Robotic Waste Sorting Technology: Toward a Vision-Based Categorization System for the Industrial Robotic Separation of Recyclable Waste

Abstract

The use of robots in waste processing plants can significantly improve the processing of recyclables. Such robots need sophisticated visual and manipulation skills to be able to work in the extremely heterogeneous, complex, and unpredictable waste sorting industrial environment. This article considers the implementation of an autonomous robotic system for the categorization and physical sorting of recyclables according to material types. In particular, it focuses on the development of a low-cost computer vision module based on deep learning technologies to identify and sort items. To facilitate further research endeavors, the data set of recyclable images and a group of image processing scripts for object identification, masking, and synthetic placement against multiple backgrounds are available in an open source GitHub repository (https://github.com/kskmar/ReSort-IT.git). The deep-trained computer vision module is integrated with a robotic system that undertakes the physical separation of recyclables. The composite system is deployed in a waste processing plant, where it is successfully assessed in recyclable sorting under difficult and demanding industrial conditions.