Scheduled System Maintenance:
On May 6th, single article purchases and IEEE account management will be unavailable from 8:00 AM - 12:00 PM ET (12:00 - 16:00 UTC). We apologize for the inconvenience.
By Topic

Intelligent Control, 1988. Proceedings., IEEE International Symposium on

Date 24-26 Aug. 1988

Filter Results

Displaying Results 1 - 25 of 134
  • Proceedings IEEE International Symposium on Intelligent Control 1988

    Publication Year: 1988
    Save to Project icon | Request Permissions | PDF file iconPDF (35 KB)  
    Freely Available from IEEE
  • Fuzzy logic systolic array for real-time approximate reasoning

    Publication Year: 1988 , Page(s): 628 - 632
    Cited by:  Papers (1)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (288 KB)  

    Rule-based expert systems and approximate reasoning in fuzzy logic are discussed, and the logic architectures for two fuzzy-logic expert systems are developed. The logic architectures are mapped onto two linear systolic arrays, and the step-processors for the systolic arrays are developed. The results show that the fuzzy-logic rule-based expert systems can be realized in systolic arrays with high parallelism and throughput View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Robotic deburring of two dimensional parts with unknown geometry

    Publication Year: 1988 , Page(s): 459 - 464
    Cited by:  Papers (1)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (532 KB)  

    Two of the problems in robotic deburring are addressed: tracking the planar two-dimensional part contour and control of the metal removal process. The tracking mechanism is a roller bearing mounted on a force sensor at the robot endpoint. The tracking controller utilizes the force measured by this force sensor to find the normal vector to the part surface. Using the part contour information the robot travels along the edge of the part. The metal removal algorithm uses another set of contact forces, cutting forces generated by the cutter, to develop a stable metal removal. This algorithm generates electronic compliancy for the robot along the edge of the part. This electronic compliancy causes the robot to slow down when the cutter encounters a burr. A set of experimental results is given to verify the effectiveness of the approach View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Information fractals in evidential reasoning

    Publication Year: 1988 , Page(s): 34 - 39
    Cited by:  Papers (1)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (476 KB)  

    Evidential reasoning based on a fractal model of belief is outlined. The specific focus is on the fractal modeling of belief functions. After a qualitative justification and interpretation of this model, several concepts and tools needed for its incorporation into evidential reasoning are formally defined. A particularly important concept is that of conductivity, as it provides the basis of partial evidential matching in the present approach to reasoning by analogy. A conductivity analysis algorithm is derived, and it is illustrated by an application to a simple object classification problem. The fractal model provides potentially powerful mechanisms for a quantitative measure of relevance of a piece of evidence to a knowledge base, and a systematic approach to the coarsening and refining of frames of discernment. The proposed model is motivated by applications to the design of intelligent systems, such as sensor-based dexterous manipulators that must operate in unstructured environments in the presence of high levels of uncertainty View full abstract»

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

    Publication Year: 1988 , Page(s): 642 - 647
    Cited by:  Papers (1)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (432 KB)  

    How a software design method for distributed real-time applications can be used to design distributed manufacturing control systems which consist of several concurrent tasks executing on multiple modes supported by a local area network is described. The application is a manufacturing control system which controls part manufacturing in a high-volume, low-flexibility assembly plant. The method addresses the needs of distributed real-time manufacturing applications by providing criteria for structuring subsystems into concurrent tasks. The method leads to a design which is primarily message based View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A corner detection-based object representation technique for 2-D images

    Publication Year: 1988 , Page(s): 186 - 190
    Cited by:  Papers (2)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (328 KB)  

    A corner detection-based object representation technique that operates on a thinned binary image is presented. The proposed method consists of two computational phases. The first phase involves the use of a corner detection method which detects the corners in the image. The second phase is a curve-following process that establishes the topological relationships between the corners for a complete object representation. The final output of the method is a list of corners, each identified by its position, the number of its edges, and the neighboring corners connected to it. Experimental results on a computer-generated line-drawing and an image of a real object are presented. The method gives reasonably good results for the images used in the test experiments View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Learning in a multiresolutional conceptual framework

    Publication Year: 1988 , Page(s): 564 - 568
    Cited by:  Papers (1)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (372 KB)  

    A real-time system for the control of an autonomous vehicle consisting of a nested hierarchy of control modules is discussed. The proposed intelligent controller has nonhomogeneous knowledge representation and a neural-network-based decision-making system operating in real time. The focus is on the Pilot module, which provides the real-time guidance of the system. It is responsible for the generation and tracking of dynamically feasible trajectories which follow the planned path given by the upper level (Navigator) and avoid local obstacles. Control of a complex system (mobile robot) is facilitated by the use of a feedforward neural network. How such an approach addresses constant response time of decision-making (control) and online learning and adaptability is discussed. Dealing with constraints is done via a multiresolutional system of dynamic avoidance regions, which are analogous to the concept of potential field by require much simpler representation and computational procedures View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • An approach to implementing a knowledge-based controller

    Publication Year: 1988 , Page(s): 648 - 651
    Cited by:  Papers (7)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (304 KB)  

    The results of building a knowledge-based adaptive controller for a DC-motor-driven, angular-positioning servo-trainer are presented. The approach used is general in the sense that tools have been built which will support knowledge-based identification, control law calculation, and controller implementation in response to changes in the system plant. However, the implementation is restricted to lead-lag compensation of a single-input, single-output linear, continuous plant and is currently limited by the accuracy of the model identification results. The system is capable of executing the cycle of identification, controller design, and implementation in approximately 10 s for a servo trainer used for classroom laboratory experiments. A significant analytical shortfall exists in that an assessment of the stability of such a system is not possible using currently available techniques. The system is described, and the tools developed for an inference engine to support reasoning about time-sensitive events are discussed View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Application of heuristic search and information theory to sequential fault diagnosis

    Publication Year: 1988 , Page(s): 291 - 296
    Cited by:  Papers (4)  |  Patents (1)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (656 KB)  

    The problem of constructing optimal and near-optimal test sequences to diagnose permanent faults in electronic and electromechanical systems is considered. The test sequencing problem is formulated as an optimal binary AND/OR decision tree construction problem, whose solution is known to be NP-complete. The approach is based on integrating concepts from information theory and heuristic AND/OR graph search methods to subdue the computational explosion of the optimal test sequencing problem. Lower bounds on the optimal cost-to-go are derived from the information-theoretic concepts of Huffman coding and entropy, which ensure that an optimal solution is found using the heuristic AND/OR graph search algorithms. This makes it possible to obtain optimal test sequences to problems that are intractable with the traditional dynamic programming techniques. In addition, a class of test sequencing algorithms that provide a tradeoff between optimality and complexity have been derived using the ε-optimal and limited search strategies. The effectiveness of the algorithms is demonstrated on several test cases. As a by-product, this approach to test sequencing can be adapted to solve a wide variety of binary identification problems arising in other fields View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • High-speed obstacle avoidance for mobile robots

    Publication Year: 1988 , Page(s): 382 - 384
    Cited by:  Papers (3)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (484 KB)  

    A real-time obstacle avoidance approach for mobile robots has been developed and implemented. This approach permits the detection of unknown obstacles simultaneously with the steering of the mobile robot to avoid collisions and the advance of the robot toward the target. The approach, called the virtual force field technique, integrates two known concepts: certainty grids for obstacle representation and potential fields for navigation. This combination is especially suitable for the accommodation of inaccurate sensor data (such as those produced by ultrasonic sensors) as well as for sensor fusion, and it allows continuous motion of the robot without stopping in front of obstacles. Experimental results from a mobile robot running at a maximum speed of 0.78 m/s demonstrate the power of the proposed algorithm View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • FABB: a blackboard development tool and its application to command and control

    Publication Year: 1988 , Page(s): 208 - 210
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (324 KB)  

    The Ford Aerospace Blackboard System (FABB) and its application to intelligent command and control are described. FABB is a blackboard development tool built upon Knowledge Craft that combines and extends many of the features found in current university blackboard shells. Extended use is made of Knowledge Craft's context mechanisms, both to isolate multiple blackboards within a single knowledge base and to allow independent knowledge sources to perform alternate world reasoning. Intelligent control of the problem-solving process is obtained by defining control blackboards, control knowledge sources, and control data objects. High-level plans and strategies are predefined before program execution and chosen opportunistically in a manner that best suits the problem situation. FABB is being used as the development tool in the initial stage of building a command and control system that analyzes and combines multiple, and often incomplete and inaccurate, information in an effort to identify enemy plans intelligently View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Grasp impedance: examples of finger's targeted impedance

    Publication Year: 1988 , Page(s): 479 - 483
    Cited by:  Papers (2)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (336 KB)  

    Two examples of formulating the targeted impedance of fingers of a mechanical hand are presented. A unified model of targeted impedance, based on the physical equivalence postulate of the closed-loop dynamics behavior of fingers, is used. Based on this postulate, the parameters of the targeted impedance can be selected such that the dynamic behavior of the closed-loop system satisfies specific task requirements. The first example is a formulation of the targeted impedance based on the object desired grasp stiffness properties at the point of interaction with the environment. The second example is a formulation of the targeted impedance for the case where the grasped object has some oscillatory motion, such that the oscillation of the object is minimized about some nominal equilibrium point. A method of obtaining the finger configuration based on the static relationship of the targeted impedance is also presented View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A learning algorithmic scheme for collision free navigation

    Publication Year: 1988 , Page(s): 569 - 573
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (344 KB)  

    A learning algorithmic scheme for collision-free navigation is presented. This scheme determines the minimum collision-free navigation path of an autonomous platform by using a trial and error process and past navigation knowledge and by extracting the current information from the surrounding environment. This scheme is related to the Odysseus autonomous navigation platform. However, it could be made into a general-purpose scheme with simple modifications. Simulated results for an illustrative example in a graphical representation are provided View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Real time experiments in neural network based learning control during high speed nonrepetitive robotic operations

    Publication Year: 1988 , Page(s): 513 - 518
    Cited by:  Papers (8)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (468 KB)  

    A learning control technique which uses an extension of the CMAC (cerebellar model articulation controller) network developed by J.S. Albus is discussed, and the results of real-time control experiments which involved learning the dynamics of a five-axis industrial robot during high-speed, nonrepetitive movements are presented. During each control cycle, a training scheme was used to adjust the weights in the network in order to form an approximate dynamic model of the robot in appropriate regions of the control space. Simultaneously, the network was used during each control cycle to predict the actuator drives required to follow a desired trajectory, and these drives were used as feedforward terms in parallel to a fixed gain linear feedback controller. Trajectory tracking errors were found to converge to low values within a few training trails for both repetitive and nonrepetitive operations View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Hybrid representations of real-time control rules for manufacturing process control in electronics manufacture

    Publication Year: 1988 , Page(s): 745 - 750
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (376 KB)  

    The authors present the results of experiments to determine the empirical control rules needed in the control of the dispensing of the small quantities of adhesives used to secure surface mount components to mixed technology printed circuit boards before wave soldering. Rule representations needed to control the dispensing system and to adapt elements of its behavior to changes in material property parameters are discussed. The authors also describe the implementation of a diagnostic system operating on a pressure-time pulse from the dispensing equipment. This system is a part of the controller that is needed for the dispensing system and the manufacturing cell in which it is contained. The cell and a control system that is currently under construction are also presented View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Autonomous planning in time-varying environments: a case study

    Publication Year: 1988 , Page(s): 356 - 361
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (448 KB)  

    A simulation of a specific example of an intelligent control system is described. The simulation includes a rich description of the environment in which the intelligent controller operates, including dynamic models of the physical systems under control. The primary goal of the modeling effort is to evaluate alternative real-time resource algorithms needed for certain planning tasks in stressing time-varying environments. The simulation permits investigation into high-level plan generation (e.g. object sequencing), which relies on a rather rich internal description of the operational environment. Simple sequencing algorithms have been developed and evaluated using the simulation. The model provides a tool suitable for addressing the interdependence of platform engineering parameters (acceleration, refire rate, field of view, range) and platform management (e.g. sequencing algorithm) and the resulting overall effectiveness View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A hierarchical planner for autonomous underwater vehicle control: the distributed control system multicomputer (DCSM) workbench

    Publication Year: 1988 , Page(s): 221 - 226
    Cited by:  Papers (2)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (532 KB)  

    The objective of the DCSM project is to develop and test hardware and operating-system-level concepts in support of knowledge-based architectures for the execution of command and control for autonomous vehicles. Research is concentrated on the areas of multicomputer hardware, system software, and the ways in which they can support knowledge-based application software as well as traditional control programs. The primary goal of this program is to develop a multicomputer architectural environment capable of supporting differing topologies of processing hardware, memory association and interconnection. A prototype distributed planning framework which allows evaluation of the coordination of plans in terms of goals, assertions, and informational usage is described. An example vehicle control mission is evaluated and decomposed into a planning hierarchy which aids in modeling the interaction of an AUV (autonomous underwater vehicle) and a manned submarine View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Applying intelligent robotics and vision to mail processing

    Publication Year: 1988 , Page(s): 724 - 729
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (396 KB)  

    The vision-guided robotic irregular parcels and pieces singulation (generalized bin-picking) and address block location technologies are described. The technological requirements and limitations are examined and discussed. Other mail singulation technologies for letters and flats that use vision-guided intelligent robots and computer-controlled intelligent mechanisms are reviewed View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A review of artificial intelligence in feedback control

    Publication Year: 1988 , Page(s): 40 - 45
    Cited by:  Papers (1)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (396 KB)  

    The use of knowledge-based techniques in feedback control is reviewed. Fuzzy linguistic control, qualitative causal control, and procedural control, as well as reinforcement learning and induction, are discussed. A brief comparison of these techniques in terms of some key characteristics is presented View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Application of connectionist learning methods to manufacturing process monitoring

    Publication Year: 1988 , Page(s): 709 - 712
    Cited by:  Papers (4)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (324 KB)  

    It is demonstrated that connectionist learning networks can monitor manufacturing processes to determine causal relationships with an accuracy competitive with that of conventional statistical techniques. Moreover, the network operates online, in realtime, and with substantial savings in computational complexity as compared with conventional CIM techniques. Two approaches are compared. One employs standard procedures to find correlations between sensor measurements and quality. The sensor data from the production line are collected over a period of time, and correlations are made offline at infrequent intervals using analyses such as linear regression. The second approach is to estimate the correlations incrementally, as the data are collected, online and in real-time. The estimates are updated incrementally using connectionist learning procedures. Simulation results are presented for a fluorescent bulb manufacturing line View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A dynamically evolving learning network for intelligent control

    Publication Year: 1988 , Page(s): 529 - 533
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (388 KB)  

    A variation on the adaptive learning network (ALN), which is used for dynamic system identification is discussed. The dynamically evolving ALN (DEALN) is self-organizing and operates online to generate a model of a dynamic plant. The network evolves the necessary structure and parameter values to mimic and predict the plant to within a specified tolerance. An intelligent controller can use the DEALN to simulate the plant, perform diagnoses, and plan coarse and fine control strategies. A high-level intelligent planner can also generate and program lower-level control laws to be implemented by the network, much as a human automates a skill. Results of an initial implementation which indicate that an online self-structuring learning network can be developed are presented View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Maintainability analysis for intelligent controls

    Publication Year: 1988 , Page(s): 385 - 388
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (676 KB)  

    The issue of software maintainability analysis for intelligent controls is discussed. Software maintainability can be expressed as the probability that the downtime caused by software error shall be no more than a specified time when maintenance action is performed in accordance with the prescribed procedures and resources. The proposed approach makes use of systematic analysis such as failure modes, effects, and criticality analysis (FMECA) or an equivalent methodology. The purpose is to predict missing requirements that could help in reducing the downtime. The procedure used involves constructing the program instruction flow chart, documenting maintainability requirements, and software failure mode and effects analysis. Examples of the development of requirements are presented View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Planning via heuristic search in a Petri net framework

    Publication Year: 1988 , Page(s): 350 - 355
    Cited by:  Papers (12)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (716 KB)  

    An artificial intelligence planning system's main components consist of a planner and a problem domain. The problem domain is the environment about which the planner reasons and on which it takes action. In the paper, a special type of extended input/output Petri net is defined and then used as the problem representation for a wide class of problem domains. A planning strategy is developed using results from the theory of heuristic search. In particular, using the developed Petri net framework and metric spaces, a class of heuristic functions that are both admissible and consistent for the A* algorithm is specified. The planning system architecture is discussed, and, as an illustration of the results, two simple planning problems are modeled and solved View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Automated knowledge base generation from CAD databases using relaxation techniques

    Publication Year: 1988 , Page(s): 211 - 214
    Cited by:  Papers (1)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (328 KB)  

    A system that converts the computer-aided design (CAD) database description of a process control system into a frame-oriented knowledge base for a diagnostic expert control system is described. The target expert system for the automated knowledge generation is NASA's Knowledge-Based Autonomous Test Engineer (KATE), developed to assist in the monitoring and control of Space Shuttle ground support systems. KATE retains the structure of the system it has knowledge about in its frame representations and derives understanding of the target system from intercomponent relationship knowledge held within those frames. A CAD database generated for a particular process control system contains all the structural information required to reconstruct the system, but little or no functional data. A functional description can be inferred in some cases from the CAD data; however, the complexity of such a system for a domain as large as process control is extensive. The construction and operation of an automated knowledge generation software system that performs the conversion from CAD database to knowledge base are discussed View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Time domain effects of model order reduction

    Publication Year: 1988 , Page(s): 603 - 607
    Cited by:  Papers (2)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (300 KB)  

    It is suggested that a preliminary and essential step in the design of flight control systems for highly augmented aircraft is obtaining an accurate open-loop dynamics model. Very large-order open-loop state-space models are constructed from analytical and empirical data obtained from knowledge of the vehicle's aerodynamics, propulsion, and structure dynamics. A balancing methodology for reducing a very large-order state-space representation to a more practical size is discussed. The balancing algorithm has a frequency domain error bound that guarantees the the magnitude of the reduced-order model's frequency response will be bounded. It is suggested that implementing techniques to preserve the number of nonminimum-phase zeros while performing model order reduction, and using residualizaton to match the steady-state magnitude, should improve the time history responses. A 140th-order aeroservoelastic model and a fourth-order critically damped system with an oscillator are considered as examples View full abstract»

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