Development of a potential field estimator for a path-planning application using neural networks /

and United Space Alliance.

Bibliographic Details
Main Author: Smith, Darin William
Format: Thesis eBook
Language:English
Published: [Place of publication not identified] : [publisher not identified] ; 1997.
Subjects:
Online Access:Link to OAKTrust copy
Description
Summary:and United Space Alliance.
application. The potential field estimator was developed
classification may then be used to find a set of weighting
classify a three-dimensional obstacle field on the basis of
described here, a reduction of approximately seven percent of
estimator for a locally constrained autonomous path-planning
factors that are used to reduce the computational effort
framework for the potential field estimator and the path-
geometrical statistical data. The results of the
higher than desired for path-planning problems, providing
is the product of research performed for Texas A&M University
measured as the total central processing unit (CPU) time
needed to solve a path-planning problem. Using the method
opportunities for further research. Computational expense is
planning application it supports is presented. This thesis
problem is observed. The computational expense is still
shown that a back-propagation neural network may be used to
spent solving a path-planning problem. The mathematical
the worst-case total computational time for a path-planning
This thesis presents the development of a potential field
to be useful for solving classification problems. It is
using back-propagation neural networks, which have been shown
Item Description:"Major subject: Aerospcae Engineering".
Vita.
Physical Description:ix, 80 leaves : illustrations ; 28 cm.
Also available online.
Issued also on microfiche from Lange Micrographics.
Bibliography:Includes bibliographical references: pages 65-66.