Autonomous Drone Platform
A vision-guided autonomous quadrotor built around a Jetson Orin Nano and an Orbbec depth camera, with a laser-cut carbon fibre airframe. Final year project.
- Jetson Orin Nano
- ROS 2
- Orbbec Gemini 336
- C++
- Python
- CAD
The problem
Autonomous flight in cluttered, GPS-denied environments needs the whole stack to work together: a depth sensor that returns usable geometry indoors, enough onboard compute to close the perception loop without a ground station, and an airframe stiff enough that the vibration doesn't destroy your state estimate.
This is my final year project — building that platform end to end rather than buying it.
Approach
I took the Stanford MSL TrajBridge drone as the hardware reference design and worked outward from the compute and sensing I already had.
Perception and compute. An Orbbec Gemini 336 depth camera paired with an NVIDIA Jetson Orin Nano for onboard inference. The Orin Nano is the pivot point of the design — it's enough to run depth processing and a navigation policy onboard, which means the aircraft doesn't depend on a radio link to stay alive.
Airframe. I originally planned a 3D-printed frame and abandoned it after working the numbers: for the stiffness required it came out both too heavy and too weak compared to carbon fibre. The design moved to laser-cut carbon fibre sheet for the primary structure, keeping 3D printing for non-structural mounts and sensor brackets, where its geometric freedom actually pays for itself.
Propulsion. Built around AIR 2216/KV920 motors, sized against the mass budget the carbon frame and the Orin Nano impose.
Explore the airframe
I built an interactive schematic of this aircraft — orbit it, and select any component to see its specs, what it's wired to, and whether it actually exists yet. The geometry is generated procedurally in code rather than loaded from a mesh file, so it stays honest as the build changes.
Where it stands
In progress. The frame design and the compute and sensing selection are settled; the current work is propulsion sizing and integration.
What I took from it
The frame decision was the useful lesson. The 3D-printed version was the obvious path, and the analysis said no — a good reminder that convenient manufacturing is not the same as appropriate manufacturing, and that on an airframe the mass budget arbitrates every argument.