Computer vision approach for controlling educational robotic arm based on object properties

Abstract

This research presents an autonomous robotic frame work for academic, vocational and training purpose. The platform is centred on a 6 Degree Of Freedom (DOF) serial robotic arm. Two on-board cameras develop a computer vision system for detection and autonomous object/target manipulation placed randomly on a target surface and controls an educational robotic arm to pick it up and move it to a predefined destination. The computer vision is initially used to identify the colour and shape of the object. The system applies Centre-Of-Mass based computation, filtering and colour segmentation algorithm to locate the target and the position of the robotic arm. The proposed platform finds its potential to teach technical courses (like Robotics, Control, Electronics, Image-processing and Computer vision) and to implement and validate advanced algorithms for object manipulation and grasping, trajectory generation, path planning, etc. Experimental results demonstrated the effectiveness and robustness of the system.