Modeling environmental impacts on cognitive performance for artificially intelligent entities
Authors
Guthrie, Pierce C.
Subjects
vigilance
attention
path finding
A* search
human information processing
attention
path finding
A* search
human information processing
Advisors
Sciarini, Lee
Guerrero, Michael
McDowell, Perry
Date of Issue
2017-06
Date
Jun-17
Publisher
Monterey, California: Naval Postgraduate School
Language
Abstract
The Marine Corps utilizes virtual simulations as a training tool for ground combat operations. Currently, the artificial intelligence of simulation entities does not exhibit appropriate performance degradation due to environmental conditions, such as heat and humidity. To address these gaps, this thesis reviews existing approaches to modeling the influence of environmental factors, specifically heat and humidity, on human performance in vigilance and attention tasks. We present a novel agent behavior model that incorporates a modified A* search pathfinding algorithm based on empirical evidence of human information processing under the specified environmental conditions. Next, an implementation of the agent behavior model is presented in a military-relevant virtual game environment. We then outline a quantitative approach to test the agent behavior model within the virtual environment. Results show that our human information processing–based agent behavior model demonstrates plausible agent performance degradation in hot, humid temperature environments when compared to paths around the danger area in mild temperature environments. The results of this research provide an approach for implementing an agent behavior model that accounts for environmental impacts on cognitive performance. We recommend future work to validate the model in a human subjects experiment to facilitate improving the realism of simulation training.
Type
Thesis
Description
Supplementary material in library RRS
Series/Report No
Department
Computer Science (CS)
Organization
Identifiers
NPS Report Number
Sponsors
Funder
Format
Citation
Distribution Statement
Approved for public release; distribution is unlimited.
Rights
This publication is a work of the U.S. Government as defined in Title 17, United States Code, Section 101. Copyright protection is not available for this work in the United States.