aalto1 untyped-item.component.html
A Transformer based task execution digital twin of 3-DOF maneuvering of Bulk Carrier for autonomous maritime systems
Loading...
Access rights
openAccess
CC BY
CC BY
Creative Commons license
Except where otherwised noted, this item's license is described as openAccess
publishedVersion
URL
Journal Title
Journal ISSN
Volume Title
A1 Alkuperäisartikkeli tieteellisessä aikakauslehdessä
This publication is imported from Aalto University research portal.
View publication in the Research portal (opens in new window)
View/Open full text file from the Research portal (opens in new window)
View publication in the Research portal (opens in new window)
View/Open full text file from the Research portal (opens in new window)
Unless otherwise stated, all rights belong to the author. You may download, display and print this publication for Your own personal use. Commercial use is prohibited.
Date
Major/Subject
Mcode
Degree programme
Language
en
Pages
22
Series
Ocean Engineering, Volume 341
Abstract
This study contributes to the advancement of Maritime Autonomous Surface Ships (MASS) by developing a task execution model within a digital twin framework to simulate ship maneuvering in open water using machine learning techniques. The dataset comprises real-world navigational data collected from a Kamsarmax bulk carrier sailing from Brazil to China across the Atlantic Ocean between March and May 2023. The research focuses on comparing the performance of a Transformer encoder with the well-established Long Short-Term Memory (LSTM) model. Results demonstrate that the Transformer outperforms LSTM across most maneuvering dimensions, particularly in surge and sway motions, achieving lower Mean Absolute Error (MAE) during both training and validation. Notably, the Transformer exhibited high precision in modeling ship position. While both models were computationally efficient and suitable for real-time deployment, the Transformer model was approximately three times larger in size. Challenges remained in accurately capturing the yaw rate for both models. Overall, the Transformer encoder shows strong potential for integration into digital twin systems, offering a robust path toward real-time, high-fidelity modeling of ship dynamics in autonomous maritime applications.
Description
Publisher Copyright: © 2025 The Authors
Other note
Citation
Shehata, A, Zhang, M, Tsoulakos, N & Kujala, P 2025, 'A Transformer based task execution digital twin of 3-DOF maneuvering of Bulk Carrier for autonomous maritime systems', Ocean Engineering, vol. 341, 122797. https://doi.org/10.1016/j.oceaneng.2025.122797