Classifying components with different geometric shapes by UR5 cobot

Machine learning is a major subset of artificial intelligence studies in the literature. Deep learning is also a specialized machine learning technique which includes convolutional neural networks. In deep learning techniques, it is not necessary to manually extract features from the training dataset for object recognition and classification problems. Image processing with deep learning techniques has a significant advantage of extracting the necessary features automatically for classification, by processing the training dataset through neural networks. In this thesis, a MATLAB based object recognition program is created using deep learning techniques to recognise and classify components with different geometric shapes, more specifically screws, washers and nuts, which are fed to the experiment setup randomly and one by one from an assembly line. The performances of Alexnet, Googlenet and Squeezenet algorithms, which have been widely used in the literature for image recognition problems, are investigated, in order to decide which object recognition algorithm can be used in the software part of the thesis. A common data set, which consists of the photos of the objects, is prepared for recognising and classifying screws, washers and nuts. Instead of the objects that already present in the library of each algorithm, each algorithm is trained by this data set with the transfer learning method. The performance of trained algorithms are initially tested on a software medium with the photos of data set reserved as test data. Afterwards a benchmark test is carried out on the actual hardware with an USB webcam for those algorithms. The tests performed on both software and hardware revealed that the Squeezenet algorithm achieved the highest performance. The object recognition program with the Squeezenet algorithm performs communication with UR5 collaborative robot (cobot) through TCP/IP by sending a unique message for each prediction case. A robot control program is designed with Polyscope programming language which exists on robot's teach pendant to control the robot's movements. The robot control program receives the prediction output of a MATLAB based object recognition program by continuously listening to a specific port over TCP/IP and completes the classification process by moving the robot arm according to received message to pick up the component and put it into the relevant box. A voltage controlled electromagnet is used as an end effector for the robot arm since the screws, washers and nuts used in this thesis study have ferromagnetic characteristics. Different scenarios are prepared on the Polyscope based robot control program to perform the necessary tasks of the robot arm for each component. Finally, the performance of the overall system is put to test and both the hardware and the software parts are observed to be operating successfully.