Developing the world's first autonomous AI system for air traffic control

An ambitious EPSRC prosperity partnership applying machine learning, agent-based modelling, and high-fidelity simulation to one of aviation's most complex challenges.

Explore Research Learn More

15+

Publications

Institutions

Years Active

Scroll

Impact & Scale

Research at the Frontiers of Aviation AI

15+

Publications

Institutions

30+

Researchers

Years Active

Digital Twin

A high-fidelity digital twin for developing AI agents and new tools for air traffic management.

Agents

AI agents that manage complex air traffic scenarios using a range of complementary approaches.

Assurance

Assurance, explainability, and validation research for trustworthy AI in air traffic control.

Featured Research

Featured Publications

View All

A Probabilistic Digital Twin of UK En Route Airspace for Training and Evaluating AI Agents for Air Traffic Control

Nick Pepper, Adam Keane, Amy Hodgkin, Dewi Gould, Edward Henderson, Lynge Lauritsen, Christos Vlahos, George De Ath, Richard Everson, Richard Cannon, Alvaro Sierra Castro, John Korna, Ben Carvell, Marc Thomas

AIAA SciTech Forum2026

Human-in-the-Loop Testing of AI Agents for Air Traffic Control with a Regulated Assessment Framework

Ben Carvell, Marc Thomas, Andrew Pace, Christopher Dorney, George De Ath, Richard Everson, Nick Pepper, Adam Keane, Samuel Tomlinson, Richard Cannon

AIAA SciTech Forum2026

A Sector-Specific Probabilistic Approach for 4D Aircraft Trajectory Generation

Nick Pepper, George De Ath, Ben Carvell, Amy Hodgkin, Tim Dodwell, Marc Thomas, Richard Everson

Transportation Research Part C2025

News & Media

Latest Updates

All News

LinkedIn (Ben Carvell)September 2026

Can a machine pass real air traffic control exams?

One of Project Bluebird's AI agents reaches the satisfactory standard in NATS's Area Basic summative exams, recreated in the digital twin and marked by the instructors who assess human trainees.

The ConversationAugust 2026

As the skies get busier, will AI help air traffic controllers keep planes flying safely?

Rob Procter explores how AI decision-support agents could help controllers manage rising traffic — and why establishing trust in their capabilities must come first.

LinkedIn (Marc Thomas)July 2026

What would happen if we let AI do the air traffic control instead of humans?

A 24-hour trial of the digital twin of UK airspace: five types of AI agent control sectors in three instances while a fourth shadows live operations for comparison with human controllers.

The Turing PodcastJune 2026

Cleared for Takeoff: Navigating the Future of AI Air Traffic Control

Ben Carvell and air traffic controller Andy Pace on what controllers do, the three Bluebird research themes, and where responsibility sits when AI assists.

See It in Action

Watch Project Bluebird

Featured

Project Bluebird: An AI system for air traffic control

An overview of the Project Bluebird research programme, its goals, partners, and impact on the future of air traffic management.

Cleared for Takeoff: Navigating the Future of AI Air Traffic Control

Project Bluebird: Revolutionising Air Traffic Control with AI and digital twins