By Topic

Systems, Man and Cybernetics, IEEE Transactions on

Issue 9 • Date Sep 1995

Filter Results

Displaying Results 1 - 8 of 8
  • A neural network based feedforward adaptive controller for robots

    Page(s): 1281 - 1288
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (524 KB)  

    In this paper, an adaptive controller for robot manipulators which uses neural networks is presented. The proposed control scheme is based on PD feedback plus a feedforward compensation of full robot dynamics. The feedforward signal is obtained by summing up the weighted outputs of a set of fixed multilayer neural nets. The controller is adaptive to robot dynamics and payload uncertainties. A stability analysis which takes into account neural network learning errors is included. Simulation results showing the feasibility and performance of the approach are given View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Optimum multisensor data fusion for image change detection

    Page(s): 1340 - 1347
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (876 KB)  

    Optimum multisensor data fusion is addressed for image change detection based on the optimum likelihood ratio test for the statistical dependence of the luminance signals in additive Gaussian noise. It is demonstrated that the information to be transmitted from the sensors to the fusion center is the maximum likelihood estimates of the correlation coefficients between pairs of consecutive image frames. Experimental results illustrate that the detection error decreases as the number of sensors and/or frames increases View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Estimation of spatial distortion as a function of geometric parameters of perspective

    Page(s): 1323 - 1333
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1068 KB)  

    As part of a study on the relationship between geometric parameters of perspective and judgments of spatial information, 15 subjects estimated the degree of spatial distortion within a computer-generated perspective display. The experiment task was to estimate “skewness,” the projected angle (in screen spate coordinates) between two parallel vertical computer-generated droplines (in world space coordinates) which varied as a function of the radial distance, station point distance, and the geometric field of view. These variables will influence the perceived size, depth, and height of objects displayed in the scene. Thus, estimating skewness as a function of display parameters is a relevant task for display design because it enables an intermediate variable (skewness) to be measured that will subsequently influence estimates of azimuth, elevation, size, and perceived depth within a perspective scene. In order to compare the subject's estimate of skewness with the actual on-screen distortion produced by the geometric parameters of perspective, a mathematical procedure for calculating the actual projected skewness angle was developed. The difference between the subject's estimated skewness and the actual on-screen skewness angle was analyzed as the response variable. The results indicated that both the station point and radial distance were significant factors in determining the accuracy with which subjects estimated the distortion in the perspective scene. However, there was no significant relationship between the geometric field of view used to design the perspective display and the subject's ability to judge the skewness angle in the perspective projection. The implications of the results for the design of spatial instruments and for performance of spatial tasks using perspective displays is discussed View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Switching models for nonstationary random environments

    Page(s): 1334 - 1339
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1372 KB)  

    Learning automata are stochastic finite state machines that attempt to learn the characteristic of an unknown random environment with which they interact. The fundamental problem is that of learning, through feedback, the action which has the highest probability of being rewarded by the environment. The problem of designing automata for stationary environments has been extensively studied. When the environment is nonstationary, the question of modeling the nonstationarity is, in itself, a very interesting problem. In this paper, the authors generalize the model used in Tsetlin (1971, 1973) to present three models of nonstationarity. In the first two cases, the nonstationarity is modeled by a homogeneous Markov chain governing the way in which the characteristics change. The final model considers the more general case when the transition matrix of this chain itself changes with time in a geometric manner. In each case the authors analyze the stochastic properties of the resultant switching environment. The question of analyzing the various learning machines when interacting with these environments introduces an entire new avenue of open research problems View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A neural network approach to photometric stereo inversion of real-world reflectance maps for extracting 3-D shapes of objects

    Page(s): 1289 - 1300
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1000 KB)  

    Presents a neural network approach to the problem of photometric stereo inversion of the reflectance maps of real-world objects for the purpose of estimating the 3-D attitudes of the surface patches of objects. As in the photometric stereo approach, here also the observation that there is a one-to-one mapping between the n-tuples of the photometric stereo image intensities and the orientations of the surface normals is valid. A multilayered feedforward neural network with backpropagation training algorithm is used as dimensionality reducer to effectively encode this mapping by associating the two components of surface normals to the observed intensities from three photometric stereo images of the underlying surface patches. The training patterns are sampled from the images of a Gaussian sphere of average reflectance containing both diffuse and specular components. The neural network thus trained has been tested on images of real-world objects with different shapes and reflectance properties. Using the surface normals estimated by the neural network, 3-D shapes of the objects have been reconstructed to a good approximation View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Fuzzy partitions of the sample space and fuzzy parameter hypotheses

    Page(s): 1314 - 1322
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (704 KB)  

    In this paper, a generalization of parameter hypotheses tests used in statistical inference is presented. This leads to fuzzy hypotheses defined as imprecise predictions about the unknown parameter of a family of distribution functions in question, rather than exactly and sharply given assertions about its location in the parameter space. The notion of fuzzy partitions is discussed in the first part of this paper and details regarding their structure in relation to possibility theoretical interpretations are investigated subsequently. In the second part the authors introduce the notions of fuzzy tests and disclose the impacts of an ill defined counter hypothesis (i.e., hypotheses, partly supporting the same subset of the parameter space) on the reliability of such a fuzzy test. An example demonstrates the consistency of the notion of fuzzy tests with the classical crisp case in statistical inference View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Stream Option Manager (SOM): automated integration of aircraft separation, merging, stream management, and other air traffic control functions

    Page(s): 1269 - 1280
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1020 KB)  

    Stream Option Manager (SOM) is a proposed concept for automated integration of aircraft separation, merging and stream management, using linear programming techniques. It was developed as part of a research and development initiative for air traffic control (ATC) automation concepts, sponsored by the Federal Aviation Administration (FAA) and performed by MITRE Corporation. SOM is research; it has not been approved by the FAA for use in future ATC. SOM's purpose is to resolve possible problems involving multiple aircraft with given flight paths. Each aircraft must be separated by a minimum distance from every other aircraft at all times, and certain sets of aircraft (e.g., those about to land at a particular airport) must be merged or metered (lined up, or separated in trail by a given distance). Aircraft in sets called streams must be separated in the along-route direction at all times. Each aircraft is also subject to certain speed limits. Given the pilot-preferred flight paths, and separation, metering, stream, and speed requirements, SOM finds modified flight paths for each aircraft that satisfy all the requirements yet stay as close as possible to the pilot-preferred paths. SOM's algorithm represents the (x, y, z) positions of each aircraft at future times as variables in a linear program. The requirements are expressed or approximated by linear inequalities or equalities. Pilot preferences are approximated by a linear objective function. The SOM algorithm has been implemented successfully in a prototype simulation in 2D. Scenarios with up to 15 aircraft and 24 separation and/or merging problems have been resolved View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Dependency analysis in constraint negotiation

    Page(s): 1301 - 1313
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (996 KB)  

    Problems in engineering design are constraint-oriented and often involve multiple perspectives. Designers must consider not only functional requirements of a product but also its life-cycle perspectives. Each perspective has its own set of constraints which may contain conflicting or unsatisfied requirements. A human designer can not be aware of all constraints and design alternatives all the time. The objective of this paper is to develop a methodology to assist designers in negotiation of constraints. A network model is proposed to represent relationships among design variables. An algorithm is developed to derive dependencies between design variables and goals. Based on the dependencies obtained, design modifications are generated for resolving conflicts. In the second part of the paper, a fuzzy-logic-based approach is used to model imprecise dependencies between variables in the case when no sufficient quantitative information is available. The approach proposed can be used to increase the amount of information provided to the designers for making decisions View full abstract»

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