Image: © aapsky/Stock.adobe.com
Using AI/ML in satellite monitoring has the potential to decrease costs and reduce satellite downtime, the team says.
Dublin-based Réaltra Space Systems Engineering has won a European Space Agency (ESA) contract to work on a project that will develop AI and machine learning use-cases on the failure detection and recovery systems in Low Earth Orbit satellites.
Réaltra is working with Ubotica, a space-tech company also based in Dublin, acting as the subcontractor. Meanwhile, the team’s project, titled ‘Machine Learning-Based On-Board Autonomy,’ which funded under the ESA’s General Support Technology Program, has already completed the preliminary design review.
The team’s aim is to deliver high performance AI/ML systems on satellites which can function using low power, capable of running its algorithms with low-latency inferencing capabilities – which means that the satellite data will be processed quickly through the AI model before any appropriate action is taken.
For this project, Réaltra will be utilising data sets from the EIRSAT-1 – Ireland’s first satellite launched last year.
According to the team, using AI/ML for satellite monitoring has the potential to decrease the operating costs by reducing the need for human intervention, as well as reducing satellite downtime.
The technology offers the ability to detect and respond to anomalies in real-time while also enabling the wider use of commercial off-the-shelf electronics, further driving costs of future avionics systems down.
“As the global space economy continues to grow, we recognise the importance of developing and progressing new technologies to meet current and future demands,” said Danny Gleeson, the CCO of Réaltra.
“We are delighted to have secured this ESA project and look forward to working on new, cutting-edge space technology.”
According to US government data, the number of active satellites in the Low Earth Orbit could reach more than 60,000 by 2030 – up from the nearly 10,000 satellites in orbit as of this May.
James Murphy, the project lead and space software and AI engineer at Réaltra said: “With the advent of large satellite constellations, there is an increasing need for these satellites to become smarter. On-board AI will soon be a requirement for satellite missions to enable levels of autonomy never before seen.
“Advancing research in AI for Space is an important part of developing the space industry and preparing for the next generation of space flight.”
Fintan Buckley, the CEO of Ubotica said: “In addition to enabling real-time on-orbit decision-making, autonomous operations, and streamlining data processing, applying space AI to address the on-board fault detection, isolation, and recovery challenge is a significant step forward in maximising the operational lifetime of these satellites.
“Solutions like space AI are pivotal in enhancing communication, situational awareness, and scalability, ensuring the expanding satellite network adapts to future needs.”
Two Réaltra-developed hardware technologies – a video telemetry system and a global navigation satellite system made it to space earlier this year on-board the ESA’s Ariane 6 rocket, a contract the company won the year prior.
While just weeks ago, Ubotica, in collaboration with NASA published a research paper on ‘Dynamic Targeting’ for Earth observation, showcasing how the team uses AI to develop intelligent satellite systems.
Don’t miss out on the knowledge you need to succeed. Sign up for the Daily Brief, Silicon Republic’s digest of need-to-know sci-tech news.
