Over £600,000 for the University of Leicester

Scientists at the University of Leicester are developing a method to shrink artificial intelligence algorithms, enabling smarter spacecraft.

It is one of more than 20 national space projects to be announced by DSIT Secretary of State Peter Kyle on the opening day of the Farnborough International Airshow. The £33 million projects come from the UK Space Agency’s National Space Innovation Program – designed to invest in high-potential technologies to drive innovation and unlock growth in the UK.

REALM (Rapid Information Extraction for Remote Sensing of the Spacecraft Environment by Applying Lightweight Machine Learning Models to Payload Computing Systems) has received £690,000 of funding and will be a multidisciplinary team effort from the University of Leicester, which involves the School of Computing and Mathematical Sciences. and the School of Physics and Astronomy, as well as Space Park Leicester, the University’s £100 million science and innovation park.

They aim to develop and demonstrate simplified machine learning algorithms capable of meeting spacecraft power and computing performance requirements using drones. Current machine learning algorithms are too large and complex to accommodate the limited power and performance of spacecraft computing systems. This presents a significant barrier to enabling smarter spacecraft.

REALM aims to address this problem by using a SSP (Spare-Split-Parallelism) design framework that can compress a large multi-spectral remote sensing deep learning algorithm by at least 45% without any performance impact. The performance of the algorithm will be demonstrated on a small-scale space-compatible graphics processing unit (GPU), and its effectiveness will be validated by flying a drone equipped with a multispectral payload as a preliminary step towards space readiness in collaboration with commercial partners.

It is one of 15 ‘Kick Starter’ projects which will receive £9 million between them. They will support technologies and applications that are at an early stage of development and increase readiness for commercial and scientific use. The projects cover a wide range of space-related capabilities, from on-orbit maintenance and production, as well as the development of advanced materials and the use of satellite imagery. A further eight major projects will receive £24m of the total.

Lead researcher Professor Tanya Vladimirova from the School of Computing and Mathematical Sciences at the University of Leicester said: “Until now, real-time information extraction with deep learning-level performance has not been achieved from space. Our novel approach to greatly reduce algorithm size while maintaining high-accuracy performance provides a disruptive enabling technology poised to unlock a wide range of real-time services in space that previously would not have been possible due to complexity their calculation.”

DSIT Secretary of State Peter Kyle said: “From tackling climate change to keeping in touch with loved ones, space technologies play an important role in many aspects of our everyday lives.

“But supporting the growth of UK space companies is also essential to driving economic growth, increasing productivity and creating wealth in every community.

“Our £33 million investment in these projects highlights the huge potential of the UK space industry, especially as we work with international partners.”

Dr Paul Bate, CEO of the UK Space Agency, said: “These new projects will help drive growth, create high-quality jobs, protect our planet and preserve the space environment for generations to come. They go to the heart of what we want to achieve as a national space agency supporting cutting-edge innovation, spreading opportunities across the UK and delivering the benefits of space back to citizens on Earth.”