The Implementasi Inverse Kinematic Pada Lengan Robot Untuk Proses Pemilahan Barang Berdasarkan Objek Menggunakan Computer VisionTER VISION

Implementation of Inverse Kinematics on a Robotic Arm for the Sorting Process of Goods Based on Objects Using Computer Vision

Abstract

This research applies the inverse kinematics method to control the motion of a robotic arm designed to sort objects based on their color and shape using a computer vision approach. The developed system consists of several components, including a conveyor, an external camera, a robotic arm, an ESP32 microcontroller, and a SCADA platform for system monitoring and control. The external camera captures images of objects moving along the conveyor, which are processed using the HSV algorithm to detect colors—red, yellow, and blue—and the YOLOv8 model to classify object shapes such as cubes and cylinders. The detection results are used as references by the inverse kinematics algorithm to calculate the joint angles of the robotic arm in order to reach the specified target coordinates, allowing the objects to be moved to their respective positions. Experimental results show that the image processing subsystem performs reliably under various lighting conditions, including low illumination and environments with multiple surrounding objects. In addition, the inverse kinematics test showed an average positional deviation of about 1–2 cm from the desired coordinates. Overall, the system is capable of performing object sorting based on color and shape.