AHFE Open AccessHuman Factors and Simulation
Editors: Daniel Barber, Julia Wright
Topics: Simulation and Modelling
Publication Date: 2025
ISBN: 978-1-964867-56-4
DOI: 10.54941/ahfe1005991
Articles
A Human Multi-Agent Teaming Testbed, Escape Room Simulation
Scalability of multi-agent systems is quickly becoming a crucial area of research as artificial agents become more capable and sophisticated. This is particularly relevant in the context of increasingly ubiquitous AI and automation. A key challenge to furthering research in the area of human-multi-agent teams is having suitable test domains that are simple enough to allow thorough analysis, yet rich enough to foster an appropriate level of human-agent interaction. We present a new open-source test domain designed and developed to explore the dynamics of human interactions with multi-agent systems and the factors that enable and inhibit scalability.Our desire to understand and model the factors that influence scalability and related measures led us to search for a testbed simulation that could provide a suite of capabilities. First, it needed to model a specific type of activity, where the human owns the mission goals and coordinates the efforts of multiple agents to achieve a common goal. Second, we needed to be able to control the interaction and observability of the agents. Lastly, we needed to be able to adjust the autonomy of the agents. After researching available testbeds, we did not find many simulations that met these criteria, were readily available, open-source, easy to use, and most importantly, provided the desired human interaction dynamics. As such, we developed a suitable simulation testbed to explore measures of scalability and how both the characteristics of the technology and the human users affect the scalability of human multi-agent teams.The mission scenario we found that exemplifies the collaborative teamwork dynamics we are interested in is the escape room; a cooperative human team game that became popular in the last couple of decades. The escape room models the aspects of teamwork we were looking for: exploration, partial knowledge, distributed execution, interdependent decision-making, and puzzle-solving. Our escape room simulation is a single-player game where the human player directs a team of agents to explore several rooms to collect keys to open doors. The simulation can be simple with just a few keys and doors or increasingly complex with several layers of keys and doors to solve.In the escape room simulation, we can control the two main drivers of scalability: interaction and automation. The testbed is instrumented to measure both, as well as a host of additional relevant measures for analyzing scalability. We explain how the testbed supports several of the more popular models of scalability as well as our own variant. The simulation was developed using the p5 JavaScript library and the p5.js web editor. The source code is freely accessible online for tailoring the environment and modifying agent capabilities. With the increase of AI and agent capabilities and the desire to employ ever larger multi-agent teams, it is important to have a simulation to test out theories to better understand what influences, constrains and enables effective human multi-agent teaming. Our simulation provides a valuable tool for researchers and practitioners in this evolving field.
Lawrence Perkins, Hakki Erhan Sevil, Matthew Johnson
Open Access
Article
Conference Proceedings
A Neural Network Approach to Modeling Human Behavior in Conflict Zones
This paper explores the multifaceted phenomenon of collaborationism, with a particular focus on its manifestation during the ongoing Russian aggression against Ukraine. Collaborationism, defined as the act of cooperating with occupying forces, poses significant challenges to national security, social cohesion, and international stability. By examining the socio-political, economic, and ideological factors that influence individual decisions to collaborate, this study provides a comprehensive framework for understanding and predicting collaborationist behavior in conflict zones.Leveraging extensive data collected from Ukraine, the research employs an innovative approach using neural networks to model the emergence of collaborationism. The study identifies key indicators that contribute to an individual's propensity to collaborate, including material well-being, ideological alignment, moral qualities, and exposure to trigger events such as economic hardship or coercion by occupying forces. These indicators are analyzed within a broader socio-political context, revealing complex interactions between pre-existing conditions and situational pressures. The use of neural networks allows for the development of predictive models capable of simulating human behavior in high-stress environments, thereby offering valuable insights for both academic research and practical applications in conflict management.The findings highlight the importance of understanding human factors in shaping collaborationist behavior. By integrating psychological, economic, and ideological variables into a unified framework, the research demonstrates how individuals' decisions are influenced by a combination of intrinsic beliefs and external pressures. The study also underscores the role of moral and ethical considerations, which can either mitigate or exacerbate the likelihood of collaboration, depending on the individual's perception of legitimacy and survival. These insights are critical for designing interventions aimed at reducing the occurrence of collaborationism and fostering resilience within vulnerable populations.From a simulation perspective, the paper presents a novel application of neural networks to model human behavior in conflict scenarios. By simulating the interplay between individual characteristics and environmental factors, the proposed framework provides a dynamic tool for predicting collaborationist behavior under varying conditions. This approach not only enhances our understanding of human behavior in conflict zones but also offers practical applications for policymakers, security agencies, and humanitarian organizations. For instance, the predictive models can be used to identify at-risk individuals or communities, enabling targeted interventions that address the root causes of collaborationism, such as economic deprivation or ideological polarization.The broader implications of this research extend beyond the Ukrainian context. As Europe faces growing internal and external threats, understanding the dynamics of collaborationism becomes increasingly relevant for enhancing national and international security frameworks. The study's findings emphasize the need for comprehensive strategies that address both the symptoms and underlying drivers of collaborationism, including socio-economic disparities, political instability, and ideological manipulation. By incorporating predictive modeling and simulation into security planning, governments and international organizations can develop proactive measures to strengthen societal resilience against occupation and coercion.In conclusion, this research bridges the gap between human factors, simulation, and security studies by providing a robust framework for analyzing and predicting collaborationist behavior. The integration of neural networks and human factors research offers a powerful tool for understanding the complex interplay of individual and environmental influences, paving the way for innovative strategies to mitigate collaborationism and enhance resilience in conflict-affected regions.
Maryna Zharikova, Stefan Pickl
Open Access
Article
Conference Proceedings
Simulation for Artificial Intelligence Modeling and Assessment
Recent developments in autonomous fighter jets and concepts such as an autonomous wingman are pushing the boundaries for human-autonomy teaming in high-risk military flight operations. Many of these concepts explore the use of aides to accelerate pilot decision-making and reduce cognitive demands. Artificial Intelligence (AI) is a key enabling technology for decision support and automation of flight processes. Machine learning (ML) techniques are the primary method of training and validating modern AI models which requires representative data of increasing size. Acquiring this data is often a major blocker to the development of AI models. This becomes even more challenging when the target domain is aircraft for the U.S. Department of Defense (DoD) where existing datasets may be classified and/or inaccessible. A second requirement in the development of an AI model is an operational environment to integrate, execute, and assess performance in a closed-loop system. The ability to assess the AI safely in a live environment can also be difficult as when technology hasn’t yet fully matured. To address these challenges in the development of AI models for a decision support system, Southwest Research Institute (SwRI) leveraged the U.S. Air Force Research Laboratory’s (AFRL) Advanced Framework for Simulation, Integration, and Modeling (AFSIM) as a solution. This paper explores lessons learned in using AFSIM and its recently added support for the Python programming language to create a testbed for generating data of sufficient size to train Artificial Neural Networks (ANNs) to perform decision support and demonstrated in a closed-loop manner with new/live data.
Daniel Barber, Lauren Reinerman-jones
Open Access
Article
Conference Proceedings
Human Factors Challenges for Extended Reality Aviation Training Simulation
Extended reality (XR) technologies, encompassing augmented, mixed, and virtual reality (AR/MR/VR), hold immense potential for flight training, offering immersive and cost-effective training solutions. However, these systems face several technological challenges, as well as issues related to human factors and ergonomics, that hinder their full integration into aviation training programs, especially for military pilots. These issues must be addressed to ensure an XR-equipped flight simulator provides a realistic and reliable training environment. This requires iterative refinement of XR technologies through a multidisciplinary design approach. To meet these demands, the US Air Force Research Lab's Gaming Research Integration for Learning Laboratory® (GRILL®) conducts research that integrates human factors principles, game-based technology, and rigorous experimental design to increase operational efficiency and effectiveness. Incorporating human factors and ergonomic principles into XR flight training environments can lead to effective, reliable tools for flight training. These takeaways can be utilized across other industries. GRILL scientists are researching these issues, focusing on areas such as adapting simulation training based on biometric data, selecting technology that meets human factors requirements, and establishing best practices for optimizing dynamic XR training environments for intuitive interaction.
Stephanie Fussell, Summer Rebensky, Stephen Mcgee
Open Access
Article
Conference Proceedings
Examples and Lessons Learned Utilizing the Generalized Intelligent Framework for Tutoring (GIFT)
The Generalized Intelligent Framework for Tutoring (GIFT) is an open-source intelligent tutoring system (ITS) framework that can be used to create ITSs in any topic area (Goldberg & Sinatra, 2023). Flexibility is a large part of GIFT’s design, and there are many different ways that it can and has been used. In our discussion as part of the “SIG: Intelligent Tutoring Systems and Generalized Intelligent Framework for Tutoring-GIFT: Applicability to Industry, Academia, and Government” panel, and in the current paper, we focus on two different examples of using GIFT, and the lessons learned. These examples and lessons learned provide insight into how GIFT has been used, and how others could use it for their own work. The two use cases to be discussed are relevant to Human Factors professionals and include using GIFT to create and provide online adaptive lessons prior to the beginning of a class and using GIFT for real-time assessment during a data collection. In the first example, GIFT was used to create adaptive courses which were provided to students online prior to an in-person class. The discussion focuses on the features of GIFT that were used, and the type of adaptations that GIFT made. Further, lessons learned from defining the associated GIFT course concepts, and designing the GIFT courses are discussed. In the second example, GIFT was used for real time assessment during a data collection effort utilizing a handheld tablet to readily and easily track team performance over time. The data outputs were then utilized to guide After Action Reviews following the scenarios. Our panel discussion will showcase different ways that GIFT can and has been used, and provide SIG participants the opportunity to ask questions that are relevant to their own work.
Anne Sinatra, Lisa Townsend, Benjamin Goldberg, Paige Lawton
Open Access
Article
Conference Proceedings
Curiosity Games: Enhancing STEM Education in a VR Math Game Through GIFT Integration
The proposed integration of the Generalized Intelligent Framework for Tutoring (GIFT) into Curiosity Games, our Mars-based VR math game, represents a transformative approach to STEM education and training. Designed to engage middle and high school students, the game immerses learners in a dynamic educational experience while fostering skills critical for future careers in defense, aerospace, and STEM fields. Developed by the U.S. Army and its collaborators, GIFT provides advanced adaptive learning capabilities, real-time assessments, and robust monitoring tools that align seamlessly with the game’s structured classroom and exploratory open-world design. Students are able to use the game using VR or a desktop based application. The classroom component, set within a Martian observatory, will leverage GIFT to support a traditional adaptive course design. Students will follow a structured step-by-step process aligned with the 5E model: Math Conceptual Exercises (Engage and Explore), Apply Arithmetic (Explain and Elaborate), Test Questions (Evaluate), and culminating in Hands-On Activities (Elaborate). Progression is tied to performance, with students required to achieve a passing score of 80% or higher to move to the next stage. GIFT will issue credits as students successfully complete activities, tying in-game rewards to academic achievement.GIFT Integration Highlights:1. Real-Time Adaptive Support:-GIFT will provide tiered intervention to assist students who struggle with tasks, increasing teacher efficiency by prioritizing resources. These tiers include:-The AutoTutor Support is used first for immediate assistance.-Peer-to-Peer Support, where GIFT identifies proficient students to mentor peers, is the next intervention employed.-Small Group Support, where GIFT groups students with similar needs and facilitates teacher-hosted sessions, can be further employed.-One-on-One Teacher Support, dynamically pairing individual students with teachers based on real-time data to optimize outcomes, is the final intervention employed after the previous more time efficient options have been exhausted.2. Game Master Interface:-Teachers monitor progress, control adaptive exercises, and provide feedback through Objectives, Assessment, and Teams and Roles panels.3. After-Action Reviews (AAR):-Time-synced playback and video panels enable detailed reviews and targeted feedback.4. Open-World Exploration:-Students use credits to build Martian civilizations, solve tactical scenarios, and complete engineering challenges, with adaptive difficulty based on performance.Expected Outcomes:The integration of GIFT will enhance learning outcomes through personalized, adaptive support, improve teacher efficiency by optimizing resource allocation, and inspire the next generation of STEM professionals. This project aligns with the Department of Defense’s goals of fostering a technically skilled workforce and demonstrates the potential of integrating intelligent tutoring systems into immersive educational platforms.Lessons Learned:Leveraging GIFT’s existing tools minimizes development time for features such as teacher dashboards, multiplayer support, and scenario authoring. Utilizing these resources allows for efficient implementation and scalability, ensuring maximum return on investment.
Caila Deabreu, Eric Osorio, Hong Liu
Open Access
Article
Conference Proceedings