Tufan Kumbasar | Istanbul Technical University (original) (raw)

Papers by Tufan Kumbasar

Research paper thumbnail of Toward Learning Human-Like, Safe and Comfortable Car-Following Policies With a Novel Deep Reinforcement Learning Approach

IEEE Access

In this paper, we present an advanced adaptive cruise control (ACC) concept powered by Deep Reinf... more In this paper, we present an advanced adaptive cruise control (ACC) concept powered by Deep Reinforcement Learning (DRL) that generates safe, human-like, and comfortable car-following policies. Unlike the current trend in developing DRL-based ACC systems, we propose defining the action space of the DRL agent with discrete actions rather than continuous ones, since human drivers never set the throttle/brake pedal level to be actuated, but rather the required change of the current pedal levels. Through this humanlike throttle-brake manipulation representation, we also define explicit actions for holding (keeping the last action) and coasting (no action), which are usually omitted as actions in ACC systems. Moreover, based on the investigation of a real-world driving dataset, we cast a novel reward function that is easy to interpret and personalized. The proposed reward enforces the agent to learn stable and safe actions, while also encouraging the holding and coasting actions, just like a human driver would. The proposed discrete action DRL agent is trained with action masking, and the reward terms are completely derived from the real-world dataset collected from a human driver. We present exhaustive comparative results to show the advantages of the proposed DRL approach in both simulation and scenarios extracted from real-world driving. We clearly show that the proposed policy imitates human driving significantly better and handles complex driving situations, such as cut-ins and cutouts , implicitly, in comparison with a DRL agent trained with a widely-used reward function proposed for ACC, a model predictive control structure, and traditional car-following approaches. INDEX TERMS Adaptive cruise control, reinforcement learning, deep learning, naturalistic driving, advanced driving assistance systems.

Research paper thumbnail of Aggressive maneuvering of a quadcopter via differential flatness-based fuzzy controllers: From tuning to experiments

Research paper thumbnail of Tıp-2 Bulanık Modellerin Tersinin Alınması Ve Bulanık Model Tabanlı Kontrolör Tasarımı

Research paper thumbnail of Type-2 Fuzzy Logic Control in Computer Games

Studies in Fuzziness and Soft Computing, 2018

In this chapter, we will present the novel applications of the Interval Type-2 (IT2) Fuzzy Logic ... more In this chapter, we will present the novel applications of the Interval Type-2 (IT2) Fuzzy Logic Controllers (FLCs) into the research area of computer games. In this context, we will handle two popular computer games called Flappy Bird and Lunar Lander. From a control engineering point of view, the game Flappy Bird can be seen as a classical obstacle avoidance while Lunar Lander as a position control problem. Both games inherent high level of uncertainties and randomness which are the main challenges of the game for a player. Thus, these two games can be seen as challenging testbeds for benchmarking IT2-FLCs as they provide dynamic and competitive elements that are similar to realworld control engineering problems. As the game player can be considered as the main controller in a feedback loop, we will construct an intelligent control systems composed of three main subsystems: reference generator, the main controller, and game dynamics. In this chapter, we will design and then employ an IT2-FLC as the main controller in a feedback loop such that to have a satisfactory game performance while be able to handle the various uncertainties of the games. In this context, we will briefly present the general structure and the design methods of two IT2-FLCs which are the Single Input and the Double Input IT2-FLCs. We will show that an IT2 fuzzy control structure is capable to handle the uncertainties caused by the nature of the games by presenting both simulations and real-time game results in comparison with its Type-1 and conventional counterparts. We believe that the presented design methodology and results will provide a bridge for a wider deployment of Type-2 fuzzy logic in the area of the computer games.

Research paper thumbnail of Call for papers: Special Session for FUZZ 2017 "SS7-Advances to Type-2 Fuzzy Logic Control

Research paper thumbnail of Correction to: Deep learning frameworks to learn prediction and simulation focused control system models

Applied Intelligence, 2021

Research paper thumbnail of A New Insight on the Mappings of Type-2 Fuzzy Logic Systems

2019 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE), 2019

In this paper, we provide a new insight on the mappings of Interval Type-2 (IT2) Fuzzy Logic Syst... more In this paper, we provide a new insight on the mappings of Interval Type-2 (IT2) Fuzzy Logic Systems (FLSs) in comparison to its Type-1 (T1) counterparts. For the sake of simplicity, we focus on Single input IT2 (SIT2) FLSs that employ the Karnik Mendel (KM) or the Nie-Tan (NT) Centre of Sets Calculation Method (CSCM). Through theoretical investigations, it is shown that there does exist an equivalent SIT2-FLS representation with a Single input T1 (ST1) FLS that uses Rational Polynomial Functions (RBFs) in their rule consequents. It is concluded that SIT2-FLSs cannot be implemented with traditional ST1-FLSs. It is also revealed that the extra degree of freedom provided by IT2 fuzzy sets and CSCM results with RBFs that can generate much more complex mapping when compared to its T1 counterparts. It is also proven that SIT2-FLSs can be seen as adaptive ST1-FLSs that are tuned via a collection of ST1-FLSs. Thus, SIT2-FLSs have adaptive feature property that does not exists in ST1-FLSs. It is also shown that the SIT2-FLS employing the KM is more complex but also capable to accommodate a much wider range of mappings when compared its NT counterpart.

Research paper thumbnail of On the design and gain analysis of IT2-FLC with a case study on an electric vehicle

2017 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE), 2017

In this paper, we will present the gain analysis of an Internal Type-2 (IT2) Fuzzy Logic Controll... more In this paper, we will present the gain analysis of an Internal Type-2 (IT2) Fuzzy Logic Controller (FLC) that employs the Nie-Tan method and validated our theoretical results on the control of realistic Electric Vehicle (EV) model. In this context, we will firstly present the analytical derivation of the employed IT2-FLC structure and its output in closed form. We will then investigate the gain variations with respect to the Footprint of Uncertainty (FOU) design parameter of the IT2-FLC. We will define aggressive and smooth control regions based on the gain of IT2 FLCs in comparison with its type-1 counterpart. We will also present the FOU parameter settings that obtain aggressive or smooth control actions based on derived controller gains. We will extend these gain analysis into controller design to achieve desired control action. We will present the simulation studies in which aggressive and smooth IT2-FLCs are compared and evaluated on the EV model for different control performance measures. The results will show that the presented gain analysis provides better understanding about the effect of the FOU parameter and an initiative way to tune IT2-FLC for control system applications.

Research paper thumbnail of Altitude and Position Control of Parrot Mambo Minidrone with PID and Fuzzy PID Controllers

2019 11th International Conference on Electrical and Electronics Engineering (ELECO), 2019

Minidrones are widely used as they are not only fast quadcopters with high manoeuvrability but al... more Minidrones are widely used as they are not only fast quadcopters with high manoeuvrability but also excellent research platforms for indoor usage. In this study, we provide the design and deployment of the PI-PD and Fuzzy PI-PD (FPI-PD) structures to solve position control problem of the Parrot Mambo Minidrone. In this context, we derive nonlinear mathematical model of Parrot Mambo Minidrone to obtain the control models of the minidrone. Then, via the control models, firstly PI-PD control systems are designed for the altitude and position control systems. Then, to handle the coupled nonlinearities, FPI-PD controllers are designed and employed in the position control loop of minidrone. The presented comparative real-world experiment results clearly show that the proposed control systems outperform the built-in ones. Moreover, the results show that the performance of FPI-PD is better than the built-in PD and designed PI-PD control systems.

Research paper thumbnail of TORCS oyun ortamında bulanık mantık tabanlı akıllı bir otonom araç kontrol sistemi tasarımı

Bu çalışmada TORCS (The Open Racing Car Simulator) oyun ortamında bulanık mantık tabanlı otonom a... more Bu çalışmada TORCS (The Open Racing Car Simulator) oyun ortamında bulanık mantık tabanlı otonom araç kontrol sistemi tasarımı yapılmıştır. Bu çalışmadaki amaç, aracın yol bariyerlerine çarpasını engelleyerek hiçbir zarar almadan ve yol sınırları içerisinde kalmasını sağlayarak pistin dışına çıkmadan yarışı tamamlamasıdır. Bu bağlamda, aracın otonom bir şekilde ilerleyebilmesi için bulanık mantık ve klasik kontrol yapılarından oluşan akıllı bir sistem geliştirilmiştir. Aracın vites geçişleri otomatik hale getirildikten sonra aracın gerçekçi bir şekilde hızlanması/yavaşlamasını sağlamak ve de aracın sabit bir hızda gitmesi için bulanık mantık tabanlı bir gaz/fren kontrol sistemi tasarlanmıştır. Ayrıca, aracın pistin dışına çıkmadan ilerleyebilmesi ve de virajlarda pist içinde kalabilmesi için bulanık mantık tabanlı bir direksiyon kontrol sistemi geliştirilmiştir. Geliştirilen bu uzman tabanlı sistem sayesinde, aracın önünde bulunan virajın yönüne ve keskinliğine göre de aracın bulunması gereken uygun pozisyon hesaplanmıştır. Geliştirilen akıllı kontrol sistemin oyun performansına https://youtu.be/qOvEz3-PzRo bağıntısından ulaşılabilir.

Research paper thumbnail of Self-Commissioning of Electrical Parameters for Sensorless IPMSM Drives

2019 11th International Conference on Electrical and Electronics Engineering (ELECO), 2019

The performance of sensorless field oriented controlled interior permanent magnet synchronous mot... more The performance of sensorless field oriented controlled interior permanent magnet synchronous motors highly depends on motor parameters. However, exact parameter values of motors mostly are not known and thus it takes a lot of effort to tune drive to get ready to control different motors. In order to be able to tune the gains of controllers and position observer in sensorless drives, electrical parameters such as resistance and inductances need to be estimated. In this study, recursive least squares method is applied for estimation of electrical parameters (R, Ld, Lq) during standstill and then current controllers are tuned automatically. At the same time, by updating sliding mode current observer parameters deployed in sensorless control algorithm, motor becomes ready for sensorless speed control in very short time. Both the proposed self-commissioning and sensorless drive developed in this paper are implemented in real time on TI C2000 DSP controller and tested on different motors.

Research paper thumbnail of Big Bang-Big Crunch optimized hierarchical sliding-mode control of X-Z inverted pendulum

Simulation Modelling Practice and Theory, 2018

Research paper thumbnail of Learning with Type-2 Fuzzy activation functions to improve the performance of Deep Neural Networks

Engineering Applications of Artificial Intelligence, 2019

Research paper thumbnail of Interval type-2 fuzzy PID controllers and an online self-tuning mechanism

Pamukkale University Journal of Engineering Sciences, 2016

Bu çalışmada, Aralık değerli tip-2 bulanık PID (ADT2-BPID) kontrolörlerin içyapıları incelenmiş o... more Bu çalışmada, Aralık değerli tip-2 bulanık PID (ADT2-BPID) kontrolörlerin içyapıları incelenmiş olup ve de yeni bir öz-ayarlama önerilmiştir. Bu amaçla ilk olarak geleneksel yani tip-1 bulanık PID (T1-BPID) kontrolörler ile ADT2-BPID kontrolörlerin yapısal özellikleri ve tasarım parametreleri incelenmiştir. T1-BPID kontrolörler için önerilmiş olan bir öz-ayarlama yöntemi olan fonksiyon tabanlı özayarlama yöntemi ADT2-BPID kontrolör yapılarına uygulanmıştır. Bu öz ayarlama yöntemi yardımıyla ADT2-BPID kontrolörün ölçekleme çarpanlarının çevrimiçi ayarlanabileceği gösterilmiştir. Önerilen özayarlamalı ADT2-BPID tasarımında sırasıyla T1-BPID, ADT2-BPID kontrolörleri tasarlanmıştır. Benzetim çalışmasında önerilen özayarlamalı yapı tip-1 ve aralık değerli tip-2 eşdeğerleriyle doğrusal olmayan bir konik tank sistemi üzerinde karşılaştırılmıştır. Önerilen öz ayarlamalı ADT2-BPID kontrolör yapısı ile hem ADT2-BPID kontrolör içyapısından gelen fazladan serbestlik derecesi hem de fonksiyon ayarlayıcı tabanlı öz ayarlama yöntemi sayesinde tip-1 bulanık ve tip-2 bulanık eşdeğerlerine kıyasla daha iyi sonuçlar vermiştir. In this study, the general structure of interval type-2 fuzzy PID (IT2-FPID) controllers and a self-tuning mechanism for IT2-FPID controller is presented. In this context, we will present and examine the controller structures of the type-1 fuzzy PID (T1-FPID) and IT2-FPID controllers on a generic a symmetrical 3x3 rule base. Then, an online self-tuning mechanism for IT2-FPID controllers is presented. The presented selftuning mechanism, which was firstly presented for T1-FPID, controllers, tunes the scaling factors of IT2-FPID with respect to the current error value of the control system. A systematic design approach has been also presented for the self-tuning IT2-FPID structure. The performance of the T1-FPID, IT2-FPID and Self-Tuning IT2-FPID structures has been investigated on a simulation study conducted on a nonlinear tank system. The results have shown that, since the proposed approach has more extra degree of freedom provided by its interval type-2 fuzzy sets and self-tuning mechanism, the self-tuning IT2FPID resulted with a superior control performance in comparison with its type-1 and interval type-2 counterparts.

Research paper thumbnail of General derivation and analysis for input–output relations in interval type-2 fuzzy logic systems

Research paper thumbnail of A design methodology and analysis for interval type-2 fuzzy PI/PD controllers

ABSTRACT In this paper, a systematical methodology is introduced to construct the rule base of an... more ABSTRACT In this paper, a systematical methodology is introduced to construct the rule base of an interval type-2 fuzzy logic controller based on an existing linear PI/PD controller. An easy and rapid generation of the fuzzy rules can be achieved through this technique. In addition, analytical structure of this controller is derived. A closed-fonn of the fuzzy controller output is achieved under the circumstances that the input type-2 membership functions a,re diamond-shaped and a closed-form inference engine is used. Consequently, a linear control law is transformed to a nonlinear structure and certain elaborations can be done on the parameters of the evolved closed output structure. Moreover, the designer can benefit from the nonlinear structure of the proposed controller and the extra degree of freedom of type-2 fuzzy sets. It can be concluded from the results that the proposed controller can be more robust to the parameter uncertainties and eliminate the oscillations much better than type-1 fuzzy logic and linear conventional controllers.

Research paper thumbnail of Type-2 fuzzy model based controller design for neutralization processes

ISA Transactions, 2012

In this study, an inverse controller based on a type-2 fuzzy model control design strategy is int... more In this study, an inverse controller based on a type-2 fuzzy model control design strategy is introduced and this main controller is embedded within an internal model control structure. Then, the overall proposed control structure is implemented in a pH neutralization experimental setup. The inverse fuzzy control signal generation is handled as an optimization problem and solved at each sampling time in an online manner. Although, inverse fuzzy model controllers may produce perfect control in perfect model match case and/or non-existence of disturbances, this open loop control would not be sufficient in the case of modeling mismatches or disturbances. Therefore, an internal model control structure is proposed to compensate these errors in order to overcome this deficiency where the basic controller is an inverse type-2 fuzzy model. This feature improves the closed-loop performance to disturbance rejection as shown through the real-time control of the pH neutralization process. Experimental results demonstrate the superiority of the inverse type-2 fuzzy model controller structure compared to the inverse type-1 fuzzy model controller and conventional control structures.

Research paper thumbnail of Exact inversion of decomposable interval type-2 fuzzy logic systems

International Journal of Approximate Reasoning, 2013

It has been demonstrated that type-2 fuzzy logic systems are much more powerful tools than ordina... more It has been demonstrated that type-2 fuzzy logic systems are much more powerful tools than ordinary (type-1) fuzzy logic systems to represent highly nonlinear and/or uncertain systems. As a consequence, type-2 fuzzy logic systems have been applied in various areas especially in control system design and modelling. In this study, an exact inversion methodology is developed for decomposable interval type-2 fuzzy logic system. In this context, the decomposition property is extended and generalized to interval type-2 fuzzy logic sets. Based on this property, the interval type-2 fuzzy logic system is decomposed into several interval type-2 fuzzy logic subsystems under a certain condition on the input space of the fuzzy logic system. Then, the analytical formulation of the inverse interval type-2 fuzzy logic subsystem output is explicitly driven for certain switching points of the Karnik-Mendel type reduction method. The proposed exact inversion methodology driven for the interval type-2 fuzzy logic subsystem is generalized to the overall interval type-2 fuzzy logic system via the decomposition property. In order to demonstrate the feasibility of the proposed methodology, a simulation study is given where the beneficial sides of the proposed exact inversion methodology are shown clearly.

Research paper thumbnail of Online tuning of fuzzy PID controllers via rule weighing based on normalized acceleration

Engineering Applications of Artificial Intelligence, 2013

Abstract In this study, an on-line tuning method is proposed for fuzzy PID controllers via rule w... more Abstract In this study, an on-line tuning method is proposed for fuzzy PID controllers via rule weighing. The rule weighing mechanism is a fuzzy rule base with two inputs namely;“error” and “normalized acceleration”. Here, the normalized acceleration provides relative information on the fastness or slowness of the system response. In deriving the fuzzy rules of the weighing mechanism, the transient phase of the unit step response of the closed loop system is to be analyzed. For this purpose, this response is assumed to be divided into ...

Research paper thumbnail of Inverse fuzzy model control with online adaptation via big bang-big crunch optimization

2008 3rd International Symposium on Communications, Control, and Signal Processing, ISCCSP 2008, 2008

Abstract Fuzzy logic modeling is a powerful tool in representing nonlinear systems. Moreover, inv... more Abstract Fuzzy logic modeling is a powerful tool in representing nonlinear systems. Moreover, inverse fuzzy model can be used as a controller in an open loop fashion to produce perfect control. However, in the case of modeling mismatches and disturbances that might occur on the system, open loop control would not be sufficient. In that case, the modeling errors and disturbances could be compensated by internal model control (IMC) with an on-line model adaptation scheme. The on-line adaptation is usually accomplished ...

Research paper thumbnail of Toward Learning Human-Like, Safe and Comfortable Car-Following Policies With a Novel Deep Reinforcement Learning Approach

IEEE Access

In this paper, we present an advanced adaptive cruise control (ACC) concept powered by Deep Reinf... more In this paper, we present an advanced adaptive cruise control (ACC) concept powered by Deep Reinforcement Learning (DRL) that generates safe, human-like, and comfortable car-following policies. Unlike the current trend in developing DRL-based ACC systems, we propose defining the action space of the DRL agent with discrete actions rather than continuous ones, since human drivers never set the throttle/brake pedal level to be actuated, but rather the required change of the current pedal levels. Through this humanlike throttle-brake manipulation representation, we also define explicit actions for holding (keeping the last action) and coasting (no action), which are usually omitted as actions in ACC systems. Moreover, based on the investigation of a real-world driving dataset, we cast a novel reward function that is easy to interpret and personalized. The proposed reward enforces the agent to learn stable and safe actions, while also encouraging the holding and coasting actions, just like a human driver would. The proposed discrete action DRL agent is trained with action masking, and the reward terms are completely derived from the real-world dataset collected from a human driver. We present exhaustive comparative results to show the advantages of the proposed DRL approach in both simulation and scenarios extracted from real-world driving. We clearly show that the proposed policy imitates human driving significantly better and handles complex driving situations, such as cut-ins and cutouts , implicitly, in comparison with a DRL agent trained with a widely-used reward function proposed for ACC, a model predictive control structure, and traditional car-following approaches. INDEX TERMS Adaptive cruise control, reinforcement learning, deep learning, naturalistic driving, advanced driving assistance systems.

Research paper thumbnail of Aggressive maneuvering of a quadcopter via differential flatness-based fuzzy controllers: From tuning to experiments

Research paper thumbnail of Tıp-2 Bulanık Modellerin Tersinin Alınması Ve Bulanık Model Tabanlı Kontrolör Tasarımı

Research paper thumbnail of Type-2 Fuzzy Logic Control in Computer Games

Studies in Fuzziness and Soft Computing, 2018

In this chapter, we will present the novel applications of the Interval Type-2 (IT2) Fuzzy Logic ... more In this chapter, we will present the novel applications of the Interval Type-2 (IT2) Fuzzy Logic Controllers (FLCs) into the research area of computer games. In this context, we will handle two popular computer games called Flappy Bird and Lunar Lander. From a control engineering point of view, the game Flappy Bird can be seen as a classical obstacle avoidance while Lunar Lander as a position control problem. Both games inherent high level of uncertainties and randomness which are the main challenges of the game for a player. Thus, these two games can be seen as challenging testbeds for benchmarking IT2-FLCs as they provide dynamic and competitive elements that are similar to realworld control engineering problems. As the game player can be considered as the main controller in a feedback loop, we will construct an intelligent control systems composed of three main subsystems: reference generator, the main controller, and game dynamics. In this chapter, we will design and then employ an IT2-FLC as the main controller in a feedback loop such that to have a satisfactory game performance while be able to handle the various uncertainties of the games. In this context, we will briefly present the general structure and the design methods of two IT2-FLCs which are the Single Input and the Double Input IT2-FLCs. We will show that an IT2 fuzzy control structure is capable to handle the uncertainties caused by the nature of the games by presenting both simulations and real-time game results in comparison with its Type-1 and conventional counterparts. We believe that the presented design methodology and results will provide a bridge for a wider deployment of Type-2 fuzzy logic in the area of the computer games.

Research paper thumbnail of Call for papers: Special Session for FUZZ 2017 "SS7-Advances to Type-2 Fuzzy Logic Control

Research paper thumbnail of Correction to: Deep learning frameworks to learn prediction and simulation focused control system models

Applied Intelligence, 2021

Research paper thumbnail of A New Insight on the Mappings of Type-2 Fuzzy Logic Systems

2019 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE), 2019

In this paper, we provide a new insight on the mappings of Interval Type-2 (IT2) Fuzzy Logic Syst... more In this paper, we provide a new insight on the mappings of Interval Type-2 (IT2) Fuzzy Logic Systems (FLSs) in comparison to its Type-1 (T1) counterparts. For the sake of simplicity, we focus on Single input IT2 (SIT2) FLSs that employ the Karnik Mendel (KM) or the Nie-Tan (NT) Centre of Sets Calculation Method (CSCM). Through theoretical investigations, it is shown that there does exist an equivalent SIT2-FLS representation with a Single input T1 (ST1) FLS that uses Rational Polynomial Functions (RBFs) in their rule consequents. It is concluded that SIT2-FLSs cannot be implemented with traditional ST1-FLSs. It is also revealed that the extra degree of freedom provided by IT2 fuzzy sets and CSCM results with RBFs that can generate much more complex mapping when compared to its T1 counterparts. It is also proven that SIT2-FLSs can be seen as adaptive ST1-FLSs that are tuned via a collection of ST1-FLSs. Thus, SIT2-FLSs have adaptive feature property that does not exists in ST1-FLSs. It is also shown that the SIT2-FLS employing the KM is more complex but also capable to accommodate a much wider range of mappings when compared its NT counterpart.

Research paper thumbnail of On the design and gain analysis of IT2-FLC with a case study on an electric vehicle

2017 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE), 2017

In this paper, we will present the gain analysis of an Internal Type-2 (IT2) Fuzzy Logic Controll... more In this paper, we will present the gain analysis of an Internal Type-2 (IT2) Fuzzy Logic Controller (FLC) that employs the Nie-Tan method and validated our theoretical results on the control of realistic Electric Vehicle (EV) model. In this context, we will firstly present the analytical derivation of the employed IT2-FLC structure and its output in closed form. We will then investigate the gain variations with respect to the Footprint of Uncertainty (FOU) design parameter of the IT2-FLC. We will define aggressive and smooth control regions based on the gain of IT2 FLCs in comparison with its type-1 counterpart. We will also present the FOU parameter settings that obtain aggressive or smooth control actions based on derived controller gains. We will extend these gain analysis into controller design to achieve desired control action. We will present the simulation studies in which aggressive and smooth IT2-FLCs are compared and evaluated on the EV model for different control performance measures. The results will show that the presented gain analysis provides better understanding about the effect of the FOU parameter and an initiative way to tune IT2-FLC for control system applications.

Research paper thumbnail of Altitude and Position Control of Parrot Mambo Minidrone with PID and Fuzzy PID Controllers

2019 11th International Conference on Electrical and Electronics Engineering (ELECO), 2019

Minidrones are widely used as they are not only fast quadcopters with high manoeuvrability but al... more Minidrones are widely used as they are not only fast quadcopters with high manoeuvrability but also excellent research platforms for indoor usage. In this study, we provide the design and deployment of the PI-PD and Fuzzy PI-PD (FPI-PD) structures to solve position control problem of the Parrot Mambo Minidrone. In this context, we derive nonlinear mathematical model of Parrot Mambo Minidrone to obtain the control models of the minidrone. Then, via the control models, firstly PI-PD control systems are designed for the altitude and position control systems. Then, to handle the coupled nonlinearities, FPI-PD controllers are designed and employed in the position control loop of minidrone. The presented comparative real-world experiment results clearly show that the proposed control systems outperform the built-in ones. Moreover, the results show that the performance of FPI-PD is better than the built-in PD and designed PI-PD control systems.

Research paper thumbnail of TORCS oyun ortamında bulanık mantık tabanlı akıllı bir otonom araç kontrol sistemi tasarımı

Bu çalışmada TORCS (The Open Racing Car Simulator) oyun ortamında bulanık mantık tabanlı otonom a... more Bu çalışmada TORCS (The Open Racing Car Simulator) oyun ortamında bulanık mantık tabanlı otonom araç kontrol sistemi tasarımı yapılmıştır. Bu çalışmadaki amaç, aracın yol bariyerlerine çarpasını engelleyerek hiçbir zarar almadan ve yol sınırları içerisinde kalmasını sağlayarak pistin dışına çıkmadan yarışı tamamlamasıdır. Bu bağlamda, aracın otonom bir şekilde ilerleyebilmesi için bulanık mantık ve klasik kontrol yapılarından oluşan akıllı bir sistem geliştirilmiştir. Aracın vites geçişleri otomatik hale getirildikten sonra aracın gerçekçi bir şekilde hızlanması/yavaşlamasını sağlamak ve de aracın sabit bir hızda gitmesi için bulanık mantık tabanlı bir gaz/fren kontrol sistemi tasarlanmıştır. Ayrıca, aracın pistin dışına çıkmadan ilerleyebilmesi ve de virajlarda pist içinde kalabilmesi için bulanık mantık tabanlı bir direksiyon kontrol sistemi geliştirilmiştir. Geliştirilen bu uzman tabanlı sistem sayesinde, aracın önünde bulunan virajın yönüne ve keskinliğine göre de aracın bulunması gereken uygun pozisyon hesaplanmıştır. Geliştirilen akıllı kontrol sistemin oyun performansına https://youtu.be/qOvEz3-PzRo bağıntısından ulaşılabilir.

Research paper thumbnail of Self-Commissioning of Electrical Parameters for Sensorless IPMSM Drives

2019 11th International Conference on Electrical and Electronics Engineering (ELECO), 2019

The performance of sensorless field oriented controlled interior permanent magnet synchronous mot... more The performance of sensorless field oriented controlled interior permanent magnet synchronous motors highly depends on motor parameters. However, exact parameter values of motors mostly are not known and thus it takes a lot of effort to tune drive to get ready to control different motors. In order to be able to tune the gains of controllers and position observer in sensorless drives, electrical parameters such as resistance and inductances need to be estimated. In this study, recursive least squares method is applied for estimation of electrical parameters (R, Ld, Lq) during standstill and then current controllers are tuned automatically. At the same time, by updating sliding mode current observer parameters deployed in sensorless control algorithm, motor becomes ready for sensorless speed control in very short time. Both the proposed self-commissioning and sensorless drive developed in this paper are implemented in real time on TI C2000 DSP controller and tested on different motors.

Research paper thumbnail of Big Bang-Big Crunch optimized hierarchical sliding-mode control of X-Z inverted pendulum

Simulation Modelling Practice and Theory, 2018

Research paper thumbnail of Learning with Type-2 Fuzzy activation functions to improve the performance of Deep Neural Networks

Engineering Applications of Artificial Intelligence, 2019

Research paper thumbnail of Interval type-2 fuzzy PID controllers and an online self-tuning mechanism

Pamukkale University Journal of Engineering Sciences, 2016

Bu çalışmada, Aralık değerli tip-2 bulanık PID (ADT2-BPID) kontrolörlerin içyapıları incelenmiş o... more Bu çalışmada, Aralık değerli tip-2 bulanık PID (ADT2-BPID) kontrolörlerin içyapıları incelenmiş olup ve de yeni bir öz-ayarlama önerilmiştir. Bu amaçla ilk olarak geleneksel yani tip-1 bulanık PID (T1-BPID) kontrolörler ile ADT2-BPID kontrolörlerin yapısal özellikleri ve tasarım parametreleri incelenmiştir. T1-BPID kontrolörler için önerilmiş olan bir öz-ayarlama yöntemi olan fonksiyon tabanlı özayarlama yöntemi ADT2-BPID kontrolör yapılarına uygulanmıştır. Bu öz ayarlama yöntemi yardımıyla ADT2-BPID kontrolörün ölçekleme çarpanlarının çevrimiçi ayarlanabileceği gösterilmiştir. Önerilen özayarlamalı ADT2-BPID tasarımında sırasıyla T1-BPID, ADT2-BPID kontrolörleri tasarlanmıştır. Benzetim çalışmasında önerilen özayarlamalı yapı tip-1 ve aralık değerli tip-2 eşdeğerleriyle doğrusal olmayan bir konik tank sistemi üzerinde karşılaştırılmıştır. Önerilen öz ayarlamalı ADT2-BPID kontrolör yapısı ile hem ADT2-BPID kontrolör içyapısından gelen fazladan serbestlik derecesi hem de fonksiyon ayarlayıcı tabanlı öz ayarlama yöntemi sayesinde tip-1 bulanık ve tip-2 bulanık eşdeğerlerine kıyasla daha iyi sonuçlar vermiştir. In this study, the general structure of interval type-2 fuzzy PID (IT2-FPID) controllers and a self-tuning mechanism for IT2-FPID controller is presented. In this context, we will present and examine the controller structures of the type-1 fuzzy PID (T1-FPID) and IT2-FPID controllers on a generic a symmetrical 3x3 rule base. Then, an online self-tuning mechanism for IT2-FPID controllers is presented. The presented selftuning mechanism, which was firstly presented for T1-FPID, controllers, tunes the scaling factors of IT2-FPID with respect to the current error value of the control system. A systematic design approach has been also presented for the self-tuning IT2-FPID structure. The performance of the T1-FPID, IT2-FPID and Self-Tuning IT2-FPID structures has been investigated on a simulation study conducted on a nonlinear tank system. The results have shown that, since the proposed approach has more extra degree of freedom provided by its interval type-2 fuzzy sets and self-tuning mechanism, the self-tuning IT2FPID resulted with a superior control performance in comparison with its type-1 and interval type-2 counterparts.

Research paper thumbnail of General derivation and analysis for input–output relations in interval type-2 fuzzy logic systems

Research paper thumbnail of A design methodology and analysis for interval type-2 fuzzy PI/PD controllers

ABSTRACT In this paper, a systematical methodology is introduced to construct the rule base of an... more ABSTRACT In this paper, a systematical methodology is introduced to construct the rule base of an interval type-2 fuzzy logic controller based on an existing linear PI/PD controller. An easy and rapid generation of the fuzzy rules can be achieved through this technique. In addition, analytical structure of this controller is derived. A closed-fonn of the fuzzy controller output is achieved under the circumstances that the input type-2 membership functions a,re diamond-shaped and a closed-form inference engine is used. Consequently, a linear control law is transformed to a nonlinear structure and certain elaborations can be done on the parameters of the evolved closed output structure. Moreover, the designer can benefit from the nonlinear structure of the proposed controller and the extra degree of freedom of type-2 fuzzy sets. It can be concluded from the results that the proposed controller can be more robust to the parameter uncertainties and eliminate the oscillations much better than type-1 fuzzy logic and linear conventional controllers.

Research paper thumbnail of Type-2 fuzzy model based controller design for neutralization processes

ISA Transactions, 2012

In this study, an inverse controller based on a type-2 fuzzy model control design strategy is int... more In this study, an inverse controller based on a type-2 fuzzy model control design strategy is introduced and this main controller is embedded within an internal model control structure. Then, the overall proposed control structure is implemented in a pH neutralization experimental setup. The inverse fuzzy control signal generation is handled as an optimization problem and solved at each sampling time in an online manner. Although, inverse fuzzy model controllers may produce perfect control in perfect model match case and/or non-existence of disturbances, this open loop control would not be sufficient in the case of modeling mismatches or disturbances. Therefore, an internal model control structure is proposed to compensate these errors in order to overcome this deficiency where the basic controller is an inverse type-2 fuzzy model. This feature improves the closed-loop performance to disturbance rejection as shown through the real-time control of the pH neutralization process. Experimental results demonstrate the superiority of the inverse type-2 fuzzy model controller structure compared to the inverse type-1 fuzzy model controller and conventional control structures.

Research paper thumbnail of Exact inversion of decomposable interval type-2 fuzzy logic systems

International Journal of Approximate Reasoning, 2013

It has been demonstrated that type-2 fuzzy logic systems are much more powerful tools than ordina... more It has been demonstrated that type-2 fuzzy logic systems are much more powerful tools than ordinary (type-1) fuzzy logic systems to represent highly nonlinear and/or uncertain systems. As a consequence, type-2 fuzzy logic systems have been applied in various areas especially in control system design and modelling. In this study, an exact inversion methodology is developed for decomposable interval type-2 fuzzy logic system. In this context, the decomposition property is extended and generalized to interval type-2 fuzzy logic sets. Based on this property, the interval type-2 fuzzy logic system is decomposed into several interval type-2 fuzzy logic subsystems under a certain condition on the input space of the fuzzy logic system. Then, the analytical formulation of the inverse interval type-2 fuzzy logic subsystem output is explicitly driven for certain switching points of the Karnik-Mendel type reduction method. The proposed exact inversion methodology driven for the interval type-2 fuzzy logic subsystem is generalized to the overall interval type-2 fuzzy logic system via the decomposition property. In order to demonstrate the feasibility of the proposed methodology, a simulation study is given where the beneficial sides of the proposed exact inversion methodology are shown clearly.

Research paper thumbnail of Online tuning of fuzzy PID controllers via rule weighing based on normalized acceleration

Engineering Applications of Artificial Intelligence, 2013

Abstract In this study, an on-line tuning method is proposed for fuzzy PID controllers via rule w... more Abstract In this study, an on-line tuning method is proposed for fuzzy PID controllers via rule weighing. The rule weighing mechanism is a fuzzy rule base with two inputs namely;“error” and “normalized acceleration”. Here, the normalized acceleration provides relative information on the fastness or slowness of the system response. In deriving the fuzzy rules of the weighing mechanism, the transient phase of the unit step response of the closed loop system is to be analyzed. For this purpose, this response is assumed to be divided into ...

Research paper thumbnail of Inverse fuzzy model control with online adaptation via big bang-big crunch optimization

2008 3rd International Symposium on Communications, Control, and Signal Processing, ISCCSP 2008, 2008

Abstract Fuzzy logic modeling is a powerful tool in representing nonlinear systems. Moreover, inv... more Abstract Fuzzy logic modeling is a powerful tool in representing nonlinear systems. Moreover, inverse fuzzy model can be used as a controller in an open loop fashion to produce perfect control. However, in the case of modeling mismatches and disturbances that might occur on the system, open loop control would not be sufficient. In that case, the modeling errors and disturbances could be compensated by internal model control (IMC) with an on-line model adaptation scheme. The on-line adaptation is usually accomplished ...