Development of a robotic manipulator for object detection using a convolutional neural network

V diplomskem delu smo izdelali robotski manipulator. V ta namen smo razvili algoritme za izvajanje giba iz točke v točko ter linearnega giba. Pri izvajanju teh gibov smo uporabili kvadratni, kubični ter sinusni profil poti. Ustvarili smo grafični vmesnik za nadzorovanje robotskega manipulatorja. Robot smo nadgradili s kamero. Z uporabo nevronske mreže in strojnim vidom smo izdelali aplikacijo, kjer vrh robota sledi roki uporabnika. Algoritme gibanja in profile poti smo predhodno simulirali z uporabo programa MSC Adams.In this thesis, we have created a robotic arm. For this research, we developed algorithms for linear and point-to-point motions. These algorithms use quadratic, cubic and sine profiles for servo easing. We have upgraded the robot arm with a camera. Using a neural network and machine vision, we developed an application where the top of the robot follows the hand of the user. Before implementation, we tested all the motion algorithms using MSC Adams