Imagine if air traffic controllers had a crystal ball that could spot traffic jams in the sky an hour before they happen. Instead of reacting to chaos in real-time, this tool uses AI to predict where planes will bunch up and suggests ways to fix it early. It's like a smart GPS for the sky that helps avoid the digital equivalent of a highway pile-up.
Air traffic controllers often face sudden 'hotspots' or congestion that current tools only predict 20 minutes in advance. This leads to high workloads, fuel inefficiency, and operational delays.
An AI-based prediction function for 4D areas of high complexity and accompanying HMI concepts for flow managers.
If you are an ANSP dealing with high controller workload and unexpected sector overloads — this project developed an AI-based tool that predicts hotspots 1 hour in advance. This allows for better demand-capacity balancing and reduces the stress on air traffic controllers.
If you are an ATM technology provider dealing with outdated flight plan-based prediction tools — this project developed a 4D trajectory prediction system. This enables the creation of smarter interfaces that bridge the gap between flow management and tactical control.
If you are an airline dealing with fuel waste due to tactical ATC interventions and delays — this project developed a resolution strategy for hotspots. This leads to more fuel-efficient trajectories and more predictable flight operations.
Based on available project data, no commercial pricing is provided as the project is EU-funded with a contribution of EUR 1,139,244 for research and development.
The project aims to reach TRL2, meaning it is currently in the conceptual and formulation stage and not yet ready for full industrial scale.
Based on available project data, specific licensing terms are not mentioned, though the project involves a consortium of 5 partners including an academic institution and industry providers.
The tool is designed to bridge the gap between Flow Management Positions (FMP) and Controller Working Positions (CWP) through new Human Machine Interface (HMI) concepts.
The project period runs from 2023-09-01 to 2026-02-28.
The consortium is highly industry-weighted with an 80% industry ratio, comprising 4 industrial partners (including 2 SMEs) and 1 university. This structure suggests a strong focus on practical application, combining academic research from the University of Malta with the operational expertise of an ANSP and ATM technology providers across 4 countries.
Contact the University of Malta regarding the ASTRA project coordination.
Contact SciTransfer to explore licensing opportunities for AI-driven ATM tools.
