Showing papers in "IEEE Transactions on Fuzzy Systems in 2004"

A hierarchical type-2 fuzzy logic control architecture for autonomous mobile robots

Abstract: Autonomous mobile robots navigating in changing and dynamic unstructured environments like the outdoor environments need to cope with large amounts of uncertainties that are inherent of natural environments. The traditional type-1 fuzzy logic controller (FLC) using precise type-1 fuzzy sets cannot fully handle such uncertainties. A type-2 FLC using type-2 fuzzy sets can handle such uncertainties to produce a better performance. In this paper, we present a novel reactive control architecture for autonomous mobile robots that is based on type-2 FLC to implement the basic navigation behaviors and the coordination between these behaviors to produce a type-2 hierarchical FLC. In our experiments, we implemented this type-2 architecture in different types of mobile robots navigating in indoor and outdoor unstructured and challenging environments. The type-2-based control system dealt with the uncertainties facing mobile robots in unstructured environments and resulted in a very good performance that outperformed the type-1-based control system while achieving a significant rule reduction compared to the type-1 system.

Delay-dependent guaranteed cost control for T-S fuzzy systems with time delays

Abstract: This study introduces a guaranteed cost control method for nonlinear systems with time-delays which can be represented by Takagi-Sugeno (T-S) fuzzy models with time-delays. The state feedback and generalized dynamic output feedback approaches are considered. The generalized dynamic output feedback controller is presented by a new fuzzy controller architecture which is of dual indexed rule base. It considers both the dynamic part and the output part of T-S fuzzy model which guarantees that the controller without any delay information can stabilize time-delay T-S fuzzy systems. Based on delay-dependent Lyapunov functional approach, some sufficient conditions for the existence of state feedback controller are provided via parallel distributed compensation (PDC) first. Second, the corresponding conditions are extended into the generalized dynamic output feedback closed-loop system via so-called generalized PDC technique. The upper bound of time-delay can be obtained using convex optimization such that the system can be stabilized for all time-delays whose sizes are not larger than the bound. The minimizing method is also proposed to search the suboptimal upper bound of guaranteed cost function. The effectiveness of the proposed method can be shown by the simulation examples.

On the representation of intuitionistic fuzzy t-norms and t-conorms

Abstract: Intuitionistic fuzzy sets form an extension of fuzzy sets: while fuzzy sets give a degree to which an element belongs to a set, intuitionistic fuzzy sets give both a membership degree and a nonmembership degree. The only constraint on those two degrees is that their sum must be smaller than or equal to 1. In fuzzy set theory, an important class of triangular norms and conorms is the class of continuous Archimedean nilpotent triangular norms and conorms. It has been shown that for such t-norms T there exists a permutation /spl phi/ of [0,1] such that T is the /spl phi/-transform of the Lukasiewicz t-norm. In this paper we introduce the notion of intuitionistic fuzzy t-norm and t-conorm, and investigate under which conditions a similar representation theorem can be obtained.

Granular prototyping in fuzzy clustering

Abstract: We introduce a logic-driven clustering in which prototypes are formed and evaluated in a sequential manner. The way of revealing a structure in data is realized by maximizing a certain performance index (objective function) that takes into consideration an overall level of matching (to be maximized) and a similarity level between the prototypes (the component to be minimized). The prototypes identified in the process come with the optimal weight vector that serves to indicate the significance of the individual features (coordinates) in the data grouping represented by the prototype. Since the topologies of these groupings are in general quite diverse the optimal weight vectors are reflecting the anisotropy of the feature space, i.e., they show some local ranking of features in the data space. Having found the prototypes we consider an inverse similarity problem and show how the relevance of the prototypes translates into their granularity.

Neuro-fuzzy control of a robotic exoskeleton with EMG signals

Abstract: We have been developing robotic exoskeletons to assist motion of physically weak persons such as elderly, disabled, and injured persons. The robotic exoskeleton is controlled basically based on the electromyogram (EMG) signals, since the EMG signals of human muscles are important signals to understand how the user intends to move. Even though the EMG signals contain very important information, however, it is not very easy to predict the user's upper-limb motion (elbow and shoulder motion) based on the EMG signals in real-time because of the difficulty in using the EMG signals as the controller input signals. In this paper, we propose a robotic exoskeleton for human upper-limb motion assist, a hierarchical neuro-fuzzy controller for the robotic exoskeleton, and its adaptation method.

Computing derivatives in interval type-2 fuzzy logic systems

Abstract: This paper makes type-2 fuzzy logic systems much more accessible to fuzzy logic system designers, because it provides mathematical formulas and computational flowcharts for computing the derivatives that are needed to implement steepest-descent parameter tuning algorithms for such systems. It explains why computing such derivatives is much more challenging than it is for a type-1 fuzzy logic system. It provides derivative calculations that are applicable to any kind of type-2 membership functions, since the calculations are performed without prespecifying the nature of those membership functions. Some calculations are then illustrated for specific type-2 membership functions.

Stability analysis of discrete-time fuzzy dynamic systems based on piecewise Lyapunov functions

Abstract: This paper presents a stability analysis method for discrete-time Takagi-Sugeno fuzzy dynamic systems based on a piecewise smooth Lyapunov function. It is shown that the stability of the fuzzy dynamic system can be established if a piecewise Lyapunov function can be constructed, and moreover, the function can be obtained by solving a set of linear matrix inequalities that is numerically feasible with commercially available software. It is also demonstrated via numerical examples that the stability result based on the piecewise quadratic Lyapunov functions is less conservative than that based on the common quadratic Lyapunov functions.

Fuzzy identification using fuzzy neural networks with stable learning algorithms

Abstract: In general, fuzzy neural networks cannot match nonlinear systems exactly. Unmodeled dynamic leads parameters drift and even instability problem. According to system identification theory, robust modification terms must be included in order to guarantee Lyapunov stability. This paper suggests new learning laws for Mamdani and Takagi-Sugeno-Kang type fuzzy neural networks based on input-to-state stability approach. The new learning schemes employ a time-varying learning rate that is determined from input-output data and model structure. Stable learning algorithms for the premise and the consequence parts of fuzzy rules are proposed. The calculation of the learning rate does not need any prior information such as estimation of the modeling error bounds. This offer an advantage compared to other techniques using robust modification.

A generalized concept for fuzzy rule interpolation

Abstract: The concept of fuzzy rule interpolation in sparse rule bases was introduced in 1993. It has become a widely researched topic in recent years because of its unique merits in the topic of fuzzy rule base complexity reduction. The first implemented technique of fuzzy rule interpolation was termed as /spl alpha/-cut distance based fuzzy rule base interpolation. Despite its advantageous properties in various approximation aspects and in complexity reduction, it was shown that it has some essential deficiencies, for instance, it does not always result in immediately interpretable fuzzy membership functions. This fact inspired researchers to develop various kinds of fuzzy rule interpolation techniques in order to alleviate these deficiencies. This paper is an attempt into this direction. It proposes an interpolation methodology, whose key idea is based on the interpolation of relations instead of interpolating /spl alpha/-cut distances, and which offers a way to derive a family of interpolation methods capable of eliminating some typical deficiencies of fuzzy rule interpolation techniques. The proposed concept of interpolating relations is elaborated here using fuzzy- and semantic-relations. This paper presents numerical examples, in comparison with former approaches, to show the effectiveness of the proposed interpolation methodology.

Support vector learning mechanism for fuzzy rule-based modeling: a new approach

Abstract: This paper describes a fuzzy modeling framework based on support vector machine, a rule-based framework that explicitly characterizes the representation in fuzzy inference procedure. The support vector learning mechanism provides an architecture to extract support vectors for generating fuzzy IF-THEN rules from the training data set, and a method to describe the fuzzy system in terms of kernel functions. Thus, it has the inherent advantage that the model does not have to determine the number of rules in advance, and the overall fuzzy inference system can be represented as series expansion of fuzzy basis functions. The performance of the proposed approach is compared to other fuzzy rule-based modeling methods using four data sets.

Fuzzy target tracking control of autonomous mobile robots by using infrared sensors

Abstract: The theme of this paper is to design a real-time fuzzy target tracking control scheme for autonomous mobile robots by using infrared sensors. At first two mobile robots are setup in the target tracking problem, where one is the target mobile robot with infrared transmitters and the other one is the tracker mobile robot with infrared receivers and reflective sensors. The former is designed to drive in a specific trajectory. The latter is designed to track the target mobile robot. Then we address the design of the fuzzy target tracking control unit, which consists of a behavior network and a gate network. The behavior network possesses the fuzzy wall following control (FWFC) mode, fuzzy target tracking control (FTTC) mode, and two fixed control modes to deal with different situations in real applications. Both the FWFC and FTTC are realized by the fuzzy sliding-mode control scheme. A gate network is used to address the fusion of measurements of two infrared sensors and is developed to recognize which situation is belonged to and which action should be executed. Moreover, the target tracking control with obstacle avoidance is also investigated in this paper. Both computer simulations and real-time implementation experiments of autonomous target tracking control demonstrate the effectiveness and feasibility of the proposed control schemes.

Improved possibilistic C-means clustering algorithms

Abstract: A possibilistic approach was proposed in a previous paper for C-means clustering, and two algorithms realizing this approach were reported in two previous papers. Although the possibilistic approach is sound, these two algorithms tend to find identical clusters. In this paper, we modify and improve these algorithms to overcome their shortcoming. The numerical results demonstrate that the improved algorithms can determine proper clusters and they can realize the advantages of the possibilistic approach.

Output feedback tracking control of robot manipulators with model uncertainty via adaptive fuzzy logic

Abstract: Many robot controllers require not only joint position measurements but also joint velocity measurements; however, most robotic systems are only equipped with joint position measurement devices. In this paper, a new output feedback tracking control approach is developed for the robot manipulators with model uncertainty. The approach suggested herein does not require velocity measurements and employs the adaptive fuzzy logic. The adaptive fuzzy logic allows us to approximate uncertain and nonlinear robot dynamics. Only one fuzzy system is used to implement the observer-controller structure of the output feedback robot system. It is shown in a rigorous manner that all the signals in a closed loop composed of a robot, an observer, and a controller are uniformly ultimately bounded. Finally, computer simulation results on three-link robot manipulators are presented to show the results which indicate good position tracking performance and robustness against payload uncertainty and external disturbances.

Quantitative weights and aggregation

Abstract: Based on the strong idempotency of aggregation operators, quantitative weights are incorporated into the fusion process. Our general method is compared with some previous specific cases. More details about weighted aggregation based on some penalty function is given. Further, weighted integral based aggregation linked to quantifier-based fuzzy measures is investigated, especially weighted OWA operators. Several examples are included.

Supervisory recurrent fuzzy neural network control of wing rock for slender delta wings

Abstract: Wing rock is a highly nonlinear phenomenon in which an aircraft undergoes limit cycle roll oscillations at high angles of attack. In this paper, a supervisory recurrent fuzzy neural network control (SRFNNC) system is developed to control the wing rock system. This SRFNNC system is comprised of a recurrent fuzzy neural network (RFNN) controller and a supervisory controller. The RFNN controller is investigated to mimic an ideal controller and the supervisory controller is designed to compensate for the approximation error between the RFNN controller and the ideal controller. The RFNN is inherently a recurrent multilayered neural network for realizing fuzzy inference using dynamic fuzzy rules. Moreover, an on-line parameter training methodology, using the gradient descent method and the Lyapunov stability theorem, is proposed to increase the learning capability. Finally, a comparison between the sliding-mode control, the fuzzy sliding control and the proposed SRFNNC of a wing rock system is presented to illustrate the effectiveness of the SRFNNC system. Simulation results demonstrate that the proposed design method can achieve favorable control performance for the wing rock system without the knowledge of system dynamic functions.

Induction of fuzzy-rule-based classifiers with evolutionary boosting algorithms

Abstract: This paper proposes a novel Adaboost algorithm to learn fuzzy-rule-based classifiers. Connections between iterative learning and boosting are analyzed in terms of their respective structures and the manner these algorithms address the cooperation-competition problem. The results are used to explain some properties of the former method. The evolutionary boosting scheme is applied to approximate and descriptive fuzzy-rule bases. The advantages of boosting fuzzy rules are assessed by performance comparisons between the proposed method and other classification schemes applied on a set of benchmark classification tasks.

Generating an interpretable family of fuzzy partitions from data

Abstract: In this paper, we propose a new method to construct fuzzy partitions from data. The procedure generates a hierarchy including best partitions of all sizes from n to two fuzzy sets. The maximum size n is determined according to the data distribution and corresponds to the finest resolution level. We use an ascending method for which a merging criterion is needed. This criterion is based on the definition of a special metric distance suitable for fuzzy partitioning, and the merging is done under semantic constraints. The distance we define does not handle the point coordinates, but directly their membership degrees to the fuzzy sets of the partition. This leads to the introduction of the notions of internal and external distances. The hierarchical fuzzy partitioning is carried independently over each dimension, and, to demonstrate the partition potential, they are used to build fuzzy inference system using a simple selection mechanism. Due to the merging technique, all the fuzzy sets in the various partitions are interpretable as linguistic labels. The tradeoff between accuracy and interpretability constitutes the most promising aspect in our approach. Well known data sets are investigated and the results are compared with those obtained by other authors using different techniques. The method is also applied to real world agricultural data, the results are analyzed and weighed against those achieved by other methods, such as fuzzy clustering or discriminant analysis.

OWA operators in data modeling and reidentification

Abstract: This paper is devoted to the application of aggregation operators and to the application of ordered weighting averaging (OWA) operators to data mining. In particular, we consider two application of OWA operators in this field: model building and information extraction. The latter application is oriented to the reidentification procedures.

Observer-based robust H/sub /spl infin// control for fuzzy systems using two-step procedure

Abstract: This paper investigates both robust H/sub /spl infin// analysis and synthesis problems involving observer-based fuzzy control via linear matrix inequality methods for which efficient optimization techniques are available. The observer and controller are capable of disturbance-rejection in the presence of unknown but bounded disturbance. We present results in a unified fashion applicable to both continuous- and discrete-time problems with or without uncertainty. Finally, the validity and applicability of the approach are demonstrated by examples.

Effective optimization for fuzzy model predictive control

Abstract: This paper addresses the optimization in fuzzy model predictive control. When the prediction model is a nonlinear fuzzy model, nonconvex, time-consuming optimization is necessary, with no guarantee of finding an optimal solution. A possible way around this problem is to linearize the fuzzy model at the current operating point and use linear predictive control (i.e., quadratic programming). For long-range predictive control, however, the influence of the linearization error may significantly deteriorate the performance. In our approach, this is remedied by linearizing the fuzzy model along the predicted input and output trajectories. One can further improve the model prediction by iteratively applying the optimized control sequence to the fuzzy model and linearizing along the so obtained simulated trajectories. Four different methods for the construction of the optimization problem are proposed, making difference between the cases when a single linear model or a set of linear models are used. By choosing an appropriate method, the user can achieve a desired tradeoff between the control performance and the computational load. The proposed techniques have been tested and evaluated using two simulated industrial benchmarks: pH control in a continuous stirred tank reactor and a high-purity distillation column.

Stability and stabilization of fuzzy large-scale systems

Abstract: This paper investigates the stability and stabilization problems for the fuzzy large-scale system in which the system is composed of a number of Takagi-Sugeno fuzzy model subsystems with interconnections. The stability criterion of the fuzzy large-scale system without control is derived first. Instead of fuzzy parallel distributed compensation design, linear state feedback control is used in the stabilization work. Each local control is obtained from Riccati equation of the corresponding subsystem and the interconnection terms are used to determine the local feedback gain determination. Based on Lyapunov criterion, some conditions are derived under which the whole fuzzy large-scale system is stabilized asymptotically. A numerical example is given to illustrate the control design procedure and its effectiveness.

A new intelligent digital redesign for T-S fuzzy systems: global approach

Abstract: This paper proposes a novel and efficient global intelligent digital redesign technique for a Takagi-Sugeno (T-S) fuzzy system. The term of intelligent digital redesign involves converting an existing analog fuzzy-model-based controller into an equivalent digital counterpart in the sense of state-matching. The proposed method should be notably discriminated from the previous works in that it allows us to globally match the states of the overall closed-loop T-S fuzzy system with the predesigned analog fuzzy-model-based controller and those with the digitally redesigned fuzzy-model-based controller, and further to examine the stabilizability by the redesigned controller in the sense of Lyapunov. The key idea is that the global intelligent digital redesign problem is viewed as a convex minimization problem of the norm distance between nonlinearly interpolated linear operators to be matched. Sufficient conditions for the global state-matching and the stability of the digitally controlled system are formulated in terms of linear matrix inequalities (LMIs). A complex nonlinear system, Duffing-like chaotic oscillator is simulated and demonstrated to validate the feasibility and effectiveness of the proposed digital redesign technique, which implies the safe applicability to the digital control system.

Automatic design of fuzzy controllers for car-like autonomous robots

Abstract: This paper describes the design and implementation of a fuzzy control system for a car-like autonomous vehicle. The problem addressed is the diagonal parking in a constrained space, a typical problem in motion control of nonholonomic robots. The architecture proposed for the fuzzy controller is a hierarchical scheme which combines seven modules working in series and in parallel. The rules of each module employ the adequate fuzzy operators for its task (making a decision or generating a smoothly varying control output), and they have been obtained from heuristic knowledge and numerical data (with geometric information) depending on the module requirements (some of them are constrained to provide paths of near-minimal lengths). The computer-aided design tools of the environment Xfuzzy 3.0 (developed by some of the authors) have been employed to automate the different design stages: 1) translation of heuristic knowledge into fuzzy rules; 2) extraction of fuzzy rules from numerical data and their tuning to give paths of near-minimal lengths; 3) offline verification of the control system behavior; and 4) its synthesis to be implemented in a true robot and be verified on line. Real experiments with the autonomous vehicle ROMEO 4R (designed and built at the Escuela Superior de Ingenieros, University of Seville, Seville, Spain) demonstrate the efficiency of the described controller and of the methodology followed in its design.

A fuzzy gain-scheduler for the attitude control of an unmanned helicopter

Abstract: In this paper, we address the design of an attitude controller that achieves stable, and robust aggressive maneuverability for an unmanned helicopter. The controller proposed is in the form of a fuzzy gain-scheduler, and is used for stable and robust altitude, roll, pitch, and yaw control. The controller is obtained from a realistic nonlinear multiple-input-multiple-output model of a real unmanned helicopter platform, the APID-MK3. The results of this work are illustrated by extensive simulation, showing that the objective of aggressive, and robust maneuverability has been achieved.

Fuzzy system-based adaptive iterative learning control for nonlinear plants with initial state errors

Abstract: In this paper, a fuzzy system-based adaptive iterative learning controller is proposed for a class of non-Lipschitz nonlinear plants which can repeat a given task over a finite time interval. The variable initial resetting state errors at the beginning of each trial is considered. To overcome the initial errors, a time-varying boundary layer is introduced to design an error function. Based on the error function, the main structure of this controller is constructed by a fuzzy iterative learning component and a feedback stabilization component. The fuzzy system is used as an approximator to compensate for the plant unknown nonlinearity. Since the optimal parameters for a good fuzzy approximation are in general unavailable, the adaptive algorithms are derived along the iteration axis to search for suitable parameter values and then guarantee the closed-loop stability and learning convergence. It is shown that all the adjustable parameters as well as internal signals remain bounded for all iterations. There even exist initial state errors, the norm of tracking error vector will asymptotically converge to a tunable residual set as iteration goes to infinity and the learning speed can be easily improved if the learning gain is large.

A novel Takagi-Sugeno-based robust adaptive fuzzy sliding-mode controller

Abstract: In this paper, a nonlinear dynamic system is first approximated by N fuzzy-based linear state-space subsystems. To track a trajectory dominant by a specific frequency, the reference models with desired amplitude and phase features are established by the same fuzzy sets of the system rule. Similarly, the same fuzzy sets of the system rule are employed to design robust fuzzy sliding-mode control (RFSMC) and adaptive fuzzy sliding-mode control (AFSMC). The difference between RFSMC and AFSMC is that AFSMC contains an updating law to learn system uncertainties and then an extra compensation is designed. It is different from the most previous papers to learn the whole nonlinear functions. As the norm of the sliding surface is inside of a defined set, the updating law starts; simultaneously, as it is outside of the other set, the updating law stops. For the purpose of smoothing the possibility of discontinuous control input, a transition between RFSMC and AFSMC is also assigned. Under the circumstances, the proposed control [robust adaptive fuzzy sliding-mode control (RAFSMC)] can automatically tune as a RFSMC or an AFSMC; then the advantages coming from the RFSMC and AFSMC are obtained. Finally, the stabilities of the overall system of RFSMC, AFSMC, and RAFSMC are verified by Lyapunov stability theory. The compared simulations among RFSMC, AFSMC, and RAFSMC are also carried out to confirm the usefulness of the proposed control scheme.

On the distributivity of implication operators over T and S norms

Abstract: In this paper, we explore the distributivity of implication operators [especially Residuated (R)- and Strong (S)-implications] over Takagi (T)- and Sugeno (S)-norms. The motivation behind this work is the on going discussion on the law [(p/spl and/q)/spl rarr/r]/spl equiv/[(p/spl rarr/r)/spl or/(q/spl rarr/r)] in fuzzy logic as given in the title of the paper by Trillas and Alsina. The above law is only one of the four basic distributive laws. The general form of the previous distributive law is J(T(p,q),r)/spl equiv/S(J(p,r),J(q,r)). Similarly, the other three basic distributive laws can be generalized to give equations concerning distribution of fuzzy implications J on T- and S- norms. In this paper, we study the validity of these equations under various conditions on the implication operator J. We also propose some sufficiency conditions on a binary operator under which the general distributive equations are reduced to the basic distributive equations and are satisfied. Also in this work, we have solved one of the open problems posed by M. Baczynski (2002).

A simple neuro-fuzzy impulse detector for efficient blur reduction of impulse noise removal operators for digital images

Abstract: A new impulse noise detector based on neuro-fuzzy methods is presented. The proposed detector comprises two identical neuro-fuzzy subdetectors combined with a decision maker. The internal parameters of the subdetectors are adaptively adjusted by training. Training of the subdetectors is accomplished by using a simple computer generated artificial image. The detector can be combined with any impulse noise removal operator. The operation of the detector is completely independent of the noise removal operator and it has no influence on the filtering behavior of the operator. Experimental results show that the proposed detector significantly reduces the distortion effects of any impulse noise removal operator even if the operator already has its own noise detector.

Linear fuzzy clustering techniques with missing values and their application to local principal component analysis

Abstract: In this paper, we propose two methods for partitioning an incomplete data set with missing values into several linear fuzzy clusters by extracting local principal components. One is an extension of fuzzy c-varieties clustering that can be regarded as the algorithm for the local principal component analysis of fuzzy covariance matrices. The other is a simultaneous application of fuzzy clustering and principal component analysis of fuzzy correlation matrices. Both methods estimate prototypes ignoring only missing values and they need no preprocessing of data such as the elimination of samples with missing values or the imputation of missing elements. Numerical examples show that the methods provide useful tools for interpretation of the local structures of a database.

Hybrid fuzzy control of robotics systems

Abstract: This paper presents a new approach towards optimal design of a hybrid fuzzy controller for robotics systems. The salient feature of the proposed approach is that it combines the fuzzy gain scheduling method and a fuzzy proportional-integral-derivative (PID) controller to solve the nonlinear control problem. The resultant fuzzy rule base of the proposed controller can be decomposed into two layers. In the upper layer, the gain scheduling method is incorporated with a Takagi-Sugeno (TS) fuzzy logic controller to linearize the robotics system for a given reference trajectory. In the lower layer, a fuzzy PID controller is derived for all the locally linearized systems by replacing the conventional PI controller by a linear fuzzy logic controller, which has different gains for different linearization conditions. Within the guaranteed stability region, the controller gains can be optimally tuned by genetic algorithms. Simulation studies on a pole balancing robot and a multilink robot manipulator demonstrate the effectiveness and robustness of the proposed approach.