The REALM (Rapid information extraction for environmental remote sensing on board spacecraft through application of light Machine Learning models in payload computing systems) project has secured Pounds 690,000. It is a collaborative effort by the University of Leicester, involving the School of Computing and Mathematical Sciences, the School of Physics and Astronomy, and Space Park Leicester, the University's pioneering Pounds 100 million science and innovation park.
The team's goal is to develop and demonstrate compact machine learning algorithms that can meet spacecraft power and computing performance requirements using drones. Current machine learning algorithms are too large and complex for the limited power and performance capacities of spacecraft computing systems, creating a significant obstacle to developing smarter spacecraft.
REALM intends to overcome this challenge by employing a novel sparse-split-parallelism (SSP) design framework, capable of compressing a large multi-spectral remote sensing deep learning algorithm by at least 45% without sacrificing performance. The algorithm's efficiency will be showcased on a small-scale space-compatible graphical processing unit (GPU) and validated through drone tests equipped with a multispectral payload, as an initial step towards space readiness in collaboration with commercial partners.
This project is one of 15 'Kick Starter' initiatives that will share Pounds 9 million in funding. These projects aim to advance technologies and applications in early development stages, increasing their readiness for commercial and scientific applications. The projects encompass a diverse array of space-related capabilities, including in-orbit servicing and manufacturing, advanced material development, and satellite imagery utilization. Additionally, eight major projects will receive Pounds 24 million of the total investment.
Professor Tanya Vladimirova, Principal Investigator from the University of Leicester School of Computing and Mathematical Sciences, stated: "To date, real-time information extraction with deep-learning level performance has not been achieved from space. Our novel approach to reduce algorithm size considerably while maintaining high accuracy performance provides a disruptive enabling technology poised to unlock a wide range of real-time services from space that previously would not have been possible due to their computational complexity."
DSIT Secretary of State Peter Kyle added: "From combating climate change to staying connected with loved ones, space technologies play an important role in many aspects of our day-to-day lives. But backing the growth of UK space companies is also essential for driving economic growth, boosting productivity, and creating wealth in every community. Our Pounds 33m investment in these projects highlights the huge potential of the UK's space industry, especially as we collaborate with international partners."
Dr Paul Bate, CEO of the UK Space Agency, commented: "These new projects will help kickstart growth, create more high-quality jobs, protect our planet and preserve the space environment for future generations. They go to the heart of what we want to achieve as a national space agency that supports cutting-edge innovation, spreads opportunity across the UK and delivers the benefits of space back to citizens on Earth."
Related Links
School of Computing and Mathematical Sciences University of Leicester
All about the robots on Earth and beyond!
| Subscribe Free To Our Daily Newsletters |
| Subscribe Free To Our Daily Newsletters |
