THERMAL SCIENCE

International Scientific Journal

Jun-Nan Tian

,

Zheng-Rong Xiang

,

Yun-Cai Yan

DESIGN OF WASTE SORTING SYSTEM COMBINING RASPBERRY PI AND ROBOTIC ARM

ABSTRACT
With the acceleration of urbanization, the amount of household waste generated has increased sharply. In order to solve this problem and promote the intelligent upgrade of urban garbage disposal, a garbage sorting system combining Raspberry Pi and robotic arm was designed. The hardware part of the system includes components such as Raspberry Pi main control board, robotic arm extension board, six degree of freedom robotic arm, USB camera, etc. The software utilizes platforms such as VNC and Jupyter Lab to train a suitable model by improving the Yolov4-tiny algorithm, which is then ported to the Raspberry Pi. The camera module detects the category of garbage, and the Raspberry Pi main control board controls the movement of the robotic arm to classify the garbage and send it to the correct location. The test results show that the average recognition success rates of the system under strong light, weak light, and normal light conditions are 92.00%, 93.00%, and 96.50%, respectively.
KEYWORDS
Raspberry Pi, Robotic arm, Waste sorting, Improve Yolov4-tiny algorithm
PAPER SUBMITTED: 2025-07-11
PAPER REVISED: 2025-10-15
PAPER ACCEPTED: 2025-12-30
PUBLISHED ONLINE: 2026-07-25
DOI REFERENCE: https://doi.org/10.2298/TSCI250711152T
REFERENCES (10)
[1] Phong, N. T., et al., The Role of Information in Enhancing Waste Sorting Capability among Consumers in Lao Cai City, Vietnam, Sustainability, 16(2024), (14), 6244, pp.1-15
[2] Hajovsky, R., et al., Design of an IoT-Based Monitoring System as a Part of Prevention of Thermal Events in Mining and Landfill Waste Disposal Sites: A Pilot Case Study, IEEE Transactions on Instrumentation and Measurement, 72(2023), pp.1-14
[3] Toaçar, M.E., et al., Waste Classification Using AutoEncoder Network with Integrated Feature Selection Method in Convolutional Neural Network Models, Measurement, 153 (2020), 107459, pp.1-25
[4] Fang, B. B., et al., Artificial Intelligence for Waste Management in Smart Cities: a Review, Environmental Chemistry Letters, 21 (2023), 4, pp.1959-1989
[5] Wang, C., et al., A Smart Municipal Waste Management System Based on Deep-learning and Internet of Things, Waste Management, 135(2021), 1, pp.20-29
[6] Verma, V., et al., A Deep Learning-Based Intelligent Garbage Detection System Using an Unmanned Aerial Vehicle, Symmetry, 14(2022), 5, 960, pp.1-15
[7] Ahangar, S. S., et al., Sustainable Design of a Municipal Solid Waste Management System in an Integrated Closed-loop Supply Chain Network Using a Fuzzy Approach: a Case Study, Journal of Industrial and Production Engineering, 38 (2021), 5, pp.323-340
[8] Debnath, P., et al., MQTT-Based Adaptive Estimation Over Distributed Network Using Raspberry Pi Pico W, IEEE Embedded Systems Letters, 16(2024), 4, pp.517-520
[9] Yu, K., et al., High Speed and Precision Underwater Biological Detection Based on the Improved YOLOV4-Tiny Algorithm, Journal of Marine Science and Engineering, 10 (2022), 12, 1821, pp.1-14
[10] Lin, Y. H., et al., Locating Image Objects With Probability Distributions, IEEE Signal Processing Letters, 29(2022), 1, pp.2722-2726
PDF VERSION [DOWNLOAD]
Design of waste sorting system combining Raspberry Pi and robotic arm

© 2026 Society of Thermal Engineers of Serbia. Published by the Vinča Institute of Nuclear Sciences, National Institute of the Republic of Serbia, Belgrade, Serbia. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution 4.0 International licence