Learning algorithm for drawing using Baxter robotic arm

U ovome radu opisan je robot Baxter i njegove glavne karakteristike, posebno obraćajući pažnji na one karakteristike koje će biti korištene tijekom izrade projekta. Na samom početku rada opisuje se postupak analize slike pri kojem se koristi Pythonova biblioteka OpenCV. Korištene funkcije iz ove biblioteke su detaljno opisane i prikazani su dobiveni rezultati. Zatim se uvodi pojam dubokog učenja i zajedno s njim opisane su glavne karakteristike neuronskih mreža. Za treniranje neuronske mreže upotrjebljena je MINST baza podataka, a za razvoj algoritma koristi se Pythonova biblioteka Keras. Završni dio rada se bazira na teach-in tehnici učenja snimanja i reproduciranja trajektorija povučenih robotskom rukom. Na samom kraju su prikazani i opisan dobiveni rezultati.In this paper, the robot Baxter and its main features are described, paying particular attention to those characteristic that will be used during the project. At the very beginning of the work, the process of image analysis using the Python OpenCV library is described. The functions used in this library are described in detail and the results are presented. Then the concept of deep learning is introduced and together with it are described the main features of the neural networks. For training neural networks was used MINST database, and for developing algorithm Python library Keras. The final part of the work is based on teach-in technique of recording and reproduction of trajectories withdrawn by robotic hands. At the very end, the results are shown and described