Patil et al. Res. Trends Int. J. Technol. Innov., April - June 2026, 1 (2) : 36-44
1Department of Mechanical Engineering, College of Engineering Pune, Pune, India; 2Department of Robotics and Automation, PSG College of Technology, Coimbatore, India
Article History
Accepted : 28 May 2026
Published : 29 Jun 2026
Publication Issue
Volume 1, Issue 2
April - June 2026
Page Number36–44
Manual sorting of recyclable waste is labour-intensive and exposes workers to hazardous materials, motivating vision-guided robotic sorting on mixed municipal solid waste streams. This paper integrates a YOLOv8 object detector with a six-degree-of-freedom robotic arm and suction gripper to identify and sort four recyclable material classes from a conveyor stream. Tested over 2,000 mixed items on a pilot conveyor rig, the system achieved 94.7 percent detection precision and a successful pick rate of 89.3 percent at a throughput of 32 items per minute.
Keywords - robotic sorting, YOLOv8, waste management, computer vision, recycling automation
Municipal recycling facilities increasingly face labour shortages for manual sorting lines, and mixed-material items and contamination make simple colour or weight-based automated sorting insufficient, motivating vision-based approaches capable of discriminating material types under variable lighting and occlusion.
A YOLOv8-medium detector was fine-tuned on a custom-annotated dataset of 9,600 images covering PET bottles, aluminium cans, cardboard and HDPE containers on a conveyor belt, with detections mapped to world coordinates via a calibrated overhead camera and fed to a six-DOF robotic arm fitted with a vacuum suction gripper for pick-and-place sorting into four bins.
The system achieved 94.7 percent mean detection precision at 0.5 IoU across the four material classes, with a successful pick-and-place rate of 89.3 percent, most failures attributable to overlapping items obscuring the gripper approach vector. Sustained throughput averaged 32 items per minute, approaching typical manual sorting-line rates for a single station.
Vision-guided robotic sorting using modern single-stage detectors can approach human sorting throughput on well-defined recyclable streams. Future work will address item overlap handling through multi-view camera fusion.
[1] Jocher G. et al., YOLOv8, Ultralytics, 2023. [2] Sarc R. et al., Digitalisation and intelligent robotics in value chain of circular economy oriented waste management, Waste Management, 2019.
© 2026 The Author(s). Published by IJEIA Editorial Office. This is an open access article under the Creative Commons Attribution 4.0 International License (CC BY 4.0).
Harshad Patil, Kavya Nambiar (2026). Vision-Guided Robotic Arm for Autonomous Sorting of Recyclable Waste Using YOLOv8. IJEIA, 1(2), 36-44.