Robotic Arm System with Computer Vision for Colour Object Sorting

Abstract

This study presents the development of robotic arm with computer vision functionalities to recognise the objects with different colours, pick up the nearest target object and place it into particular location. In this paper, the overview of the robotic arm system is first presented. Then, the design of five-degrees of freedom (5-DOF) robotic arm is introduced, followed by the explanation of the image processing technique used to recognize the objects with different colours and obstacle detection. Next, the forward kinematic modelling of the robotic arm using Denavit-Hartenberg algorithm and solving the inverse kinematic of the robotic arm using modified flower pollination algorithm (MFPA) are interpreted. The result shows that the robotic arm can pick the target object accurately and place it in its particular place successfully. The concern on user safety is also been taken into consideration where the robotic arm will stop working when the user hand (obstacle) is detected and resume its process when there is no obstacle.