(03)

Science

↓ (W14 ‘26 · Mar 30–Apr 5)
01openalex2026-03-30S. Sun, Liangbin Zhao, Ming Deng, Xiuju FuDOI ↗ (opens in a new tab)

From Vessel Trajectories to Safety-Critical Encounter Scenarios: A Generative AI Framework for Autonomous Ship Digital Testing (opens in a new tab)

The paper introduces a generative AI framework that converts real-world ship trajectories from AIS data into realistic safety-critical encounter scenarios for testing autonomous maritime navigation systems. It uses a multi-scale temporal variational autoencoder to improve trajectory realism and robustness, even with noisy AIS data. The method enables scalable generation of diverse high-risk scenarios beyond historical records, supporting digital testing and safety assessments. Code for the framework is publicly available.

02crossref2026-03-30Van Truong Nguyen, Xuan Long Nguyen, Dang Thai Vu, Hanh Hoang Thi HongDOI ↗ (opens in a new tab)

Legal Challenges of Maritime Autonomous Surface Ships: A Comparative Study of Neighboring States and Implications for Vietnam (opens in a new tab)

The study examines legal challenges posed by Maritime Autonomous Surface Ships (MASS), highlighting benefits and unresolved issues. It reviews regional policies, including standards, test areas, and sandboxes, from neighboring countries, while assessing the adequacy of international conventions. Recommendations are provided for Vietnam and other ASEAN nations to expedite MASS regulation development and testing strategies. The paper also stresses the importance of enhanced regional cooperation in ASEAN.

03crossref2026-06-30Xiaohui Wang, Yingjun Zhang, Shaobo Wang, Zhiyuan JiangDOI ↗ (opens in a new tab)

A negotiation method for cooperative collision avoidance between ships in mixed navigation scenarios: model construction, strategy driving, and unilateral learning (opens in a new tab)

The study introduces a bilateral negotiation model to enable autonomous and conventional ships to coordinate collision avoidance in mixed navigation scenarios. Using the Zeuthen strategy for bargaining and unilateral Bayesian learning for information estimation, the method improves negotiation efficiency with minimal data exchange from conventional ships. Simulation results show it resolves uncoordinated encounters, reduces unnecessary evasive maneuvers by autonomous ships, and enhances navigational safety. The approach addresses gaps in collaborative collision avoidance for heterogeneous fleets.

04crossref2026-03-30Junwei Dong, Ze Sun, Peng Zhang, Jiale Zhang +2 moreDOI ↗ (opens in a new tab)

Research on Autonomous Ship Route Planning Based on Time-Dynamic Theta* Algorithm Under Complex and Extreme Sea Conditions (opens in a new tab)

The study introduces a Time-Dynamic Theta* (TDM-Theta*) algorithm to improve autonomous ship route planning in complex and extreme sea conditions. The method combines traditional any-angle path planning with a temporal dimension and incorporates real-time significant wave height as a dynamic constraint. Simulation tests across nine cases showed the algorithm efficiently generates optimal paths in static terrains and achieves 100% proactive risk avoidance in extreme weather scenarios with multiple typhoons, with minimal computational overhead. The research supports real-time safe route decision-making for intelligent ships in volatile maritime environments.

05crossref2026-06-30Jae-Yong Lee, Ho Namgung, Joo-Sung KimDOI ↗ (opens in a new tab)

Development of collision-case-based testing scenarios for validating autonomous ship collision-avoidance algorithms (opens in a new tab)

This study introduces a framework for creating realistic collision-avoidance testing scenarios for autonomous ships by analyzing actual collision cases. The framework involves collecting collision data, extracting ship trajectories, and developing diverse encounter situations by adjusting ship roles and positions. The resulting scenarios reflect real-world complexities, such as rule violations, dynamic encounters, speed changes, and environmental factors. These scenarios aim to improve the validation of collision-avoidance algorithms and enhance maritime safety.

06openalex2026-03-31Dwitya Harits Waskito, Rafet Emek Kurt, Osman TuranDOI ↗ (opens in a new tab)

Comprehensive literature review of systemic safety analysis: trends and development in the maritime sector☆ (opens in a new tab)

This study reviews system-theoretic safety approaches (STAMP, STPA, CAST) in the maritime sector using a hybrid methodology combining PRISMA, bibliometrics, and scoping. STPA is identified as the dominant method, particularly for Maritime Autonomous Surface Ships (MASS) and remote operations. Key gaps include limited validation, inconsistent loss scenario treatment, and weak integration of human and organizational factors. The review of 76 papers (2015–2024) highlights STPA’s growing use and its integration with quantitative methods like QRA.

08crossref2026-03-30Jianan Luo, Zhichen Liu, Haifeng Tang, Chenchen Jiao +2 moreDOI ↗ (opens in a new tab)

A High-Density Bathymetric Data Model and System Construction Approach Integrated with S-100 for Unmanned Surface Vessel Intelligent Navigation (opens in a new tab)

The study introduces a new method for modeling and managing high-density bathymetric data using the S-100 framework, specifically the IHO S-102 standard. It employs a relational database and a three-level indexing system to organize and retrieve data efficiently throughout its lifecycle. The approach includes convex hull-based geometric constraints for interpolating water depth data and an HDF5-based storage model with block storage and version control, reducing storage space by 83.6%. Field tests in the East China Sea confirmed the generated S-102 data met international standards and achieved high terrain restoration accuracy.

10crossref2026-03-30Jinwu Tong, Xin Zhang, Xinyun Lu, Han Cao +2 moreDOI ↗ (opens in a new tab)

Lightweight Visual Localization of Steel Surface Defects for Autonomous Inspection Robots Based on Improved YOLOv10n (opens in a new tab)

**Summary:** This paper introduces KDM-YOLO, a lightweight visual localization method for detecting steel surface defects, built on YOLOv10n. The approach improves feature extraction, context modeling, and multi-scale fusion using KWConv, C2f-DRB, and an MSAF module. Results show Precision, Recall, and mAP@50 of 91.0%, 93.9%, and 95.4%, with 3.29M parameters and 155.6 f/s inference speed.

11openalex2026-04-03Muhammad Ilham Fahreza, Enna Hirata, Kazuhiko ISHIGURO, Kevin X. LiDOI ↗ (opens in a new tab)

Data-driven risk mitigation of Southeast Asian maritime security (opens in a new tab)

The study introduces a data-driven framework combining Bayesian networks (BN) and TOPSIS to analyze and mitigate piracy risks in the Strait of Malacca. Key risk factors like "ship area boarded" and "crew response" were identified, with ship-level interventions proving more effective than broader measures like joint patrols. Despite existing measures, the model estimates a 57% probability of successful piracy, underscoring the need for improved strategies. The framework offers policymakers a quantitative tool for prioritizing anti-piracy actions, though it currently excludes socio-political factors and is tailored to Southeast Asia.

12openalex2026-03-31Ali Khumaidi, Ridwan Raafi'udin, Nusa Setiani Triastuti, Linda MarlindaDOI ↗ (opens in a new tab)

Ensemble-Based Machine Learning with PSO and GA for Ship Coating Detection Using Portable Vis/NIR (opens in a new tab)

This study introduces a method for detecting ship coating quality using portable Vis/NIR spectroscopy and machine learning. The approach combines spectral transformation (Nippy) with feature selection techniques (PSO and GA) and ensemble learning models. Results indicate that the proposed method outperforms single baseline models and traditional feature selection methods, achieving 99.33% accuracy with LDA when using Nippy and PSO. The ensemble models maintained stable performance across different preprocessing and feature selection stages.

13crossref2026-03-31Yu-Zhu Xiang, Zhengrong XiangDOI ↗ (opens in a new tab)

Game-Based Adversarial Control for Unmanned Surface Vessels via Fully Actuated System Approach (opens in a new tab)

The paper presents a zero-sum game-based adversarial control method for unmanned surface vessels (USVs) using a fully actuated system approach (FASA) to handle disturbances. A reinforcement learning algorithm with an actor-critic architecture and policy iteration is introduced, eliminating the need for precise system dynamics through off-policy learning with neural networks. The study shows that the evaluation function converges toward optimality while neural network weights remain bounded. Simulation results validate the effectiveness of the proposed approach.

14crossref2026-03-31Nazreen Rusli, Zulkifli Zainal Abidin, Muhammad Aiman Norazuddin, Taufik YunaharDOI ↗ (opens in a new tab)

An Integrated Controller System For Unmanned Surface Vehicles (USV) (opens in a new tab)

Nazreen Rusli, Zulkifli Zainal Abidin, Muhammad Aiman Norazuddin, and Taufik Yunahar (2026) present an integrated controller system for Unmanned Surface Vehicles (USVs), designed to enhance maritime operations in environmental monitoring, resource exploration, and security. The "CxSense" controller, developed by IIUM’s Centre for Unmanned Technologies and Prostrain Technologies, meets high industry standards (IPx8, ESD, and vibration tests) for robustness and reliability. Battery-powered USVs, like those using CxSense, reduce environmental impact by eliminating direct water pollutants compared to traditional fuel-powered vessels. The system aims to improve maritime safety, efficiency, and sustainability in Malaysia and neighboring regions.

15crossref2026-03-31Konstantin Prostakevich, Igor' Sikarev, Igor' Yurin, Yuriy Kozlov +1 moreDOI ↗ (opens in a new tab)

Conceptualization of information and communication system development for remotely operated maritime transport in Arctic region (opens in a new tab)

The study by Prostakevich et al. (2026) outlines strategic directions for developing information and communication systems for remotely operated Arctic maritime transport, focusing on information security. Using methods like foresight technologies and OSINT, the authors propose signal-relay architectures to maintain connectivity between vessels and remote control centers amid information threats. The research highlights practical recommendations for implementing these communication systems in Arctic conditions.

16crossref2026-03-30C. J. BerryDOI ↗ (opens in a new tab)

Powering Change: Electrically Operated Subsea Safety Module for Future Well Intervention (opens in a new tab)

This paper discusses the need for hydraulic intervention in oil and gas wells, which uses chemicals or fluids under pressure for maintenance, remediation, or stimulation. It highlights the challenges of delivering fluids to subsea wells, requiring dedicated intervention vessels with remotely operated vehicles (ROVs) and specialized equipment like a subsea safety module (SSM). The SSM, as per API recommended practice 17G2, provides isolation valves, downline connection points, and an injection connection point for safe well intervention. Fluids can be injected at various locations, such as the subsea Christmas Tree or retrievable choke, depending on access availability.

21openalex2026-04-03大月 智史, S. Otsuki, 八田 直樹, N. Hatta +7 more

Hierarchical Vessel Safe Operation in A Port through CBF, MPC and RRT-like Spatiotemporal Path Planning (opens in a new tab)

This paper presents a hierarchical framework for ensuring safe vessel operations in ports using Control Barrier Functions (CBF), Model Predictive Control (MPC), and a Rapidly-exploring Random Tree (RRT)-like spatiotemporal path planning method. The approach integrates real-time collision avoidance and optimal trajectory planning to enhance navigation safety. The authors demonstrate the system's effectiveness through simulations and experiments in port environments. The proposed method aims to reduce risks and improve operational efficiency for autonomous or semi-autonomous vessels.

22openalex2026-04-02Jiyong Kwon, Ujin Jeon, Sooji Lee, Guang Lin

AIVV: Neuro-Symbolic LLM Agent-Integrated Verification and Validation for Trustworthy Autonomous Systems (opens in a new tab)

AIVV introduces a hybrid framework using Large Language Models (LLMs) to automate Verification and Validation (V&V) for autonomous systems. It addresses limitations of deep learning models in anomaly classification by deploying a role-specialized LLM council to collaboratively validate faults and assess system responses against natural-language requirements. The framework generates actionable V&V artifacts, such as gain-tuning proposals, and was tested successfully on a time-series simulator for Unmanned Underwater Vehicles (UUVs). AIVV aims to replace manual Human-in-the-Loop (HITL) processes, offering a scalable solution for system oversight.

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