Two weeks ago, I had the pleasure of hosting a conference about “AI in space” during the MéléeNumérique event organised by La Mêlée.
I had the chance to talk with a highly interested audience about my experience with embedded AI for satellite anomaly detection.
As stipulated by Arianne Group, a few more years will be needed before artificial intelligence can be used at its full potential for critical space missions (ariane.group/en/news/), so every step counts!
During this talk, I discussed the requirements for embedded AI algorithms in the context of a space mission and the algorithm developed as part of the DIAG-RAD project that met these requirements.
The DyD² algorithm, a practical and effective solution, enables real-time detection of anomalies in dynamic systems.
The best part: it is open-source! If you are interested, don’t hesitate to look at the GitHub project page!
https://github.com/Adrien-Dorise/DyD2_Dynamic_Double_Anomaly_Detection