Browsing by Author "Taglioglu, Gokce Burak"

Now showing 1 - 2 of 2

Citation - WoS: 1
Citation - Scopus: 1
Humanoid Robot Arm Design, Simulation, Kinesthetic Learning, Impedance Control and Suggestions
(Gazi Univ, Fac Engineering Architecture, 2022) Ertugrul, Seniz; Kaya, Ozan; Turkmen, Dila; Eraslan, Hulya; Taglioglu, Gokce Burak; Gulec, Musa Ozgun
Robot technology is constantly developing and the studies in this field are also increasing in our country. Universities, machine-manufacturing and defense industry have been either doing or planning robot projects. This study presents designing of a humanoid robot arm desired to be cooperative so that it can work as dual arm or with human operator. Mechanical design, kinematic and dynamic analysis, kinesthetic learning, impedance control, software and hardware studies were carried out within the scope of the study. The stages from the initial design of the humanoid robot arm to the control, the problems encountered, the experiences gained and the suggestions for advanced designs are shared in a very comprehensive way in this article. It has been explained in an easy-to-understand manner in order to be useful for national robot projects which are being developed especially for commercial purposes. Mechanical design, dynamic analyses, simulation and other files will be shared as open source with interested researchers.
Citation - WoS: 7
Citation - Scopus: 7
The Series Elastic Gripper Design, Object Detection, and Recognition by Touch
(Asme, 2022) Kaya, Ozan; Taglioglu, Gokce Burak; Ertugrul, Seniz
In recent years, robotic applications have been improved for better object manipulation and collaboration with human. With this motivation, the detection of objects has been studied with a series elastic parallel gripper by simple touching in case of no visual data available. A series elastic gripper, capable of detecting geometric properties of objects, is designed using only elastic elements and absolute encoders instead of tactile or force/torque sensors. The external force calculation is achieved by employing an estimation algorithm. Different objects are selected for trials for recognition. A deep neural network (DNN) model is trained by synthetic data extracted from standard tessellation language (STL) file of selected objects. For experimental setup, the series elastic parallel gripper is mounted on a Staubli RX160 robot arm and objects are placed in pre-determined locations in the workspace. All objects are successfully recognized using the gripper, force estimation, and the DNN model. The best DNN model is capable of recognizing different objects with the average prediction value ranging from 71% to 98%. Hence, the proposed design of the gripper and the algorithm achieved the recognition of selected objects without the need for additional force/torque or tactile sensors.