Development of a robotic manipulator under ROS system

Abstract

The rise of Industry 4.0 has enabled the robots to flourish both in industry and academia in recent years; for robot users, the robot operating system employed is mainly developed by various robot manufacturers for private use. The main goal of this study is to build a five-axis robotic manipulator using 3D printing technology and then apply the open source ROS (Robot Operating System) platform and MoveIt to control the robotic arm. Consequently, the robot arm URDF model, GUI interface control, motion path planning, real-time actuation and data feedback can be obtained. Furthermore, an eye-to-hand camera and deep learning using Tensorflow are integrated to the developed robot arm. Experimental results validate the ROS-based robot arm for object recognition and sorting task.