(03)

Science

↓ (W35 ‘26 · Aug 24–30)
01openalex2026-08-28Andrés Yair Carvajal Bolivar, Fernando Jesus Guevara CarazasDOI ↗ (opens in a new tab)

Real-Time Obstacle Avoidance System for Autonomous Vessels Using Sensor Fusion (opens in a new tab)

This paper details a real-time obstacle avoidance system for autonomous vessels, tested in a 2D maritime simulation. The system uses a proximity detection algorithm built with Pygame to adjust ship trajectories and prevent collisions with static or moving obstacles. It incorporates a ship motion model and particle system for realistic environmental representation. The approach aims to support autonomous navigation, telemetry control, and intelligent maritime transport solutions.

02openalex2026-08-25P. Saleem AkramDOI ↗ (opens in a new tab)

Supporting Dataset for Liability Governance for AI-Powered Maritime Autonomous Surface Ships (MASS) (opens in a new tab)

This paper provides a supporting dataset for liability governance in AI-powered Maritime Autonomous Surface Ships (MASS). It includes legal and regulatory materials, a comparative liability analysis, and a Hybrid Multi-Layer Liability Governance Framework. The dataset underpins research on structuring accountability for MASS operations. Published in 2026, the work is authored by P. Saleem Akram.

03openalex2026-08-27Mehdi El Krari, Jonathan Smith, Maria FoxDOI ↗ (opens in a new tab)

Marine Autonomous Vehicle Fleet Scheduling to Maximise Scientific Impact (opens in a new tab)

This paper introduces a mixed-integer linear programming (MILP) model to automate and optimize the scheduling of Marine Autonomous Vehicle (MAV) fleets for scientific data collection. The model considers operational constraints like battery life and data collection time windows while maximizing data yield and minimizing vehicle use and energy consumption. It integrates with ship itineraries for mid-mission battery swaps or faster transit and scales efficiently, solving problems for hundreds of MAVs in minutes. The framework also supports scenario analysis and provides visualizations to aid decision-making.

04openalex2026-08-24Runbang Liu, Zhiyu Zhu, Huilin Ge, Jing Wang +2 moreDOI ↗ (opens in a new tab)

Maritime ship target detection based on visible and infrared modal image fusion (opens in a new tab)

This paper introduces VIMF-YOLO, a deep learning model for maritime ship detection that fuses visible and infrared images to overcome single-modality limitations. The model, based on YOLO v8, uses a dual-modal fusion module (DMFM) and efficient multi-scale attention (EMA) to enhance feature extraction and representation. A paired dataset of visible and infrared ship images was created to test the model, which demonstrated higher detection accuracy compared to state-of-the-art algorithms. The approach leverages complementary strengths of both modalities for improved performance.

05openalex2026-08-25Liantin Gao, Juan Lu, Yuefei Wang, Qiang Yan +5 moreDOI ↗ (opens in a new tab)

Development of a controller for autonomous berthing and unberthing of intelligent ships with large-angle attitude maneuvering based on Lyapunov method (opens in a new tab)

This paper presents a control framework for autonomous berthing and unberthing of a 5000-ton inland cargo ship, addressing challenges like environmental disturbances, precise attitude control, and energy efficiency. A Lyapunov-based controller with time-varying gains and sliding-mode terms stabilizes roll, pitch, and yaw within 10–15 seconds in simulations under strong wind, wave, and current disturbances. The system integrates SLAM mapping, visual recognition, and dynamic obstacle avoidance to generate safe, smooth, and energy-optimal trajectories. Compared to traditional methods, it reduces control energy consumption while providing theoretical support for real-world applications.

07openalex2026-08-27Vedran Simic, Erik Veitch, Ole Andreas Alsos, Taufik Akbar SitompulDOI ↗ (opens in a new tab)

Passenger experience of an autonomous urban ferry: Evidence from a public trial in Norway (opens in a new tab)

This study analyzed feedback from 146 passengers who tested an 8.6-meter autonomous ferry in Trondheim, Norway. Most passengers reported feeling safe, found the ferry easy to use, and would recommend it to others. However, nearly 20% were unclear about emergency evacuation procedures. The research highlighted that spatial comfort and clear pre-ride information improved perceived safety and willingness to use the ferry without a safety host.

08openalex2026-08-27André J. H. Olaisen, Jo EidsvikDOI ↗ (opens in a new tab)

Autonomous underwater vehicle sampling for hotspots in chlorophyll A (opens in a new tab)

Researchers developed an algorithm for autonomous underwater vehicles (AUVs) to efficiently map chlorophyll A hotspots by prioritizing sampling locations based on expected improvement. The system uses a Gaussian random field model to represent chlorophyll variations in space and time, updating in real-time with in-situ measurements. Field trials in Norway demonstrated the method’s adaptive sampling capabilities, comparing chlorophyll data with zooplankton distributions. Simulations showed the approach outperformed alternative sampling strategies.

10openalex2026-08-27David SoldaniDOI ↗ (opens in a new tab)

Claude Code Complete User Handbook (opens in a new tab)

The *Claude Code Complete User Handbook* by David Soldani (2026) outlines best practices for safely operating Claude Code, an agentic work environment with filesystem access, shell execution, and multi-agent orchestration. It identifies systemic failure risks—such as unreviewed hooks or over-scoped connectors—and emphasizes four key principles: defining completion conditions, separating control layers, treating third-party tools as supply-chain dependencies, and trusting observed evidence over agent statements. The book includes 34 chapters covering installation, governance, and verification, with citations for all claims and an evidence ledger for corrections. It also maps controls to external frameworks and proposes an adoption maturity model, labeling unverified claims explicitly.

12openalex2026-08-24Zhengjiao Qi, Yukuan Wang, Jingxian Liu, Jing QuDOI ↗ (opens in a new tab)

Wind-constrained Pareto multi-objective reinforcement learning for low-carbon vessel traffic organization in port approach channels (opens in a new tab)

This study introduces a wind-constrained framework for vessel traffic organization in port approach channels, using a Pareto-based multi-objective reinforcement learning algorithm (Pareto MO-PPO). The method incorporates real-time wind data to model propulsion, CO₂ emissions, and engine-load limits, enabling dynamic speed adjustments. Tested at Caofeidian Port, the approach reduced emissions by 11.41% compared to first-come, first-served scheduling, with a 7.49% increase in system time. The framework offers port operators multiple policy options to balance efficiency and emissions.

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