Wyniki wyszukiwania - BazTech

Ograniczanie wyników

1 TransNav : International Journal on Marine Navigation and Safety of Sea Transportation

1 2025

Powiadomienia systemowe

Sesja wygasła!
Sesja wygasła!

Znaleziono wyników: 1

Liczba wyników na stronie

Wyniki wyszukiwania

Wyszukiwano:
w słowach kluczowych: maritime traffic monitoring

Sortuj według:

Ogranicz wyniki do:

LEAS: An AI-based Demonstrator as Decision Support Tool for Traffic Monitoring at VTS Centers

Stach Thomas, Koch Paul

TransNav : International Journal on Marine Navigation and Safety of Sea Transportation

2025

Vol. 19 No. 1

301--308

Maritime traffic is prevalent worldwide, with particularly high density in coastal waters. To ensure safety and efficiency, Vessel Traffic Service (VTS) centers monitor and coordinate maritime traffic. For this purpose, VTS centers utilize various sensor and communication technologies such as radar, Automatic Identification System (AIS), electro-optical systems or radio communication. Additionally, any Vessel Traffic Service Operator (VTSO) is motivated to utilize a Decision Support Tool (DST). The LEAS project addresses emerging challenges at VTS centers. One key challenge results from the continuous evolution of maritime traffic, in particular, its ever increasing automation and autonomization. Another key challenge is the growing shortage of skilled workers. Consequently, it is crucial to process increasing volume of maritime traffic data while maintaining or improving safety and efficiency. DSTs at VTS centers must be adapted to these emerging challenges, accordingly. In the LEAS project, we develop and evaluate a demonstrator which represents a DST. This demonstrator is being developed in close collaboration with VTSOs to address these challenges. Most notably, it has a situation detection which makes use of Artificial Intelligence (AI) methods and displays relevant information in an intuitive Human-Machine Interface (HMI). The demonstrator is evaluated using simulated traffic scenarios in the German Bight and Baltic Sea, with VTSOs as test subjects. This paper provides an overview of the project and demonstrator. First, we introduce the key requirements for the demonstrator and discuss their impact on the system architecture. Next, we present its AI-based situation detection. We explain the underlying formalism of the situation detection and resolution as well as its implementation in the demonstrator. Finally, we evaluate the capabilities and limitations. The paper concludes with an outlook to future work with focus on potential deployment at DST at VTS centers.