This project aims to develop: Deep learning-based solutions for versatile waste detection and sorting, a Robotic-based modular system for safe and efficient planning and cooperative handling of waste materials, and a Data-analytics tool to support and digitalize the waste management process planning. The scope of the project is focused on solving particular problems that are common in the waste sorting industry and pointed out as bottlenecks by three early adopter companies, leaders in waste management industry in Serbia (eReciklaza – Nis, Kappa Star Recycling – Belgrade, Unitrade Export – Belgrade, Eko Sistem – Jagodina).

This project investigates how innovations in collaborative robotics, cloud, IoT, and artificial intelligence could be utilized to automate or improve Serbian state-of-the-art practice in waste sorting and recycling (focusing on PET, cans and electronics materials) – which are more human-centered and facilitates the road towards a circular economy. The additional challenges of the existing recycling practices are hazardous workplace conditions as well as the dirty and dusty environment, which make them well suited to be supported by robots. 
CircuBot focuses on several specific objectives for advancing the recycling industry, with major implications to better reuse of waste materials, environmental protection, shortage of workers and enhancing human labor aspect in waste sorting and handling, and consequently creates added value in ecology, economy and healthcare.

     Figure 1. AI-generated photo of future waste sorting.

     Figure 2. Aim and scope of the CircuBot project: To utilize collaborative robotics, artificial intelligence, internet of things, cloud, and data analytics to digitalize and improve waste sorting.

This research was supported by The Science Fund of Republic Serbia, Grant #6784, GREEN –CircuBot