Intelligent Cruise Cabin Layout Design based on Reinforcement Learning

Jing Xu; Kefeng Yan

doi:10.6919/ICJE.202609_12(9).0018

Authors

Jing Xu Shandong Jiaotong University, Weihai 264200, China
Kefeng Yan Shandong Jiaotong University, Weihai 264200, China

DOI:

https://doi.org/10.6919/ICJE.202609_12(9).0018

Keywords:

Cruise Cabin Layout; Intelligent Generation; Layout Optimization; Digital Ship Design.

Abstract

This study focuses on the layout optimization of passenger spaces on cruise ships and proposes a reinforcement learning-based method for compartment arrangement in digital ship design. Traditional layout planning relies mainly on manual experience and repeated adjustments, making it difficult to respond efficiently to changes in deck boundaries, structural conditions, and functional requirements. The proposed method considers deck area, compartment boundaries, structural constraints, circulation, and functional relationships, and uses reinforcement learning to generate and adjust layout schemes through continuous interaction with the design environment. A diversity mechanism is introduced to reduce repeated layouts and provide more alternatives for designers. The results show that the method can generate feasible passenger compartment layouts under different design conditions while meeting the main spatial and functional requirements. The study provides a practical approach for improving the efficiency of cruise ship compartment planning and promoting the application of intelligent methods in digital ship design.

Downloads

Download data is not yet available.

References

[1] Hu, R., Huang, Z., Tang, Y., van Kaick, O., Zhang, H., & Huang, H. (2020). Graph2Plan: Learning floorplan generation from layout graphs. ACM Transactions on Graphics, 39(4), 118:1–118:14.

[2] Li, J., Guo, H., Zhang, S., Wu, X., & Shi, L. (2019). Optimum design of ship cabin equipment layout based on SLP method and genetic algorithm. Mathematical Problems in Engineering, 2019, Article 9492583.

[3] Louvros, P., Boulougouris, E., & Coraddu, A. (2022). Multi-objective optimisation as an early design tool for smart ship internal arrangement. Ships and Offshore Structures, 17(6), 1392–1402.

[4] Meng, X., Sun, H., & Kang, J. (2021). Equipment layout optimization based on human reliability analysis of cabin environment. Journal of Marine Science and Engineering, 9(11), 1263.

[5] Nauata, N., Chang, K.-H., Cheng, C.-Y., Mori, G., & Furukawa, Y. (2020). House-GAN: Relational generative adversarial networks for graph-constrained house layout generation. In Computer Vision – ECCV 2020 (pp. 162–177). Springer.

[6] Su, S., Zheng, Y., Xu, J., & Wang, T. (2020). Cabin placement layout optimisation based on systematic layout planning and genetic algorithm. Polish Maritime Research, 27(1), 162–172.

[7] Zhang, H., Yu, Y., Song, Z., Han, Y., Yang, Z., & Ti, L. (2024). Method for collaborative layout optimization of ship equipment and pipe based on improved multi-agent reinforcement learning and artificial fish swarm algorithm. Journal of Marine Science and Engineering, 12(7), 1187.

[8] Heinbach, B., Burggräf, P., & Wagner, J. (2023). Deep reinforcement learning for layout planning: An MDP-based approach for the facility layout problem. Manufacturing Letters, 38, 40–43.