Late last year the European Space Agency selected 12 projects for funding to advance computing techniques and AI. Could the E.S.A also have been in the EAP?
ESA launched the first artificially intelligent Earth observation satellite in September 2020. Named ɸ-sat (pronounced phi-sat), the satellite carried an AI-accelerator chip that automatically discards cloudy images and send only useful data down to Earth.
Smarter Satellites: ESA Discovery Accelerates AI in Space
PARIS (ESA PR) — Could we capitalise on the Earth-based digital revolution to make our satellites smarter? ESA Discovery is funding 12 projects that will explore the potential of applying the latest developments in artificial intelligence (AI) and advanced computing paradigms to make satellites...newspaceglobal.com
The latest step came in October 2021, when the Discovery element of ESA’s Basic Activities – working together with Φ-lab and ESA’s new commercialisation department – launched a call for ideas on how we can make space systems more powerful using novel computing techniques and AI. The most interesting ideas have now been selected for funding.
The selected ideas involve new technologies developed outside the space sector – including blockchain, edge computing, and neuromorphic computing (inspired by the workings of the human brain),” says Gabriele. “The ideas address amazing applications across the space domain including early detection of methane gas and natural disasters, autonomous rovers on the Moon, space surveillance and tracking – all because information could be processed more efficiently.”
View attachment 23797
Opportunity: The Application of Neuromorphic Processors to SatCom Applications
Our mission is to connect Europe. We join engineers, entrepreneurs and investors to forge strong links between institutions, industries, and businesses.
artes.esa.int
Opportunity: The Application of Neuromorphic Processors to SatCom Applications
Our mission is to connect Europe. We join engineers, entrepreneurs and investors to forge strong links between institutions, industries, and businesses.
ABOUT THE PROPOSED ACTIVITY
The proposed activity will take the form of an investigation into the application of neuromorphic processor architectures within satcom systems; focussing on AI-based applications that require massive parallelism/matrix-based computer operations, but also considering other applications where the use of neuromorphic processors could benefit the performance, reliability, power consumption, or cost of satcom payloads.The activity will assess and compare the performance and implementation of the identified applications when run on standard processor solutions (i.e., GPU/CPUs/ FPGA/ AI-Accelerators, etc.) compared to neuromorphic designs to quantify any gains in terms of computational time, power consumption, reliability, and processor footprint as well as other relevant figures of merit. In addition, the activity should identify new applications that are considered prohibitive to run on standard architecture on-board processors and for which neuromorphic processors therefore represent an enabler. Together with Neuromorphic Processors, the contractor shall research and explore their software technology counterpart. That is, the use of new ML models like Spiking Neural Networks that when implemented on Neuromorphic Processors, exhibit favourable properties such as low power consumption, fast inference, and event-driven information processing. Spiking neural networks or third generation artificial neural networks are a new type of neural networks that functionally mimic natural neural networks even closer than traditional artificial neural networks.
Finally, the study will include a survey of the current state-of-the-art for neuromorphic processor products and solutions, as well as corresponding software toolkits and frameworks, and identify suitable radiation tolerant devices (e.g., novel memristors and MRAM) that could be incorporated into neuromorphic processor-based architectures. A specific goal would be to provide early identification of any industrial dependencies that may exist for critical components.
For the last two years, we have put together in ESA a team of experts in the fields of Neuromorphic Computing, Event-based sensors, Machine Learning, On-board Payload Data Processing and On-board AI-accelerated hardware to explore the technological challenges and potential enablers of neuromorphic computing in space.
I bit more info from the European Space Agency about satelite communications
