Hacker News: pacetest

New comment by pacetest in "Autonomous drone defeats human champions in racing first"

pacetest — Sat, 07 Jun 2025 14:48:43 +0000

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.

New comment by pacetest in "Autonomous drone defeats human champions in racing first"

pacetest — Sat, 07 Jun 2025 12:32:11 +0000

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.

New comment by pacetest in "Autonomous drone defeats human champions in racing first"

pacetest — Thu, 05 Jun 2025 07:47:45 +0000

No, but there's a previous paper for the controller used: https://arxiv.org/abs/2504.21586

New comment by pacetest in "Autonomous drone defeats human champions in racing first"

pacetest — Thu, 05 Jun 2025 07:45:07 +0000

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.

New comment by pacetest in "Autonomous drone defeats human champions in racing first"

pacetest — Thu, 05 Jun 2025 07:32:33 +0000

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.