Yazar "Cetin, Halil" seçeneğine göre listele

Listeleniyor 1 - 3 / 3
  • Küçük Resim Yok
    Öğe
    Imitation and Learning of Human Hand Gesture Tasks of the 3D Printed Robotic Hand by Using Artificial Neural Networks
    (IEEE, 2016) Ergene, Mehmet Celalettin; Durdu, Akif; Cetin, Halil
    In this study social learning and skill acquisition of a robotic hand via teaching and imitation was aimed. The subject of Human-Robot collaboration, which includes the theme of this paper, is a common field of experiments in our age of technology. Many disabilities can be defeated or many other things, which a human being would not be able to do, can be done with the help of this technology. As an example, a robotic hand can be a light of hope of a person who does not have a hand or wants to hold an object remotely over the internet. So that in our paper it is explained how a robotic hand can learn via imitation. In the experiment a robotic hand, which was printed by a 3D printer, was used and controlled wirelessly by a computer that recognizes human hand gesture via image processing algorithms. The communication between the computer and the robot is provided with a Bluetooth module. First of all, the image processing algorithms such as filtering and background subtraction were applied to the frames of the camera and extracted the features. Secondly, the process of teaching and testing of Artificial Neural Networks (ANNs) was made for the recognition of the hand and the gestures. After that, recognized actions were imitated by the robotic-hand hardware. Eventually, the learning of the robot via imitation was achieved with some small errors and the results are given at the end of the paper.
  • Küçük Resim Yok
    Öğe
    Path planning of mobile robots with Q-learning
    (IEEE, 2014) Cetin, Halil; Durdu, Akif
    Robotic systems which rapidly continue its development are increasingly used in our daily life. Mobile robots both draw the map where they may move in their environment and reach to the determined target in the shortest time by going on the shortest way in their prepared map. In this paper, Q-learning-based path planning algorithm is presented to find a target in the maps which are obtained by mobile robots. Q-learning is a kind of reinforcement learning algorithm that detects its environment and shows a system which makes decisions itself that how it can learn to make true decisions about reaching its target. The fact that a mobile robot truly finds targets that are located on different points in a few sample maps by processing our proposed Q-learning-based path planning algorithm is shown at the end of the paper.
  • Küçük Resim Yok
    Öğe
    Robot Imitation of Human Arm via Artificial Neural Network
    (IEEE, 2014) Durdu, Akif; Cetin, Halil; Komur, Hasan
    In this study, a robot arm that can imitate human arm is designed and presented. The potentiometers are located to the joints of the human arm in order to detect movements of human gestures, and data were collected by this way. The collected data named as "movement of human arm" are classified by the help of Artificial Neural Network (ANN). The robot performs its movements according to the classified movements of the human. Real robot and real data are used in this study. Obtained results show that the learning application of imitating human action via the robot was successfully implemented. With this application, the platforms of robot arm in an industrial environment can be controlled more easily; on the other hand, robotic automation systems which have the capability of making a standard movements of a human can become more resistant to the errors.