This paper presents an AI-based robotic system designed to efficiently sort waste from a moving conveyor belt. Leveraging advanced computer vision techniques and robotic manipulation, the system accurately identifies and categorizes waste items. A deep learning model, trained on a dataset of common waste items, is integrated into a centralized PLC controller. The PLC also directly controls the robot’s joints, ensuring precise synchronization with the conveyor belt. Experimental results demonstrate the system’s ability to achieve high accuracy in waste classification and sorting, proving the feasibility of integrating AI-based models into industrial environments. By automating the waste sorting process, this system contributes to a more sustainable future by reducing waste and promoting recycling.

Robots for Sustainability: Real-Time AI-Based Robotic Waste Sorting from a Moving Conveyor

Boschetti G.;Fabris T.;Sinico T.
2025

Abstract

This paper presents an AI-based robotic system designed to efficiently sort waste from a moving conveyor belt. Leveraging advanced computer vision techniques and robotic manipulation, the system accurately identifies and categorizes waste items. A deep learning model, trained on a dataset of common waste items, is integrated into a centralized PLC controller. The PLC also directly controls the robot’s joints, ensuring precise synchronization with the conveyor belt. Experimental results demonstrate the system’s ability to achieve high accuracy in waste classification and sorting, proving the feasibility of integrating AI-based models into industrial environments. By automating the waste sorting process, this system contributes to a more sustainable future by reducing waste and promoting recycling.
2025
Mechanisms and Machine Science
3rd International Workshop IFToMM for Sustainable Development Goals, I4SDG 2025
9783031911507
9783031911514
File in questo prodotto:
Non ci sono file associati a questo prodotto.
Pubblicazioni consigliate

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11577/3570324
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 1
  • ???jsp.display-item.citation.isi??? ND
  • OpenAlex ND
social impact