Organizational Unit:
Institute for Robotics and Intelligent Machines (IRIM)

Permanent Link
https://hdl.handle.net/1853/70657
Research Organization Registry ID
Description
Previous Names
Parent Organization
Parent Organization
Includes Organization(s)
Organizational Unit
Organizational Unit
ArchiveSpace Name Record

Filters

1993 - 1999 5
5
2 2
5
5
Reset filters

Settings
End date: 1999 × Start date: 1990 × search.filters.applied.f.isOrgUnitOfPublicationTitle: Institute for Robotics and Intelligent Machines (IRIM) × search.filters.applied.f.resourcesubtype: Pre-print ×

Publication Search Results

Now showing 1 - 5 of 5
  • Thumbnail Image
    Item
    A generalized approach to real-time pattern recognition in sensed data
    (Georgia Institute of Technology, 1999-12) Howard, Ayanna M. ; Padgett, Curtis
    Many applications that focus on target detection in an image scene develop algorithms specific to the task at hand. These algorithms tend to be dependent on the type of input data used in the application and thus generally fail when transplanted to other detection spaces. We wish to address this data dependency issue and develop a novel technique which autonomously detects, in real time, all target objects embedded in an image scene irrespective of the imagery representation. We accomplish this task using a heirarchical approach in which we use an optimal set of linear filters to reduce the data dimensionality of an image scene and then spatially locate objects in the scene with a neural network classifier. We prove the generality of this approach by applying it to two distinctly separate applications. In the first application, we use our algorithm to detect a specified set of targets for an Automatic Target Recognition (ATR) task. The data for this application is retrieved from two-dimensional camera imagery. In the second task, we address the problem of sub-pixel target detection in a hyperspectral image scene. This data set is represented by hyperspectral pixel bands in which target objects occupy a portion of a hyperspectral pixel. A summarized description of our algorithm is given in the following section.
  • Thumbnail Image
    Item
    Modeling Mechanisms with Nonholonomic Joints Using the Boltzmann-Hamel Equations
    (Georgia Institute of Technology, 1997-02) Obergfell, Klaus ; Book, Wayne J.
    This article describes a new technique for deriving dynamic equations of motion for serial chain and tree topology mech anisms with common nonholonomic constraints. For each type of nonholonomic constraint, the Boltzmann-Hamel equations produce a concise set of dynamic equations. These equations are similar to Lagrange's equations and can be applied to mechanisms that incorporate that type of constraint. A small library of these equations can be used to efficiently analyze many different types of mechanisms. Nonholonomic constraints are usually included in a La grangian setting by adding Lagrange multipliers and then eliminating them from the final set of equations. The ap proach described in this article automatically produces a minimum set of equations of motion that do not include La grange multipliers.
  • Thumbnail Image
    Item
    Modelling for Two-Time Scale Force/Position Control of Flexible Robots
    (Georgia Institute of Technology, 1996-04) Rocco, Paolo ; Book, Wayne J.
    Distributed flexibility of the links is a severe obstacle for the endpoint position control of lightweight manipulators. In order to accomplish with satisfactory performance certain tasks involving a controlled interaction of the tip of the robot with the worksurfaces, a combined control of the motion and the contact forces can provide some advantages, as it is now recognized for rigid robots. This paper presents a model of a flexible robot interacting with a rigid environment, together with a control scheme designed to achieve the simultaneous control of both the motion of the end effector and the forces at the contact. The time scale separation of the control actions, deriving from singular perturbation theory, is exploited in the design of the controller, which is made up by modular and easy-to-tune components. Simulation results obtained on a detailed nonlinear model of an existing 2 d.o.f. flexible arm are also given.
  • Thumbnail Image
    Item
    Integrated Modeling, Simulation, and Animation of Rigid Arms and Vehicles through Object-Oriented Programming
    (Georgia Institute of Technology, 1994-02) Schmitt, Paul Richard ; Hogan, John E. ; Cameron, Jonathan M. ; Book, Wayne J.
    This paper describes an object-oriented system, "MBSIM" (MultiBody SIMulator), that models, simulates, and animates the kinematics and dynamics of robotic arms and vehicles. This system creates a three dimensional graphical environment which can be used as a tool in robotic design and control.
  • Thumbnail Image
    Item
    Control and Control Theory for Flexible Robots
    (Georgia Institute of Technology, 1993-04) Magee, David P. ; Book, Wayne J.
    As the requirements for robot performance increase, the dynamics of the manipulator become more dominated by flexibility. These flexible effects generate model uncertainty which reduces the end-point positioning accuracy of the manipulator. Residual vibration or tip deflection due to uncertain payloads may contribute to the error in tip position. This paper addresses several control strategies currently used by researchers to account for flexibility in robots and their ability to perform tasks despite the flexibility.