Cambridge University science and engineering developing AI system for air traffic control.
Cambridge engineers will build a Digital Twin of UK airspace and a related machine learning system that collaborates with humans, as part of a business-led research project announced in support of the government’s UK Innovation Strategy. The Prosperity Partnership is one of eight being supported with an investment of almost £60 million by the Engineering and Physical Sciences Research Council (EPSRC), part of UK Research and Innovation (UKRI), businesses and universities.
Investigators of the collaborative research project titled Project Bluebird: An AI system for air traffic control. The vision is to deliver the world’s first artificial intelligence (AI) system to control airspace in live trials, working with air traffic controllers to help manage the complexities of their role. This system utilises digital twinning and machine learning technologies and includes tools and methods that promote safe and trustworthy use of AI. Such tools will become more important with growing use of uncrewed aircraft and airspace playing a crucial role in delivering aviation’s commitment to net zero emissions by 2050.
The project has three main research themes:
Develop a probabilistic Digital Twin of UK airspace. This real-time, physics-based computer model will predict future flight trajectories and their likelihoods – essential information for decision-making. It will be trained on a NATS (National Air Traffic Services) dataset of at least 10 million flight records, and will take into account the many uncertainties in ATC (air traffic control), such as weather, or aircraft performance.
Build a machine learning system that collaborates with humans to control UK airspace. Unlike current human-centric approaches, this system will simultaneously focus on both the immediate, high-risk detection of potential aircraft conflicts, and the lower risk strategic planning of the entire airspace, thus increasing the efficiency of ATC decision-making. To achieve this, researchers will develop algorithms that use the latest machine learning techniques, such as reinforcement learning, to optimise aircraft paths.
Design methods and tools that promote safe, explainable and trustworthy use of AI in ATC systems. This will involve experiments with air traffic controllers to understand how they make decisions, so that these behaviours can be taught to AI systems. The project will also explore ethical questions such as where the responsibility lies if a human-AI system makes a mistake; how to build a system that is trusted by humans; and how to balance the need for both safety and efficiency.
Professor Girolami, Sir Kirby Laing Professor of Civil Engineering, Royal Academy of Engineering Research Chair at the University of Cambridge, Academic Lead for CSIC and Programme Director for Data-Centric Engineering at The Alan Turing Institute, will work on the development of the Digital Twin.
“The Data-Centric Engineering programme at The Alan Turing Institute has been working with the National Air Traffic Service since 2018 and Project Bluebird is the latest collaboration in this partnership,” he said. “It is particularly exciting to see The Turing’s world-class foundational research in AI, Machine Learning, and Digital Twins coming together and being set to deliver next-generation airspace control in addressing the many challenges we face towards 2050.”
Dr Weller, Principal Research Fellow in Machine Learning at the University of Cambridge, Programme Director for Artificial Intelligence at The Alan Turing Institute and Turing Fellow, will work on the machine learning system and will design methods and tools that promote safe, explainable and trustworthy use of AI in ATC systems.
“I am thrilled to be part of a wonderful team of academics and practitioners focused on delivering trustworthy AI for mission-critical air traffic control in practice,” he said.
Dr Weller has also been announced as a co-investigator of a second Prosperity Partnership titled Project FAIR: Framework for responsible adoption of artificial intelligence in the financial services industry. The project will see The Alan Turing Institute, HSBC, and other organisations, develop the trustworthy, data-driven AI decision-making approaches that are needed for the wider adoption of these technologies in the financial and professional services sector.
Prosperity Partnerships build on existing UK strengths in industry and academia to develop new technologies, processes, and skills that will deliver economic growth and create jobs across the UK.
EPSRC Executive Chair Professor Dame Lynn Gladden said: “Artificial intelligence, digital chemistry and Digital Twins are some of the new and transformative technologies that will help to drive the Net Zero revolution, address major societal challenges, and deliver prosperity to the UK.
“By bringing together UK businesses and universities, these new Prosperity Partnerships will generate the knowledge and innovations that will enable these cutting-edge technologies to realise their transformative potential across a diverse range of sectors.”