Ubotica Technologies has announced that its CVAI™ artificial intelligence (AI) technology has been successfully deployed into orbit on board the PhiSat-1 satellite, which was launched from the Vega Launch Complex in Kourou, French Guiana on September 4, 2020.
PhiSat-1 is part of an ambitious and ground-breaking programme funded by the European Space Agency (ESA) and supported by Enterprise Ireland, in which state-of-the-art Deep Learning technology for the in-orbit processing of Earth Observation data is being deployed on a European satellite for the first time.
Irish-designed Intel Movidius Myriad 2 Vision Processing Unit
The Ubotica CVAI™ AI technology, which is based on the Irish-designed Intel Movidius Myriad 2 Vision Processing Unit, will enable decisions to be made on-board PhiSat-1 rather than on the ground, resulting in faster, more efficient applications being deployed on the satellite.
The AI task being demonstrated on PhiSat-1 is that of automatic cloud detection on images captured by the satellite’s advanced hyperspectral sensor.
This is the first of a number of programmes in which Ubotica is working with leading players in the European space sector to enable the development and deployment of highly performant AI applications in space, in a time and cost-efficient manner, using Commercial Off The Shelf (COTS) components.
Aubrey Dunne, co-founder and vice-president (VP) of engineering at Ubotica Technologies, said: “We are very excited to be a key part of the PhiSat-1 mission by enabling the demonstration of AI in an autonomous CubeSat application, in conjunction with ESA and our European partners.
Two years of effort
"This mission is the culmination of two years of effort by Ubotica, in collaboration with ESA, to characterise and prepare the Myriad 2 device for deployment in space.
"Myriad’s low-power, high-performance compute is ideally suited to satellite applications, and Ubotica’s AI technology harnesses this compute to effectively address the opportunities that we are seeing emerge in the ‘New Space’ paradigm.”
Damien English TD, Minister of State for Business, Employment and Retail, said: “The key role of Ubotica Technologies in Europe’s first smart satellite, which will allow for decision making and processing on board, is yet another example of the extraordinary and impressive capabilities of Irish high-tech start-up companies.
"This significant achievement, supported by national RD&I programmes in addition to Ireland’s membership of the European Space Agency and the EU Space programmes, will enable Ireland to realise the vision of the National Space Strategy for Enterprise alongside the aims of Future Jobs Ireland, particularly the enhancement of skills in areas including AI and Machine Learning (ML).
More effectively address climate disruption
"Additionally, and importantly, the contribution of Ubotica Technologies to the PhiSat-1 mission will further equip Europe and Ireland to more effectively address climate disruption, an issue which is requiring an increasingly urgent response”.
Tom Kelly, Enterprise Ireland divisional manager, innovation and competitiveness, said: “Enterprise Ireland is delighted to be part of this European success story.
"The technology originally developed by Movidius, with support from Enterprise Ireland, has been brought to space by Ubotica, one of our exciting new high-tech startup companies. This a truly groundbreaking application – a European first – that will have a profound impact on Earth Observation and contribute to informing our response to climate change.”
Josef Aschbacher, director of Earth Observation programmes, European Space Agency, said: "The Myriad 2 chip, which was developed with Irish expertise at Movidius [subsequently bought by Intel] and brought to space by Ubotica, an AI start-up, is a prime example of Ireland's innovation power in space.
'Huge potential from this technology'
"The AI chip is the core element of the PhiSat-1 experiment and is the first AI chip on a European Earth observation satellite. PhiSat-1 will allow ESA to explore the power of AI in space. I expect huge potential from this technology for future Earth observation satellites, which would reduce costs while at the same time increasing performance.”
Gianluca Furano, ESA Data Systems and on-board computing lead, European Space Agency, said: “The spin in of AI/ML technology in space applications will eventually lead to a breakthrough in on-board data processing capabilities thus allowing new, exciting applications in all fields [remote sensing, exploration, opportunistic science].
"It will for example allow concentration of the data acquired over multiple sensors reducing the required number of electronic units, saving mass, power, volume and reducing harness complexity.
"Technology is by no way restricted to one domain, as it is applicable to both platform and payload sides allowing to provide, except for its main purpose, useful by-products. What we have done with PhiSat-1 is a world's first, that will show industries and institutions that 'edge AI in space' is now, not in a decade's time.”