Cleared for Takeoff: Navigating the Future of AI Air Traffic Control
47 minutes Posted Jun 16, 2026 at 7:04 am.
The Hidden Chessboard at the heart of Air Traffic Control
Meet Ben Carvell and Andy Pace
What Air Traffic Control Officers (ATCOs) Do
Safety Rules for aviation
Introducing Project Bluebird
3 Main themes of Bluebird’s research: Digital Twins, AI Agents for Air Traffic Control, and Trust
The legal and moral responsibility of Air Traffic Control Officers
The Science: The Physics Informed ML (PML) behind Bluebird. Including dealing with variability and the unknown.
Rules Optimisation versus Reinforcement Learning (RL)
A blast from the past
A collaboration with Johns Hopkins University tackling the issue of explainability in RL introducing ‘Relevant traffic’
TRUST: Safety Minima vs Collisions in Airspace – what is ‘non-negotiable’?
Interrogating the AI’s logic
A curriculum for machines? The AI’s and ATCOs final exam
00 Bringing an ATCO onto project Bluebird – tool support for ATCOs
Intuition vs learning – the ‘mystical ATCO scan’
The ever-crowding airspace and increasing challenges to ATCOs
The history of Bluebird: 2020 versus now
How ATCOs really feel about Bluebird
Introducing Falcon - Are humans the ultimate guarantor of safety, or is our cognitive limit the ceiling for system efficiency?
Move 37 and the potential for discovery
Collaboration between institutions and the real outputs Bluebird has made (the game!)
wrap up
0:00
47:19
Show notes
Join Amelia, Andy and Ben as they discuss the challenges and opportunities of building an AI system to assist ATCOs in one of the most safety-critical industries in the world.
This podcast uses Podbean for stats, and dynamic audio, and Podtrac for stats. Learn more on this podcast's About tab. Dynamic Audio may cause this episode's timestamps to be slightly off.