(03)

Science

↓ (W17 ‘26 · Apr 20–26)
01crossref2026-04-21Tun Hao Hsu, Hui-Huang TaiDOI ↗ (opens in a new tab)

RECOMMENDED ADJUSTMENTS TO SHIP CREW TRAINING IN PREPARATION FOR LEVEL 2 MARITIME AUTONOMOUS SURFACE SHIP TECHNOLOGIES (opens in a new tab)

This paper examines adjustments needed for ship crew training to prepare for Level 2 Maritime Autonomous Surface Ship (MASS) technologies. Using the decision analytic network process, the study identifies crew competencies as the most critical factor. Recommended training includes monitoring MASS decision-making, integrating software and hardware, and artificial intelligence. The authors also suggest a modular design approach for MASS vessels.

02openalex2026-04-22Achema Iyamadi Timothy, A. A. Obiniyi, J. B. AgbogunDOI ↗ (opens in a new tab)

A Systematic Literature Review of Cybersecurity Risks in Autonomous and Digitalised Maritime Systems (opens in a new tab)

This systematic review examines cybersecurity risks in digitalised and autonomous maritime systems, analyzing 52 studies from 2018–2025. It identifies three key themes: risk assessment frameworks, vulnerabilities in cyber-physical systems, and challenges in human factors, regulations, and validation. The findings highlight the use of hybrid risk models and AI-driven approaches but note gaps in real-world testing, regulatory alignment, and human-centric solutions. The study calls for standardized, empirically validated cybersecurity frameworks and improved maritime-specific training.

03openalex2026-04-24Donglei Yuan, Xianghua Tao, Guanghui Li, Xiaochi Li +3 moreDOI ↗ (opens in a new tab)

A Cross-Control-Logic and Disturbance-Adaptive Line-Adhering Intelligent Navigation Framework for Autonomous Ships (opens in a new tab)

This paper introduces a navigation framework for autonomous ships that improves path-following in curved routes and under wind or current disturbances. It uses a rough-set classifier to detect disturbances and adjusts PID, LQR, and MPC controllers in real time. A Bézier-based method refines paths to match ship maneuvering limits, while Nomoto and MMG models ensure dynamic feasibility. Simulations demonstrate better precision, robustness, and comfort compared to traditional heading-keeping autopilots.

04openalex2026-04-21Takefumi Higaki, Hitoshi Yoshioka, Nobukazu Wakabayashi, Hirotada HashimotoDOI ↗ (opens in a new tab)

Diffusion route planner: Data-driven modeling of human ship navigation that implicitly balances safety, efficiency, and rule compliance under complex geographical constraints (opens in a new tab)

The paper introduces a diffusion route planner (DRP) that models human ship navigation using 181 days of AIS–radar-integrated data from a training ship. In tests, the DRP followed COLREGs Rules 13–17 in one-on-one scenarios and maintained safety margins in complex, multi-ship real-sea conditions. Unlike other data-driven methods, it handled realistic constraints better due to offline training on fused sensor data. The approach also showed potential to incorporate additional rules and local regulations without explicit programming.

05openalex2026-04-21Steven DauerDOI ↗ (opens in a new tab)

Bridging Maritime Autonomy and Certification Through Operational Design Domain Frameworks (opens in a new tab)

The paper by Steven Dauer (2026) addresses certification gaps for Maritime Autonomous Surface Ships (MASS), as current regulations assume human crews. It proposes an Operational Design Domain (ODD) framework to define safe operating limits—such as environmental conditions, sensor reliability, and traffic scenarios—for autonomous vessels in open ocean settings. The framework includes cascade triggers for degraded conditions and a Mandatory Scenario Coverage Matrix to ensure thorough testing. It aligns with Flag State oversight and Classification Society guidelines, offering a structured approach for integrating autonomy into maritime systems.

06crossref2026-04-20Chunyu Song, Xiaomin Guo, Jianghua SuiDOI ↗ (opens in a new tab)

Autonomous berthing path tracking of a 4-DOF ship under nonlinear model predictive control (opens in a new tab)

This study presents a nonlinear model predictive control (NMPC) method for autonomous ship berthing, using a 4-DOF (sway, surge, yaw, roll) dynamic model. The approach integrates moving horizon estimation (MHE) and real-time trajectory optimization to adapt to environmental changes. Simulations in the Port of Hamburg showed track errors under 2 meters and berthing position errors of just 0.3 meters. The method outperforms traditional PID and NMPC controls in rough sea conditions, improving reliability for unmanned ships.

07crossref2026-04-22Rajesh Patil, Magnus LöfstrandDOI ↗ (opens in a new tab)

A Safety-Constrained Multi-Objective Optimization Framework for Autonomous Mining Systems: Statistical Validation in Surface and Underground Environments (opens in a new tab)

This paper presents a unified, safety-constrained optimization framework for autonomous mining systems, integrating sensor fusion, edge intelligence, and digital twin-based decision support for surface and underground environments. The approach uses mathematical modeling and multi-objective optimization to improve vehicle dynamics, drilling mechanics, and fleet coordination under GNSS-denied and extreme Nordic conditions. Validation through Monte Carlo simulations and statistical testing showed productivity gains of ~24.3%, energy reductions of ~12.8%, and safety risk decreases of ~48.6% compared to baseline systems. Key performance drivers identified include localization accuracy, communication delay, and optimization weighting.

08crossref2026-04-21Ruoyun Huang, Xiang Zheng, Jianhua Wang, Gongxing Wu +2 moreDOI ↗ (opens in a new tab)

Nighttime Encounter Situation Recognition for Unmanned Surface Vessels Based on Images of Vessel Navigation Lights (opens in a new tab)

This study introduces an image-based method to recognize nighttime encounter situations for unmanned surface vessels (USVs) by analyzing vessel navigation lights. A 3D model of navigation lights and encounter scenarios was created following COLREGs, and a dataset was generated through simulations. The method extracts features from navigation-light images and achieves classification accuracies of 96.6%–98.3% in simulations. Field tests with a small USV demonstrated 96.2% accuracy for light recognition and 94.94% for encounter situation recognition.

09openalex2026-04-23Silvia Carpitella, Antonella Certa, Cinzia Muriana, Costanza Laura ParlapianoDOI ↗ (opens in a new tab)

Decision-making tools enabling sustainable maintenance strategies of naval systems: a comparison of multi-criteria approaches (opens in a new tab)

This study compares multi-criteria decision-making tools to prioritize failure modes in naval systems for sustainable maintenance. It applies the Analytic Hierarchy Process (AHP) alone and combined with ELECTRE I to rank failure modes using criteria like Severity, Occurrence, Detection, Economic Factor, Sustainability Maintenance Strategies, and Management and Data Security. The top-ranked failure modes from both methods are compared to identify similarities and differences. A sensitivity analysis assesses the robustness of the results.

10crossref2026-04-20Thomas MüllerDOI ↗ (opens in a new tab)

SafeNav: A Safety-Constrained Reinforcement Learning Framework for Autonomous Mobile Robot Navigation with Collision-Aware Path Planning (opens in a new tab)

SafeNav is a reinforcement learning framework for autonomous mobile robots that combines a collision-aware A* path planner with a PPO-based velocity controller, linked by a safety filter using Control Barrier Functions. The system extends existing methods to handle dynamic obstacles and includes safety enhancements like a guided entropy schedule and Lagrangian constraints to limit safety violations. In 1,800 simulation trials, SafeNav achieved a 95.8% navigation success rate at 20% obstacle density, a 0.48% safety violation rate, and a 31.4% reduction in path length compared to baselines. The framework aims to improve safety, efficiency, and real-world applicability in industrial environments.

11crossref2026-04-24Alaa Khalifa, Keir Groves, Joaquin CarrascoDOI ↗ (opens in a new tab)

Development of a tendon-driven serial manipulator for an aquatic autonomous surface vehicle (opens in a new tab)

This paper presents a 2-DOF tendon-driven manipulator for aquatic Autonomous Surface Vehicles (ASVs), such as the MallARD platform, to expand their operational range for both underwater and surface tasks. The design places actuators above the waterline, using wires to power the joints, allowing operation in high-radiation environments, handling heavy payloads, and resisting water exposure. A real-world prototype was built and tested, demonstrating feasibility with joint angle errors below 2.1° RMS. The inverse kinematics were solved analytically, and experimental results confirm its potential for underwater applications.

12crossref2026-04-22Artem Holovan, Vytautas Dubra, Andrii HolovanDOI ↗ (opens in a new tab)

Augmented Reality in Maritime Navigation: Future Solutions for Young Navigators (opens in a new tab)

This study explores how augmented reality (AR) can be integrated into maritime navigation to assist young navigators. Based on a review of existing research, AR improves situational awareness by displaying navigational data directly in the user’s field of view, reducing distractions and aiding performance in low-visibility or high-traffic scenarios. It also supports team decision-making through real-time, context-aware information sharing. However, its effectiveness depends on well-designed interfaces and proper training.

13openalex2026-04-21Alex Beaudin, Bjørn Andreas Kristiansen, Kristoffer Gryte, Corrado Chiatante +3 moreDOI ↗ (opens in a new tab)

Multi-Step Gaussian Process Propagation for Adaptive Path Planning (opens in a new tab)

This paper introduces OLAhGP, a Gaussian process-based path planning method for robotic environmental monitoring that adapts to multi-modal sensing data while incorporating constraints. The approach optimizes future waypoints in a receding horizon framework, using the Gaussian process posterior to guide decisions. Tested on an autonomous surface vessel with oceanic algal bloom data, it outperforms existing methods by improving path informativeness and reducing misclassification errors in chlorophyll-rich waters. Results show better accuracy in bloom detection with the same number of samples.

14openalex2026-04-24Ahmetcan Önal, Andaç Töre ŞamiloğluDOI ↗ (opens in a new tab)

Adaptive Data-Driven Control of Autonomous Underwater Vehicles: Bridging the Gap Between Simulation and Experimental Baseline via LSTM-MPC (opens in a new tab)

This study introduces an LSTM-MPC control framework to improve velocity stabilization in Autonomous Underwater Vehicles (AUVs) under unpredictable marine conditions. The approach uses an LSTM neural network to predict velocity and integrates it with Model Predictive Control (MPC) to optimize performance while accounting for actuator limits. An online learning mechanism allows real-time adaptation to disturbances and sensor noise without relying on analytical models. Experimental results show the method outperforms PID-based controls, reducing tracking errors in rotational axes while maintaining precision in translational movements.

15crossref2026-04-20Nini Zhang, Weikai Tan, Ran Yan, Sudong Xu +2 moreDOI ↗ (opens in a new tab)

Advanced prediction of maritime vessel traffic flow using spatio-temporal multi-graph convolutional networks within inland waterways (opens in a new tab)

This study introduces a deep-learning model combining multi-graph convolutional networks and gated recurrent units to predict maritime vessel traffic flow in inland waterways. The approach uses three unstructured graphs to capture spatio-temporal relationships between traffic locations, improving feature extraction. Tested on two real-world datasets, the model outperformed conventional methods in both regional and station-based predictions. The results suggest enhanced accuracy and reliability for waterway management and lock scheduling.

16openalex2026-04-23Goran Vojković, Melita Milenković, Lea Vojković, Toni MeštrovićDOI ↗ (opens in a new tab)

Recommendations for the Development of a Legal Framework for Remote Piloting (opens in a new tab)

This paper examines the need for a legal framework to govern remote piloting, where sea pilots assist vessels from mainland locations using live-streaming technology. It highlights cost benefits but stresses the importance of clear regulations to define the pilot’s role, responsibilities, and duty boundaries. Without international standardization, legal challenges may hinder remote pilotage adoption. The authors outline key tasks for developing these regulations.

17openalex2026-04-25Yong ChenDOI ↗ (opens in a new tab)

Simulated Marine Environment Maps for USV Path Planning Experiments (opens in a new tab)

This paper provides three simulated marine environment maps for testing unmanned surface vessel (USV) path-planning methods. The maps feature varied obstacle layouts and were used to compare RRT*, Dubins-RRT*, and the proposed VR-LSRS-RRT* algorithm. Performance was measured in solution time, path length, smoothness, convergence, and tracking accuracy. The files are shared to ensure reproducibility of the study’s simulation conditions.

18openalex2026-04-23Minhazul Arefin, Xia Feng, Hongsheng HeDOI ↗ (opens in a new tab)

ezTwin: A Scalable Framework for Rapid Building Digital Twin for Hydro-Informatics (opens in a new tab)

The *ezTwin* framework enables rapid creation of hydrologic digital twins using minimal geospatial inputs like reservoir coordinates and river centerlines. It generates 3D geo-registered scenes in Unreal Engine with Cesium-based Google 3D Tiles, displaying live water levels and river bathymetry variations. The system integrates an unmanned surface vessel to collect real-time sonar depth data, refining the twin’s mesh and dynamically adjusting survey routes to reduce uncertainty. This approach simplifies deployment, supports flood scenario planning, and ensures real-time synchronization with physical conditions.

19crossref2026-04-21LAMPROS NIKOLOPOULOS, Evangelos BoulougourisDOI ↗ (opens in a new tab)

A ROBUST HOLISTIC OPTIMIZATION SHIP DESIGN APPROACH WITH VOYAGE SIMULATION PRINCIPLES AND ITS APPLICATIONS (opens in a new tab)

The paper introduces the Robust Holistic Optimisation Ship Design Approach (RHODA), a novel framework for designing large commercial vessels like bulkers and tankers. RHODA integrates voyage simulation with uncertainties in voyage, environmental, market, and methodological factors to improve early-stage decision-making. It systematically explores multi-variable, multi-objective design options to address IMO decarbonization goals and market volatility. A case study demonstrates its advantages over deterministic approaches for bulk carrier design.

20openalex2026-04-24Tingyun Li, Jianwei HuangDOI ↗ (opens in a new tab)

Distributed intelligent monitoring network system for ship engine room automation based on FCS (opens in a new tab)

This paper presents a ship engine room monitoring system based on Field Control System (FCS) that is open, decentralized, and integrated using computer networks and fieldbuses. It introduces a network controller as a field data collector to standardize shared data and improve interaction interfaces for engine room monitoring. The system aims to enable comprehensive, intelligent management of ships while supporting seamless integration with shore-based information systems. The design addresses big data-era demands in shipping technology applications.

21crossref2026-04-23Junfu Yuan, Haijun Wei, Chen LiDOI ↗ (opens in a new tab)

Numerical Investigation of Aerodynamic Characteristics of Biomimetic Wingsails for Unmanned Surface Vehicles (opens in a new tab)

This study numerically analyzed the aerodynamic performance of four biomimetic wingsails—modeled after owl, merganser, seagull, and teal wings—for unmanned surface vehicles (USVs). Using the SST k-ω turbulence model, researchers found the merganser airfoil achieved the highest lift coefficient (3.21) across angles of attack from 0° to 60°, followed by the seagull airfoil, while the teal airfoil performed weakest. Flow separation and trailing-edge vortices, particularly in the merganser design, were observed to impact lift by causing unsteady backflow on the suction surface. The findings offer guidance for selecting efficient wingsail designs for USVs.

22crossref2026-04-23Mevni PiyarisiDOI ↗ (opens in a new tab)

Incentives in decentralised autonomous organisations (opens in a new tab)

The paper explores how competitive incentives in decentralised autonomous organisations (DAOs) affect member effort and overall success. It offers practical insights for those designing incentive structures in such organisations. The study focuses on the relationship between incentives and performance outcomes. Findings are intended to guide practitioners in optimising DAO governance.

23openalex2026-04-22Harry Robertshaw, Nikola Fischer, Han‐Ru Wu, Andrea Walker Perez +5 more

Toward Safe Autonomous Robotic Endovascular Interventions using World Models (opens in a new tab)

This study explores a world-model-based reinforcement learning (RL) framework, TD-MPC2, for autonomous endovascular navigation in mechanical thrombectomy. Tested on diverse patient anatomies in simulations, TD-MPC2 outperformed the Soft Actor-Critic (SAC) algorithm with a 58% success rate (vs. 36%) and lower vessel contact forces (0.15 N). In vitro experiments using patient-specific phantoms showed comparable success rates (68% vs. 60%) but better path efficiency for TD-MPC2, though with longer procedure times. The results demonstrate the potential of world models for safer and more adaptable AI-driven endovascular interventions.

24crossref2026-04-20Zhenbin Li, Xinzong Zeng, Linkun Chen, Xiangwei Li +1 moreDOI ↗ (opens in a new tab)

Towards the Era of Autonomous Network (opens in a new tab)

This paper explores IP autonomous driving network (ADN) technology, addressing challenges in IP transport networks and their evolution. It outlines the concept of IP ADN, reviews its application in transport networks, and analyzes the network management lifecycle during operations and maintenance (O&M). The authors discuss interactions among engineers, devices, and systems while proposing architectural solutions. The book targets professionals, designers, developers, and researchers in IP networking and data communications.

© 2026 Ship Autonomy · Summaries are AI-generated; articles belong to their publishers · Privacy · Contact