This recycling bin sorts waste by audio classification

While a large percentage of our waste can be recycled, only a small percentage actually makes it to the proper facility due, in part, to improper sorting. So, in an effort to keep more of our waste from ending up in landfills without requiring additional labor, Samuel Alexander built a smart recycling bin that relies on machine learning to automatically categorize waste based on from the noise of the collision and sort them into separate internal compartments. .

Because the trash should know what the trash is thrown into, Alexander started this project by first building a minimal rig with an Arduino Nano 33 BLE Sense to capture audio and send it to a project Edge Impulse. From there, the samples were split into 60 one-second samples for each type of trash, including cans, paper, bottles, and random background noise. The model, once trained, was then deployed to the Nano as a custom Arduino library.

With the board now able to distinguish the type of waste thrown away, Alexander got to work on the remaining portions of the smart bin. The base received a stepper motor that rotates the four compartments to line up with a servo-operated hatch while a LiPo battery powers everything for completely cordless operation.

To learn more about how this hack was created, you can check out Alexander's article here on Hackaday.io.