Developing a Decision Support System for Vessel Traffic Services

The growing use of digitalization and automation aboard ships is attracting increasing attention. Research and prototype development are currently transitioning from partially to highly or fully automated and autonomous vessels. As these advancements impact not just individual ships or crews but entire systems, it is crucial to guarantee the seamless integration of these innovations into the existing infrastructure. However, less attention has been paid to the technical and operational integration of such vessels into the existing system of conventional ships and shore-side traffic monitoring services. Therefore, this project aims to develop and evaluate an AI-based decision support system for shore-based monitoring and decision support for future traffic, including vessels of various degrees of autonomy. Together with the project partners (German Aerospace Center (DLR), the Maritime Institute Warnemünde e.V. (SIW), the Fraunhofer Institute for Maritime Logistics and Services (CML), and Bergmann Marine) Fraunhofer Institute for Communication, Information Processing and Ergonomics (FKIE) investigates how artificial intelligence (AI) can support the user in detecting anomalies in the navigational behaviour of different vessels and prevent the escalation of dangers under complex conditions. As even the most advanced system can result in serious mistakes if it does not fit the users' needs and work processes, a major part of the project Shoreside decision support for traffic situations with highly automated or autonomous ships (LEAS) is devoted to creating a user-friendly interface that effectively represents the AI components. This paper explains the development process and the evaluation of the human-machine interface (HMI), including user acceptance testing. Particular emphasis is placed on the final evaluation, where vessel traffic service (VTS) operators interacted with the system while performing a complex simulated monitoring task. This enabled the identification of several implications as well as challenges, which are discussed in the paper. The project is funded by the German Federal Ministry of Research, Technology, and Space (BMFTR) as part of civil security research in the field of artificial intelligence in civil security research.