@aarav_patel0436

Today I finished the main code and PCB design work for the drone tracking and interception project. The software side is now working, including the turret tracking system and the depth perception setup. I tested the camera-based tracking, servo movement, and position estimation, and the system is able to detect and follow the target properly. A big part of the project also changed direction. At first, I was trying to hack into a commercial drone controller and control the drone that way, but that turned out to be unreliable and difficult to build on. After testing, debugging, and experimenting with different control methods, I pivoted to designing my own custom PCBs for the drone instead. I am still using the original drone frame, but the electronics will be custom-made so I can control the motors and hardware much more directly. I also finished designing the custom PCBs for the project. One board is for the drone-side control hardware, and the other is for the turret/control setup that connects the computer, camera, stepper, servos, and control electronics together in a cleaner and more organized way. After a lot of debugging, redesigning, and checking the layouts, the boards are ready to be manufactured. At this point, most of the major development work is complete. The code is finished, the tracking and depth perception systems have been tested, and the PCB files are ready. Now I just need to wait for the custom PCBs to arrive so I can assemble the hardware, test everything together, and finish the final version of the project. I couldn’t post all my videos and screenshots in this one post, but hopefully everyone will be able to see them in the future.

Finally, I’m getting close to finishing both the turret and the drone-control system.On the turret side, the vision tracking pipeline is working with the servo. The detector can find the drone, estimate its position in the camera frame, and send movement commands to the tracking hardware. The next major step is testing the full pan-and-tilt behavior together, so the turret can smoothly follow a moving drone instead of only proving that one axis works. This will involve tuning the tracking response, reducing jitter, and making sure the servo and pan mechanism move accurately without overshooting.On the drone-control side, this was a huge milestone. After accidentally damaging the drone controller board, repairing it, and spending hours debugging different circuit designs, I finally got computer-based control working through a Raspberry Pi Pico 2. The Pico acts as a ground-station hardware bridge: it receives control commands from the computer over USB and converts them into analog joystick-like signals that the drone remote can understand.One of the biggest problems was that the original joystick potentiometers were still physically connected to the controller board, so they were pulling the signal voltage back toward center. After testing with a voltmeter, I found that the Pico was sending the correct signal, but the controller board was loading it down. Changing the resistor value in the filter circuit gave the Pico enough authority over the signal line while still keeping the output controlled and smooth.At this point, the system can successfully influence the drone remote from the computer. The next step is to finish testing all control channels, verify the voltage ranges with the multimeter, and then move into careful live movement tests. This is the first time the project has connected the detection/tracking software to real hardware control in a way that actually works.

After taking a brief pause from this project during finals week, I’m excited to share that I finally got real-time drone tracking working.

The system can now detect my drone from a live camera feed using a custom-trained YOLOv8 model and draw reliable bounding boxes around it. From there, I calculate the center of the drone’s bounding box, compare it to the center of the camera frame, and use that offset to track where the drone is moving. I also started mapping that position onto a 3D graph using OpenCV, with only one camera instead of a multi-camera setup.

This took quite a bit of math and debugging. I had to work through monocular camera geometry, pixel offsets, scaling, and OpenCV visualization before the tracking started making sense. I also trained and tested my own drone detection model, then built the pipeline so the model can run live, pick the highest-confidence drone detection, and output useful position/error data in real time.

The next step is connecting this tracking system to the physical turret. The code now calculates horizontal and vertical error values from the drone’s position in the frame, which can be sent to an Arduino to control pan and tilt movement.

Currently I’m working on “hacking” into this small drone I own, and doing some resoldering and rewiring so that this store-bought drone can be controlled digitally though my Arduino instead of through a human with its remote. Then using this digital control system, I can then intercept the larger flying drone and take it down.