Research Software Engineer
Laver Building 701
Laver Building, University of Exeter, North Park Road, Exeter, EX4 4QE, UK
I am a Research Software Engineer, in Exeter's Research Software Engineering Group. I have experience with simulation design, trajectory prediction & optimisation, and machine learning, applied in a variety of aerospace and healthcare settings.
Our group is based in the Laver building: come drop by and say hello! Otherwise find me on LinkedIn.
MPhil in Computer Science at the University of Exeter. Part-time & in-progress.
MEng (Hons) in Aeronautics and Astronautics from the University of Southampton (1st Class).
After completing my MEng at the University of Southampton, I spent two years working as a Design Engineer at Dyson, performing research and development around new technologies and products. My work here was varied, from the rapid prototyping of electronic systems, to computational analysis, to unsupervised machine learning, and much more.
Following this, I spent two years working as a Data Scientist with the University of Exeter and a local health-tech start-up, working towards improving clinic experience for both staff and patients, through the analysis of their spatial trajectories. Finally, prior to my role as a Research Software Engineer, I worked as a Research Fellow, with Prof. Mark Kelson and Institute of Data Science. Here I was investigating themes of open and transparent research, and reproducibility, across a variety of disciplines.
I am currently working on Project Bluebird, a partnership between the University of Exeter, The Alan Turing Institute, and NATS, the National Air Traffic Service. We are building the worlds first Artificial Intelligence (AI)-driven system to control a section of airspace in live trials.
Please see the project description for more information on the key research themes below:
- 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 dataset of at least 10 million flight records, and will take into account the many uncertainties in ATC, 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 air traffic control systems. This will involve experiments with 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.