Article Per Year (5 Year)
p-Index From 2021 - 2026
0.23
P-Index
This Author published in this journals
All Journal Jurnal Teknik Mesin, Industri, Elektro dan Informatika
Abrar Al Makassari Yusuf Abdu Matto
Politeknik Negeri Ujung Pandang
Computer Science & IT Electrical & Electronics Engineering Industrial & Manufacturing Engineering

Published : 1 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search

 1 
Implementasi YOLOv8 pada Sistem Pemilah Sampah Otomatis Menggunakan Lengan Robot Riesa Krisna Astuti Sakir; Abrar Al Makassari Yusuf Abdu Matto; Sahbuddin Abdul Kadir
Jurnal Teknik Mesin, Industri, Elektro dan Informatika Vol. 5 No. 1 (2026): Jurnal Teknik Mesin, Industri, Elektro dan Informatika
Publisher : Lembaga Pengembangan Kinerja Dosen

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.55606/jtmei.v5i1.6314

Abstract

The primary challenge in establishing a sustainable environment lies in the efficiency of waste management, which remains heavily dominated by manual sorting methods. Current technological developments are generally limited to passive smart bins that lack the capability to perform autonomous physical actions. Therefore, an innovative active system equipped with a robotic arm is required to execute automated picking and placing operations based on waste categories. This study designs and implements an automated waste-sorting system utilizing the YOLOv8 algorithm for real-time object detection during the picking and placing phases. The system operates through two primary integrated stages driven by visual processing. In the first stage (picking), a web camera identifies the position and material type of the waste—specifically plastic, paper, or glass—enabling the robotic arm's end-effector to grip the object precisely. In the second stage (placing), the spatial coordinates derived from the classification model direct the robotic arm to deposit the waste into the designated bin. Architecturally, image processing is executed by a Raspberry Pi 4, while the mechanical actuator controls are managed by an Arduino Mega microcontroller. Experimental results demonstrate that this vision-based, two-stage coordinated system operates with high classification accuracy and rapid responsiveness. The successful integration of these technologies overcomes the functional limitations of conventional smart bins and offers a viable solution for smart environment initiatives and industrial automation.
Co-Authors Riesa Krisna Astuti Sakir Sahbuddin Abdul Kadir