Scrapsort: An Autonomous System for Sorting Objects at the Edge

An implementation of a machine learning-based system for sorting objects in real-time. The system operates independently of the cloud with limited space, power, and cost. We explore the specific application of sorting recyclables at the edge, which stands in contrast from existing waste processing systems that use highly complex software and hardware in order to classify and sort a large variety of items coming from several different waste streams. Moving the sorting process closer to the point of waste generation reduces the risk of contaminating recyclables and enables local data collection to train the classification system on specific waste sources. This eases the classification task which enables the use of cheap, low-power electronics. Specifically, our system uses a low-power microcontroller with an on-board camera module and a convolutional neural network (CNN) accelerator for classifying items. This microcontroller also controls a series of stepper motors that drive a set of mechanical arms to physically sort objects that move along a conveyor belt.

Task List