Fraunhofer Center for Maritime Logistics and Services

Abstract The growing adoption of autonomous technologies in the maritime industry creates a critical challenge for safe navigation: a communication gap between Maritime Autonomous Surface Ships (MASS) and human operators, both on conventionally crewed vessels and in shore-based control centers like Vessel Traffic Services (VTS). This gap is particularly pronounced in voice-based Very High Frequency (VHF) radio communication, which remains essential for mutual intent-sharing, conflict resolution, and coordinated navigation in a mixed-fleet environment. This paper introduces a forward-looking vision for an artificial intelligence (AI) powered framework aimed at achieving fully digitized maritime radio communication for MASS. The proposed system is structured around four tightly integrated modules: Sensory Input Stage, Text and Context Extraction, Contextualization and Reasoning - LLM Agent Loop, and Response Generation and Broadcasting. These components work cohesively to transform traditional voice radio exchanges into a machine-interpretable and protocol-compliant communication pipeline. This paper presents a comprehensive exposition of the framework’s architecture, accompanied by a structured development roadmap and appropriate evaluation methodologies for each module. It also introduces a novel concept of tiered autonomy levels for digital radio communication, emphasizing the critical role of human-in-the-loop supervision. By enabling autonomous ships to interpret, process, and respond to VHF transmissions in real time, this framework not only enhances operational efficiency but also contributes to the safe and standardized integration of autonomous technologies within the complex maritime ecosystem.

Abstract This paper investigates the optimization of Automatic Identification System (AIS) message transmission for Virtual Aids to Navigation (VATONs) in maritime communication networks under challenging environmental conditions. The study addresses critical network bottlenecks by analysing the impact of path loss (α = 2 to 4.0) on communication reliability and evaluating opportunistic networking solutions, specifically Epidemic routing protocols, for enhanced message delivery. Using OMNeT++ simulations with 40 vessels across a 100km × 100km maritime area, we demonstrate that traditional shore-to-ship communication suffers significant degradation when path loss exponents exceed 2.8, with packet reception rates dropping below 20% at α > 3.2. Our research reveals that Epidemic routing can effectively address these connectivity gaps through ship-to-ship relay mechanisms, maintaining critical VATON position updates even when direct shore-based communication fails. The findings indicate that opportunistic networking achieves substantial improvements in message delivery rates under adverse conditions. This work presents a proof-of-concept demonstration of opportunistic networking principles in maritime environments, establishing a foundation for future field validation studies.

Number-conserved subspace encoding reduces resources needed for quantum simulations, but scalable complexity trade-off bounds for M modes and N particles with O(NlogM) qubits have remained unknown. We study qubit-gate-measurement trade-offs through the lens of classical/quantum error correction complexity and develop a framework of fermionic gate and measurement complexity based on classical encoder/decoder appearing in the error correction framework. We demonstrate optimal encoding with random classical parity check code and propose the Fermionic Expectation Decoder for scalable probability decoding in O(M4) bases. The protocol is tested with variational quantum eigensolver on LiH in the STO-3G and 6-31G bases, and H2 potential energy curve in the 6-311G* basis.

Abstract The usage of Maritime Autonomous Surface Ships in coastal and heavily used maritime environments necessitates advanced navigation systems capable of fully complying with the International Regulations for Preventing Collisions at Sea 1972 and not only open sea encounters. A significant challenge in this domain is enabling autonomous vessels to understand and navigate complex collision avoidance scenarios dictated by Rule 9 Narrow Channels and Rule 10 Traffic Separation Schemes. These rules are not well covered by research and only partial solutions have been proposed. To address this, we propose a ruleset for a system that can blend the traffic situation and geometric constraints extracted from Electronic Navigational Charts in S-57 format. The proposed ruleset extends our previous work on operationalization of COLREGs by introducing spatial features describing the maritime geometries relevant for traffic situations in Narrow Channels and Traffic Separation Schemes. We apply the ruleset to various traffic situations, showing how the inclusion of geometric context improves decision-making by reducing ambiguity and therefore enables the assessment of traffic situations and ship encounters in the vicinity of Narrow Channels and Traffic Separation Schemes. Our work outlines how the integration of spatial features into a rule-based system enables autonomous navigation capabilities of MASS for safe operations and compliance with maritime regulations.

Deep learning object detection methods, like YOLOv5, are effective in identifying maritime vessels but often lack detailed information important for practical applications. In this paper, we addressed this problem by developing a technique that fuses Automatic Identification System (AIS) data with vessels detected in images to create datasets. This fusion enriches ship images with vessel-related data, such as type, size, speed, and direction. Our approach associates detected ships to their corresponding AIS messages by estimating distance and azimuth using a homography-based method suitable for both fixed and periodically panning cameras. This technique is useful for creating datasets for waterway traffic management, encounter detection, and surveillance. We introduce a novel dataset comprising of images taken in various weather conditions and their corresponding AIS messages. This dataset offers a stable baseline for refining vessel detection algorithms and trajectory prediction models. To assess our method's performance, we manually annotated a portion of this dataset. The results are showing an overall association accuracy of 74.76 %, with the association accuracy for fixed cameras reaching 85.06 %. This demonstrates the potential of our approach in creating datasets for vessel detection, pose estimation and auto-labelling pipelines.

The applications of heavy-duty Unmanned Aerial Vehicles (UAV) are as manifold as well-developed spanning from first response in emergencies to wildlife observations and inspection of infrastructure. The latter aspect is the focus of this work, allowing the time-intensive inspection of port-infrastructure to be done by means of UAV operating from an Autonomous Surface Vehicle (ASV) to increase mission range. To allow for continuously inspecting while additionally extending the mission duration, a Battery Hot Swap (BHS) station has been developed and the initial design and lab-tests validated. While previous works presented design criteria, development of the initial system as well as buoyancy testing on the ASV– this study presents the results of real-world testing within a port environment as well as the design improvements implemented. For the first time the system is installed on the custom-developed ASV ‘SeaML:SeaLion’ while being powered by the ships’ batteries and controlled remotely, therefore proving the capability of performing a complete hot swap without human intervention. The swapping routine could be successfully demonstrated and from landing to take off was completed within less than 3 minutes.

In the area of maritime rescue, the factor time in the event of an accident and the associated conduct of rescue operations is of fundamental importance. A difference in the arrival of the rescue forces from a few minutes can decide in the worst case between death or complete recovery of an injured person. First, this paper briefly addresses peculiarities of ship accidents and examines in particular communication-enhancing measures to avoid them. In this context, current developments in the field of automatic speech recognition by artificial intelligence are presented on the basis of the research project ARTUS - Automated Transcription of Maritime VHF Radio Communication for SAR Mission Coordination. Based on the technology used in the project to transcribe the content of maritime radio messages and to locate as well as identify vessels, its potential challenges and safety benefits are analyzed.

Globalization and new environmental legislations lead to a rising need for new technological developments for the shipping industry, especially creating smart ports, smart waterways and smart ships. However, since these developments are on the horizon and thus not currently not state of the art, emphasis is on reducing emissions from shipping. To reduce the amount of CO2 emitted by the maritime transport sector, the European Parliament introduced a regulation, which came into force in 2018, establishing a CO2 emission Monitoring, Reporting, and Verification System. In order to measure and assess global ship emissions, an estimation model will be developed. Using AIS and environmental data, ship’s resistance through water will be modelled. Based on the main engine used, the presumed fuel consumption of a voyage and thus the emissions can be indicated and hourly energy requirements for each ship worldwide quantified. Based on the knowledge gained from historical evaluations, a target/actual comparison enables the evaluation of the performance of a ship and thus the identification of emission reduction potentials.

This paper will give an intro into the technical backbone of the EMSN and derive necessary specifications to allow for objective testing in large scale. Further, it will demonstrate the potential of EMSN as a maritime safety test-bed on the STM case. Therefore, the simulations executed within the EMSN are evaluated regarding their safety level in order to demonstrate the effects of various measures to improve safety. Based on a fuzzy logic approach, numerical Data from the EMSN Data-Tracker is used as an input to assess a present traffic situation from the perspective of a specific ship and outputs a comprehensive safety index developed by expert opinions. The safety index is used to further analyze navigators’ behavior and decisions in different maritime traffic scenarios that are executed within the EMSN.

At a cross-docking terminal, inbound shipments are directly transshipped across the terminal to designated outbound trucks, so that delays and inventories are kept as low as possible. We consider an operational truck scheduling problem, where a dock door and a start time have to be assigned to each inbound truck. A set of outbound trucks is scheduled beforehand and, therefore, departure times are fixed. If a shipment is not unloaded, transshipped to the outbound gate and loaded onto the designated outbound truck before its departure, we consider the shipments's value as lost profit. The objective is to minimize total lost profit. This paper at hand formalizes the resulting truck scheduling problem. We settle its computational complexity and develop heuristics (namely, decomposition procedures and simulated annealing) in order to tackle the problem. We show the efficiency of these heuristics by means of a computational study. Last but not least, a case study is presented.