Quadcopter with OAK-D depthAI stereo camera

I have upgraded my quadcopter XJ470 with a Skydroid T12 radio, an OAK-D depthAI stereo camera and a Raspberry Pi 4 companion computer. This configuration enables state-of-the art artificial intelligence drone piloting. The skydroid t12 enables long distance telemetry and video. The OAK-D combines depth measurements and artificial object detection. The RPi 4 has an WiFi access point enabling remote desktop communication by means of VNC. Avoidance python scripts are uploaded to the RPi 4, generating mavlink drone messages controlling the quadcopter. A test video demontrates the new features.

You need to be a member of diydrones to add comments!

Join diydrones

Comments

andre van calster December 20, 2021 at 5:43am

Hi Glenn. Thx. I have a github summarizing most of my work: https://github.com/avncalst/drone_cnn. This was my first test with the OAK-D. I intend to elaborate more on my avoidance script and improve it a lot.

GitHub - avncalst/drone_cnn: python cnn files for drone obstacles avoidance

python cnn files for drone obstacles avoidance. Contribute to avncalst/drone_cnn development by creating an account on GitHub.
Glenn Gregory December 19, 2021 at 3:24pm

Hi nice work. I have a OAK-D camera on the way also. I'm interested further with what you are using this for? Are you doing any kind of localization? Do you have a blog or github with more info?

This reply was deleted.