Harrison P. Crowell
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Harrison P. Crowell has a total of 15 co-authors. Here are the top co-authors by number of shared publications:
- Andrea Krausman
DEVCOM Army Research Laboratory
2 shared publications - Daniel Eric Forster
DEVCOM Army Research Laboratory
2 shared publications - David Chhan
Lamarr Institute for Machine Learning and Artificial Intelligence
2 shared publications - Kimberly Pollard
DEVCOM Army Research Laboratory
2 shared publications - Shan Lakhmani
DEVCOM Army Research Laboratory
2 shared publications - Angela C. Boynton
U.S. Army Combat Capabilities Development Command (DEVCOM) Analysis Center
1 shared publication
Latest Publications
- 31 December 2025
- Published by John Benjamins Publishing Company
- Vol. 26 (2) , 229-266
Exploring trust in AI-supported military teams using sentiment analysis
Examining sentiment in team communications can provide information about trust among teammates. Natural language processing (NLP) models provide an efficient means of sentiment analysis. However, military teams and other professional teams use language that differs from what NLP models are trained on, leading to potentially inaccurate sentiment analysis. This study investigates the novel application of two advanced NLP models, DistilBERT and GPT-2, for sentiment analysis of expert military teams conducting AI-supported combat missions in a high fidelity simulation environment. Our fine-tuning process resulted in improved sentiment classification accuracy. The sentiment measures also correlated with measures of team trust and trust in the AI systems, providing valuable insight into the relationship between sentiment and trust in human-AI teaming scenarios. The generalized approach we describe may be useful for adapting sentiment analysis and NLP techniques to military teams, and may help measure trust dynamics and team states in human machine integrated teams.
- 31 December 2025
- Published by John Benjamins Publishing Company
- Vol. 26 (2) , 229-266
Exploring trust in AI-supported military teams using sentiment analysis
Examining sentiment in team communications can provide information about trust among teammates. Natural language processing (NLP) models provide an efficient means of sentiment analysis. However, military teams and other professional teams use language that differs from what NLP models are trained on, leading to potentially inaccurate sentiment analysis. This study investigates the novel application of two advanced NLP models, DistilBERT and GPT-2, for sentiment analysis of expert military teams conducting AI-supported combat missions in a high fidelity simulation environment. Our fine-tuning process resulted in improved sentiment classification accuracy. The sentiment measures also correlated with measures of team trust and trust in the AI systems, providing valuable insight into the relationship between sentiment and trust in human-AI teaming scenarios. The generalized approach we describe may be useful for adapting sentiment analysis and NLP techniques to military teams, and may help measure trust dynamics and team states in human machine integrated teams.
- 24 January 2019
- Published by Taylor & Francis in IISE Transactions on Occupational Ergonomics and Human Factors
- Vol. 7 (3-4) , 199-212
Design, Evaluation, and Research Challenges Relevant to Exoskeletons and Exosuits: A 26-Year Perspective From the U.S. Army Research Laboratory
Efforts to develop exoskeletons and exosuits for military uses have been underway for many years. Assessments, evaluations, and research studies conducted at the U.S. Army Research Laboratory have been instrumental in that development. This work has provided design guidance for system developers, refined methods and metrics to characterize the state-of-the-art in exoskeleton and exosuit development, and identified gaps in knowledge needed for system designers and evaluators. Several design and evaluation challenges and areas needing further research are identified in this article, which are intended for use by ergonomics and human factors practitioners so they can contribute to the development and fielding of exoskeletons and exosuits for military applications. Background: Exoskeletons and exosuits intended to augment strength and endurance would be very useful for military tasks, particularly carrying heavy loads for long distances over terrain that cannot be traversed by vehicles. Such systems could relieve the burden felt when carrying these loads or reduce the energetic cost of walking while carrying loads, and may also reduce the risk of injury. Purpose: This article is intended to highlight key challenges that designers, evaluators, and researchers need to consider and address in order to further the development of exoskeletons and exosuits designed to assist with military load carriage. Methods: This overview is based on many years of experience with exoskeleton and exosuit assessments, evaluations, and research studies conducted at the U.S. Army Research Laboratory. Results: The challenges faced by designers of exoskeletons and exosuits for military load carriage include issues related to the unique equipment that must be carried, the variety of movements that must be accommodated, and the range of environments in which the systems must operate. Evaluators must take into consideration an array of issues from subjects and training to methods and metrics appropriate for the technical maturity and intended use of the system. Exoskeleton and exosuit system design and evaluation both need to be done in a manner that promotes the development of systems that are safe for the user. The research challenges are gaps in knowledge relevant to both design and evaluation issues. These gaps include a need for additional kinematic and kinetic data to be used in system design, and the need to develop control systems that anticipate movements and adapt to the user. Other knowledge gaps include user-system interface issues and training methods and assessments. Conclusion: The development and fielding of exoskeletons and exosuits will depend on designers, evaluators, and researchers who address the challenges presented herein.
- 24 January 2019
- Published by Taylor & Francis in IISE Transactions on Occupational Ergonomics and Human Factors
- Vol. 7 (3-4) , 199-212
Design, Evaluation, and Research Challenges Relevant to Exoskeletons and Exosuits: A 26-Year Perspective From the U.S. Army Research Laboratory
Efforts to develop exoskeletons and exosuits for military uses have been underway for many years. Assessments, evaluations, and research studies conducted at the U.S. Army Research Laboratory have been instrumental in that development. This work has provided design guidance for system developers, refined methods and metrics to characterize the state-of-the-art in exoskeleton and exosuit development, and identified gaps in knowledge needed for system designers and evaluators. Several design and evaluation challenges and areas needing further research are identified in this article, which are intended for use by ergonomics and human factors practitioners so they can contribute to the development and fielding of exoskeletons and exosuits for military applications. Background: Exoskeletons and exosuits intended to augment strength and endurance would be very useful for military tasks, particularly carrying heavy loads for long distances over terrain that cannot be traversed by vehicles. Such systems could relieve the burden felt when carrying these loads or reduce the energetic cost of walking while carrying loads, and may also reduce the risk of injury. Purpose: This article is intended to highlight key challenges that designers, evaluators, and researchers need to consider and address in order to further the development of exoskeletons and exosuits designed to assist with military load carriage. Methods: This overview is based on many years of experience with exoskeleton and exosuit assessments, evaluations, and research studies conducted at the U.S. Army Research Laboratory. Results: The challenges faced by designers of exoskeletons and exosuits for military load carriage include issues related to the unique equipment that must be carried, the variety of movements that must be accommodated, and the range of environments in which the systems must operate. Evaluators must take into consideration an array of issues from subjects and training to methods and metrics appropriate for the technical maturity and intended use of the system. Exoskeleton and exosuit system design and evaluation both need to be done in a manner that promotes the development of systems that are safe for the user. The research challenges are gaps in knowledge relevant to both design and evaluation issues. These gaps include a need for additional kinematic and kinetic data to be used in system design, and the need to develop control systems that anticipate movements and adapt to the user. Other knowledge gaps include user-system interface issues and training methods and assessments. Conclusion: The development and fielding of exoskeletons and exosuits will depend on designers, evaluators, and researchers who address the challenges presented herein.