BLUE
Profile banner
M
marsokod.bsky.social
@marsokod.bsky.social
Space Engineer, co-founder @SpaceUp_FR , Space and OSS enthusiast. Supaero and Michigan alumni framapiaf.org/@marsokod
15 followers118 following54 posts
Mmarsokod.bsky.social

Imagine coding a self driving car going trans US. A simple way would be to code all the movements from the get go. But as soon as a small issue arises, it is game over. So you can either make sure there are no issues (expensive) or have something to correct the course when there is one. 2/2

0
Mmarsokod.bsky.social

And for orbital mechanics, yes we can do it. But when something goes wrong (thruster malfunction, error in pointing), it can be complex to recover in real time with traditional algorithms. Given the difficulties in sat comms, this meant a lot of effort was put on making sure things go right 1/2

1
Mmarsokod.bsky.social

There are many different applications. I worked on close proximity manoeuvres where we were using deep learning for pose estimation, you can do something similar for Lunar/Mars landing. You can also pre-process your data onboard to save on the data budget. And you can also do analytics in real time.

2
Mmarsokod.bsky.social

J'ai eu quelque chose de très léger sur Londres. Difficile à voir à l'oeil nu, mais une exposition longue sur le téléphone permet de bien voir le phénomène. Mais nuages + pollution lumineuse n'aide pas.

0
Profile banner
M
marsokod.bsky.social
@marsokod.bsky.social
Space Engineer, co-founder @SpaceUp_FR , Space and OSS enthusiast. Supaero and Michigan alumni framapiaf.org/@marsokod
15 followers118 following54 posts