Yazar "Sen, Mehmed Oguz" seçeneğine göre listele

Listeleniyor 1 - 3 / 3
  • Küçük Resim Yok
    Öğe
    A Blockchain-Oriented Task Scheduling and Allocation System for ROS Enabled Mobile Robots
    (Ieee-Inst Electrical Electronics Engineers Inc, 2025) Sen, Mehmed Oguz; Okumus, Fatih; Fatih Kocamaz, Adnan
    In multi-mobile robot applications, the operational processes such as the management of robots, task assignment, monitoring of assigned tasks, communication and coordination between robots, and data storage are executed through a centralized server system. Therefore, most critical decisions are made on this centralized server rather than by the robots themselves. However, working in a centralized system has numerous disadvantages such as the obligation to maintain a server, routing all communication through a central unit, susceptibility to connectivity issues that render the system inoperable, and increased bandwidth requirements as the number of robots increases. Moreover, any communication issues between the server computers and any of the robots in centralized systems affect the entire system's operation. To address these limitations, a blockchain-powered distributed communication system for inter-robot communication has been developed in this study. A task allocation application between robots has been implemented on this developed distributed communication system. In the application, Hyperledger Fabric (HLF) has been utilized as the blockchain platform due to its advantages. Each robot is a peer in the blockchain network in the proposed system. A cost function which is computed in all robots has been introduced to reduce the communication load in the blockchain network during task distribution and to enable optimal task allocation among robots. With the proposed system, robots compute and choose the most suitable tasks using the cost function, hence transactions on the blockchain network are kept at optimal level. After reaching consensus of peers on task allocations via HLF, task data are transmitted to robots by Robot Operating System (ROS) integration. With the proposed system, a dynamic and distributed architecture has been introduced and implemented where mobile robots can communicate with each other over a blockchain network without the need for a centralized server. In experimental studies conducted on real robots, the proposed system demonstrated optimal task allocation across multiple phases, effectively adapting to various task requirements in different scenarios. For instance, in one scenario, the system effectively allocated a total of 9 tasks, distributed across two phases: 3 tasks in the first phase and 6 tasks in the second phase. This study presents an innovative contribution to the literature on communication of robots and task allocation. Also, this study has a high potential to be adapted to industrial applications including robotic instruments.
  • Küçük Resim Yok
    Öğe
    Artificial Immune System Optimization Based Duplex Kinect Skeleton Fusion
    (Ieee, 2017) Gunduz, Ali Fatih; Sen, Mehmed Oguz; Karci, Ali; Yeroglu, Celaleddin
    Human motion tracking, which requires both motion sensing hardware and algorithms based on computer vision, is an enjoyable and active research area with diverse applications. As a depth sensor device Kinect is a famous hardware component for this task. In this work, we studied using more than one Kinect camera to obtain better motion tracking which is applicable for motion capture. We synthetically created two camera data from one and then focused on de-noising and fusing these data in order to obtain more realistic skeleton joint coordinates. Artificial Immune System (AIS) optimization algorithm is suggested and used for this task. As a result we obtained 30% better fusion results from noisy synthetic data. Our results showed that AIS is a promising algorithm for obtaining optimal joint coordinates in the fusion of multiple Kinect skeleton data.
  • Küçük Resim Yok
    Öğe
    Comparison of Trajectories Formed With Kinect Motion Capture Data
    (Ieee, 2015) Sen, Mehmed Oguz; Erturkler, Metin
    Motion capture is the process of recording people or object movements. Generally, marker based systems are used for this process. In these systems, motion data is acquired by placing markers on certain points on the object whose motion is going to be captured. However preserving markers' positions on the object, dependency on the object, high cost and requirement of specially designed workspace causes difficulties in usage. In recent years, development of motion sensing camera systems like Microsoft Kinect became an alternative of marker based systems. In this study, Frechet distance algorithm is suggested for similarity measurement of movement trajectories that are formed by motion capture data acquired using Microsoft Kinect cameras. Measurement of movement similarity is crucial for certain applications. (activity recognition, object classification, path finding for humanoid robots etc.)