KUZGUN Fighter UAV
An 11.9 kg autonomous combat UAV that dogfights, evades air defenses, and dives at targets — all without human input. Year 1 was the KUZGUN platform. Year 2 is an evolution with variable sweep wings. Still in progress.
KUZGUN — Fighting UAV
KUZGUN was built for the TEKNOFEST 2025 Fighting UAV competition. The goal was to eliminate human dependency in air combat — the UAV handles target detection, locking, dogfight maneuvering, and air defense evasion completely on its own.
At 11.9 kg with a thrust-to-weight ratio of 1.26, it hits 106 km/h, takes off in 5 meters, and flies for 35 minutes on cruise. The software stack runs YOLOv11m detection, ByteTrack multi-object tracking, and A* path planning — all on a Jetson Orin Nano with a triple-redundant comm link.
Core Systems
The autonomous stack that handles detection, combat maneuvering, threat evasion, and communication.
Autonomous Dogfighting
The UAV identifies rival aircraft, locks on autonomously to score points, and executes evasive maneuvers when targeted. No human input during combat — the system decides when to track, lock, and break away.
Computer Vision Stack
YOLOv11m for detection (51.5% mAP, benchmarked against SSD and Faster R-CNN), ByteTrack for multi-object tracking (best FPS and lowest ID switches vs SORT/DeepSORT), and Horn-Schunck optical flow for tracking targets that leave the camera frame.
Kamikaze & Precision Dive
Receives target coordinates from the competition server via QR code, flies to the point autonomously, checks for rivals, ensures altitude > 100m, then executes a -45° dive with an out-turned U-tail design to read QR codes at high speed using C++ OpenCV.
A* Air Defense Evasion
Pulls real-time coordinates of active air defense systems from the competition server and uses an A* Search Algorithm to calculate the safest flight path through defended airspace. Recalculates paths dynamically as new threats appear.
Triple-Redundant Comms
RFD868X for long-range telemetry (40 km range, FHSS). Quectel EC25-E LTE Cat 4 for 4G video streaming (720p H.264 via UDP). Ubiquiti Loco M5 Wi-Fi bridge (5 GHz, 5 km) as backup for both telemetry and video.
Hardware Integration
Pixhawk 2.4.8 flight controller running MAVLink, Jetson Orin Nano (8GB) for AI, RPi HQ Camera (12.3MP, 50-60 FPS at 1080p). Dual battery system — 12S 16Ah 60C for propulsion, separate 3S 4.2Ah for avionics — with DC-DC converters for clean power.
Vision & Tracking
The vision pipeline has three layers. YOLOv11m handles initial detection — we benchmarked it against SSD and Faster R-CNN, and it gave the best balance of accuracy (51.5% mAP) and speed on the Jetson's GPU.
ByteTrack handles frame-to-frame object tracking. We tested SORT and DeepSORT too, but ByteTrack beat them on both FPS and ID switch rate — critical when you're tracking a rival UAV during high-speed maneuvers.
The clever part: when a target leaves the camera frame, we don't lose it. Horn-Schunck optical flow estimates where it went, so the UAV can predict the rival's position and re-acquire as soon as it's back in view.
PID controllers translate angular differences between the UAV heading and the target position into real-time flight commands — approach, lock, or break.
Real-time target tracking on aerial footage — 348 avg FPS, 206 FPS live tracking.
Aerodynamics & Propulsion
CFD analysis validated the aerodynamic design. The prototype was tested in XPS before the final carbon fiber build.
Fail-safes: autonomous landing on signal loss or battery below 20%.
Variable Sweep Wing
Year 2 is an evolution of the KUZGUN platform — same competition, new airframe. We're building a variable sweep wing UAV that can change wing angle mid-flight. Wings swept back for high-speed dashes and dogfighting, wings forward for slow-speed loiter and precision maneuvers.
I'm handling the aerodynamic analysis in OpenVSP, the computer vision upgrades (OpenCV + YOLO for target detection), and integrating the sweep mechanism with the Ardupilot flight controller so the wing angle changes are coordinated with the autopilot's control loops.
This project is actively being developed. The aerodynamic design is done, the software stack from Year 1 is being adapted, and we're currently building the physical prototype with the sweep mechanism.
- ✓Aerodynamic design (OpenVSP)
- ✓Year 1 software stack
- ◐Sweep wing mechanism
- ◐CV upgrades + integration
- ○Physical prototype build
- ○Flight testing
Year 2 variable sweep wing design — wings change angle for different flight profiles.
Two years of building combat UAVs
This project covers autonomous navigation, real-time computer vision, cryptographic communications, aerodynamic design, embedded AI, and now variable geometry — all for a competitive combat scenario.
Get in touch