Research Article
AI-Based Loading Conditions Automatic Generation Method for Ships
@INPROCEEDINGS{10.1007/978-3-032-38705-9_12, author={Young-Soo Han and Kyungho Lee and Youngsu Kim and Younwook Nam and Soyoung Park}, title={AI-Based Loading Conditions Automatic Generation Method for Ships}, proceedings={Intelligent Transport Systems. 9th EAI International Conference, INTSYS 2025, Marietta, GA, USA, December 10, 2025, Proceedings}, proceedings_a={INTSYS}, year={2026}, month={10}, keywords={Smart Ship Autonomous Ship Design Automation Trim and Stability Booklet Reinforcement Learning}, doi={10.1007/978-3-032-38705-9_12} }- Young-Soo Han
Kyungho Lee
Youngsu Kim
Younwook Nam
Soyoung Park
Year: 2026
AI-Based Loading Conditions Automatic Generation Method for Ships
INTSYS
Springer
DOI: 10.1007/978-3-032-38705-9_12
Abstract
The shipbuilding and ship operation industries are experiencing an increasing demand for full automation. However, considering the large-scale production and operational facilities, research and development are currently focused on achieving phased unmanned operations. To prepare for a voyage, ships are required to assess their stability and structural strength, taking into account the type and quantity of cargo loaded, bunkering conditions, and other relevant factors. Such evaluations are mandated from the design stage through approval of the Trim and Stability Booklet. Also, officers rely on this information to assess whether a given loading condition allows safe sailing with respect to stability and longitudinal strength. In special circumstances, such as navigating in heavy weather, dedicated ballast conditions must also be examined, requiring calculations and evaluations that reflect current operational data. However, in smart ships with more than a 70% reduction in crew, or in fully unmanned vessels, these tasks must be handled with limited resources either by a small number of crew or shore-based fleet operation centers, thereby necessitating intelligent decision-support systems. This study investigates methods for intelligently evaluating loading conditions to support rapid decision-making and examines their applicability through testing.