AI Grand Prix Autonomy Stack
A full autonomous drone-racing stack for the AI Grand Prix VQ1 competition: classical computer vision gate detection, a finite-state mission controller, and real-time MAVLink setpoint control.
What we set out to solve.
Autonomous drone racing requires sub-second perception, decision, and control loops on commodity hardware — without GPS, without external cues, and without compute-heavy deep learning. Every gram of CPU spent on inference is speed lost on the track.
How we built it.
HSV gate detection
Gates are detected with a tuned HSV threshold pipeline and circular contour fit — fast, deterministic, and explainable. No model weights, no GPU; the entire perception path runs in tens of milliseconds on the onboard processor.
FSM mission controller
A finite state machine sequences flight: INIT → ARM_HOVER → SEEK_GATE → APPROACH → THROUGH. State transitions key off gate confidence and pose error, giving predictable, debuggable behavior at race speed.
MAVLink control loop
Position and velocity setpoints stream over MAVLink via pymavlink at the flight controller’s native rate. A tuning sweep across PID and lookahead parameters shaved 55 seconds off the lap time on the simulated course.
The numbers.
What it changed.
A racing autonomy stack that proves you do not need deep learning for every robotics problem. Classical CV plus disciplined control engineering delivers competitive performance — with a fraction of the compute and none of the model-drift risk.