By Topic

Intelligent Control, 2004. Proceedings of the 2004 IEEE International Symposium on

Date 2-4 Sept. 2004

Filter Results

Displaying Results 1 - 25 of 107
  • Visual servoing with velocity observer and neural compensation

    Publication Year: 2004, Page(s):454 - 459
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (651 KB) | HTML iconHTML

    The normal visual servoing of robot has two drawbacks: it needs joint velocity sensors, and cannot guarantee zero steady state error. We make two modifications to overcome these problems. Sliding-mode observer is applied to estimate the joint velocities, and a RBF neural network is used to compensate gravity and friction. Based on Lyapunov and input-to-state stability analysis, we prove the stabil... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Sliding windows in non-destructive testing systems

    Publication Year: 2004, Page(s):448 - 453
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (632 KB) | HTML iconHTML

    It is very important to improve noise immunity in ultrasonic nondestructive testing systems. This objective is achieved by reflected signal de-noising. The wavelets transform based methods are widely used for noise reduction in recent time. Effectiveness of the wavelets transform based de-noising procedure depends on the signal to noise ratio. The signal to noise ratio in a non-destructive testing... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Application of generalized adaptive wavelet neural network based on resemblance coefficient to signal recognition

    Publication Year: 2004, Page(s):443 - 447
    Cited by:  Papers (3)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (639 KB) | HTML iconHTML

    A novel approach called generalized adaptive wavelet neural network based on resemblance coefficient (GAWNN-RC) is proposed to extract the most discriminatory information from radar emitter signals and to recognize different radar emitter signals with different intra-pulse modulation laws In this work. Because a weighted linear combination of dilated and translated replica of a mother wavelet can ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Markov-localization through color features comparison

    Publication Year: 2004, Page(s):437 - 442
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (743 KB) | HTML iconHTML

    Self-localization plays a fundamental role in all the activities of a service mobile robot, from simple point-to-point navigation to complex fetch-and-carry tasks. In particular, in presence of an environment which changes dynamically, a trade-off must be found between apparently opposite characteristics: uniqueness (i.e. the ability to univocally recognize every location in the environment) and d... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A time-varying output feedback controller for nonlinear systems with linear output structure

    Publication Year: 2004, Page(s):340 - 345
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (670 KB) | HTML iconHTML

    This work presents a solution for the design of a time-varying and parametric output feedback controller for known general nonlinear dynamic systems subjected to linear output structure. The controller consists of two parts: an adaptive observer and a time-varying controller. Under a certain assumption on the nonlinear dynamics of the system, a stable and nonlinear adaptive observer can be firstly... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Smart, intelligent and cogent MEMS based sensors

    Publication Year: 2004, Page(s):431 - 436
    Cited by:  Papers (4)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (785 KB) | HTML iconHTML

    The paper develops a terminology to describe sensors which have been enhanced in some way by the integration of some additional processing circuitry. Several terms, current in the literature, including 'smart sensors' and 'intelligent sensors' are discussed and the 'cogent sensor' is introduced. This is followed by a brief review of existing and potential applications of artificial intelligence (A... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Natural language interface for mobile robot navigation control

    Publication Year: 2004, Page(s):210 - 215
    Cited by:  Papers (1)  |  Patents (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (712 KB) | HTML iconHTML

    Natural language command is very abstract. On the other hand, a mobile robot command should be very specific with actual numbers. Thus natural language processing and robot navigation has a big gap. In our research, we fill the gap integrating separately built natural language system and navigation system. We connect them by middleware standard to improve portability and efficiency. We use CORBA, ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Constructing and reconstructing characters, words and sentences

    Publication Year: 2004, Page(s):334 - 339
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (658 KB) | HTML iconHTML

    A problem of generating and manipulating characters, words and sentences is studied. First, characters are obtained as the trace of cross-sectional area between a virtual writing plane and a virtual writing device modeled by a circular cone which is moving in three dimensional space. Such a motion is designed as a sum of weighted and time-shifted B-spline functions. The so-called control polygon, ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • H control for fuzzy time-delay systems via descriptor system approach

    Publication Year: 2004, Page(s):407 - 412
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (594 KB) | HTML iconHTML

    We consider the H disturbance attenuation of Takagi-Sugeno fuzzy retarded and neutral type time-delay systems. For these fuzzy time-delay systems, a descriptor system approach is taken to analyze and synthesize fuzzy time-delay systems. We first make an H-norm analysis and obtain sufficient conditions for an H∞-norm to be less than a prescribed number. Suf... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A multiple internal model approach to movement planning

    Publication Year: 2004, Page(s):186 - 191
    Cited by:  Papers (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (661 KB) | HTML iconHTML

    Under the hypothesis that any human motion could be decomposed into dynamic movement primitives (DMPs), sets of second order differential equations are used as the internal model (IM) to describe primitive movements. The spacial and temporal scalabilities of the internal model could be used to simplify the learning process. In this paper, we present an approach to movement learning based on intern... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Design of a fuzzy logic-based bidirectional mapping for Kohonen networks

    Publication Year: 2004, Page(s):425 - 430
    Cited by:  Papers (3)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (675 KB) | HTML iconHTML

    In control engineering identifying the model of a system as well as inverting this model is an important task. Neural networks have recently shown great success in identifying a model and fuzzy logic allows in some cases to invert the model and to describe it in a way that human beings can understand it. An algorithm is described that combines the advantages of both techniques. It is a self-organi... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Adaptive backstepping control of a class of MIMO systems

    Publication Year: 2004, Page(s):204 - 209
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (633 KB) | HTML iconHTML

    Adaptive output feedback control of a class of multiple-input multiple-output systems is considered in the presence of unknown disturbances. Except the signs of the term multiplying the control are assumed, no other knowledge on the unknown parameters is required. The control design is achieved by using backstepping, tuning functions, SDU factorization and estimating parameters. It is shown that t... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Motion recovery for a class of movements under perspective observation

    Publication Year: 2004, Page(s):328 - 333
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (664 KB) | HTML iconHTML

    The recovery of motion for a class of movements in the space by using the perspective observation of one point is considered In this work. The motion equation can cover a wide class of practical movements in the space. The estimations of the position and motion parameters which are all time-varying are simultaneously developed in the proposed algorithm. The formulated problem can be converted into... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Neural network controller for manipulation of micro-scale objects

    Publication Year: 2004, Page(s):55 - 60
    Cited by:  Papers (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (622 KB) | HTML iconHTML

    A novel reinforcement learning-based neural network (RLNN) controller is presented for the manipulation and handling of micro-scale objects in a micro-electromechanical system (MEMS). In MEMS, adhesive, surface tension, friction and van der Waals forces are dominant. Moreover, these forces are typically unknown. The RLNN controller consists of an action NN for compensating the unknown system dynam... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Analysis of TS-fuzzy-model-based systems via shifted Chebyshev series

    Publication Year: 2004, Page(s):403 - 406
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (557 KB) | HTML iconHTML

    By use of the elegant operational properties of the shifted Chebyshev series, a direct computational algorithm for solving the Takagi-Sugeno (TS) fuzzy-model-based dynamic equations is developed In this work. The basic idea is that the state variables are expressed in terms of the shifted Chebyshev series. The new method simplifies the procedure of solving the TS-fuzzy-model-based dynamic equation... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Decentralized adaptive robust controllers guaranteeing uniform asymptotic stability for uncertain large scale time-delay systems

    Publication Year: 2004, Page(s):505 - 510
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (638 KB) | HTML iconHTML

    The problem of decentralized robust control is considered for large-scale systems with delayed state perturbations and external disturbances. Here, the upper bounds of the delayed state perturbations and external disturbances are assumed to be unknown. The adaptation laws are proposed to estimate such unknown bounds, and by making use of the updated values of these unknown bounds, a class of decen... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Adaptive regulation of robots using approximate models

    Publication Year: 2004, Page(s):180 - 185
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (726 KB) | HTML iconHTML

    Many control schemes have been proposed in the literature of robot control, while most of them assume either partial or full models of the kinematics, dynamics and actuator to be known exactly. Hence system stability cannot be guaranteed if all models of kinematics, dynamics and actuator are uncertain. We proposed a new task-space adaptive control scheme for regulation of robots with approximate k... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Stability and H disturbance attenuation analysis for symmetric Takagi-Sugeno fuzzy systems

    Publication Year: 2004, Page(s):310 - 315
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (632 KB) | HTML iconHTML

    We study the stability and H disturbance attenuation properties for a class of Takagi-Sugeno fuzzy systems composed of a finite number of linear time-invariant symmetric subsystems. We focus our attention on discrete-time systems. We show that when all the subsystems are Schur stable, the fuzzy system is asymptotically stable under arbitrary IF-THEN rule. Furthermore, we show tha... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Neural gain scheduling multiobjective genetic fuzzy PI control

    Publication Year: 2004, Page(s):483 - 488
    Cited by:  Papers (4)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (680 KB) | HTML iconHTML

    This work proposes a gain scheduling adaptive control scheme based on fuzzy systems, neural networks and genetic algorithms for nonlinear plants. A fuzzy PI controller is developed, which is a discrete time version of a conventional one. Its data base as well as the constant PI control gains are optimally designed by using a genetic algorithm for simultaneously satisfying the following specificati... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Fast sequential learning methods on RBF-network using decomposed training algorithms

    Publication Year: 2004, Page(s):84 - 89
    Cited by:  Papers (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (631 KB) | HTML iconHTML

    This work investigates novel sequential learning methods applied on a decomposed form of training algorithms using radial basis function (RBF) network. The dynamic expansion of RBF network by adding neurons to the hidden layer during the course of training facilitates the weight update to be decomposed on neuron by neuron basis. The fast or minimal update approach which can be adopted with ease on... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Operation-oriented advanced process control

    Publication Year: 2004, Page(s):252 - 257
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (723 KB) | HTML iconHTML

    Since the 1980s, the world-wide process industries have adopted and benefited from the applications of advanced process control (APC), particularly the model predictive control (MPC). Among many implementations of the APC technology, some successfully demonstrated substantial financial benefits but others failed to exhibit much advantage over conventional control technologies. These failures might... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Improved identification algorithm for B-spline modelling of output probability density functions

    Publication Year: 2004, Page(s):143 - 148
    Cited by:  Papers (3)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (648 KB) | HTML iconHTML

    An improved modelling technique has been developed for the B-spline approximation of the output probability density functions (PDFs). By reformulating the B-spline links between the weights vector and the output PDFs, the new algorithm decomposes the previous scanning identification into two separate operations, therefore reduces the dimension of the least square calculation and improves its effic... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Translating PWA systems into MLD systems

    Publication Year: 2004, Page(s):37 - 42
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (664 KB) | HTML iconHTML

    This work presents two algorithms which translate piecewise affine (PWA) systems into mixed logical and dynamical (MLD) systems. The two algorithms correspond to two different formulations of PWA systems. One of them consists of affine subsystems with switching regions between them, the other one consists of affine subsystems bounded by a convex region. Each algorithm is illustrated with an exampl... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Robust and stabilized MPC formulations for fault tolerant and reconfigurable flight control

    Publication Year: 2004, Page(s):222 - 227
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (761 KB) | HTML iconHTML

    Model predictive control (MPC) solves an optimization at every sampling instance to achieve commanded set-points and control objectives subject to constraints on control inputs and system states. Reconfigurable flight control is an application where the capabilities and flexibility of such optimization based control methods can be fully utilized and exploited. The online control optimization can i... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • On continuous Petri-net-type fuzzy cognitive maps: generalized approach

    Publication Year: 2004, Page(s):419 - 424
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (610 KB) | HTML iconHTML

    The work presents the generalized to the continuous type Petri nets and continuous fuzzy cognitive map and emphases: 1) the necessity to introduce continuous time dimension when practical interrelations in the real-world are modeled and investigated; and 2) the common description for both models which up till now were considered as different. Simplified examples of modeling from the field of inter... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.