(03)

Science

↓ (W16 ‘26 · Apr 13–19)
01crossref2026-04-17Chien-Chang Chou, Miao-Ying Chen, Ren-Jun Huang, Hsien‐Pin Hsu +2 moreDOI ↗ (opens in a new tab)

Integrating Qualitative AHP and Quantitative AIS to Berth Location Selection for Maritime Autonomous Surface Ship Mooring at the Kaohsiung Port (opens in a new tab)

This study evaluates berth locations at Kaohsiung Port for mooring Maritime Autonomous Surface Ships (MASS) by combining expert input with a two-step method: the qualitative Analytic Hierarchy Process (AHP) and quantitative Automatic Identification System (AIS). Researchers identified three key assessment aspects, nine criteria, and three potential berth alternatives. The analysis determined that the 7th Container Centre is the most suitable berth for MASS mooring. Findings aim to guide port authorities and operators in transitioning to intelligent port infrastructure.

02crossref2026-04-19Konstantinos Voutzoulidis, Ioannis TigkasDOI ↗ (opens in a new tab)

A Parallel STPA–FTA Risk Assessment Framework for Maritime Autonomous Surface Ships: Development and Case Study Application (opens in a new tab)

This paper presents a combined risk assessment framework for Maritime Autonomous Surface Ships (MASS) that merges System-Theoretic Process Analysis (STPA) and Fault Tree Analysis (FTA). The approach runs both methods in parallel within a shared system architecture to link hazards, unsafe actions, and failure events. A case study of a semi-autonomous freight vessel in the North Sea highlights risks like perception errors, communication failures, and collision misjudgments. The framework aims to improve safety assessments by connecting systemic control issues to accident pathways.

03crossref2026-04-14Chen-Wei Chen, Jiahao Yin, Jialin Lu, Chin-Yin Chen +2 moreDOI ↗ (opens in a new tab)

Dynamic Trajectory Tracking and Autonomous Berthing Control of a Container Ship Based on Four-Quadrant Hydrodynamics (opens in a new tab)

This paper introduces an autonomous berthing control system for large container ships, addressing nonlinear hydrodynamics and maneuvering challenges in restricted waters. It uses a four-quadrant propeller model within an improved MMG framework and a dynamic line-of-sight guidance system paired with PD/PI controllers. Validation against S-175 ship data showed errors under 15%, while simulations for the B-573 ship at Yangshan Port demonstrated a 62% reduction in trajectory error under strong currents. The system achieved smooth deceleration from 6.4 m/s to a full stop in 588 seconds, confirming its feasibility in complex maritime conditions.

04openalex2026-04-07Wahidul Sheikh SheikhDOI ↗ (opens in a new tab)

Evidence-Unit Mapping (EUM) Database of MASS Safety and Economic Performance Claims (2017–2026) (opens in a new tab)

The **Evidence-Unit Mapping (EUM) Database** breaks down 67 studies on Maritime Autonomous Surface Ships (MASS) into 158 specific safety and economic performance claims. It categorizes data by IMO autonomy levels (DoA 1–4), focus areas, and research methods (quantitative, qualitative, or review). Each claim is assigned a binary or weighted impact score (-1, 0, +1) for safety and cost-efficiency. The dataset includes source references, thematic metadata, and direct quotes from the original studies to justify scoring.

05crossref2026-04-18Helmy M. El Zoghby, Soliman M. Sharaf, Ahmed F. Bendary, Ahmed HessienDOI ↗ (opens in a new tab)

Enhanced trajectory tracking for autonomous navigation of wheeled mobile robots using an adaptive fuzzy PID controller (opens in a new tab)

This paper introduces an adaptive fuzzy PID controller to improve trajectory tracking in wheeled mobile robots (WMRs) operating in unstructured environments. The controller addresses challenges like nonlinear dynamics, wheel slips, actuator noise, and external disturbances using a cascaded structure with real-time parameter adaptation. Simulations on complex lemniscate curves show reduced RMS tracking error compared to conventional PID and adaptive dynamic control methods. The approach demonstrates robustness against parameter variations and disturbances while maintaining computational efficiency for real-time applications.

06openalex2026-04-16Xinjie Han, Qi Han, Yunsheng Fan, Dongdong MuDOI ↗ (opens in a new tab)

MAAT: A Marine-Aware Adaptive Tracker for Robust and Real-Time Multi-Object Tracking in Maritime Environments (opens in a new tab)

The paper introduces MAAT (Marine-Aware Adaptive Tracker), a multi-object tracking system designed for maritime environments to improve autonomous navigation of unmanned surface vehicles (USVs). It enhances ByteTrack by adding an adaptive Kalman filter and a density-aware association strategy to handle challenges like platform jitter and nonlinear object motion. Tested on the Singapore Maritime Dataset, MAAT achieves 44.37 MOTA and 43.857 IDF1 while running in real time at 41.4 FPS. The results show MAAT provides robust and accurate tracking for dynamic maritime conditions.

07crossref2026-04-17Lansu Dai, Burak KantarciDOI ↗ (opens in a new tab)

A SOTIF-Oriented Framework for Safety Assessment in Autonomous Vehicles using Integrated Fault Tree and Bayesian Network Analysis (opens in a new tab)

This paper introduces a safety assessment framework for autonomous vehicles by combining Fault Tree Analysis (FTA) and Bayesian Network (BN) to address both failures and functional insufficiencies, such as perception and sensor limitations. The approach enables qualitative and quantitative analysis, accounting for dynamic dependencies and uncertainties in real-world driving conditions. A case study on object detection failures identified weather and occlusion as major contributors, responsible for 45.76% and 58.72% of failures, respectively. The framework offers actionable insights for improving autonomous vehicle reliability under the Safety of the Intended Functionality (SOTIF) standard.

08crossref2026-04-13Xiaoyan (Jenny) Liu, Chi Hoang, Sharon NgDOI ↗ (opens in a new tab)

EXPRESS: Automated Versus Human-Operated: Impact of AI-Driven Autonomous Stores on Prosocial Behavior (opens in a new tab)

This study examines how AI-driven autonomous stores affect prosocial behavior, finding that consumers act less prosocially after interacting with them compared to human-operated stores. The decline stems from reduced social connectedness due to the lack of human interaction at key service points. The effect holds for both non-embodied and humanlike AI systems but can be lessened under specific conditions, such as joint consumption or consumer-welfare-focused AI framing. The research highlights potential social costs of automated retail and suggests strategies to mitigate them.

09openalex2026-04-16Satoru Morikawa, Masaki Yoda, Takehito Ouchi, Takazumi Yasui +13 moreDOI ↗ (opens in a new tab)

PDGFRα-positive mesenchymal stem/stromal cells contribute to autonomous vascular formation through in-body tissue architecture (opens in a new tab)

This study explores how PDGFRα-positive mesenchymal stem/stromal cells (MSCs) enable the formation of vascularized tissues within implanted molds through in-body tissue architecture (iBTA). Using PDGFRα reporter mice, researchers found these cells associated with blood vessels and expressed MSC markers (CD73, CD90, CD105), showing multi-lineage differentiation potential in lab tests. The method was successfully tested in pigs, producing organized vascular tissue and collagen within two weeks. iBTA avoids cell isolation and immunosuppression by using the body’s own MSCs for tissue engineering.

10openalex2026-04-14Min Wang, Jinwen Gao, Chenhao Li, Mei Hong +3 moreDOI ↗ (opens in a new tab)

Dynamic Obstacle Avoidance Algorithm for Unmanned Vessels Based on FDWA and IBA*—IGWO Fusion (opens in a new tab)

This paper introduces a dynamic obstacle-avoidance algorithm for unmanned surface vehicles (USVs) by merging Fuzzy-enhanced Dynamic Window Approach (FDWA) with an Improved Bidirectional A*–Improved Grey Wolf Optimizer (IBA*–IGWO) framework. The method improves traditional DWA by optimizing the initial heading angle and using a fuzzy controller to adjust weight coefficients in the cost function, enhancing adaptability in varying environments. The IBA*–IGWO algorithm provides a global route, with key nodes serving as local endpoints for FDWA to ensure optimal navigation and dynamic adjustments. Simulation results confirm the method’s effectiveness in avoiding unknown and dynamic obstacles while returning USVs to pre-planned routes.

11openalex2026-04-13Pranav Kedia, Rajini Makam, Heiko Hamann, Suresh SundaramDOI ↗ (opens in a new tab)

BIND-USBL: Bounding IMU Navigation Drift using USBL in Heterogeneous ASV-AUV Teams (opens in a new tab)

The paper *BIND-USBL* introduces a cooperative localization system for Autonomous Underwater Vehicles (AUVs) in GPS-denied environments, where drift from inertial navigation is a major issue. The framework uses Autonomous Surface Vessels (ASVs) with Ultra-Short Baseline (USBL) acoustic positioning to provide intermittent fixes, reducing dead-reckoning errors. Key components include a multi-ASV formation model, a conflict-graph-based scheduler for efficient acoustic updates, and delayed fusion of USBL data with inertial measurements. Simulations demonstrate improved localization performance based on survey scale, acoustic coverage, and ASV-AUV team geometry.

12openalex2026-04-13Dana Feng, Bhada Yun, April WangDOI ↗ (opens in a new tab)

From Junior to Senior: Allocating Agency and Navigating Professional Growth in Agentic AI-Mediated Software Engineering (opens in a new tab)

This study examines how agentic AI affects professional agency in software engineering, comparing junior and senior developers. Juniors, who grew up with AI, often struggle with over-reliance or avoidance, while seniors maintain control by delegating tasks and using pre-AI instincts. Organizational policies, not personal choice, primarily limit agency. The authors propose three practices to preserve agency in coding, learning, and mentorship as AI becomes more autonomous.

13crossref2026-04-17Qi Li, Liming TaoDOI ↗ (opens in a new tab)

A vessel-guided multi-task deep learning framework with visual interpretability for simultaneous retinal vessel segmentation and multi-disease classification from fundus images (opens in a new tab)

Qi Li and Liming Tao (2026) developed V-MNet, a deep learning framework that simultaneously performs retinal vessel segmentation and multi-disease classification from fundus images. The model uses a vessel-guided mechanism to improve classification accuracy, achieving a Dice coefficient of 0.831 for segmentation and an average AUC of 0.978 for disease classification across four public datasets. It also incorporates Grad-CAM for visual interpretability, highlighting lesion regions to aid clinical decision-making. Ablation studies confirmed the effectiveness of its multi-task and vessel-guided design.

14crossref2026-04-19Yunhao Zhang, Huafeng DingDOI ↗ (opens in a new tab)

Cooperative Learning NN-Based Fault-Tolerant Formation of Networked Unmanned Surface Vehicles with Input Saturation and Prescribed Performance (opens in a new tab)

This paper presents a fault-tolerant control (FTC) algorithm for unmanned surface vehicles (USVs) to maintain formation under challenges like disturbances, model uncertainties, actuator faults, and input saturation. The method combines cooperative learning neural networks, distributed disturbance observers, and backstepping techniques, with shared neural network weights improving coordination. An auxiliary system and actuator matrix address input saturation and propeller failures, ensuring errors stay within predefined performance limits. Simulations with four USVs confirm the algorithm’s effectiveness in maintaining formation and reducing tracking error oscillations compared to non-learning methods.

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