Yazar "Kivrak, Hasan" seçeneğine göre listele

Listeleniyor 1 - 6 / 6
  • Küçük Resim Yok
    Öğe
    Cyber-physical system architecture of autonomous robot ecosystem for industrial asset monitoring
    (Elsevier, 2024) Kivrak, Hasan; Karakusak, Muhammed Zahid; Watson, Simon; Lennox, Barry
    Driven by advancements in Industry 4.0, the Internet of Things (IoT), digital twins (DT), and cyber-physical systems (CPS), there is a growing interest in the digitalizing of asset integrity management. CPS, in particular, is a pivotal technology for the development of intelligent and interconnected systems. The design of a scalable, low-latency communication network with efficient data management is crucial for connecting physical and digital twins in heterogeneous robot fleets. This paper introduces a generalized cyber-physical architecture aimed at governing an autonomous multi-robot ecosystem via a scalable communication network. The objective is to ensure accurate and near-real-time perception of the remote environment by digital twins during robot missions. Our approach integrates techniques such as downsampling, compression, and dynamic bandwidth management to facilitate effective communication and cooperative inspection missions. This allow for efficient bi-directional data exchange between digital and physical twins, thereby enhancing the overall performance of the system. This study contributes to the ongoing research on the deployment of cyber-physical systems for heterogeneous multi-robot fleets in remote inspection missions. The feasibility of the approach has been demonstrated through simulations in a representative environment. In these experiments, a fleet of robots is used to map an unknown building and generate a common 3D probabilistic voxel-grid map, while evaluating and managing bandwidth requirements. This study represents a step forward towards the practical implementation of continuous remote inspection with multi-robot systems through cyber-physical infrastructure. It offers potential improvements in scalability, interoperability, and performance for industrial asset monitoring.
  • Küçük Resim Yok
    Öğe
    Cyber-WISE: A Cyber-Physical Deep Wireless Indoor Positioning System and Digital Twin Approach
    (Mdpi, 2023) Karakusak, Muhammed Zahid; Kivrak, Hasan; Watson, Simon; Ozdemir, Mehmet Kemal
    In recent decades, there have been significant research efforts focusing on wireless indoor localization systems, with fingerprinting techniques based on received signal strength leading the way. The majority of the suggested approaches require challenging and laborious Wi-Fi site surveys to construct a radio map, which is then utilized to match radio signatures with particular locations. In this paper, a novel next-generation cyber-physical wireless indoor positioning system is presented that addresses the challenges of fingerprinting techniques associated with data collection. The proposed approach not only facilitates an interactive digital representation that fosters informed decision-making through a digital twin interface but also ensures adaptability to new scenarios, scalability, and suitability for large environments and evolving conditions during the process of constructing the radio map. Additionally, it reduces the labor cost and laborious data collection process while helping to increase the efficiency of fingerprint-based positioning methods through accurate ground-truth data collection. This is also convenient for working in remote environments to improve human safety in locations where human access is limited or hazardous and to address issues related to radio map obsolescence. The feasibility of the cyber-physical system design is successfully verified and evaluated with real-world experiments in which a ground robot is utilized to obtain a radio map autonomously in real-time in a challenging environment through an informed decision process. With the proposed setup, the results demonstrate the success of RSSI-based indoor positioning using deep learning models, including MLP, LSTM Model 1, and LSTM Model 2, achieving an average localization error of <= 2.16 m in individual areas. Specifically, LSTM Model 2 achieves an average localization error as low as 1.55 m and 1.97 m with 83.33% and 81.05% of the errors within 2 m for individual and combined areas, respectively. These outcomes demonstrate that the proposed cyber-physical wireless indoor positioning approach, which is based on the application of dynamic Wi-Fi RSS surveying through human feedback using autonomous mobile robots, effectively leverages the precision of deep learning models, resulting in localization performance comparable to the literature. Furthermore, they highlight its potential for suitability for deployment in real-world scenarios and practical applicability.
  • Küçük Resim Yok
    Öğe
    Physiological Data-Based Evaluation of a Social Robot Navigation System
    (Ieee, 2020) Kivrak, Hasan; Uluer, Pinar; Kose, Hatice; Gumuslu, Elif; Barkana, Duygun Erol; Cakmak, Furkan; Yavuz, Sirma
    The aim of this work is to create a social navigation system for an affective robot that acts as an assistant in the audiology department of hospitals for children with hearing impairments. Compared to traditional navigation systems, this system differentiates between objects and human beings and optimizes several parameters to keep at a social distance during motion when faced with humans not to interfere with their personal zones. For this purpose, social robot motion planning algorithms are employed to generate human-friendly paths that maintain humans' safety and comfort during the robot's navigation. This paper evaluates this system compared to traditional navigation, based on the surveys and physiological data of the adult participants in a preliminary study before using the system with children. Although the self-report questionnaires do not show any significant difference between navigation profiles of the robot, analysis of the physiological data may be interpreted that, the participants felt comfortable and less threatened in social navigation case.
  • Küçük Resim Yok
    Öğe
    RSS-Based Wireless LAN Indoor Localization and Tracking Using Deep Architectures
    (Mdpi, 2022) Karakusak, Muhammed Zahid; Kivrak, Hasan; Ates, Hasan Fehmi; Ozdemir, Mehmet Kemal
    Wireless Local Area Network (WLAN) positioning is a challenging task indoors due to environmental constraints and the unpredictable behavior of signal propagation, even at a fixed location. The aim of this work is to develop deep learning-based approaches for indoor localization and tracking by utilizing Received Signal Strength (RSS). The study proposes Multi-Layer Perceptron (MLP), One and Two Dimensional Convolutional Neural Networks (1D CNN and 2D CNN), and Long Short Term Memory (LSTM) deep networks architectures for WLAN indoor positioning based on the data obtained by actual RSS measurements from an existing WLAN infrastructure in a mobile user scenario. The results, using different types of deep architectures including MLP, CNNs, and LSTMs with existing WLAN algorithms, are presented. The Root Mean Square Error (RMSE) is used as the assessment criterion. The proposed LSTM Model 2 achieved a dynamic positioning RMSE error of 1.73 m, which outperforms probabilistic WLAN algorithms such as Memoryless Positioning (RMSE: 10.35 m) and Nonparametric Information (NI) filter with variable acceleration (RMSE: 5.2 m) under the same experiment environment.
  • Küçük Resim Yok
    Öğe
    Social navigation framework for assistive robots in human inhabited unknown environments
    (Elsevier - Division Reed Elsevier India Pvt Ltd, 2021) Kivrak, Hasan; Cakmak, Furkan; Kose, Hatice; Yavuz, Sirma
    In human-populated environments, robot navigation requires more than mere obstacle avoidance for safe and comfortable human-robot interaction. Socially aware navigation approaches become vital for deploy-ing mobile service robots in human interactive environments, where the robot operates in interaction with human implicitly or explicitly. These approaches aim to generate human-friendly paths in human-robot interactive environments considering social cues and human behaviour patterns. This paper proposes a social navigation framework for mobile service robots, maintaining humans' safety and comfort while navigating towards the goal location in human interactive environments. Our main contribution is that the presented social navigation framework is designed to be used in human interac-tive unknown environments. To achieve this goal, we use a variant of a pedestrian model called Collision Prediction based Social Force model (CP-SFM). This model is particularly developed for low or average density environments and takes the motion of the people tracked in the environment into account during the navigation. The model is employed as a local planner to generate human-friendly plausible routes for our service robot in corridor like indoor environment scenarios. A variety of different extensions and improvements of the conventional social force model are employed in the implementation stage. A novel improvement in producing multi-level mapping, identifying obstacle repulsion points and adopting CP-SFM for application in motion planning as local task solver is presented. The whole framework has been implemented as ROS nodes, and tested both in real world and simulation environments and successfully verified based on the obtained results. (C) 2020 Karabuk University. Publishing services by Elsevier B.V.
  • Küçük Resim Yok
    Öğe
    Waypoint based path planner for socially aware robot navigation
    (Springer, 2022) Kivrak, Hasan; Cakmak, Furkan; Kose, Hatice; Yavuz, Sirma
    Social navigation is beneficial for mobile robots in human inhabited areas. In this paper, we focus on smooth path tracking and handling disruptions during plan execution in social navigation. We extended the social force model (SFM)-based local planner to achieve smooth and effective social path following. The SFM-based local motion planner is used with the A* global planner, to avoid getting stuck in local minima, while incorporating social zones for human comfort. It is aimed at providing smooth path following and reducing the number of unnecessary re-plannings in evolving situations and a waypoint selection algorithm is proposed. The whole plan is not directly assigned to the robot since the global path has too many grid nodes and it is not possible to follow the path easily in such a dynamic and uncertain environment inhabitated by humans. Therefore, the extracted waypoints by the proposed waypoint selection algorithm are incrementally sent to the robot for smooth and legible robot navigation behavior. A corridor like scenario is tested in a simulated environment for the evaluation of the system and the results demonstrated that the proposed method can create paths that respect people's social space while also eliminating unnecessary replanning and providing that plans are carried out smoothly. The study presented an improvement in the number of replannings, path execution time, path length, and path smoothness of 90.4%, 53.7%, 8.3%, 55, 2%, respectively.