Digital Twin
Project Bluebird's high-fidelity digital twin of UK airspace is a safe environment for developing and evaluating AI agents, and enables fast prototyping of new tools to support air traffic management.
Capabilities
High-Fidelity Simulation
Our digital twin replicates UK airspace, including aircraft dynamics, airspace configurations, weather effects, and procedures, producing realistic scenarios grounded in operational data.
Probabilistic Trajectory Generation
A probabilistic machine learning model trained on historical data generates realistic trajectories, capturing real-world uncertainty in aircraft behaviour due to weather, pilot intent and operational factors.
Live Data Streaming
Incorporating live radar data, flight plans, and meteorological feeds to create simulation scenarios that mirror actual operational conditions, allowing real-time assessment of agents.
Open-Source Platform
BluebirdATC is our open-source release, enabling researchers worldwide to build upon our work and advance the field of aviation AI.
Explore the Platform
Access the open-source Bluebird simulation environment and technical documentation.
Read Our Digital Twin Research
Explore publications on digital twin simulation, trajectory modelling, and evaluation for air traffic control.
- Graph-based Complexity Forecasts in UK En Route Airspace Using Relevant Aircraft Interactions
US-Europe ATRD Symposium, 2026
- Conditioning Aircraft Trajectory Prediction on Meteorological Data with a Physics-Informed Machine Learning Approach
AIAA SciTech Forum, 2026
- Fast Surrogate Models for Adaptive Aircraft Trajectory Prediction in En route Airspace
AIAA SciTech Forum, 2026
- A framework for assuring the accuracy and fidelity of an AI-enabled Digital Twin of en route UK airspace
AIAA SciTech Forum, 2026