Yazar "Gelen, Gökhan" seçeneğine göre listele
Listeleniyor 1 - 8 / 8
Sayfa Başına Sonuç
Sıralama seçenekleri
Öğe A New Collision Avoidance Approach for Automated Guided Vehicle Systems Based on Finite State Machines(2024) Çoban, Mustafa; Gelen, GökhanAutomated guided vehicles are transportation systems that are widely used in factories, warehouses, and distribution centers. It is of great importance to ensure the control and coordination of vehicles for safe and efficient transportation in multi-vehicle systems. In this study, a control strategy is proposed to enforce collision avoidance of automated guided vehicles operating in a shared zone and overlapping route environment. In the proposed method, while finite state machines are used to model the movement of automated guided vehicles in the environment, the Q-learning method, one of the most common reinforcement learning algorithms, is used for collision avoidance. The presented approach uses the decentralized node-based approach to reduce computational complexity. The proposed method has been validated through simulation performed with vehicle applications that can move both unidirectional and bidirectional. The simulation results show that our presented approach can avoid potential collisions and greatly increase overall efficiency.Öğe Düşük Çözünürlüklü Resimlerden Göz Merkezi Belirleme ve İris Yarıçapı Kestirimi için İyileştirilmiş Bir Algoritma(Tayfun UYGUNOĞLU, 2022) Dursun, Fatih; Gelen, GökhanGöz merkezinin doğru bir şekilde belirlenmesi problemi insan-bilgisayar etkileşimi, yüz tanıma, iris tanıma, bakış noktası tahmini gibi birçok bilgisayarla görü uygulamasında önemli bir yere sahiptir. Bu uygulamalarda elde edilen doğruluk değerleri, göz merkezi belirleme algoritmasının performansına doğrudan bağlıdır. Göz merkezi belirlenmesi amacıyla önerilen metotların çoğunluğu laboratuvar şartlarında alınan yüksek çözünürlüklü resimlere uygulanmaktadır. Yüksek çözünürlüklü ve kontrollü şartlarda alınan resimlerde göz merkezi oldukça doğru bir şekilde belirlebilse de düşük çözünürlüklü resimlerde belirleme işlemi çok daha zordur. Bu çalışmada göz merkezi ve iris yarıçapının düşük çözünürlüklü resimlerde belirlenmesine yönelik bir metot önerilmiştir. Önerilen metot, yüz ve göz bölgeleri algılama, göz merkezini kabaca belirleme ve iyileştirme aşamalarından oluşan çok aşamalı bir yapıya sahiptir. Göz merkezi konumunun kabaca belirlenmesi amacıyla göz bölgesinin gradyan verisine ve irisin dairesel şekline dayanan bir metot kullanılmıştır. Kabaca belirleme algoritması ile iris sınırları içerisinde bir nokta belirlenmiştir. İris içerisinde belirlenen nokta etrafındaki bölgeye, bu çalışmada önerilen iyileştirme algoritması uygulanarak göz merkezinin tam konumu belirlenmiştir. Önerilen yaklaşımının performansı, bu alanda yaygın olarak kullanılan veri seti üzerinde test edilerek ve bulunan sonuçların diğer metotlarla karşılaştırılması sunulmuştur.Öğe İnsan-robot etkileşiminin biyomimetik yaklaşımla sağlanması(2019) Gelen, Gökhan; Özcan, SinanBu çalışmada, insan kol ve el hareketlerinin taklit edilmesiyle insanrobot etkileşimini sağlayan biyomimetik bir yaklaşım sunulmuştur. İnsan kol hareketleriyle robotun aynı doğrultuda hareket etmesi sağlanmış ve el hareketleri ile de robot tutucusunun kontrolü sağlanmıştır. Robot hareketi için; ilk olarak insan elinin, bel hizasında orijin noktası olarak belirlenen noktaya olan konumunu verecek kinematik model oluşturulmuştur. Modellemede, insan kolu, ön kol, pazı ve omuz olmak üzere üç ayrı uzuv olarak incelenmiştir. Omuza, pazıya ve ön kola yerleştirilen algılayıcılar ile dönüş açısı bilgileri elde edilmiş ve uzuv uzunlukları ile birlikte matematiksel modelde kullanılmıştır. Bu hesaplamalarda rotasyon kinematiği ve hareket kinematiği matrisleri kullanılmıştır. Tutucu kontrolü için ise bünyesinde EMG sensörleri bulunduran MYO kol bandı kullanılmıştır. Bu kol bandı üzerindeki EMG sensörleri ile kol kaslarından parmak hareketleri algılatılmıştır ve bu hareketler doğrultusunda pnömatik tutucu kontrol edilmiştir. Uygulamalarda 6-eksen robot kolu kullanılmıştır. Hesaplanan konum verileri ve tutucu bilgisi ethernet üzerinden TCP/IP protokolü ile robot denetleyicisine aktarılmaktadır. Robotun hesaplanan konuma gitmesini ve tutucu kontrolünü sağlayan kod oluşturularak robota aktarılmıştır. Yapılan testlerde, endüstriyel robotun insan kol ve el hareketleri ile başarılı biçimde kontrol edildiği gözlemlenmiştir.Öğe Realization of human-robot collaboration in hybrid assembly systems by using wearable technology(Ieee, 2018) Çoban, Mustafa; Gelen, GökhanTogether with improvements in robot technology, the number of research conducted on the interaction between humans and robots has increased. As a result of these researches, collaborative robots (cobot) emerged. The fourth industrial revolution, usage of wearable technologies, and the internet of things increase the significance of cobot and its applications. In this study, the realization of human-robot collaboration in hybrid assembly systems in which humans and robots cooperate to perform assembly tasks is aimed. The interaction between human and robot is achieved by using a wearable armband that can sense muscle signals. By using this device, the end of human operation can be recognized by the robot. In order to carry out hybrid assembly, tasks to be performed by the human and the robot are determined, and a robot control algorithm is created to ensure that the products are assembled appropriately. As a performance test, elapsed time to assemble the same number of products with human-robot collaboration is compared with the assembly process performed by the robot alone. Results show that the hybrid assembly process with human-robot collaboration is faster and more effective than the assembly process performed by the robot alone.Öğe Reliability Analysis of Assembly Processes Performed by Human-Robot Interaction(Institute of Electrical and Electronics Engineers Inc., 2019) Çoban, Mustafa; Kaymakci, O.T.; Gelen, GökhanTogether with innovations in robot technologies and the emergence of the fourth industrial revolution called Industry 4.0, collaborative robot applications have improved. Collaborative robots are the robots that provide the safe handling of many processes such as assembly, pick and place, palletizing in factories. The reliability analysis of the system has great importance in order to determine the failure conditions and failure possibilities that will occur in the systems enabling these operations. In this study, reliability analysis of assembly processes performed by human-robot interaction is presented. The reliability block diagram of the system is created and the reliability value of the system over time is determined. Then, Markov model indicating the fault conditions in the system is created and the probability of occurrence of these fault conditions is determined. The results show that if the system operates continuously for five years, the reliability will drop below 10% and the reasons that decrease the reliability are discussed in the last section. © 2019 IEEE.Öğe Supervisory Controller Design for Reactive Power Compensation(Osman SAĞDIÇ, 2020) Gelen, Ayetül; Gelen, Gökhan; Bıçak, AykutThe process of reducing the phase difference between current and voltage as much as possible by balancing the reactive power is known as reactive power compensation. With reactive power compensation, over currents and voltage drops in the transmission lines are prevented and higher quality, cheaper, and more efficient energy is provided. Reactive power compensation is done by switching capacitors with proper values. In a reactive power compensation system, capacitors are switched on and off by a controller. The switching behavior of this system can be characterized as a discrete event system (DES) that has discrete states and the state evolution depends on the occurrence of asynchronous events. In this paper, the control mechanism of a reactive power compensation system is considered in the sense of DES. The system is modeled by using automata and supervisory control structures are computed. The supervisors are obtained by using the supervisory control theory (SCT). Supervisors in the form of monolithic, reduced, and modular are synthesized to correct the power factor. The computed supervisors are also integrated with the system and simulated. The total size of supervisors, ie the total number of transitions and states of each, are compared. The computed supervisors in the form of modular ones have the smallest size. According to simulation results, it is demonstrated that the power factor is successfully corrected by all of the computed supervisors. The presented study shows how to calculate controllers for reactive power compensation systems by using the supervisory control theory. Since the supervisory control theory used in the study is a formal controller computation method, the presented approach enables the computation of formal controllers for reactive power compensation systems. The use of formal methods in the synthesis of controllers offers significant benefits in terms of realization and verification.Öğe Think-globally-act-locally approach with weighted arcs to the synthesis of a liveness-enforcing supervisor for generalized Petri nets modeling FMSs(Elsevier Science Inc, 2016) Uzam, Murat; Gelen, Gökhan; Saleh, Tahir LawanThis paper proposes a general approach, called a think-globally-act-locally method with weighted arcs (TGALW), which can be used to compute a liveness-enforcing supervisor (LES) for the Petri net (PN) model of a flexible manufacturing system (FMS) prone to deadlocks. Compared with siphon-based deadlock prevention policies that are usually rather conservative, the method is especially effective for generalized PN classes such as (SR)-R-4 and (SPR)-P-4 and also leads to optimal or near optimal LESS while maintaining the necessary computations simple. An original PNM is first transformed into a net that is behaviorally equivalent to it. A global sink/source place (GP) is used temporarily in the design steps and is finally removed when the liveness of the system is achieved. At each iteration step, bad markings are identified and then controlled by monitors through an established place-invariant based method. A condition of the optimal controllability of a bad marking is proposed, i.e., if all bad markings are optimally controlled at each iteration step, the TGALW method can find an optimal LES. Redundancy of monitors is checked. Typical examples existing in the literature are used to demonstrate applicability and the effectiveness of the proposed method. (C) 2015 Elsevier Inc. All rights reserved.Öğe Wireless teleoperation of an industrial robot by using myo arm band(Ieee, 2019) Çoban, Mustafa; Gelen, GökhanIn this work, wireless control of a 6-degree-of-freedom industrial robot by using Myo armband to carry out pick and place task is aimed. Myo armband has built in sensors such as gyroscope and electromyography sensors. The gesture and motion of human arm is detected and the robot is remotely manipulated. The movement of robot achieved by using measured roll, pitch and yaw angle of arm wearing Myo band. The control of robot gripper is achieved by sensing the opening and closing of the human hand. Bluetooth is used for the wireless communication between arm band and robot controller. It is observed that three axis position and gripper control of robot is successfully achieved. By using considered configuration, a pick and place operation is also successfully completed. The proposed configuration can be used in human-robot interaction and teleoperation studies.
