Proceedings. IEEE International Symposium on Intelligent Control 1989

25-26 Sept. 1989

Filter Results

Displaying Results 1 - 25 of 94
  • Proceedings. IEEE International Symposium on Intelligent Control 1989 (Cat. No.89TH0282-4)

    Publication Year: 1989
    Request permission for commercial reuse | PDF file iconPDF (34 KB)
    Freely Available from IEEE
  • Joint-space adaptive control of a redundant telerobot manipulator

    Publication Year: 1989, Page(s):59 - 65
    Cited by:  Papers (4)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (468 KB)

    The design of a joint-space adaptive control-scheme for controlling the slave arm motion of a dual-arm telerobot system developed to study the telerobotic operations in space is presented. Each slave arm of the dual-arm system is a kinematically redundant manipulator with 7 degrees of freedom (DOF). Using the concept of model reference adaptive control (MRAC) and the Lyapunov direct method, the au... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A frequency-domain approach to learning control: implementation for a robot manipulator

    Publication Year: 1989, Page(s):66 - 71
    Cited by:  Papers (12)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (448 KB)

    A frequency-domain approach to the analysis and design of a learning control law for linear dynamic systems is presented. In its most simple version the scheme uses two separate filters in order to achieve rapid improvements in a specified bandwidth while cutting off-perhaps unmodeled-dynamic effects which would bar the convergence. The merit of this approach is to make explicit the tradeoff betwe... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • On the generation of a variable structure airport surface traffic control system

    Publication Year: 1989, Page(s):74 - 81
    Cited by:  Papers (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (776 KB)

    A quantitative methodology for modeling variable-structure decision-making organizations and for characterizing the set of solutions to a particular organizational design problem is presented. The structures considered, deterministically process a set of simultaneous observations. This methodology models variable structures with colored Petri nets, which are used as the basic mathematical framewor... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Requirements specification for distributed intelligent systems using the Cube Tool methodology

    Publication Year: 1989, Page(s):82 - 87
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (548 KB)

    The geographical dispersion of distributed intelligent systems requires the consideration of both processes and communications in the formulation of requirements. Cube Tool is a methodology used to derive the processing and communication needs for each system function. An approach is introduced for extending the applicability of Cube Tool to the determination of requirements for distributed intell... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • On nonholonomic mobile robots and optimal maneuvering

    Publication Year: 1989, Page(s):340 - 347
    Cited by:  Papers (108)  |  Patents (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (656 KB)

    The authors consider the robot path planning problem in the presence of nonintegrable kinematic constraints, known as nonholonomic constraints. Such constraints are generally caused by one or several rolling contacts between rigid bodies and express that the relative velocity of two points in contact is zero. They make the dimension of the space of achievable velocities smaller than the dimension ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Implementation of intelligent controller using neural network state estimator

    Publication Year: 1989, Page(s):413 - 416
    Cited by:  Papers (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (200 KB)

    It is shown that the neural network can be used as a state estimator in a model-reference intelligent control system. Its learning capability and noise rejection characteristic are illustrated by the results of a simulation study. The implementation of the state estimator by a neural network was possible due to the development of a proper structure of the neural network which is capable of simulat... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • On the quantitative evaluation of functionality in distributed intelligence systems

    Publication Year: 1989, Page(s):88 - 93
    Cited by:  Papers (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (756 KB)

    A quantitative methodology is presented for identifying and evaluating the shortfalls and overlaps between the desired functionality of a distributed intelligence system, as characterized by the requirements and the functionality of a proposed or implemented system. The approach is based on developing compatible Petri net representations of the requirements and of the system architecture which for... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Task planning for Robotworld: a case study

    Publication Year: 1989, Page(s):348 - 353
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (356 KB)

    The authors describe an implemented task planning system for the placement of electronic components on a printed circuit board (PCB). The task planner assumes an assembly workstation which is similar to V. Scheinman's Robotworld (1987), in which a number of small two-degrees-of-freedom robots slide on a horizontal platten above the PCB. After obtaining a PCB specification, the task planner generat... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Near-optimal kinodynamic planning for robots with coupled dynamics bounds

    Publication Year: 1989, Page(s):354 - 359
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (488 KB)

    The authors consider the following problem: given a robot system, find a minimal-time trajectory from a start state to a goal state, while avoiding obstacles by a safety margin and respecting bounds on velocity and generalized forces. A provably good polynomial-time approximation algorithm for this problem is one for which it is possible to (1) bound the goodness of the approximate solution it pro... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A new class of neural networks suitable for intelligent control

    Publication Year: 1989, Page(s):418 - 423
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (356 KB)

    The authors deal with a class of nonlinear neural networks which are capable of forming decision regions of higher complexity than the multilayer perceptron. These nonlinear neural nets have been used in many applications, from nonlinear classification to intelligent control. They have the same feedforward topology as the multilayer perceptron, except that, in certain nodes, a nonlinear operation ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Input space representation for refinement learning control

    Publication Year: 1989, Page(s):115 - 122
    Cited by:  Papers (9)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (672 KB)

    A learning control approach called refinement, in which a fixed controller is first designed using analytic design tools is explored. This controller's performance is refined by a secondary learning controller, which is a reinforcement learning-based connectionist network. The issue is the representation of the input space of the refinement learning controller. In previous work, the input space wa... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Migration of control in distributed intelligence systems

    Publication Year: 1989, Page(s):94 - 99
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (572 KB)

    A methodology and associated models are described that allow designers of information processing and decision systems to investigate the effects their designs have on the properties of decision-making organizations. Specifically, a quantitative model of a property that becomes very important when distributed decision making is considered, the migration of control, is described. An effort is made t... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Experimental analysis of robot control: a performance standard for the PUMA-560

    Publication Year: 1989, Page(s):257 - 264
    Cited by:  Papers (12)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (628 KB)

    The tracking performance of a series of model-based control algorithms was evaluated experimentally, The model-based control issues of incomplete and/or asynchronous dynamic compensation, feedback, payload variation, and drive system interaction are analyzed. A model-based controller with complete knowledge of manipulator system dynamics and sliding mode feedback improved the tracking accuracy by ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • An intelligent control system

    Publication Year: 1989, Page(s):194 - 199
    Cited by:  Papers (4)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (540 KB)

    The authors describe an intelligent control system that combines mathematical control theory and artificial intelligence (AI) technology. A controlled reasoning paradigm is proposed to carry out such an integration. An advanced (AI) control architecture, called Schemer, is described that can support such a paradigm. Schemer embodies a computational model of problem-solving `agents' that react to, ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • From knowledge transfer to knowledge generation

    Publication Year: 1989, Page(s):387 - 392
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (444 KB)

    By discussing several case studies, the authors point out that building an expert system is not just a translation from the existing knowledge into a computer program. It is a process in which new expertise knowledge may be generated and acquired. The new knowledge may complement the solver of the prototype problem. The authors introduce several new technological investigations that complement the... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Autonomous navigation to provide long-distance surface traverses for Mars Rover Sample Return Mission

    Publication Year: 1989, Page(s):362 - 367
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (508 KB)

    Knowledge acquisition and representation techniques are developed to allow an autonomous vehicle to negotiate a path over partially unknown terrain, such as the long-distance traverses for the Mars Rover Sample Return Mission. Terrain navigation is accomplished by the following sequence of steps: the skylines from the visibility map and from the local terrain map are compared and the two 3-D curve... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Flowgraph techniques in workcell assessment and design

    Publication Year: 1989, Page(s):28 - 32
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (220 KB)

    A number of methods for obtaining useful data from flowgraph representations of robot workcell networks, including error recovery loops, are presented. The application of some of the techniques normally found in electrical network analysis and simulation systems is discussed together with the results of some simple experiments. A useful technique for estimating overall performance improvements of ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Dynamic modeling and control of nonlinear processes using neural network techniques

    Publication Year: 1989, Page(s):280 - 286
    Cited by:  Papers (3)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (452 KB)

    An adaptive network architecture of nonlinear elements and delay lines is proposed, which can be taught to model the time responses of a nonlinear, multivariable system. The structure has been applied to the modeling and control of a highly coupled multivariable process, namely, gas tungsten arc (GTA) welding. The authors present the architecture, learning algorithm, and experiments which showed t... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Programming parallel distributed control for complex systems

    Publication Year: 1989, Page(s):426 - 432
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (644 KB)

    The author considers the design of control programs for systems with many degrees of freedom and multiple goals. These systems have several features requiring nontraditional control techniques. The author proposes a framework for the control of such systems. In this framework, it is possible to create abstract domains of interest and relate them to sensed and actuated quantities. Motions are progr... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A neural-net approach to supervised learning of pole balancing

    Publication Year: 1989, Page(s):123 - 129
    Cited by:  Papers (8)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (416 KB)

    It is shown how artificial neural nets can be used to solve a difficult learning problem. The task is to balance a pole that is hinged to a movable cart by applying either a left or a right force to the cart. The control process consists of developing pattern formations to give the required motor drive control. The latter is implemented with a connectionist net of the Rumelhart semilinear feedforw... View full abstract»

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

    Publication Year: 1989, Page(s):214 - 220
    Cited by:  Papers (2)  |  Patents (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (492 KB)

    It is noted that autonomous systems provide a new magnitude of flexibility and capability for complex manufacturing requirements. All resources are modeled as intelligent entities that interact with each other in a controlled environment. Each entity has an adaptive and intelligent controller allowing the entity to autonomously pursue multiple goals as both a consumer and a producer. Environment r... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Neuromorphic learning of continuous-valued mappings in the presence of noise: application to real-time adaptive control

    Publication Year: 1989, Page(s):312 - 319
    Cited by:  Papers (3)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (464 KB)

    The ability of feedforward neural net architectures to learn continuous-valued mappings in the presence of noise is demonstrated in relation to parameter identification and real-time adaptive control applications. Factors and parameters influencing the learning performance of such nets in the presence of noise are identified. Their effects are discussed through a computer simulation of the back-er... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Learning control system design for a parallel link robot manipulator

    Publication Year: 1989, Page(s):102 - 107
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (380 KB)

    A method of iterative learning control system design based on the two-dimensional (2D) theory is applied to the trajectory tracking control problem for the parallel link robot manipulator designed at the National Institute of Standards and Technology (NIST). The 2D model for the iterative learning control system which reveals the connections between learning control systems and 2D system theory, i... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • CHIMERA II: a real-time multiprocessing environment for sensor-based robot control

    Publication Year: 1989, Page(s):265 - 271
    Cited by:  Papers (15)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (612 KB)

    The CHIMERA II multiprocessing environment has been developed for use in a wide variety of sensor-based robot systems. It provides the flexibility, performance, and Unix-compatible interface needed for fast development of a real-time control code. The features of CHIMERA II include support for multiple general purpose CPUs; support for multiple special purpose CPUs and I/O devices; a real time mul... View full abstract»

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