By Topic

Proceedings of 8th IEEE International Symposium on Intelligent Control

25-27 Aug. 1993

Filter Results

Displaying Results 1 - 25 of 108
  • Proceedings of 8th IEEE International Symposium on Intelligent Control

    Publication Year: 1993
    Request permission for commercial reuse | PDF file iconPDF (243 KB)
    Freely Available from IEEE
  • The genetic planner: The automatic generation of plans for a mobile robot via genetic programming

    Publication Year: 1993, Page(s):190 - 195
    Cited by:  Papers (6)  |  Patents (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (468 KB)

    Planning is the creation of programs to control an agent, such as a robot. The genetic planner uses artificial selection, sexual mixing (recombination) and fitness proportionate reproduction to breed computer programs (i.e., to plan). The genetic planner uses a simulation of the world to execute candidate computer programs (i.e., candidate plans). The genetic planner is described, with an example ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Modeling, control and obstacle avoidance of a mobile robot with an onboard manipulator

    Publication Year: 1993, Page(s):196 - 201
    Cited by:  Papers (4)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (632 KB)

    A systematic approach for modeling and base motion control of a mobile vehicle with an onboard robot is presented. Feedback linearization is used to take into account the complete dynamics with nonholonomic constraints. Methods from potential field theory are incorporated to provide resolution among possibly conflicting performance goals (e.g. maintaining a desired course and speed plus obstacle a... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Fuzzy rule-based adaptive force control of a single DOF mechanisms

    Publication Year: 1993, Page(s):469 - 474
    Cited by:  Papers (5)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (484 KB)

    A position/force control with completely fuzzified adaptive force control system for the single degree of freedom mechanisms is presented. The proposed force control scheme contains are adaptive fuzzy force controller and a subordinated fuzzy velocity controller. By using a second-order referent model, a model reference-based fuzzy adaptation mechanism is able to keep the error between the model a... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Modeling walker/terrain interaction to achieve reliable, autonomous walking control

    Publication Year: 1993, Page(s):202 - 207
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (516 KB)

    Walking robots are inherently complex locomotors vis-a-vis their tracked and wheeled counterparts, yet they retain advantages in their ability to traverse difficult terrain. However, this advantage may only be realized through the development of methods which allow the robot to traverse such terrain safely and reliably. Methods and insights on how to achieve this for statically-stable walking robo... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Neural network construction and rapid learning for system identification

    Publication Year: 1993, Page(s):475 - 480
    Cited by:  Patents (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (432 KB)

    A new learning algorithm is introduced and used to identify nonlinear functions in a feedforward neural network. Its distinctive features are that it transforms the problem to a quadratic optimization problem that is solved by a number of linear equations and it constructs the appropriate network that will meet the specifications. The quadratic optimization/dependence identification algorithm exte... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A neural network based RLS parameter estimation algorithm and its application in predictive control

    Publication Year: 1993, Page(s):127 - 132
    Cited by:  Papers (7)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (440 KB)

    A method which uses neural networks to improve the performance of recursive least squares (RLS) algorithms in estimating the parameters of nonlinear processes is presented. Its application in a process gain-adaptive algorithm is described. This method uses neural networks to learn the parameter updating process of standard RLS algorithms and to relate these parameters to the operating conditions. ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Coal extraction using RCS

    Publication Year: 1993, Page(s):207 - 212
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (492 KB)

    The application of the real time control system (RCS) reference model to a simulated underground coal mining machine is described. RCS is characterized by explicit software modules that perform task decomposition, sensory processing, and world modeling functions at different hierarchical levels. A detailed and sharply defined approach to RCS design characterized by task-oriented problem analysis, ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Hybrid synthesis of optimal control for discrete event systems

    Publication Year: 1993, Page(s):308 - 313
    Cited by:  Patents (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (256 KB)

    A new solution to the synthesis of optimal control for discrete event systems modeled as finite state automata is given. The problem is as follows: given a system G and a forbidden state qb, find a state feedback policy (if there is one) fmax such that a given performance index E is maximized. The solution space is first reduced by some algebraic operations and then the optimal control ... View full abstract»

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

    Publication Year: 1993, Page(s):49 - 51
    Cited by:  Papers (3)  |  Patents (7)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (280 KB)

    A hierarchical reference model architecture for real-time intelligent control is defined. At each level, generic task decomposition modules accept commands and use stored task knowledge to decompose the commands into subcommands to be sent to subordinate task decomposition modules. Both spatial and temporal task decomposition are addressed View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • On the stabilization of unstable plants via learning control

    Publication Year: 1993, Page(s):481 - 486
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (216 KB)

    Intelligent controls in general and learning control in particular typically address the control of stable plants. The performance of learning control in stabilizing the response of unstable plants is investigated View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Generalized stochastic state space neural adaptive control

    Publication Year: 1993, Page(s):133 - 138
    Cited by:  Papers (5)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (252 KB)

    A generalized stochastic neural adaptive control algorithm is presented, where the system identification is based on the state space innovations model and a neural network architecture. This identification algorithm is derived from three different optimization approaches, i.e., the gradient, Newton, and minimum variance. The control law, also based on neural networks structure, is derived from a q... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A statistical perspective of neural networks for process modeling and control

    Publication Year: 1993, Page(s):599 - 604
    Cited by:  Papers (3)  |  Patents (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (472 KB)

    Multilayer neural networks have been successfully applied to industrial process modeling and control. The prediction variance of neural networks from gradient based learning is analyzed in the presence of correlated process inputs. Several biased regression approaches, including ridge regression, principal component analysis, and partial least squares, are integrated with neural net training to re... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Unified control of contact and joint space drift in multifingered robot hands

    Publication Year: 1993, Page(s):213 - 218
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (508 KB)

    A general approach for controlling the system configuration drift resulting from the presence of nonholonomic constraints and kinematic redundancy in multifingered robot hands is presented. A redundant multifingered robot hand for grasping and manipulating an object using 3-D rolling contacts is considered. The configuration space of a multifingered robot system (i.e., the hand and a grasped objec... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Automatic verification of principal contacts using vision

    Publication Year: 1993, Page(s):314 - 319
    Cited by:  Papers (5)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (504 KB)

    Automatic recognition of unknown contacts among objects provides high-level feedback for a reactive robot system. The recognition mechanism must be online and insensitive to sensing uncertainties. A method is introduced of online using vision to extract more accurate contact information by reducing a set of initial contact hypotheses which are obtained from position/orientation sensing and subject... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Planning via search in the input/output space

    Publication Year: 1993, Page(s):548 - 553
    Cited by:  Papers (3)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (472 KB)

    The computational complexity of planning can be reduced by the synthesis of an appropriate representational hierarchy. In order to provide a formal structure for the description of such a hierarchy, the concepts of temporal and spatial resolution are defined, and a technique for the automated construction of multilevel system representations is described. The operation of contraction (or focusing ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A cost measure for efficient scheduling in intelligent machines

    Publication Year: 1993, Page(s):52 - 57
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (476 KB)

    A model of the coordination level of Saridis's intelligent machine paradigm is presented. The role of the coordination level is to translate a high-level command into a schedule of low-level primitive activities. The model presented is based on hierarchical Petri nets and stochastic learning algorithms. An analytic cost measure of the scheduling structure of the coordination level is presented. Fo... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Stable neural control of discrete systems

    Publication Year: 1993, Page(s):110 - 115
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (352 KB)

    The control of nonlinear discrete systems using neural networks is discussed. The discrete systems discussed have the form yk + 1 = b(yk,...,yk-1)uk + f(yk,...yk-1). Neural networks could be either radial basis functions (RBFs) or cerebellar model articulation controller (CMAC). The stability features are guar... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Equivalent Lyapunov and frequency domain stability conditions for iterative learning control systems

    Publication Year: 1993, Page(s):487 - 492
    Cited by:  Papers (4)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (360 KB)

    A system which repeatedly tracks a specified trajectory is considered. The error between a specified trajectory and the actual trajectory of system from the previous trial is used by an iterative learning control law in order to reduce this error on the current trial. Sufficient conditions which were developed by the authors for iterative learning system stability using Lyapunov stability theory a... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • The challenge of intelligent sensing of monitoring and control

    Publication Year: 1993, Page(s):139 - 143
    Cited by:  Papers (7)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (508 KB)

    Intelligent sensors offer new capabilities in process measurement. Traditional control and system theory models do not adequately consider the measurement uncertainty information and the nonperiodic sampling possible from intelligent sensors. A new modeling framework for systems exhibiting these irregular observations is introduced. The framework uses linear constraints and a variation of descript... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Development of a fusion algorithm for uncertain and imprecise information

    Publication Year: 1993, Page(s):605 - 610
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (492 KB)

    Distributed decision at a central processing site requires combining local decisions and evidence collected from distributed and heterogeneous information sources. A global decision maker at the fusion center is responsible for transforming the collected evidence into a common knowledge framework so that the converted information can be combined in order to deduce a concise and collective inferenc... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A simulation-based grasp planning system for multifinger robot hands

    Publication Year: 1993, Page(s):219 - 224
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (640 KB)

    The development of an advanced planning environment is described, which is especially tailored for the programming and simulating of complex assembly operations with multifinger robot hands. A new geometric-mechanic approach to the problem of planning grasp parameters for multifinger hands is presented, which considers the constraints of pick-and-place operations in manipulation and insertion task... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Selection of features and evaluation of visual measurements for 3-D robotic visual tracking

    Publication Year: 1993, Page(s):320 - 325
    Cited by:  Papers (7)  |  Patents (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (584 KB)

    An overview is presented of the vision techniques that are used in order to automatically select features, measure features' displacements, and evaluate measurements during 3-D robotic visual tracking. The most robust technique proves to be the sum-of-squared differences (SSD) optical flow technique. Several techniques for the evaluation of the measurements are presented. These techniques can also... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Adaptive learning control using affine radial basis function network approximation

    Publication Year: 1993, Page(s):505 - 510
    Cited by:  Papers (3)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (572 KB)

    A new paradigm for learning control of a generic nonlinear system is presented. The method is based on a special radial basis function network architecture and is adaptive as the input/output properties of the system are estimated and the learning control gain is computed online. The controlled system is described with a mapping between the feedforward control and an array of sampled output values... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Automatic control of robotic systems in unstructured environments

    Publication Year: 1993, Page(s):81 - 89
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (712 KB)

    The US Department of Energy's Office of Technology Development has sponsored the development of generic robotics technologies for application to a wide range of remote systems. Of primary interest is the development of technologies which enable faster, safer, and cheaper cleanup of hazardous waste sites than is possible using conventional human contact or remote manual approaches. The development ... View full abstract»

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