Masters Theses
Abstract
"A differentially steered nonholonomic mobile robot platform has been fabricated to implement and validate nonlinear control laws. The platform can also be used to validate hierarchical cooperative control techniques. As a first step towards building a fleet of autonomous robots, novel control methods are developed and implemented on the robot platform for trajectory tracking as well as point stabilization. As an extension to the development of nonlinear controllers, a novel reinforcement learning based neural network is developed to control a manipulation task for a micro-electro-mechanical system (MEMS). The nonlinear controllers developed for both the robot and the MEMS have online neural networks to compensate for the unknown nonlinear system dynamics"--Abstract, page iv.
Advisor(s)
Sarangapani, Jagannathan, 1965-
Balakrishnan, S. N.
Committee Member(s)
Agarwal, Sanjeev, 1971-
Department(s)
Electrical and Computer Engineering
Degree Name
M.S. in Electrical Engineering
Research Center/Lab(s)
Intelligent Systems Center
Publisher
University of Missouri--Rolla
Publication Date
Fall 2005
Journal article titles appearing in thesis/dissertation
- Control of a nonholonomic mobile robot
- Neural network controller for manipulation of microscale objects
Pagination
viii, 42 pages
Note about bibliography
Includes bibliographical references.
Rights
© 2005 Vijayakumar Janardhan, All rights reserved.
Document Type
Thesis - Restricted Access
File Type
text
Language
English
Subject Headings
Neural networks (Computer science)Robots -- Control systemsNonholonomic dynamical systemsMicroelectromechanical systems
Thesis Number
T 8896
Print OCLC #
71044152
Recommended Citation
Janardhan, Vijayakumar, "Design and implementation of controllers for a class of electromechanical systems" (2005). Masters Theses. 5833.
https://scholarsmine.mst.edu/masters_theses/5833
Share My Thesis If you are the author of this work and would like to grant permission to make it openly accessible to all, please click the button above.
Comments
The support received from the National Science Foundation grants ECS XXXXX and ECS 0296191 and Intelligent Systems Center for this research is greatly appreciated.