Masters Theses
Keywords and Phrases
First responders
Abstract
"First responder training is becoming ever more important in our world. Several techniques are currently being explored to train first responders in physical and virtual worlds. The First Responder Simulation and Training Environment is being developed to augment the physical training efforts. This environment has many different components including a gas model, virtual environment, sensor simulator, and human interface equipment. An addition being made to the system is autonomous agents to interact with the first responders. Genetic programming, an evolutionary computation technique, is being used to evolve agents to interact in the environment. Friendly, hostile and neutral agents are being evolved in a two dimensional grid environment. Expression and decision trees are used to represent the individuals being evolved. The terminals for the decision trees are analyzed for their effectiveness. Low selective pressure and high crossover versus mutation rate were found to produce good individuals. Genetic programming is successfully employed to generate high performance individuals in the environment"--Abstract, page iv.
Advisor(s)
Hilgers, Michael Gene
Tauritz, Daniel R.
Committee Member(s)
Hall, Richard H.
Department(s)
Computer Science
Degree Name
M.S. in Computer Science
Publisher
University of Missouri--Rolla
Publication Date
Fall 2004
Pagination
ix, 32 pages
Note about bibliography
Includes bibliographical references (pages 29-31).
Rights
© 2004 Alex Jerome Berry, All rights reserved.
Document Type
Thesis - Restricted Access
File Type
text
Language
English
Subject Headings
Evolutionary computationIntelligent agents (Computer software)Virtual reality -- Technological innovations
Thesis Number
T 8705
Print OCLC #
62300867
Recommended Citation
Berry, Alex J., "Evolving intelligent agents for adaptive first responder virtual training" (2004). Masters Theses. 3644.
https://scholarsmine.mst.edu/masters_theses/3644
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
This work was funded by the U.S. Army’s Tank-Automotive and Armaments Command (TACOM, grant #DAAE07-02-C-L068).