality of Underwater Remotely Operated Vehicle. Naše more. 2025;72(2):39-48. doi:10.17818/nm/2025/2.1
BibTeX
@article{Dang2025,
author = {Dang, Xuan-Kien and Koboević, Žarko and Phan, Nguyen-Hoang Long and Do, Viet-Dung and Ly, Soi},
title = {Artificial Neural Network for Improving the Motion Control Quality of Underwater Remotely Operated Vehicle},
journal = {Naše more},
year = {2025},
volume = {72},
number = {2},
pages = {39--48},
doi = {10.17818/nm/2025/2.1}
}
EUVIMED