CNN-Based dual arm robot for automated electronic component packing

Mechatronics Engineering, Sathyabama Institute of Science and Technology, Chennai, India

^* Corresponding Author: This email address is being protected from spambots. You need JavaScript enabled to view it.

Published online: 29 April 2026

Abstract

Convolutional Neural Network Twin Arm Robot for Automated Packing of Electronic Components is an intellectual robotic system that is developed as a COCA (Collaborative Operation Control Agent) operational handler of the identification and packaging process of miniature size electronic components like resistors, LEDs, and capacitors. To achieve the correct and lightweight object recognition, the system has been constructed using the MobileNetV2 CNN model with the help of the Raspberry Pi microcontroller and a USB web camera. Upon object detection, two 4-DOF robotic arms are operated by Arduino Mega 2560 and servo motors as well as another one is operated by the servo motors to carry out the packaging. Twin-arm System: It is implemented to enhance the speed and accuracy of the assembly of the minute electronic components. The system uses two 5V SMPS units for power supply, and L-clamps provide mechanical stability. Overall, the integration of computer vision, deep learning and robotics in this project makes the system scalable and efficient and suitable for industrial applications.