(03)

Science

↓ (W42 ‘26 · Oct 12–18)
01openalex2026-10-15Bingying Dong, Mehran Idris Khan, Yanyan LvDOI ↗ (opens in a new tab)

The duty to rescue at sea and Maritime Autonomous Surface Ships (MASS): Implementation under the IMO MASS code (opens in a new tab)

The paper examines the duty to rescue at sea in relation to Maritime Autonomous Surface Ships (MASS), arguing that autonomy does not exempt vessels from rescue obligations. It analyzes how the IMO MASS Code’s Chapter 21 translates this duty into a goal-based framework, aligning with SOLAS requirements. Flag states must enforce compliance through certification and oversight, while coastal states must integrate MASS into search and rescue (SAR) coordination and ensure survivor disembarkation. The study outlines responsibilities for both flag and coastal states to ensure MASS can effectively assist persons in distress.

02openalex2026-10-13Won-Jun Yoo, Kwang-Jun Paik, Mu-Yeong SeoDOI ↗ (opens in a new tab)

Real-time situational awareness and collision risk evaluation for autonomous ships under sensor uncertainty (opens in a new tab)

This study introduces a framework for autonomous ships to assess collision risks in real time, accounting for sensor uncertainty from AIS and radar data. It uses an Unscented Kalman Filter to estimate target-ship states and integrates uncertainty into a probabilistic ship domain, enabling metrics like Probabilistic Collision Exposure (PCE) and Expected Collision Energy (ECE). Simulations under noisy conditions showed target-position errors averaging 3 m, with PCE reducing post-CPA residual risk significantly compared to the Collision Risk Index. The framework maintained a 10-Hz update rate across single- and multi-target scenarios.

03openalex2026-10-14Kavin Govindarajan, Kaleb Ben Naveed, David Li, Devansh R. Agrawal +4 moreDOI ↗ (opens in a new tab)

Clarity-Driven Adaptive Mission Planning for a Solar-Powered Autonomous Surface Vessel (opens in a new tab)

This paper introduces an adaptive mission planning method for solar-powered autonomous surface vessels (ASVs) to optimize scientific data collection. The approach uses a clarity-driven ergodic search, where clarity is a mathematically defined measure tied to information entropy, to prioritize high-interest areas identified during the mission. The system continuously updates its path based on real-time measurements and energy constraints. Simulations and field experiments at Jordan Lake, North Carolina, validate the method’s effectiveness.

04openalex2026-10-14Aleksandr GulykDOI ↗ (opens in a new tab)

CROSS R2 Reproduction Release: Reference-Envelope Simulation of Mixed Autonomous and Human-Driven Ship Traffic (opens in a new tab)

This paper provides frozen reproduction materials for a synthetic study on mixed autonomous and human-driven ship traffic. It includes code, numerical data, reference scenarios, and instructions for independent verification. The results are not based on real-world AIS or maritime traffic data and should not be considered certified for navigation safety. The archive uses open licenses (Apache-2.0, CC BY 4.0) for author-owned content, with upstream MIT/BSD terms for third-party software, and restricts checkpoint deserialization to trusted local files.

05openalex2026-10-17Yang Yu, Zheng Wen, Shuyang Dai, Hao Qiang LinDOI ↗ (opens in a new tab)

Multi-horizon vessel trajectory prediction with a physically constrained TCN–KAN framework (opens in a new tab)

This study introduces TCN–KAN–PINN, a framework combining a multi-scale Temporal Convolutional Network (TCN), a Linear-KAN predictor, and physics-informed training to improve vessel trajectory prediction. The model extracts temporal features from historical AIS data, corrects nonlinear maneuver deviations, and enforces kinematic consistency using a time-discretized residual and adaptive loss balancing. Tested on real-world AIS data, it outperformed existing methods in accuracy, speed, and course consistency while maintaining efficient inference. Ablation studies confirmed the benefits of kinematic supervision for short-term predictions and the KAN pathway for longer horizons.

06openalex2026-10-16Bareq W. Fathi, Ahmed N. RasheedDOI ↗ (opens in a new tab)

Robust Navigation Corridor Extraction from Water Segmentation for Inland Autonomous Surface Vehicles (opens in a new tab)

This study introduces a framework converting water-segmentation masks into navigation boundaries, centerlines, and corridor metrics for inland autonomous surface vehicles. Tested on 173 low-resolution images, the proposed Edge U-Net outperformed other models, achieving an IoU of 0.964 and a Boundary-F1 score of 0.685. The evaluation highlights discrepancies between pixel-overlap scores and boundary accuracy, using additional indices like the Navigation Robustness Score. The framework focuses on reproducibility and geometric assessment but does not ensure obstacle-aware or closed-loop navigation safety.

07openalex2026-10-13Yongjie Zhu, Rongyao Wang, Jingwei Xu, Xiuquan Liu +2 moreDOI ↗ (opens in a new tab)

An improved A* algorithm and its application in path planning for unmanned surface vehicles (opens in a new tab)

The paper introduces an enhanced A* algorithm for path planning in unmanned surface vehicles (USVs) used for inland-river garbage collection, addressing both static and flowing water environments. In static conditions, the method optimizes for shortest path, time, and energy consumption, while in flowing water, it incorporates flow direction into its heuristic and uses a velocity-based energy model. Simulations demonstrate a 3.5% energy reduction with the minimum-energy path compared to the shortest-path approach. The improved A* algorithm outperforms RRT and PRM in optimality, efficiency, and adaptability across various river channels.

08openalex2026-10-13Yuxin Sun, Lu Zhang, Zengyan Zhu, Shouzheng YuanDOI ↗ (opens in a new tab)

WADNet: Weather Adversarial Decoupling Network for Marine Ship Instance Segmentation (opens in a new tab)

WADNet is a weather-adaptive framework designed for marine ship instance segmentation, addressing challenges like fog and rain that degrade image quality. It uses a Weather-Adversarial Feature Decoupling (WAFD) mechanism to reduce reliance on weather-related visual cues during training without adding inference costs. A Weather-Adaptive Dynamic Routing Mechanism (WADRM) adjusts feature transformations based on weather conditions, while Inner-CIoU improves bounding-box accuracy. Tested on a mixed-weather dataset, WADNet achieved a 63.40% Mask AP, outperforming YOLO11n-seg by 3.18 percentage points.

09openalex2026-10-15Sheng Cao, Shuxiang Guo, 严勇敢, Jian Guo +7 moreDOI ↗ (opens in a new tab)

A 2D Image Feedback-Based Autonomous Endovascular Navigation Method: A Perception and Control Framework (opens in a new tab)

This study presents a method for autonomous endovascular navigation using 2D image feedback from DSA and X-ray fluoroscopy. The system converts vessel images into a centerline graph, tracks device-tip progress, and uses a rule-based controller for navigation tasks like delivery and branch selection. Tested on a robotic platform with 65 runs, it achieved over 95% guidewire progress in all cases, with only 3.1% failing due to excessive stops. The approach shows promise but requires further testing with clinical images and varied anatomies.

10openalex2026-10-12Oluchi Jane Jide-BelloDOI ↗ (opens in a new tab)

The Future of the Law of the Sea: Emerging Challenges and the Niger Delta in a Changing Maritime Order (opens in a new tab)

This paper explores how climate change, biodiversity loss, deep-seabed activities, and geopolitical competition are reshaping the international law of the sea, focusing on UNCLOS’s adaptability. It highlights the Niger Delta as a case study where maritime law intersects with pollution, fisheries, and security challenges. The study argues that UNCLOS remains central but requires updated interpretations, new treaties, and stronger domestic enforcement. Recent agreements like the BBNJ and IMO’s MASS Code show the legal framework evolving rather than being replaced.

11openalex2026-10-17Tianpeng Huang, Huishuang Shao, Xiaozhao Jin, Zhonggang XiongDOI ↗ (opens in a new tab)

Disturbance estimator-based robust tracking control of an unmanned surface vessel with transient norm bound (opens in a new tab)

This study presents a control method for unmanned surface vessels facing external disturbances. A nonlinear disturbance estimator is designed to accurately estimate and compensate for disturbances in finite time. The approach combines sliding mode and backstepping control techniques to stabilize the vessel’s position and yaw angle, ensuring tracking errors converge to zero. Simulations validate the effectiveness of the proposed scheme, with stability confirmed through Lyapunov theory.

12openalex2026-10-12Selin Şimşek Alkan, Aslı Vural, Vildan Gürses Beşli, Sibel Zırtıloğlu +6 moreDOI ↗ (opens in a new tab)

Retinal Microvascular and Peripapillary Profiles in Mild Autonomous Cortisol Secretion Versus Nonfunctioning Adrenal Adenomas (opens in a new tab)

This study compared retinal and peripapillary microvascular features in 98 patients with mild autonomous cortisol secretion (MACS) versus nonfunctioning adrenal adenomas (NFA). No significant difference was found in deep capillary plexus vessel density between groups. Secondary findings suggested thicker superior retinal nerve fiber layer in MACS and associations between higher post-dexamethasone cortisol levels and reduced parafoveal deep capillary plexus and radial peripapillary capillary density, though some results did not survive statistical correction. The authors note these secondary findings require further validation.

13openalex2026-10-17Lifei Song, Wenyu Yu, Liwen Bai, Xiang Huang +2 moreDOI ↗ (opens in a new tab)

Cross-modal semantic–geometric filtering for USV LiDAR SLAM in dynamic water-surface environments (opens in a new tab)

This paper introduces a cross-modal semantic–geometric filtering method for LiDAR SLAM in dynamic water-surface environments, addressing issues like moving vessels and reflection-induced noise in USV mapping. The approach combines visual semantic data with LiDAR point confidence, using temporal association and adaptive attenuation to filter out interference while preserving static structures. Testing in a port-basin sequence showed an 87.18% reduction in vessel-related noise and a 77.98% decrease in reflection-affected points, alongside a 24.28% improvement in pose accuracy. The method balances noise suppression and structural preservation, enhancing trajectory consistency in dynamic conditions.

14openalex2026-10-14Youngjun Yun, Hyuntae Bang, Jiwoong Ha, Youra Jun +3 moreDOI ↗ (opens in a new tab)

Multi-agent Reinforcement Learning for Cooperative Control of Multiple Unmanned Surface Vehicle in Neutralizing Threat Vessels (opens in a new tab)

This study introduces a multi-agent reinforcement learning (MARL) system for two unmanned surface vehicles (USVs) to cooperatively deploy a capture net against threat vessels. The approach uses a high-fidelity simulation with wave and wind models, prioritizing close-range observations and resolving angular discontinuities through trigonometric transformations. The MARL framework, combined with a hierarchical reward structure, outperformed traditional guidance methods, achieving a 65% capture success rate and reducing formation collapse by three times in dynamic conditions. Results confirm the system’s effectiveness for autonomous, coordinated maritime interdiction.

15openalex2026-10-13Masoud Ebrahimi, Jackiie Samuelsson, Carolina Smigan, Abu Naser Masud +2 moreDOI ↗ (opens in a new tab)

From Maritime Regulations to Verifiable Properties with LLM Assistance (opens in a new tab)

This paper introduces a method to translate maritime safety regulations (COLREGs) from a structured language (Legata) into verifiable logical properties using a four-stage pipeline. The process relies on LLM agents (GPT-4o) for initial stages, with expert oversight and model checking (Rebeca) for verification. Evaluations show improved accuracy with a "skillful" LLM configuration, achieving higher scores in syntax, coverage, and logical completeness. The work provides a reusable pipeline, evaluation metric, and insights into regulatory clauses suitable for actor-based model checking.

16openalex2026-10-15Chaoyi Li, Jun Zhang, Gongwu Sun, Ying Mao +3 moreDOI ↗ (opens in a new tab)

Spatio-Temporal-Consistency Target-Guided Coordinate Control of Unmanned Surface Vehicles Based on Strong Prescribed-Time Stability (opens in a new tab)

This study introduces a nonlinear control method (SPT-TACC) for unmanned surface vessels (USVs) to achieve synchronized, disturbance-resistant target tracking within a predefined time. The approach converts error models into periodic delayed forms and designs a feedback-based system ensuring simultaneous arrival at tracking points. Stability is rigorously proven, and guidelines for setting convergence times are provided to prevent system divergence. Simulations confirm the method’s effectiveness.

17openalex2026-10-14Hyeonjung Choi, Minki Kim, Seong-Yeol YooDOI ↗ (opens in a new tab)

A Two-Stage Neural Network Framework for Swimming Direction Control of an Underwater Walking Robot: Kinematic Validation via Simulation and In-Air Experiments (opens in a new tab)

This study introduces a two-stage neural network framework for controlling the swimming direction of an underactuated underwater walking robot with electromagnetic feet and propellers. The first network maps target directions to foot-tip positions using a mixture density model, while the second converts these positions into joint angles. Validation in simulation and in-air experiments showed mean direction tracking errors of 4.25° and 1.53°, respectively. The approach addresses challenges in non-unique inverse kinematics for the robot’s four-degree-of-freedom legs.

18openalex2026-10-13Rolf B. Pedersen, Daniel Albert, Marius Bratrein, Broberg, Jonas, 1962- +29 moreDOI ↗ (opens in a new tab)

GoNorth 2023 Cruise Report (opens in a new tab)

The GoNorth 2023 cruise aimed to explore the Gakkel Ridge, part of the global mid-ocean ridge system, but drifting sea ice prevented access to primary survey areas. Research shifted to the western Gakkel Ridge, where a volcanic area and a hydrothermal field were mapped using underwater vehicles. Despite initial setbacks, the team discovered a unique hydrothermal field, "Ultima Thule," at 3,000 meters depth beneath sea ice. The cruise also included ice studies, sediment sampling, and an oceanographic transect across the Fram Strait.

19openalex2026-10-12Marko Perkovič, Ivica Pavić, Maciej Gucma, Sebastian Feuerstack +1 moreDOI ↗ (opens in a new tab)

Maritime security and risk assessments—2nd edition (opens in a new tab)

The second edition of *Maritime security and risk assessments* addresses evolving challenges in maritime safety, including digitization, automation, cyber-physical risks, and geopolitical threats. It expands on the first edition by exploring risk-informed decision-making, validation, and system resilience through three research streams: collision-risk sensing, human-technology interaction, and port safety. Studies use traffic data, simulations, and accident reports but face limitations like incomplete validation, sparse data, and weak cross-scale integration. Effective implementation requires trustworthy data, uncertainty management, human-centred assurance, and preparedness for cyber-physical and security failures.

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