(03)

Science

↓ (W28 ‘26 · Jul 6–12)
01crossref2026-07-07Hiba Ben Lahbib, Mohamed Taha Bennani, Jüri VainDOI ↗ (opens in a new tab)

Autonomous vessel collision avoidance verification using geometric optimization (opens in a new tab)

This paper addresses gaps in the International Regulations for Preventing Collisions at Sea (COLREG) for Maritime Autonomous Surface Ships (MASS) by incorporating relative speed variations between vessels, expanding on prior work limited to identical-speed scenarios. It adapts collision-risk geometry calculations, such as collision angle, to assess how speed differences affect navigation safety. The study refines a geometric optimization method to efficiently analyze two-dimensional encounter scenarios, maintaining near-polynomial search complexity. The approach identifies high-risk vessel positions in under half a second, making it viable for onboard navigation warning systems.

02crossref2026-07-08Linna Li, Lingyu Zhang, Seyed Parsa Parvasi, Jasmine Siu Lee LamDOI ↗ (opens in a new tab)

Machine learning-based maritime collision risk assessment and avoidance for autonomous vessels using AIS data (opens in a new tab)

This study proposes a machine learning framework using XGBoost to assess maritime collision risks for autonomous vessels, replacing the computationally intensive Dempster-Shafer model. Using AIS data, the model predicts Collision Risk Indicators (CRI) with high accuracy (95.36% R² in training, 90.21% in testing) and integrates them into collision avoidance algorithms. The approach processes high-traffic scenarios faster than traditional methods and reduces collision risk by 33.0% in autonomous-autonomous encounters and 28.7% in autonomous-conventional encounters. Results highlight improved efficiency and scalability for real-time maritime navigation safety.

03crossref2026-07-07Xiaoru Ma, Hongguang Lyu, G. H. Tan, Xikai Kang +2 moreDOI ↗ (opens in a new tab)

Autonomous collision avoidance for complex multi-ship encounters based on improved dynamic window approach (opens in a new tab)

This study enhances autonomous ship navigation by improving collision avoidance in complex multi-ship encounters. It combines Velocity Obstacle (VO) and CPA/TCPA methods to assess collision risks and applies COLREGs rules to assign give-way and stand-on responsibilities. The proposed MVO-IDWA algorithm integrates these factors into the Dynamic Window Approach to optimize decision-making. Results show the method effectively considers ship responsibilities, risk levels, and movement trends for safe navigation.

04crossref2026-07-10Myo Min Thant, Soula KyriakouDOI ↗ (opens in a new tab)

Evolving Regulatory Landscape and Environmental Perception: Myanmar’s Legal and Sustainability Readiness for Maritime Autonomous Surface Ships (MASS) Adoption (opens in a new tab)

This study examines Myanmar’s legal and sustainability readiness for Maritime Autonomous Surface Ships (MASS). Survey data from 51 seafarer officers shows 40% find Myanmar’s current legal framework insufficient for MASS adoption. About 70% of respondents believe MASS will improve environmental sustainability. The research aims to help Myanmar develop a systematic framework for future MASS operations in its coastal waters.

05crossref2026-07-10Filippo Ponzini, Michele MartelliDOI ↗ (opens in a new tab)

Camera–LiDAR Data Fusion for Enhanced Ship Situational Awareness in Maritime Environment (opens in a new tab)

This paper presents a multi-sensor fusion system combining RGB camera and LiDAR data to improve obstacle detection and situational awareness for autonomous ships. Camera data is processed using a pre-trained object detection model, while LiDAR data undergoes clustering and classification via a Random Forest algorithm. The system tracks dynamic obstacles using a Global Nearest Neighbour algorithm with Kalman filtering, reducing false positives from noisy measurements. Real-world tests demonstrated 92% track number accuracy in complex maritime scenarios.

06openalex2026-07-08Natasya Habibah, Paul Hegarty, Breda KennyDOI ↗ (opens in a new tab)

A Human-Centred View of Maritime Autonomous Surface Ships Operations Using the SHELL Model (opens in a new tab)

This study uses the SHELL model (Software, Hardware, Environment, Liveware) to create a human-focused framework for Maritime Autonomous Surface Ships (MASS). It examines how humans interact with AI-driven systems, considering regulatory software, system hardware, environmental factors, and human roles. The framework aims to improve safety and reliability by addressing key challenges in human-machine integration. It provides a foundation for future research on complex MASS operations.

07crossref2026-07-10Karim HardyDOI ↗ (opens in a new tab)

Engineering Safety Requirements for Maritime Autonomous Surface Systems: Hazard Scenarios, Control Loss, and Recovery in Degraded Operations (opens in a new tab)

This paper examines safety challenges in maritime autonomous surface systems, highlighting risks from degraded communication, unclear control authority, and delayed human intervention. It analyzes 80 documented hazard scenarios from regulations, trials, and incident reports to identify key risk areas like remote supervision, control links, and navigation interactions. The study proposes a safety engineering approach to define control constraints and recovery requirements, emphasizing the need for explicit degraded modes, fallback behaviors, and emergency coordination. Findings show safety depends more on system design and recovery protocols than autonomy level alone.

08openalex2026-07-07Gang Chen, Jianbo Zheng, Xinhao Zhao, Zhu J +2 moreDOI ↗ (opens in a new tab)

A Velocity Obstacle-fused Dynamic Window Approach with risk hysteresis for pairwise COLREGS-compliant collision avoidance of Autonomous Surface Vessels (opens in a new tab)

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

09openalex2026-07-06Chun ZOU, LONG CHEN, Hanwen Fan, Xiaobin Tian +2 moreDOI ↗ (opens in a new tab)

Enhancing maritime autonomous surface ship navigation safety: A dynamic risk assessment framework integrating system theoretic process analysis and stochastic Petri nets (opens in a new tab)

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

10openalex2026-07-08Yun‐Xi Li, Wenjin Liu, Xiang‐Yu Yao, He Van Dong +1 moreDOI ↗ (opens in a new tab)

Game‐Based Robust Formation Approaches for Networked Autonomous Surface Vessels With Input Dead‐Zone and Decision‐Making Constraints (opens in a new tab)

This paper examines robust formation control for networked autonomous surface vessels (NASVs) considering input dead-zone and decision-making constraints. It introduces a noncooperative game framework to enable flexible formation and proposes two game-based approaches: one with fast compensation for input dead-zones and another using a penalty function for decision-making constraints. The methods rely on distributed formation with partial information and are validated through simulations. Convergence analysis employs a two-time-scale method.

11crossref2026-07-08Daria de Tinguy, Tim Verbelen, Emilio Gamba, Bart DhoedtDOI ↗ (opens in a new tab)

Online Structure Learning and Planning for Autonomous Robot Navigation using Active Inference (opens in a new tab)

This paper introduces AIMAPP, a framework for autonomous robot navigation that combines mapping, localization, and decision-making using a single generative model inspired by animal navigation. The system builds and updates a sparse topological map in real-time, learns state transitions dynamically, and plans actions by minimizing Expected Free Energy to balance exploration and goal-directed behavior. Tested in real and simulated environments, AIMAPP operates without pre-training, adapts to sensor noise and failures, and outperforms existing planning methods. It is designed to be modular, self-supervised, and compatible with various sensors and robot configurations.

13openalex2026-07-08Andrew Philip Single

Development of a Real-Time Acoustic Detection and Tracking System for a Compact Autonomous Underwater Vehicle (opens in a new tab)

This study advances a real-time acoustic system for autonomous underwater vehicles (AUVs) to detect and track surface vessels using a small hydrophone array. It improves prior work by handling AUV self-noise, multi-target tracking via a particle filter with DBSCAN clustering, and closed-loop motion control. Field tests in Norfolk and Claytor Lake validated the system, while simulations confirmed stable tracking of one or two acoustic sources under varying conditions. A rear suppression tool was found essential for reliable performance when AUV self-noise interfered with detection.

14openalex2026-07-06Haicheng Shen, Xun Xu, Zhiqiang MiaoDOI ↗ (opens in a new tab)

Research on robot path tracking method based on IDDPG-MPC (opens in a new tab)

This study introduces a hybrid control method for unmanned surface vessels (USVs) combining improved deep deterministic policy gradient (IDDPG) and model predictive control (MPC). The IDDPG algorithm generates optimal heading commands, while MPC optimizes thrust and rudder angles using a nonlinear dynamics model. Simulations show the method reduces average lateral deviation by 37% and heading angle error by 21% compared to traditional ALOS-PID control. The approach improves adaptability and precision in complex marine environments.

15openalex2026-07-06Haicheng Shen (11495458), Xun Xu (276108), Zhiqiang Miao (2621947)DOI ↗ (opens in a new tab)

<p>Experimental path setting parameters.</p> (opens in a new tab)

This study introduces a hybrid control system for unmanned surface vessels (USVs) combining improved deep deterministic policy gradient (IDDPG) and model predictive control (MPC) to enhance path-following in marine environments. The IDDPG algorithm generates optimal heading commands, while MPC optimizes thrust and rudder angles using a nonlinear dynamics model. Simulation results demonstrate a 37% reduction in average lateral deviation and a 21% decrease in heading angle error compared to traditional ALOS-PID methods. The approach improves adaptability and precision in complex, dynamic conditions.

16openalex2026-07-06Haicheng Shen (11495458), Xun Xu (276108), Zhiqiang Miao (2621947)DOI ↗ (opens in a new tab)

<p>IDDPG network hyperparameters.</p> (opens in a new tab)

This study introduces a hybrid control system for unmanned surface vessels (USVs) combining improved deep deterministic policy gradient (IDDPG) and model predictive control (MPC). IDDPG generates optimal heading commands using reinforcement learning, while MPC optimizes thrust and rudder angles based on a nonlinear dynamics model. The method reduces average lateral deviation by 37% and heading angle error by 21% compared to traditional ALOS-PID control. Simulation results confirm improved adaptability and precision in complex marine environments.

17openalex2026-07-06Haicheng Shen (11495458), Xun Xu (276108), Zhiqiang Miao (2621947)DOI ↗ (opens in a new tab)

<p>Path tracking control pseudo code.</p> (opens in a new tab)

This paper presents a hybrid control system for unmanned surface vessels (USVs) combining improved deep deterministic policy gradient (IDDPG) and model predictive control (MPC). The IDDPG algorithm generates optimal heading commands, while MPC optimizes thrust and rudder angles using a nonlinear dynamics model. Simulation results show a 37% reduction in lateral deviation and a 21% decrease in heading angle error compared to traditional ALOS-PID methods. The approach enhances path-tracking precision in complex marine environments.

18crossref2026-07-08Yue Zhou, Zhuo Cheng, Jinchao FengDOI ↗ (opens in a new tab)

Changes in ecosystem carbon sequestration and their driving mechanisms in ethnic autonomous and non-autonomous areas of Western China (opens in a new tab)

Ecosystem carbon sequestration in western China increased from 2001 to 2025, with total carbon sink (TCS) rising from 1.40 to 1.60 PgC·yr⁻¹ and net primary productivity (NPP) from 440 to 500 gC·m⁻²·yr⁻¹. Ethnic autonomous areas contributed most to the carbon sink, showing higher TCS (1.14 to 1.27 PgC·yr⁻¹) but lower mean NPP (420 to 480 gC·m⁻²·yr⁻¹) compared to non-autonomous areas. NPP in autonomous areas was more sensitive to precipitation and soil moisture, while non-autonomous areas showed greater temperature sensitivity. Differences in carbon sequestration were driven by climate in autonomous areas and a mix of soil and climate factors in non-autonomous areas.

19crossref2026-07-06Hong SuDOI ↗ (opens in a new tab)

Parallel Thinking-Trace-Guided Auto-Learning for Autonomous Robots (opens in a new tab)

This paper introduces a parallel thinking-trace-guided auto-learning model for autonomous robots to improve efficiency in handling routine tasks. The system includes a main thinking system for complex scenarios, an Auto Learning and Decision System (ALDS) that converts thinking traces into executable models, and an Obvious Learning system (OBL) for storing abstract rules. Testing showed the model improved F1-scores, reduced main-thinking invocations by 80.31%, and cut latency by 75.34% while maintaining a 0.908 task success rate. Error-triggered rethinking also significantly boosted performance in conflict scenarios.

20crossref2026-07-08Xiangjie Cui, Wei Li, Jun Ning, Lu LiuDOI ↗ (opens in a new tab)

Signal Quantization and Event‐Triggered Trajectory Tracking for Multi‐Constraint Control of Unmanned Surface Vehicle (opens in a new tab)

This paper proposes an adaptive control strategy for unmanned surface vehicles (USVs) to track trajectories under thruster saturation, unknown dynamics, state constraints, and missing velocity data. It combines signal quantization and an event-triggered mechanism to reduce communication demands, while a neural network observer estimates unavailable velocity states. The approach uses neural networks to model unknown dynamics, a low-frequency gain method to reduce signal chattering, and a dynamic auxiliary system to handle thruster limits. Stability is confirmed through Lyapunov theory, and simulations verify the method’s effectiveness.

22crossref2026-07-07Fernando Crestelo Moreno, Luis Alfonso Díaz-Secades, Jesús Ángel García Maza, Antonio Lista MartinDOI ↗ (opens in a new tab)

Evaluating the impact of high-fidelity simulators on maritime education and training: enhancing competency through realistic simulation (opens in a new tab)

High-fidelity maritime simulators, like Kongsberg Polaris, improve navigation and emergency response skills for seafarers. Professionals gained more confidence and control than students, who showed higher emotional arousal. Instructors highlighted real-time feedback and scenario customization as key benefits, though challenges included maneuvering difficulties and high costs. The study supports simulator use in training but calls for better technology and adaptations for less experienced users.

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