Design of autonomous handling robotic manipulator system with3D object detection

This work deals with the possibility of integrating a 3D sensor into a robotic manipulation, with an intention to automatically detect, track and grasp an object, placing it in another location. To enhance the flexibility and easy functionality of the robot, MATLAB, a versatile and powerful programming language is used to control the robot. These kind of 6 DOF robot manipulators are widely used in industry. They find common application in assembling, packaging, palletizing and pick and place operations. For this work, a common industrial task in many factories of pick and place is implemented. For this work, a robotic system consisting of an ABB IRB120 robot equipped with a gripper and a 3D Kinect for Windows camera sensor is used. The 3D data acquisition, image processing and some different camera parameters are investigated. The information in the image acquired from the camera is used to determine the robot's working space and to recognize workpieces. This information is then used to calculate the position and orientation of the objects. Using this information, an automatic path to grasp an object was designed and developed to compute the possible trajectory to an object. To be able to detect the workpieces, object recognition techniques are applied using available algorithms in MATLAB's Computer Vision Toolbox and Image Acquisition Toolbox. These give information about object position and orientation of the object of interest. The information is then transferred to the robot for path planning via a client-to-server connection over a computer network. . The test results therefore show that the system is able to pick and place objects randomly placed in the robot's working space in real time