Neuroflight: Next Generation Flight Control Firmware
This work addresses the problem of outdated PID controllers in UAV flight control, offering a novel firmware solution for drone enthusiasts and developers, though it is incremental as it builds on existing neural network methods.
The authors tackled the lack of innovation in low-level flight control for UAVs by introducing Neuroflight, an open-source neuro-flight controller firmware, which achieves stable flight and aerobatic maneuvers with execution speeds over 2.67kHz on embedded hardware.
Little innovation has been made to low-level attitude flight control used by uncrewed aerial vehicles (UAVs), which still predominantly uses the classical PID controller. In this work we introduce Neuroflight, the first open source neuro-flight controller firmware. We present our toolchain for training a neural network in simulation and compiling it to run on embedded hardware. Challenges faced jumping from simulation to reality are discussed along with our solutions. Our evaluation shows the neural network can execute at over 2.67kHz on an Arm Cortex-M7 processor and flight tests demonstrate a quadcopter running Neuroflight can achieve stable flight and execute aerobatic maneuvers.