How Far from the Shore? Federated Maritime Intelligence for Autonomous Ship and Harbor Maneuvering
Source abstract
Abstract
Autonomous ship maneuvering in harbor environments is increasingly supported by advances in model predictive control, reinforcement learning, digital twins, multi-sensor fusion, berth allocation, and multi-agent coordination. However, these developments are often studied as separate technological domains, while real harbor autonomy requires coordinated operation across vessels, port infrastructure, regulatory systems, cybersecurity mechanisms, and human supervisory processes. This study presents an architecture-oriented critical review of autonomous ship and harbor maneuvering research published between 2015 and May 2026. The review synthesizes literature from control engineering, maritime artificial intelligence, sensor fusion, digital twins, port logistics, cyber-physical systems, regulation, cybersecurity, and human–AI supervision. The analysis introduces two conceptual contributions: a layered cyber-physical taxonomy and an integration maturity model. The taxonomy organizes autonomous harbor maneuvering into seven interdependent layers: physical dynamics, perception and sensor fusion, prediction and state estimation, control, decision and coordination, digital twin federation, and regulatory–supervisory governance. The maturity model distinguishes isolated vessel autonomy, assisted coordination, shared digital synchronization, agent-based coordination, and fully federated maritime cyber-physical autonomy. The reviewed evidence shows substantial progress in individual layers, especially control, perception, digital twins, and berth allocation. However, major gaps remain in cross-layer synchronization, semantic interoperability, regulation-aware decision-making, cybersecurity integration, and validated ship–shore federation. To address these gaps, this study proposes a Federated Maritime Cyber-Physical Architecture for autonomous harbor maneuvering. The architecture integrates vessel autonomy cores, port intelligence cores, semantic federation middleware, agent-based negotiation, regulatory verification, cybersecurity safeguards, and human supervisory interfaces. This review argues that future progress in autonomous harbor operations depends not only on stronger algorithms, but on interoperable, explainable, regulation-aware, and cyber-resilient ship–shore ecosystems.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Maritime Navigation and Safety · Maritime Transport Emissions and Efficiency · Maritime Ports and Logistics
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Institute of Marine and Environmental Sciences, University of Szczecin, 70-364 Szczecin, Poland
Faculty of Data Science and Information, INTI International University, Nilai 71800, Malaysia
Faculty of Navigation, Maritime University of Szczecin, 70-500 Szczecin, Poland
References (89)
Show source-provided references
1. Deep reinforcement learning based collision avoidance system for autonomous ships10.1016/j.oceaneng.2023.116527 ↗
2. Explainable AI for ship collision avoidance: Decoding decision-making processes and behavioral intentions10.1016/j.apor.2025.104471 ↗
3. Coordinated control of multiple autonomous surface vehicles: Challenges and advances—A systematic review10.1016/j.oceaneng.2024.119160 ↗
4. Human-like constraint-adaptive model predictive control with risk-tunable control barrier functions for autonomous ships10.1016/j.oceaneng.2024.118219 ↗
5. Multi-terminal continuous and dynamic berth allocation problem considering tidal time windows and channel constraints10.1016/j.tre.2025.104365 ↗
6. Research on model predictive control of autonomous underwater vehicle based on physics informed neural network modeling10.1016/j.oceaneng.2024.117844 ↗
7. Digital twin syncing for autonomous surface vessels using reinforcement learning and nonlinear model predictive control10.1038/s41598-025-93635-9 ↗
8. Research on hybrid policy optimization method based on deep reinforcement learning for ship heading control and path following10.1016/j.oceaneng.2025.121597 ↗
9. Honelign, L., Abebe, Y., Tullu, A., and Jung, S. (2025). Deep Reinforcement Learning-Based Enhancement of Robotic Arm Target-Reaching Performance. Actuators, 14.10.20944/preprints202501.1917.v1 ↗
10. Time-optimal obstacle avoidance of autonomous ship based on nonlinear model predictive control10.1016/j.oceaneng.2022.112591 ↗
11. Liu, J., Hao, S., Chen, Y., Wang, J., and Gao, J. (2025). A Gaussian Process-based funnel MPC for docking control of unmanned underwater vehicles by learning residual dynamics. Drones, 12.10.3390/drones9120836 ↗
12. Yara: An ocean virtual environment for research and development of autonomous sailing robots and other unmanned surface vessels10.1007/s10846-024-02212-1 ↗
13. Model-free adaptive control for unmanned surface vessels: A literature review10.1080/21642583.2024.2316170 ↗
14. Wu, Y., Liu, J., Li, X., Xiao, J., Zhang, T., Xu, H., and Zhang, L. (2025). Towards LLM enhanced decision: A survey on reinforcement learning based ship collision avoidance. J. Mar. Sci. Eng., 13.10.20944/preprints202511.0267.v1 ↗
15. Wang, P., Li, J., and Cao, X. (2024). Discrete dynamic berth allocation optimization in container terminal based on Deep Q-Network. Mathematics, 12.10.3390/math12233742 ↗
16. Multi-joint adaptive control enhanced reinforcement learning for unmanned ship10.1016/j.oceaneng.2024.120121 ↗
17. Knowledge transfer enabled reinforcement learning for efficient and safe autonomous ship collision avoidance10.1007/s13042-024-02116-4 ↗
18. Deep learning in maritime autonomous surface ships: Current development and challenges10.1007/s11804-023-00367-1 ↗
19. A collision avoidance decision-making system for autonomous ship based on modified velocity obstacle method10.1016/j.oceaneng.2020.107910 ↗
20. A multi-sensor fusion approach for maritime autonomous surface ships berthing navigation perception10.1016/j.oceaneng.2024.119965 ↗
21. Ensemble deep learning approach for marine vessel classification: Integrating CNN and vision transformers with machinery feature enhancement10.1016/j.inffus.2025.103570 ↗
22. Kim, J., Park, J., and Cho, K. (2022). Continuous autonomous ship learning framework for human policies on simulation. Appl. Sci., 12.10.3390/app12031631 ↗
23. Cloud edge enabled stacked ensemble learning framework with meta model for situation-aware maritime traffic monitoring and control systems10.1038/s41598-025-25020-5 ↗
24. MS3Net: A deep ensemble learning approach for ship classification in heterogeneous remote sensing data10.1080/01431161.2024.2302953 ↗
25. Development of a deep-learning model with maritime environment simulation for detection of distress ships from drone images
26. An enhanced CNN-enabled learning method for promoting ship detection in maritime surveillance system10.1016/j.oceaneng.2021.109435 ↗
27. Sensor fusion models in autonomous systems: A review
28. Tadros, M., Aung, M.Z., Louvros, P., Pollalis, C., Nazemian, A., and Boulougouris, E. (2025). Ship Manoeuvring Research 2010–2025: From hydrodynamics and control to digital twins, AI and MASS. J. Mar. Sci. Eng., 13.10.3390/jmse13122322 ↗
29. Eom, J.-O., Yoon, J.-H., Yeon, J.-H., and Kim, S.-W. (2023). Port digital twin development for decarbonization: A case study using the Pusan Newport International Terminal. J. Mar. Sci. Eng., 11.10.3390/jmse11091777 ↗
30. Digital twin technology in maritime: A MAAP innovation strategy10.12716/1001.19.04.21 ↗
31. Digital twins in the context of seaports and terminal facilities10.1007/s10696-023-09515-9 ↗
32. Digital twin development for berthing planning of ships10.5302/J.ICROS.2022.22.0097 ↗
33. Digital twins for ports: Derived from smart city and supply chain twinning experience10.1109/ACCESS.2023.3295495 ↗
34. Port tugboat formation multi-agent control system10.12716/1001.15.04.13 ↗
35. Intelligent port logistics: A spatiotemporal knowledge graph and AI-agent framework for berth allocation10.1016/j.aei.2025.103633 ↗
36. Optimization berth allocation in container terminals: A Pyomo and Google Colab approach10.1016/j.ocecoaman.2024.107359 ↗
37. Automated docking for marine surface vessels—A survey10.1109/ACCESS.2023.3335912 ↗
38. Energy-aware MARL for coordinated data collection in multi-AUV systems10.1109/ACCESS.2025.3606016 ↗
39. A systematic review of human–AI interaction in autonomous ship systems10.1016/j.ssci.2022.105778 ↗
40. A systematic review of reinforcement learning in Building-Integrated Photovoltaic (BIPV) optimization10.1016/j.adapen.2025.100239 ↗
41. Sensors and AI techniques for situational awareness in autonomous ships: A review10.1109/TITS.2020.3023957 ↗
42. Efficient ship track keeping using predictive PID controller
43. Alessandri, A., Donnarumma, S., Martelli, M., and Vignolo, S. (2019). Motion control for autonomous navigation in blue and narrow waters using switched controllers. J. Mar. Sci. Eng., 7.10.3390/jmse7060196 ↗
44. Design and implementation of a model-following controller for autonomous surface ships based on actor–critic reinforcement learning10.1016/j.oceaneng.2024.119157 ↗
45. A survey of multi-agent reinforcement learning for cooperative control in multi-AUV systems10.1109/ACCESS.2025.3609457 ↗
46. A multi-objective deep reinforcement learning framework for energy efficiency of autonomous harbor crafts10.1016/j.apenergy.2025.126809 ↗
47. Autonomous unmanned surface vehicle docking using large language model guide reinforcement learning10.1016/j.oceaneng.2025.120608 ↗
48. Chae, C.-J., Kim, M., and Kim, H.-J. (2020). A study on identification of development status of MASS technologies and directions of improvement. Appl. Sci., 10.10.3390/app10134564 ↗
49. Fast model predictive control of autonomous sailboats based on improved physics-informed neural networks10.1016/j.oceaneng.2025.123279 ↗
50. Prescribed time performance control of underwater vehicles based on time-varying disturbance10.1016/j.isatra.2025.12.005 ↗
51. An explicit model predictive control framework based on physics-informed neural networks10.1016/j.jprocont.2026.103634 ↗
52. Physics-informed neural nets for control of dynamical systems10.1016/j.neucom.2024.127419 ↗
53. Physics-informed neural networks with skip connections for modeling and control of gas-lifted oil wells10.1016/j.asoc.2024.111603 ↗
54. Liu, J., Chang, L., Xu, L., He, F., and He, Y. (2025). Research on the on-line identification of ship maneuvering motion model parameters and adaptive control. J. Mar. Sci. Eng., 13.10.3390/jmse13040753 ↗
55. Multi-AGV dynamic scheduling of automated container terminal based on digital twin
56. AI-driven control and optimization for renewable energy integration in smart grids: Challenges, applications, and future research directions10.1016/j.esr.2026.102049 ↗
57. Digitalization of urban multi-energy systems—Advances in digital twin applications across life-cycle phases10.1016/j.adapen.2024.100196 ↗
58. Leveraging digital twins for fault diagnosis in autonomous ships10.1016/j.oceaneng.2023.116546 ↗
59. Cai, J., Chen, G., Yin, J., Ding, C., Suo, Y., and Chen, J. (2024). A review of autonomous berthing technology for ships. J. Mar. Sci. Eng., 12.10.3390/jmse12071137 ↗
60. Integrating vessel arrival time forecasting into berth allocation decisions: A predictive-operational framework10.1016/j.aei.2025.104010 ↗
61. A geospatial grid constrained deep learning predication framework based on AIS data for improving vessel traffic services in maritime Internet of Things10.1109/JIOT.2026.3663597 ↗
62. A hierarchical reinforcement learning approach for real-time berth allocation and quay crane scheduling10.1080/00207543.2025.2542518 ↗
63. A tightly-coupled LiDAR–IMU SLAM method for quadruped robots10.1177/00202940231224593 ↗
64. A holistic hydrodynamic modeling approach for ship motion prediction and berthing strategy assessment10.1016/j.oceaneng.2025.122865 ↗
65. Optimal policies for the berth allocation problem under stochastic nature10.1016/j.ejor.2016.04.029 ↗
66. Dynamic berth allocation under uncertainties based on deep reinforcement learning towards resilient ports10.1016/j.ocecoaman.2024.107113 ↗
67. Real-time attitude control of large rectangular pipe-jacking machines using a mechanics-informed digital twin10.1016/j.autcon.2025.106373 ↗
68. Model predictive maneuvering control and energy management for all-electric autonomous ships10.1016/j.apenergy.2019.113308 ↗
69. Liu, T., Zhao, J., and Huang, J. (2024). A Gaussian-Process-Based Model Predictive Control Approach for Trajectory Tracking and Obstacle Avoidance in Autonomous Underwater Vehicles. J. Mar. Sci. Eng., 12.10.3390/jmse12040676 ↗
70. Survey of deep learning for autonomous surface vehicles in marine environments10.1109/TITS.2023.3235911 ↗
71. Trajectory tracking control of autonomous underwater vehicles: A review from classical methods to AI-based approaches10.1007/s40435-025-01963-5 ↗
72. Kinaci, O.K., and Gunes, A. (2025). A classification framework for digital twins, shadows, and models in autonomous ship navigation. WMU J. Marit. Aff.10.1007/s13437-025-00392-7 ↗
73. A port digital twin model for operational uncertainty management
74. Wang, Y., Zhang, E., Yang, A., Du, K., and Gao, J. (2025). Mixed reality-based multi-scenario visualization and control in automated terminals: A middleware and digital twin driven approach. Buildings, 15.10.3390/buildings15213879 ↗
75. HP2C-DT: High-precision high-performance computer-enabled digital twin10.1016/j.future.2025.108333 ↗
76. An optimization study on dynamic berth allocation based on vessel arrival time prediction10.1016/j.oceaneng.2025.121321 ↗
77. Dynamic speed optimization and berth reallocation for autonomous vessels under sailing time disturbances10.1109/TITS.2025.3639274 ↗
78. E2E neural predictive control for vessel: Autonomous berthing via DRL and PIM-MPC10.1016/j.ijnaoe.2025.100692 ↗
79. A data-driven framework for predicting ship berthing time and optimizing port operations at Tan Cang Cat Lai Port, Vietnam10.1016/j.cstp.2025.101441 ↗
80. Vessel arrival time to port prediction via a stacked ensemble approach: Fusing port call records and AIS data10.1016/j.trc.2025.105128 ↗
81. Optical and synthetic aperture radar image fusion for ship detection and recognition: Current state, challenges, and future prospects10.1109/MGRS.2024.3404506 ↗
82. Jones, A., Koehler, S., Jerge, M., Graves, M., King, B., Dalrymple, R., Freese, C., and von Albade, J. (2023). BATMAN: A brain-like approach for tracking maritime activity and nuance. Sensors, 23.10.3390/s23052424 ↗
83. A survey of underwater docking guidance systems10.1016/j.robot.2019.103382 ↗
84. Review on the protective technologies of bridge against vessel collision10.1016/j.tws.2024.112013 ↗
85. A Bayesian network approach to cognitive alignment and trust in human–unmanned ship collision avoidance10.1016/j.oceaneng.2025.122913 ↗
86. Meta-reinforcement learning-based collision avoidance for autonomous ship10.1016/j.oceaneng.2025.122064 ↗
87. Supporting human supervision in autonomous collision avoidance through agent transparency10.1016/j.ssci.2023.106329 ↗
88. COLREG and MASS: Analytical review to identify research trends and gaps in the development of autonomous collision avoidance10.1016/j.oceaneng.2024.117652 ↗
89. Regulatory and legal frameworks recommendations for short sea shipping maritime autonomous surface ships10.1016/j.marpol.2024.106226 ↗