Terminal airspaces (TMA), especially those serving multiple aerodromes, are some of the most complex airspaces for Air Traffic Control (ATC) in the world. Several tools (e.g. arrival manager (AMAN)) and methods (e.g. point merge and trombone) have been implemented in the recent past to increase safety, TMA capacity and trajectory efficiency. AMAN, for example, assists ATC with the provision of the best (safest and most efficient) arrival sequence. However, it is then up to controllers to achieve this sequence by issuing appropriate clearances, such as ‘Direct To’ instructions, speed adjustments, etc. These clearances are typically based on a controller's individual experience and preferences, making them prone to human error. In busy terminal airspaces, this task can be particularly challenging, with potential negative consequences for controller workload, efficiency and safety.

The TADA project will address this challenge by developing an AI-based digital assistant tool that can support controllers in their decisions to achieve the sequences proposed by the AMAN. The aim of the tool is to reduce workload, thereby increasing capacity and safety, and to provide more efficient and environmentally friendly trajectories. In addition, TADA will develop novel Human Machine Interface (HMI) concepts based on the EASA AI framework to allow human-AI teaming between the controllers and the solution, with eXplainable AI (XAI) embedded in the solution.

The project consortium consists of 6 partners from 4 European countries: INGENAV (Spain), ENAV (Italy), Monad Oy (Finland), Deep Blue (Italy), Frequentis Orthogon (Germany) and the University of Malta. The University of Malta is participating through the Institute of Aerospace Technologies which will contribute to TADA by, amongst other things: gathering historic data; developing machine learning models; participating in validation activities; and publishing the project’s outcomes.