If you are an ANSP dealing with high controller stress and safety risks — this project developed a digital assistant that predicts mental workload and automatically increases automation levels to prevent overload.
AI Digital Assistant to Prevent Air Traffic Controller Burnout and Human Error
Imagine a smart co-pilot that can tell when a human is getting overwhelmed just by reading their body signals and the current workload. It predicts when a person is about to hit their limit and automatically steps in to help, like taking over a task or simplifying the screen. It's like a stress-sensor for high-stakes jobs that adjusts the tools in real-time to keep things safe.
What needed solving
Air traffic controllers face extreme stress and cognitive overload, which can lead to safety critical errors when the workload exceeds human capacity.
What was built
A digital assistant featuring a task prediction model, a neurophysiological mental state predictor, and an adaptive automation strategy to dynamically reallocate tasks.
Who needs this
Who can put this to work
If you are a rail operator dealing with complex traffic routing and operator fatigue — this project developed a human-machine performance envelope that adjusts task allocation based on the operator's real-time stress levels.
If you are a plant manager dealing with cognitive overload during emergencies — this project developed neurophysiological assessment tools that trigger AI-based support tools when an operator's attention span drops.
Quick answers
What is the cost or pricing for this system?
Based on available project data, the EU contributed EUR 1,929,486 to the research and development, but no commercial pricing model is provided.
Can this be scaled to other industries beyond aviation?
The project uses general principles of human-AI teaming and neurophysiological assessment, which are applicable to any high-stress control environment, though it was specifically designed for air traffic control.
Who owns the IP and how is licensing handled?
Based on available project data, the project is coordinated by DEEP BLUE SRL with 9 partners, but specific licensing terms are not disclosed.
How does this integrate with existing control systems?
The system integrates via a 'Teaming Playbook' and functional requirements that allow it to trigger automation increases or request airspace changes like sector splitting.
What is the timeline for deployment?
The project period runs from 2023-09-01 to 2026-02-28, indicating it is currently in the development and validation phase.
Who built it
The consortium is well-balanced for a technical transition, consisting of 9 partners across 6 countries. With a 22% industry ratio (2 industry partners, including 2 SMEs), the project has a strong academic and research foundation (5 partners) but maintains a direct link to commercial application through the coordinator, DEEP BLUE SRL.
Contact DEEP BLUE SRL in Italy
Talk to the team behind this work.
Request a deep dive into the Human Machine Performance Envelope (HMPE) specifications.