search

nasa / OnAIR

The On-board Artificial Intelligence Research (OnAIR) Platform is a framework that enables AI algorithms written in Python to interact with NASA's cFS. It is intended to explore research concepts in autonomous operations in a simulated environment.
66 stars 15 forks source link

42 redo sbn reintegrate #135

Closed williamzhang0306 closed 3 months ago

williamzhang0306 commented 3 months ago

This branch updates the sbn_adapter data source to the current state of OnAir and including unit tests.

williamzhang0306 commented 3 months ago

Should the files config/sbn_cfs_config and data.telemetry_configs/adapter_TLM_CONFIG.json stay in this branch? I'm pretty sure they were used for testing sbn_adapter with cfs at one point, but I don't know where that testing was done.

the-other-james commented 3 months ago

I copied these changes over to a setup I have for a different project, and can confirm that it functions as expected and the OnAIR results were identical with the older SBN rework I did.

williamzhang0306 commented 3 months ago

Overall this is looking really good! I had just a few questions / nitpicks.

Can you also document how you ran this with cFS? If this is short, you can add it to the top level readme, otherwise do it in a separate doc. For cFS, can you point me to the repo you set up and I'll fork it?

Great work, thanks!

Thank you! This is the repo I used for cfs: https://github.com/williamzhang0306/cFS-OnAIR.

jlucas9 commented 3 months ago

Note that we are also including OnAir in NOS3 which includes a distribution of cFS draco-rc4 at the time of writing:

We made forks for now trying to get things working:

I can add you both to the repos if you'd like to assist directly there and collaborate more closely!