Rapid Response UAV Post-Disaster Location Network Incorporating ML, Radio Control, and Global Positioning System

Santa Clara High School
Santa Clara, California
Engineering
$819
Goal
Oct 31 at 9 AM PT
This project will launch at the date and time listed above. You can't donate to this project yet.
Approved
  • $0
    pledged
  • 0%
    funded
  • Private
    Not Launched

Build Procedures

Build Procedures:

  1. Assemble frame using provided screws and standoffs following instruction manual in the kit.

  2. Connect standoffs provided to the four underside corner screw holes of the flight controller using screws provided in the kit.

  3. Connect electronic speed controller(ESC) under the flight controller standoffs using screws provided in the kit (same screw size and shape)

  4. Connect ESC wire given in the kit into ESC port on the flight controller as shown in the diagram. Connect battery to check for smoke.

  5. Solder Analog VTX module to FC as shown in the diagram.

  6. Flash Ardupilot copter firmware onto FC using ardupilot flasher as described in the docs.

  7. Download, install, and run Mission planner configurator as described in the docs.

  8. Configure the VTX on the correct baud rate and channel as described in the docs.

  9. Solder the thermal camera to the FC as described in the diagram above.

  10. Make sure the camera and VTX work by testing OSD on VRX as described in the docs.

  11. Solder ELRS receiver to the drone as shown in the diagram above.

  12. Configure ELRS through the ELRS configurator with binding phrase through wifi as described in the docs

  13. Bind ELRS receiver to Radiomaster Boxer with binding phrase and configurator as described in docs.

  14. Solder GPS module to FC as shown in the diagram above.

  15. Setup GPS module using mission planne software as described in the docs.

  16. Configure ELRS receiver and transmitter to use MAVLink as described in the docs.

  17. Setup ELRS Backpack to communicate with Mission Planner as described in the docs.

  18. Find a dataset with aerial views of people, preferably over 15k images on roboflowf.

  19. Train YOLOV8 Transfer learning model on data on roboflow.

  20. Find a dataset with audio of people screaming on roboflow..

  21. Train a model that segments audio of people screaming out of background noise on roboflow. (Propwash, rushing wind)

  22. Setup camera feed on VRX to become a camera input to computer running Mission Planner as described in the docs.

  23. Setup MAVProxy python module for Mission Planner as described in the docs.

  24. Write a Python script that uses YOLOV8 Pytorch model and audio detection to send a ping to a streamlit webpage when they detect a human as described in the docs. It should be able to control waypoints through MAVLink telemetry and dronekit.

  25. Edit Script for MAVProxy to use streamlit input from the object detection to create and delete new waypoints based on what medications the drone is holding (metadata) as described in the docs.

  26. Design a 3d printable dropper mechanism that utilizes a servo.

  27. Attach 3d printable dropper mechanism to drone.

  28. Solder the servo to FC as shown above in the diagram.

  29. In the Python Script write new code that utilizes the servo when a drone reaches the certain waypoint as described in the docs.

  30. Setup channels for RC Controller through Arduflight Configurator as described in the docs.

  31. Configure motor direction and index (Props Out) as described in the docs.

  32. Configure Python Script to use Dijkstra’s algorithm to find closest route for drone drop as described in the docs.

Install dronekit SITL to simulate drone swarming as described in the docs.


Register or Sign in to join the conversation!