Receive free Artificial intelligence updates
We’ll send you a myFT Daily Digest email rounding up the latest Artificial intelligence news every morning.
UK researchers have developed a computer model of air traffic control that utilizes artificial intelligence to direct flight movements. This “digital twin” representation of the airspace over England is the result of a £15 million project aimed at exploring the potential role of AI in advising and, eventually, replacing human air traffic controllers. Known as project Bluebird, the research is a collaboration between National Air Traffic Services, the Alan Turing Institute, and Exeter University, with funding from UK Research and Innovation. The initial findings of the project were presented at the British Science Festival in Exeter.
The integration of AI into air traffic control has several benefits, including the ability to direct aircraft along more fuel-efficient routes to reduce environmental impact, minimize delays and congestion at busy airports like London’s Heathrow, and address the shortage of air traffic controllers who require extensive training.
Richard Everson, a professor of machine learning at Exeter University, revealed that Nats has an extensive database of past flight records, making it an ideal resource for training their AI system. The database contains 10 million flight paths, providing valuable data for the project. Human controllers and AI agents are now collaborating to process aircraft within the digital twin of UK airspace, utilizing accurate simulations of real-life air traffic.
Cannon, the research leader on Bluebird, stated, “By the end of the project in 2026, we aim to run live ‘shadow trials’ in which the AI agents will be tested on real-time air traffic data, allowing for a direct comparison with human controllers’ decision-making process.” However, Cannon emphasized that the AI system will not have the authority to determine aircraft routing.
If successful, the research is expected to lead to AI working alongside human controllers in more extensive operational trials over several years before implementing a computer-controlled system.
Nats already possesses a powerful computer system for processing data in one of the world’s busiest airspaces, but it currently does not utilize AI to predict future flight trajectories.
In the past month, the system experienced a major failure over a bank holiday weekend due to its inability to recognize a flight plan with contradictory data, resulting in travel disruptions. The Civil Aviation Authority has launched an investigation into the incident, and affected airlines are seeking compensation from Nats.
Cannon and Everson refrained from commenting on whether AI could have prevented the system failure that led to over 1,500 flight cancellations.
However, Everson stated that AI should enhance the resilience of air traffic control and reduce the risk of failure in unexpected events. The digital twin created by Bluebird covers the London flight information region, encompassing airspace over most of England and Wales.
According to Everson, the AI system routes aircraft while maintaining a necessary separation of 1,000 feet vertically and 5 nautical miles horizontally. It also ensures the safety and collision-free operation of each flight path for at least 15 minutes in the event of radio communication failure between the pilot and air traffic control.
Cannon concluded, “In every air traffic control system in the world, all decisions are made by a human. We are not saying that we want to automate the skies over the UK, but we are pushing the envelope as far as we safely can.”
Denial of responsibility! Vigour Times is an automatic aggregator of Global media. In each content, the hyperlink to the primary source is specified. All trademarks belong to their rightful owners, and all materials to their authors. For any complaint, please reach us at – [email protected]. We will take necessary action within 24 hours.
