As a beginner, after going through and completing all of the Example Notebooks available in the Jetbot Repository (which were awesome btw). I thought to myself what’s next? I have a well trained Road Following model, a well trained Collision Avoidance model and a self-made track so I decided to combine both these optimized models into one notebook and this was the result:
The Jetbot was able to follow a specific path on the track and at the same time also able to avoid collisions with obstacles that come on it’s way in real-time by bringing the Jetbot into a complete halt. The Collision Avoidance can be trained on different obstacles including vehicles, people, stop signs, traffic lights or any other object that you would expect to see on the road!
For more details on how to use the script feel free to have a look at the Github Readme and I hope you all enjoy your self-driving collision-avoidance vehicle!
Any feedbacks are welcome and I would very much love for this to be added as an extension to the original Jetbot Repo! Cheers ✌.