Evolving artificial neural network controllers for autonomous agents navigating dynamic environments.

Digital Document
File
Summary
Abstract
Abstract
This thesis presents and discusses a potential method for solving the dynamic obstacle avoidance problem using contemporary work with artificial neural networks (ANNs) and genetic algorithms (GAs) in combination with an imitation of a biological genetic process called segmental duplication. ANNs, GAs and segmental duplication are merged in the project to form SDNEAT, a type of evolutionary artificial neural network (EANN) system based on NeuroEvolution of Augmenting Topologies, or NEAT. The system is then used to develop an artificial neural network system that attempts to navigate environments incorporating both static and dynamic obstacles.
Persons
Persons
Author (aut): Lucas, Robert A.
Thesis advisor (ths): Brown, Charles
Degree Name
Degree Name
Master of Science (MSc)
Department
Department
Computer Science
DOI
DOI
https://doi.org/10.24124/2009/bpgub634
Collection(s)
Collection(s)
Dissertations and Theses
Origin Information
Date Created/Date Issued
2009
Publisher
University of Northern British Columbia
Issuance
monographic
Organizations
Degree granting institution (dgg): University of Northern British Columbia
Degree Level
Masters
Subject Topic
Subject Topic
Neural networks (Computer science)
Genetic algorithms.
Library of Congress Classification
Library of Congress Classification
QA76.87 .L83 2008
Extent
Extent
Number of pages in document: 118
Physical Form
Physical Form
electronic
Content type
Content type
Digital Document
Resource Type
Resource Type
Text
Genre
Genre
thesis
Language
Language
English
Handle
Handle
Handle placeholder
ISBN
ISBN
978-0-494-48781-5
Use and Reproduction
Use and Reproduction
Copyright retained by the author.
Rights Statement
Rights Statement
IN COPYRIGHT
unbc_15970.pdf1.8 MB
Download
21497-Thumbnail Image.png3.84 KB
Download
21497-Extracted Text.txt169.39 KB
Download

Download

Language
English
Name
Evolving artificial neural network controllers for autonomous agents navigating dynamic environments.
Authored on
MIME type
application/pdf
File size
1889939
Media Use
Original File

Share

Cite this

Lucas, Robert A. “Evolving artificial neural network controllers for autonomous agents navigating dynamic environments”. Electronic, Thesis. Dissertations and Theses. University of Northern British Columbia, 2009. https://doi.org/https://doi.org/10.24124/2009/bpgub634.