I did this project to get my feet wet with transfer learning on the Jetson Nano. The robot can recognise three simple graphical markers and navigate between them.
CAD and the Python code is here:GitHub - XRobots/tracks although I haven’t uploaded the model, but it’s very easy to train your own using the camera-capture utility and the instructions: jetson-inference/pytorch-collect-detection.md at master · dusty-nv/jetson-inference · GitHub
