(03)

Science

↓ (W34 ‘26 · Aug 17–23)
01openalex2026-08-19P. Maes, Erin R. McMahon, Doreen Jirak, Dirk van Rooy +4 moreDOI ↗ (opens in a new tab)

Towards Human Factors Evaluation of Interactions with Maritime Autonomous Surface Ships Using Full Mission Bridge Simulators: The Conventional Officer’s Perspective (opens in a new tab)

This study examines how Maritime Autonomous Surface Ships (MASS) interact with crewed vessels, focusing on the challenges faced by conventional Officers of the Watch (OOW) during collision avoidance. It introduces a framework analyzing situational awareness, mental models, and decision-making in mixed-traffic scenarios. Key issues include communication gaps, uncertainty about MASS capabilities, and trust in autonomous systems. The paper proposes using Full Mission Bridge Simulators to study OOW behavior and decision-making in these encounters.

02openalex2026-08-19Gülşah Demirhan AydınDOI ↗ (opens in a new tab)

PERFORMANCE EVALUATION OF MEMS INERTIAL SENSORS FOR AUTONOMOUS NAVAL PLATFORMS (opens in a new tab)

This study assesses MEMS inertial sensors for autonomous naval platforms, comparing low-cost and tactical-grade sensors under calm and rough sea conditions. Low-cost sensors show rapid error growth without external aiding, while tactical-grade sensors offer better stability. An Extended Kalman Filter (EKF) reduces drift by 60–80% when combined with periodic GNSS updates. Performance declines in high sea states due to increased noise and nonlinear motion.

03openalex2026-08-19Sung‐Jo Yun, Hyogon Kim, Ji‐Wook Kwon, Young‐Ho Choi +4 moreDOI ↗ (opens in a new tab)

Safety-Enhanced COLREGs-Compliant Path Planning for USVs with a CBF-Based Safety Shield (opens in a new tab)

This study introduces a path planning system for Unmanned Surface Vehicles (USVs) combining Deep Reinforcement Learning (DRL) with a Control Barrier Function (CBF)-based Safety Shield to prevent collisions and comply with maritime navigation rules (COLREGs). The system uses real-time encounter classification and a CBF-QP optimization layer to filter unsafe DRL control inputs, incorporating safety radii and COLREGs constraints. A "Shielded Training" mechanism reduces reliance on the safety filter by penalizing interventions during training. Simulations show the method lowers collision and COLREGs violation rates while maintaining real-time performance.

04openalex2026-08-18Hyuk-Cheon Kwon, Won‐Sun Ruy, Yun Hwang, Hyuk Lee +2 moreDOI ↗ (opens in a new tab)

Multi-Spectral Sensor Fusion with LiDAR Projection for Autonomous Fire Detection in Shipboard Environments (opens in a new tab)

This study presents a fire detection system for autonomous ships using a four-channel model combining RGB, infrared (IR), and ultraviolet (UV) sensors with LiDAR for localization. The system uses an Xception-based network for RGB+UV images and a dense-based network for UV time-series data, reducing false alarms from fire-like sources like welding. A YOLOv7 model with LiDAR projection improved fire source localization accuracy over traditional triangulation methods. Tests in open and occluded environments confirmed the system's effectiveness.

05openalex2026-08-17Xinjian WangDOI ↗ (opens in a new tab)

Advancements in Maritime Safety and Risk Assessment (opens in a new tab)

The paper discusses the growing importance of maritime safety and risk assessment due to trends like larger vessels, busier shipping routes, and the adoption of cleaner fuels and autonomous navigation. It highlights the shift toward data-driven decision support systems in the industry. The focus is on addressing emerging challenges in safety and risk management. The work reflects advancements in response to evolving maritime operations.

06openalex2026-08-21Monocola (モノコーラ)DOI ↗ (opens in a new tab)

Project Will: Observations #2–#3 — 32 autonomous LLM villagers with integrated memory, no institutions (opens in a new tab)

Project Will Observations #2 and #3 involved 32 autonomous LLM villagers with integrated memory (NOESIS) operating without institutions for two 6-hour runs. The experiments generated 51,390 structured events, 10,684 utterances, 401 dreams, and 151 sign texts. All major claims were independently verified, with 151 confirmed, 45 revised, and 19 refuted. The full verification ledger and datasets are publicly available, building on the author’s prior Observation #1.

07openalex2026-08-20SuhartiniDOI ↗ (opens in a new tab)

Ethical Dimensions of Human-AI Interaction in Maritime Decision-Making: An Expert Perspective (opens in a new tab)

This study explores ethical concerns in human-AI interactions within maritime decision-making, based on focus groups with 30 experts from port management, nautical, and marine engineering fields. Key themes identified include trust in AI, accountability gaps, human override practices, and generational differences in ethical perspectives. Deck Nautical experts prioritized human control, while port management experts were more accepting of AI support. Experts agreed that younger, digitally native professionals may shift away from human-primacy values, posing unprepared institutional challenges.

08openalex2026-08-18Ellen Bjørge Ekse, Bjarne Pareliussen, Victor OwolojaDOI ↗ (opens in a new tab)

A state-of-the-art review on crew competence in maritime and nuclear remote operations (opens in a new tab)

This paper reviews crew competence in remote maritime and nuclear operations, focusing on small modular reactor (SMR) propulsion for ships to cut greenhouse gas emissions. It examines how operator competence is understood in both fields, finding maritime research prioritizes functional and cognitive skills, while nuclear studies stress social competence. The study uses a scoping and systematic literature review to identify gaps in competency requirements for SMR-powered shipping. Findings suggest a need for a holistic, practice-based approach to competence in future remote operations.

09openalex2026-08-19Beibei Chen, Ping Sun, Zhonghao Jiang, Haodong Xu +1 moreDOI ↗ (opens in a new tab)

Configuration strategy for unmanned surface vehicle coordinated defense system based on particle swarm optimization (opens in a new tab)

This paper presents a Particle Swarm Optimization (PSO)-based strategy for optimizing the defensive deployment of Unmanned Surface Vessels (USVs) in maritime environments. It introduces a joint optimization metric combining area and perimeter coverage of fire ranges, accounting for varying attack speeds and detection radii. Compared to Monte Carlo search, Genetic Algorithm (GA), and Grey Wolf Optimizer (GWO), PSO demonstrated competitive coverage performance with faster computation and simpler implementation. The approach balances solution quality, efficiency, and practicality for coordinated defense in complex scenarios.

10openalex2026-08-20Changyu LeeDOI ↗ (opens in a new tab)

Multimodal Trajectory Planning for Surface Vehicles using Turning Circle-based Control Barrier Functions (opens in a new tab)

This paper introduces a trajectory planning method for autonomous surface vehicles that doesn’t rely on pre-set guide paths. It combines model predictive control (MPC) with a turning circle-based control barrier function (TC-CBF), which considers the vehicle’s turning ability and nonholonomic motion. The approach creates distinct left- and right-turning avoidance modes, improving success rates and reducing safety violations in dynamic environments. Simulations show it outperforms single-mode methods in traffic-heavy scenarios.

11openalex2026-08-17Jianqiang Shi, Sicheng Guo, Zhaokun Wang, Han Liang +3 moreDOI ↗ (opens in a new tab)

Auto-Berthing Control of Marine Vessels Under Cyber Attacks (opens in a new tab)

This paper presents an adaptive neural-network-based control method for unmanned surface vessels during automatic berthing under cyber attacks. It addresses unknown vessel dynamics, external disturbances, measurement noise, and cyber attacks using a unified nonlinear measurement model to handle signal distortions. The approach reconstructs vessel heading from unaffected yaw-rate data, employs neural networks to approximate dynamics, and uses adaptive laws to estimate uncertainties. Simulations demonstrate the method's effectiveness in maintaining bounded signals and reducing berthing tracking errors despite time-varying attacks and disturbances.

12openalex2026-08-19Ryan Cardwell, ClaudeDOI ↗ (opens in a new tab)

Multipartite Operational Identifiability of Tensor Product Structures (opens in a new tab)

This paper extends quantum device certification theory from two-part to multi-part systems. It introduces a single formula to quantify distortions in unentangled states for any subsystem division, revealing direction-dependent rigidity in multi-part systems. The study provides closed-form diagnostic tools, demonstrates per-node certification requirements, and shows how weak sectors can blind entire devices. All findings are pre-registered, validated with exact witnesses, and supported by open-source code and data.

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