(03)

Science

↓ (W27 ‘26 · Jun 29–Jul 5)
01crossref2026-09-30Zhe Ji, Yingjun Zhang, Jiahui YangDOI ↗ (opens in a new tab)

Research on an energy field model for navigation risk assessment of maritime autonomous surface ships incorporating multi-ship interaction features (opens in a new tab)

This study introduces an energy field model for assessing navigation risks in Maritime Autonomous Surface Ships (MASS), focusing on multi-ship interactions. It quantifies maritime traffic complexity using ship attributes and the Potential Risk Ship Domain (PRSD) framework, then develops a model to capture dynamic interactions between ships. The approach classifies navigation scenarios using the ALARP principle, enabling adaptive operation mode switching. Results show the model effectively identifies risk patterns in high-density traffic, improving MASS safety in complex environments.

02crossref2026-07-01Yifan XuDOI ↗ (opens in a new tab)

Legal Research on the Freedom of Navigation of Maritime Autonomous Surface Ships in the Exclusive Economic Zone (opens in a new tab)

The paper examines legal challenges posed by Maritime Autonomous Surface Ships (MASS) to the freedom of navigation in Exclusive Economic Zones (EEZ) under UNCLOS. It identifies three key issues: weakened flag State jurisdiction, conflicts between navigation freedom and coastal State security, and difficulties in enforcing the "due regard" obligation due to technical limitations. The author argues that China, as a major coastal State, should push for a "systemic jurisdiction" framework, including a navigation notification system and updated interpretations of "due regard." This approach aims to align AI-driven maritime navigation with UNCLOS while protecting national security and marine ecosystems.

03openalex2026-07-01Emre Akyuz, Selcuk Cebi, Agus HasanDOI ↗ (opens in a new tab)

Application of complex spherical fuzzy failure mode, effects, and criticality analysis for assessing potential risk of Maritime Autonomous Surface Ships (MASS) (opens in a new tab)

This study applies complex spherical fuzzy failure mode, effects, and criticality analysis (FMECA) to assess risks in Maritime Autonomous Surface Ships (MASS). The method integrates fuzzy sets to handle uncertainty and interconnected failures in autonomous maritime systems. Expert evaluations, combined using fuzzy aggregation, determined severity, occurrence, and detectability of failure modes, producing a risk priority number (RPN). The highest RPN was assigned to the human-machine interface (HMI), identifying it as the most critical failure mode for MASS operations.

04openalex2026-07-01Manlin Wang, Hongjun Tian, Maoyuan Sun, Yuhan Zhou +10 moreDOI ↗ (opens in a new tab)

Bridging Symmetric Dynamics and Asymmetric Semantic Objectives: Runtime-Assured Predictive Safety Control for Autonomous Surface Vehicles (opens in a new tab)

This paper introduces a predictive safety-control framework for autonomous surface vehicles (ASVs) that reconciles symmetric vessel dynamics with asymmetric collision-avoidance rules like COLREGs. A large language model (LLM) generates and validates structured COLREGs labels to guide asymmetric responsibilities, while a physical safety envelope, built on motion prediction and uncertainty inflation, ensures collision avoidance. A runtime assurance monitor checks semantic validity and solver performance to prevent unsafe decisions. Simulations show the approach improves rule-compliant navigation while reducing overly cautious maneuvers.

06openalex2026-07-03Siddiq Bin Salam, Sajjad Waqar AhmadDOI ↗ (opens in a new tab)

A Multi-Vendor 5G Private Network Framework for Autonomous Port Operations: Realizing Saudi Vision 2030 Smart Logistics Corridors (opens in a new tab)

This paper presents the Hybrid Multi-Vendor Private 5G Blueprint (HMP-5G), a framework designed for Saudi Arabia’s autonomous port operations under Vision 2030. It addresses limitations of current connectivity by ensuring low-latency, high-device-density support for automated vehicles, cranes, and container tracking through a three-layer system: Radio Access, Slicing, and Interoperability. The framework uses a Standalone Non-Public Network (SNPN) with on-site data processing, hard slice isolation via physical resource blocks, and multi-vendor compatibility (Huawei, Ericsson, Nokia) via O-RAN standards. Performance aligns with 3GPP benchmarks, supporting Saudi’s logistics and sustainability goals.

07openalex2026-06-29Xiao Liu, Yong Wu, Cong Wang, Hua DengDOI ↗ (opens in a new tab)

Core Competency Development Pathways for Navigation Technology Students Oriented to the Staged Evolution of Autonomous Navigation in Intelligent Ships (opens in a new tab)

This study identifies five stages of autonomous navigation in intelligent ships, based on IMO and China Classification Society guidelines. It proposes a competency framework for Navigation Technology students, emphasizing skills like smart equipment use, remote control, human-machine collaboration, and data analysis alongside traditional seamanship. The authors recommend updating training objectives, curricula, practical teaching, and assessments to align with these evolving demands. The findings aim to guide educational reforms in navigation programs.

08openalex2026-07-02Ruiheng Jiang, Thomas Bi, Raffaello D’Andrea, Aswin RamachandranDOI ↗ (opens in a new tab)

Cross-Platform Control for Autonomous Surface Vehicles via Adaptive Reinforcement Learning (opens in a new tab)

This paper introduces an adaptive reinforcement learning method for autonomous surface vehicles that allows a single control policy to work across different platforms without prior knowledge of their dynamics. The approach uses a teacher-student architecture to infer platform-specific dynamics from interaction history, enabling zero-shot deployment. Tested on two real-world platforms, the method outperformed non-adaptive baselines by up to 58% in position accuracy while nearing the performance of platform-specific controllers. The policy was trained in simulation with randomized dynamics and required no fine-tuning for real-world use.

09openalex2026-06-30Yanxi Chen, Tianliang Yao, Shaolong Tang, Jiyuan Zhao +4 moreDOI ↗ (opens in a new tab)

Learning Expert Strategy for Autonomous Robotic Endovascular Intervention via Decoupled Procedural Execution (opens in a new tab)

This study introduces a learning-based expert strategy for autonomous robotic endovascular interventions, separating high-level decision-making from low-level execution to improve safety and consistency. The method uses a reinforcement learning policy for navigation intent, refined by an expert-informed module to enforce clinical norms and vessel constraints. Tests in simulations and real-world robotic setups showed a success rate above 96%, a 29.3% reduction in operational steps, and a 13% decrease in trajectory variance. The approach enhances efficiency, predictability, and standardization compared to baseline methods.

10openalex2026-07-01Jingfeng Liu, Runze Mao, Ruihan Chen, Houxiang Zhang +1 moreDOI ↗ (opens in a new tab)

Wind-propelled ships for maritime decarbonization: Technologies, global deployment, and engineering challenges (opens in a new tab)

This paper reviews wind propulsion as a solution for decarbonizing commercial shipping amid stricter regulations. It compiles data on 96 wind-propelled ships (90 still in service by late 2025), analyzing deployment by region, ship type, and propulsion role. Five key wind propulsion systems—Flettner rotors, suction wing sails, rigid wing sails, soft sails, and kite sails—are compared for adoption and integration. Technical challenges like efficiency, safety, and economic viability, along with policy and industry guidance, are also examined.

11openalex2026-06-30G.Yu. Illarionov, Д.Н. МихайловDOI ↗ (opens in a new tab)

Basing options and usage models unmanned boats on surface ships and vessels (opens in a new tab)

The paper explores basing and deployment methods for unmanned surface vehicles (USVs) on ships, relying on foreign media reports. Advances in automatic launch and recovery systems (LARS) enable USV operations, though their development poses technical challenges. Eleven LARS types are discussed, with designs varying by vessel type, USV weight, and placement (deck or hull). The most advanced systems can function in sea conditions up to 6 points on the wave scale.

12openalex2026-07-02Aswin Ramachandran, Christopher Golling, Sebastian Burmester, Noa Sendlhofer +3 moreDOI ↗ (opens in a new tab)

Choreographing the Way of Water: A Computational Framework for Aquatic Robotic Art (opens in a new tab)

This paper introduces a computational framework, *Way of Water*, for choreographing autonomous surface vessels in open water, addressing challenges from nonlinear fluid dynamics. The system includes *Way of Water Studio*, a browser-based tool that allows artists to design music-responsive choreography using a visual timeline and advanced control algorithms. The framework integrates a custom holonomic chassis, real-time state estimation, and LTE/MQTT communication with RTK-GPS synchronization. It was validated through performances at Lake Zurich and the Venice Biennale, demonstrating its potential for robotic aquatic art.

15crossref2026-09-30Haoyang Yu, Xianku Zhang, Haoyun TangDOI ↗ (opens in a new tab)

Toughness strengthening method of course changing control for ships based on nonlinear modification (opens in a new tab)

This study introduces a cyber-resilient ship course control method using a dual-feedback switching system that alternates between positive and negative feedback to counter cyberattacks. The approach converts large-angle collision avoidance into a smaller course deviation problem and employs a second-order gain-shaping algorithm with nonlinear compensation to improve robustness. Simulations on the "Yupeng" vessel showed a 41.7% reduction in actuator amplitude, 33.2% lower rudder frequency, and 18.6% less steering energy use while maintaining course accuracy within 0.8° during attacks. Stability was confirmed through description-function analysis and the Nyquist criterion.

16openalex2026-07-02Daniel G. SchwartzDOI ↗ (opens in a new tab)

Path planning for unmanned naval surface vehicles (opens in a new tab)

Daniel G. Schwartz (2026) presents new methods for unmanned surface vehicles (USVs) to avoid both fixed and moving obstacles. The approach combines a global path planner—using Grassfire, a modified Grassfire, and a new Probabilistic Roadmap variant—with a local planner that adjusts routes based on obstacle movement. The local planner prioritizes routing USVs behind moving obstacles rather than alongside them. Simulations validate the method, comparing it to the D* algorithm and other dynamic path-planning systems.

17crossref2026-09-30Haoyun Tang, Bangchao Fu, Haiyang Guan, Ying Yang +1 moreDOI ↗ (opens in a new tab)

Fault diagnosis and restoration of ship structure monitoring signals based on machine learning (opens in a new tab)

This study proposes a machine learning-based method to diagnose and restore faulty signals in ship structure monitoring systems, combining wavelet transform, IPSO-BP neural networks, CNNs, and adaptive algorithms. Tested on model monitoring data, the method achieved over 98% diagnostic accuracy across different ship positions and outperformed LSTM and Random Forest in noise resistance. It also significantly improved signal restoration, reducing RMSE by up to 75.49% for drift faults compared to traditional methods. The approach aims to enhance the stability and safety of ship structural health monitoring.

19openalex2026-06-30V.V. Knyazhev, V.V. LoshchenkovDOI ↗ (opens in a new tab)

Energy sources for AUV docking charging stations (opens in a new tab)

This paper explores energy sources for AUV docking charging stations to enable long-term autonomous operation. Options include cable lines, nuclear power, hydrogen fuel cells, and renewable sources like wind, wave, solar, and thermal energy. The study estimates parameters for a hydrogen fuel cell system using Russian components and high-pressure gas cylinders. It also calculates the energy and power requirements for charging specific AUV models (MT-2010 and MT-2013) developed by the Institute of Marine Technology Problems.

21openalex2026-06-30Yaqiang Lu, Jipeng Zhang, Chao Song, Fankai Meng +1 moreDOI ↗ (opens in a new tab)

Mission Effectiveness Assessment of Solar-Powered Unmanned Surface Vehicles Considering Hardware States and Energy Levels (opens in a new tab)

This study introduces an enhanced ADC framework to evaluate solar-powered unmanned surface vehicles (USVs), combining hardware conditions and battery energy levels. Using Monte Carlo simulations with real solar data, it models dynamic state transitions and applies a hierarchical CRITIC method for objective performance weighting. A case study found baseline mission effectiveness at 0.661934, with energy dynamics and hardware failures causing overestimations of 38.94% and 9.48%, respectively. Results highlight the need to integrate both energy and hardware states for accurate mission assessments.

23crossref2026-07-03Matt DawsonDOI ↗ (opens in a new tab)

The Autonomous Society Needs Autonomous Individuals (opens in a new tab)

Matt Dawson argues that sociologist Zygmunt Bauman rejected the idea of sociology as a neutral or conservative discipline, instead framing it as a "science of freedom." Bauman emphasized sociological hermeneutics, readability, and tracing individual struggles to changeable social structures. His vision aimed to cultivate autonomous, questioning individuals to build an "autonomous society" where social conditions are seen as fluid, not fixed. Freedom, in Bauman’s view, involves accepting uncertainty and anxiety as part of the human condition.

24openalex2026-07-02Agnes N. Mwange, Taichi Kambara, Kouki Wakita, Kazuyoshi Hosogaya +1 more

Development and Identification of a Linear Low-Speed Ship Maneuvering Model from Full-Scale Data (opens in a new tab)

This study introduces a simplified linear state-space model to represent low-speed ship dynamics, addressing challenges in autonomous berthing and unberthing. The model's parameters were estimated using the Covariance Adaptation Strategy Evolution Strategy (CMA-ES) applied to full-scale maneuvering data. Validation showed the model closely matched empirical data. The findings suggest linear models can effectively capture ship maneuvering at low speeds.

26openalex2026-07-01Ligangao Xu, Qiang Zhang, Guibing Zhu, X X Hu +1 moreDOI ↗ (opens in a new tab)

Global robust adaptive fault-tolerant formation control of unmanned surface vessels with internal/external uncertainties and saturated actuators under deception attacks (opens in a new tab)

No abstract or body text was available, so this entry is reported from metadata only.

27openalex2026-06-29Ismet Gocer, Zakirul Bhuiyan, Shakeel Ahmad, Raza HasanDOI ↗ (opens in a new tab)

AI for Maritime Security: Comparative Evaluation of Convolutional Neural Network and Vision Transformer Architectures for Maritime Object Detection (opens in a new tab)

The study compares Convolutional Neural Network (CNN) and Vision Transformer (ViT) architectures for detecting ships in maritime environments to improve security. It evaluates these AI-based systems for real-time object detection under varying conditions. The research focuses on designing and assessing intelligent detection models to enhance maritime surveillance. No specific performance results or methods beyond the comparison are detailed.

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