Show HN: Waiting for AI Grand Prix racing SIM? Me too So I made one
An open-source simulator for Anduril's AI Grand Prix has been developed to assist contestants in preparing for the autonomous drone-racing competition. The simulator features high-fidelity physics and a real flight controller, allowing users to practice their coding skills. It is designed to be user-friendly and can be set up in a matter of minutes on various operating systems.
- ▪The simulator is based on the Elodin engine and is intended for use in a $500K drone-racing competition.
- ▪It includes features like a forward FPV camera and automatic pass-time tracking for practice runs.
- ▪Users can quickly install and configure the simulator with a few simple commands on macOS or Linux.
Opening excerpt (first ~120 words) tap to expand
AI Grand Prix Playground An open-source, Elodin-based practice simulator for Anduril's AI Grand Prix — a $500K autonomous drone-racing competition. Built so contestants can iterate on perception, planning, and control code today, while the official Virtual Qualifier 1 simulator finishes baking. What you get out of the box: High-fidelity 6-DOF physics from Elodin (deterministic, GPU-rendered, multi-rate sensors) around a generic 5-inch racing quad, our best public guess until the reference airframe is published. A real Betaflight SITL flight controller in lockstep with the physics, talking standard MAVLink-style RC + PWM over UDP. A forward FPV camera matching the AI Grand Prix tech-spec intrinsics (640×360, fx=fy=320, cx=320, cy=180, +20° up-tilt, 30 Hz).
…
Excerpt limited to ~120 words for fair-use compliance. The full article is at GitHub.