Here’s a fun project from Joerg Schultz that will help train your pooch! Here’s more via hackster.io:
How can I train my dog to stay on its mat, even when I am not in the same room? Typical feeders can treat after a given time, but they don’t know whether the dog is still on its mat or left to go somewhere else (like excitedly greeting a scared visitor :-). Here, I address this challenge using Machine Learning based Image classification. I (transfer) trained a neural network using Edge Impulse to distinguish an image of a dog on a mat from one with an empty mat…. I deployed the model on a Rasberry Pi. Finally I connected the RasPi via BueTooth to an Android App, which then can trigger a feeder. Now my dog is reinforced for staying on its mat and reinforcement stops when he leaves. All without me being present. On the long run system like this can address typical behaviuor problems like reacting to the door bell, over-exitedly greeting visitors or barking at passer-bys relying completely on positive reinforcement.
Each Friday is PiDay here at Adafruit! Be sure to check out our posts, tutorials and new Raspberry Pi related products. Adafruit has the largest and best selection of Raspberry Pi accessories and all the code & tutorials to get you up and running in no time!
No comments:
Post a Comment