Its not just a stabilization/rate control loop but the NN does both guidance and control. It is an MLP that takes state + upcoming gate positions/waypoints and controls the motors directly. I.e. there is no explicit path planning going on but rather the NN outputs motor commands that hopefully help the drone traverse the given waypoints in minimum time. I think this is quite cool because running a similar Optimal Control MPC setup is really not at all feasible on a normal STM32H7 Flight controller, especially at 1kHz.
Oh, I see how this works now! That's _incredibly_ clever, not at _all_ what I would have guessed, and quite innovative. Thank you so much for taking the time to post these explanations.
It's fundamentally different, it's using an RL trained network that gets the drone state (position, orientation, velocity) as input and directly outputs motor commands.
Not much since it doesn't take images as it's input and it's running on an embedded mcu. Based on the papers linked elsewhere in here the state vector is 24 floats and it's running at 1kHz so around 100 kB/s.
It used a small RL trained network running on the flight controllers MCU directly that controlled the motors given state (position, orientation ...) inputs. The Jetson handled vision processing.
