Human-machine Teaming Research Articles

The Silicon Sky II: The Promise of Human–Machine Teams in Weather Forecasting

The Silicon Sky II: The Promise of Human–Machine Teams in Weather Forecasting

Methods for building ontologies to ensure coordinated behavior of autonomous intellectual systems in agriculture

Ontologies are the main tool for representing domain knowledge. The need to use ontologies to ensure consistent behavior of autonomous intelligent systems in agriculture is determined by the need to create semantic interactiveness of agricultural systems and decision support systems, in which automatic knowledge inference occurs based on semantic processing of data from a sensor network. The purpose of the study is to develop methods for constructing ontologies to ensure consistent behavior of autonomous intelligent systems in agriculture. The paper presents the architecture of an intelligent control system for a heterogeneous human-machine team, consisting of an autonomous robot for active plant protection and an unmanned aerial vehicle (UAV) for monitoring the condition of the garden from the air. A multiagent architecture for constructing ontologies has been developed to ensure consistent behavior of a human-machine team. In particular, a multiagent architecture for constructing an ontology when a robot detects a new object is presented, as well as a scheme for exchanging knowledge between team members. The results obtained can be used in the development of decision support systems, in which automatic knowledge inference occurs based on semantic processing of data from a sensor network.

Interpretable Severity Scoring of Pelvic Trauma Through Automated Fracture Detection and Bayesian Inference.

Pelvic ring disruptions result from blunt injury mechanisms and are potentially lethal mainly due to associated injuries and massive pelvic hemorrhage. The severity of pelvic fractures in trauma victims is frequently assessed by grading the fracture according to the Tile AO/OTA classification in whole-body Computed Tomography (CT) scans. Due to the high volume of whole-body CT scans generated in trauma centers, the overall information content of a single whole-body CT scan and low manual CT reading speed, an automatic approach to Tile classification would provide substantial value, e. g., to prioritize the reading sequence of the trauma radiologists or enable them to focus on other major injuries in multi-trauma patients. In such a high-stakes scenario, an automated method for Tile grading should ideally be transparent such that the symbolic information provided by the method follows the same logic a radiologist or orthopedic surgeon would use to determine the fracture grade. This paper introduces an automated yet interpretable pelvic trauma decision support system to assist radiologists in fracture detection and Tile grading. To achieve interpretability despite processing high-dimensional whole-body CT images, we design a neurosymbolic algorithm that operates similarly to human interpretation of CT scans. The algorithm first detects relevant pelvic fractures on CTs with high specificity using Faster-RCNN. To generate robust fracture detections and associated detection (un)certainties, we perform test-time augmentation of the CT scans to apply fracture detection several times in a self-ensembling approach. The fracture detections are interpreted using a structural causal model based on clinical best practices to infer an initial Tile grade. We apply a Bayesian causal model to recover likely co-occurring fractures that may have been rejected initially due to the highly specific operating point of the detector, resulting in an updated list of detected fractures and corresponding final Tile grade. Our method is transparent in that it provides fracture location and types, as well as information on important counterfactuals that would invalidate the system's recommendation. Our approach achieves an AUC of 0.89/0.74 for translational and rotational instability,which is comparable to radiologist performance. Despite being designed for human-machine teaming, our approach does not compromise on performance compared to previous black-box methods.

Designing Human-Centered AI to Prevent Medication Dispensing Errors: Focus Group Study With Pharmacists.

Medication errors, including dispensing errors, represent a substantial worldwide health risk with significant implications in terms of morbidity, mortality, and financial costs. Although pharmacists use methods like barcode scanning and double-checking for dispensing verification, these measures exhibit limitations. The application of artificial intelligence (AI) in pharmacy verification emerges as a potential solution, offering precision, rapid data analysis, and the ability to recognize medications through computer vision. For AI to be embraced, it must be designed with the end user in mind, fostering trust, clear communication, and seamless collaboration between AI and pharmacists. This study aimed to gather pharmacists' feedback in a focus group setting to help inform the initial design of the user interface and iterative designs of the AI prototype. A multidisciplinary research team engaged pharmacists in a 3-stage process to develop a human-centered AI system for medication dispensing verification. To design the AI model, we used a Bayesian neural network that predicts the dispensed pills' National Drug Code (NDC). Discussion scripts regarding how to design the system and feedback in focus groups were collected through audio recordings and professionally transcribed, followed by a content analysis guided by the Systems Engineering Initiative for Patient Safety and Human-Machine Teaming theoretical frameworks. A total of 8 pharmacists participated in 3 rounds of focus groups to identify current challenges in medication dispensing verification, brainstorm solutions, and provide feedback on our AI prototype. Participants considered several teaming scenarios, generally favoring a hybrid teaming model where the AI assists in the verification process and a pharmacist intervenes based on medication risk level and the AI's confidence level. Pharmacists highlighted the need for improving the interpretability of AI systems, such as adding stepwise checkmarks, probability scores, and details about drugs the AI model frequently confuses with the target drug. Pharmacists emphasized the need for simplicity and accessibility. They favored displaying only essential information to prevent overwhelming users with excessive data. Specific design features, such as juxtaposing pill images with their packaging for quick comparisons, were requested. Pharmacists preferred accept, reject, or unsure options. The final prototype interface included (1) checkmarks to compare pill characteristics between the AI-predicted NDC and the prescription's expected NDC, (2) a histogram showing predicted probabilities for the AI-identified NDC, (3) an image of an AI-provided "confused" pill, and (4) an NDC match status (ie, match, unmatched, or unsure). In partnership with pharmacists, we developed a human-centered AI prototype designed to enhance AI interpretability and foster trust. This initiative emphasized human-machine collaboration and positioned AI as an augmentative tool rather than a replacement. This study highlights the process of designing a human-centered AI for dispensing verification, emphasizing its interpretability, confidence visualization, and collaborative human-machine teaming styles.

A survey of technologies supporting design of a multimodal interactive robot for military communication

PurposeThis paper presents a survey of research into interactive robotic systems for the purpose of identifying the state of the art capabilities as well as the extant gaps in this emerging field. Communication is multimodal. Multimodality is a representation of many modes chosen from rhetorical aspects for its communication potentials. The author seeks to define the available automation capabilities in communication using multimodalities that will support a proposed Interactive Robot System (IRS) as an AI mounted robotic platform to advance the speed and quality of military operational and tactical decision making.Design/methodology/approachThis review will begin by presenting key developments in the robotic interaction field with the objective of identifying essential technological developments that set conditions for robotic platforms to function autonomously. After surveying the key aspects in Human Robot Interaction (HRI), Unmanned Autonomous System (UAS), visualization, Virtual Environment (VE) and prediction, the paper then proceeds to describe the gaps in the application areas that will require extension and integration to enable the prototyping of the IRS. A brief examination of other work in HRI-related fields concludes with a recapitulation of the IRS challenge that will set conditions for future success.FindingsUsing insights from a balanced cross section of sources from the government, academic, and commercial entities that contribute to HRI a multimodal IRS in military communication is introduced. Multimodal IRS (MIRS) in military communication has yet to be deployed.Research limitations/implicationsMultimodal robotic interface for the MIRS is an interdisciplinary endeavour. This is not realistic that one can comprehend all expert and related knowledge and skills to design and develop such multimodal interactive robotic interface. In this brief preliminary survey, the author has discussed extant AI, robotics, NLP, CV, VDM, and VE applications that is directly related to multimodal interaction. Each mode of this multimodal communication is an active research area. Multimodal human/military robot communication is the ultimate goal of this research.Practical implicationsA multimodal autonomous robot in military communication using speech, images, gestures, VST and VE has yet to be deployed. Autonomous multimodal communication is expected to open wider possibilities for all armed forces. Given the density of the land domain, the army is in a position to exploit the opportunities for human–machine teaming (HMT) exposure. Naval and air forces will adopt platform specific suites for specially selected operators to integrate with and leverage this emerging technology. The possession of a flexible communications means that readily adapts to virtual training will enhance planning and mission rehearsals tremendously.Social implicationsInteraction, perception, cognition and visualization based multimodal communication system is yet missing. Options to communicate, express and convey information in HMT setting with multiple options, suggestions and recommendations will certainly enhance military communication, strength, engagement, security, cognition, perception as well as the ability to act confidently for a successful mission.Originality/valueThe objective is to develop a multimodal autonomous interactive robot for military communications. This survey reports the state of the art, what exists and what is missing, what can be done and possibilities of extension that support the military in maintaining effective communication using multimodalities. There are some separate ongoing progresses, such as in machine-enabled speech, image recognition, tracking, visualizations for situational awareness, and virtual environments. At this time, there is no integrated approach for multimodal human robot interaction that proposes a flexible and agile communication. The report briefly introduces the research proposal about multimodal interactive robot in military communication.

Designing human-AI systems for complex settings: ideas from distributed, joint, and self-organising perspectives of sociotechnical systems and cognitive work analysis

Real-world events like the COVID-19 pandemic and wildfires in Australia, Europe, and America remind us that the demands of complex operational settings are met by multiple, distributed teams interwoven with a large array of artefacts and networked technologies, including automation. Yet, current models of human-automation interaction, including those intended for human-machine teaming or collaboration, tend to be dyadic in nature, assuming individual humans interacting with individual machines. Given the opportunities and challenges of emerging artificial intelligence (AI) technologies, and the growing interest of many organisations in utilising these technologies in complex operations, we suggest turning to contemporary perspectives of sociotechnical systems for a way forward. We show how ideas of distributed cognition, joint cognitive systems, and self-organisation lead to specific concepts for designing human-AI systems, and propose that design frameworks informed by contemporary views of complex work performance are needed. We discuss cognitive work analysis as an example.

Closed-Loop Uncertainty: The Evaluation and Calibration of Uncertainty for Human-Machine Teams under Data Drift.

Though an accurate measurement of entropy, or more generally uncertainty, is critical to the success of human-machine teams, the evaluation of the accuracy of such metrics as a probability of machine correctness is often aggregated and not assessed as an iterative control process. The entropy of the decisions made by human-machine teams may not be accurately measured under cold start or at times of data drift unless disagreements between the human and machine are immediately fed back to the classifier iteratively. In this study, we present a stochastic framework by which an uncertainty model may be evaluated iteratively as a probability of machine correctness. We target a novel problem, referred to as the threshold selection problem, which involves a user subjectively selecting the point at which a signal transitions to a low state. This problem is designed to be simple and replicable for human-machine experimentation while exhibiting properties of more complex applications. Finally, we explore the potential of incorporating feedback of machine correctness into a baseline naïve Bayes uncertainty model with a novel reinforcement learning approach. The approach refines a baseline uncertainty model by incorporating machine correctness at every iteration. Experiments are conducted over a large number of realizations to properly evaluate uncertainty at each iteration of the human-machine team. Results show that our novel approach, called closed-loop uncertainty, outperforms the baseline in every case, yielding about 45% improvement on average.

Artificial Intelligence (AI) Trust Framework and Maturity Model: Applying an Entropy Lens to Improve Security, Privacy, and Ethical AI.

Recent advancements in artificial intelligence (AI) technology have raised concerns about the ethical, moral, and legal safeguards. There is a pressing need to improve metrics for assessing security and privacy of AI systems and to manage AI technology in a more ethical manner. To address these challenges, an AI Trust Framework and Maturity Model is proposed to enhance trust in the design and management of AI systems. Trust in AI involves an agreed-upon understanding between humans and machines about system performance. The framework utilizes an "entropy lens" to root the study in information theory and enhance transparency and trust in "black box" AI systems, which lack ethical guardrails. High entropy in AI systems can decrease human trust, particularly in uncertain and competitive environments. The research draws inspiration from entropy studies to improve trust and performance in autonomous human-machine teams and systems, including interconnected elements in hierarchical systems. Applying this lens to improve trust in AI also highlights new opportunities to optimize performance in teams. Two use cases are described to validate the AI framework's ability to measure trust in the design and management of AI systems.

Understanding Human-AI Teaming Dynamics through Gaming Environments

With the goal of better understanding Human-machine Teaming (HMT) dynamics and how team competencies that are transportable across contexts can lead to different teaming behaviors and team performances, I propose a series of three studies to explore communication, coordination and adaptation in HMT paradigms. I implement and integrate multiple AI agents and use collaborative games as testing environments to evaluate teaming effects. My work can provide findings to two higher level research questions that are widely studied in HMT: 1) the bidirectional behaviors that human and AI agents may develop when working as a team and, 2) how different types of AI agents can impact the teaming efficiency in human-AI teaming. Besides, my work can also contribute to Human-Computer Interaction and Game AI scholarship with insights into teaming dynamics in Human-AI teaming.

Biases in Stakeholder Elicitation as a Precursor to the Systems Architecting Process

Many systems engineering projects begin with the involvement of stakeholders to aid in decision-making processes. As an application of systems engineering, systems architecture involves the documentation of stakeholder needs gathered via elicitation and the transformation of these needs into requirements for a system. Within human–machine teaming, systems architecture allows for the creation of a system with desired characteristics elicited from stakeholders involved with the project or system. Though stakeholders can be excellent sources for expert opinion, vested interests in a project may potentially bias stakeholders and impact decision-making processes. These biases may influence the design of the system architecture, potentially resulting in a system that is developed with unbalanced and misrepresented stakeholder preferences. This paper presents an activity analysis of the Stakeholder Needs and Requirements Process as described in the Systems Engineering Body of Knowledge (SEBoK) to identify potential biases associated with this elicitation process. As part of the research presented in this paper, a workshop was conducted where currently practicing systems architects provided feedback regarding perceptions of biases encountered during the elicitation process. The findings of this research will aid systems architects, developers, and users in understanding how biases may impact stakeholder elicitation within the architecting process.

A Quantum-like Model of Interdependence for Embodied Human-Machine Teams: Reviewing the Path to Autonomy Facing Complexity and Uncertainty.

In this review, our goal is to design and test quantum-like algorithms for Artificial Intelligence (AI) in open systems to structure a human-machine team to be able to reach its maximum performance. Unlike the laboratory, in open systems, teams face complexity, uncertainty and conflict. All task domains have complexity levels-some low, and others high. Complexity in this new domain is affected by the environment and the task, which are both affected by uncertainty and conflict. We contrast individual and interdependence approaches to teams. The traditional and individual approach focuses on building teams and systems by aggregating the best available information for individuals, their thoughts, behaviors and skills. Its concepts are characterized chiefly by one-to-one relations between mind and body, a summation of disembodied individual mental and physical attributes, and degrees of freedom corresponding to the number of members in a team; however, this approach is characterized by the many researchers who have invested in it for almost a century with few results that can be generalized to human-machine interactions; by the replication crisis of today (e.g., the invalid scale for self-esteem); and by its many disembodied concepts. In contrast, our approach is based on the quantum-like nature of interdependence. It allows us theorization about the bistability of mind and body, but it poses a measurement problem and a non-factorable nature. Bistability addresses team structure and performance; the measurement problem solves the replication crisis; and the non-factorable aspect of teams reduces the degrees of freedom and the information derivable from teammates to match findings by the National Academies of Science. We review the science of teams and human-machine team research in the laboratory versus in the open field; justifications for rejecting traditional social science while supporting our approach; a fuller understanding of the complexity of teams and tasks; the mathematics involved; a review of results from our quantum-like model in the open field (e.g., tradeoffs between team structure and performance); and the path forward to advance the science of interdependence and autonomy.

AI Trust Framework and Maturity Model: Improving Security, Ethics and Trust in AI

The following article develops an AI Trust Framework and Maturity Model (AI-TFMM) to improve trust in AI technologies used by Autonomous Human Machine Teams Systems (A-HMT-S). The framework establishes a methodology to improve quantification of trust in AI technologies. Key areas of exploration include security, privacy, explainability, transparency and other requirements for AI technologies to be ethical in their development and application. A maturity model framework approach to measuring trust is applied to improve gaps in quantifying trust and associated metrics of evaluation. Finding the right balance between performance, governance and ethics also raises several critical questions on AI technology and trust. Research examines methods needed to develop an AI-TFMM and validates it against a popular AI technology (Chat GPT). OpenAI's GPT, which stands for "Generative Pre-training Transformer," is a deep learning language model that can generate human-like text by predicting the next word in a sequence based on a given prompt. ChatGPT is a version of GPT that is tailored for conversation and dialogue, and it has been trained on a dataset of human conversations to generate responses that are coherent and relevant to the context. The article concludes with results and conclusions from testing the AI Trust Framework and Maturity Model (AI-TFMM) applied to AI technology. Based on these findings, this paper highlights gaps that could be filled with future research to improve the accuracy, efficacy, application, and methodology of the AI-TFMM.

Anthropogenic Object Localization: Evaluation of Broad-Area High-Resolution Imagery Scans Using Deep Learning in Overhead Imagery.

Too often, the testing and evaluation of object detection, as well as the classification techniques for high-resolution remote sensing imagery, are confined to clean, discretely partitioned datasets, i.e., the closed-world model. In recent years, the performance on a number of benchmark datasets has exceeded 99% when evaluated using cross-validation techniques. However, real-world remote sensing data are truly big data, which often exceed billions of pixels. Therefore, one of the greatest challenges regarding the evaluation of machine learning models taken out of the clean laboratory setting and into the real world is the difficulty of measuring performance. It is necessary to evaluate these models on a grander scale, namely, tens of thousands of square kilometers, where it is intractable to the ground truth and the ever-changing anthropogenic surface of Earth. The ultimate goal of computer vision model development for automated analysis and broad area search and discovery is to augment and assist humans, specifically human-machine teaming for real-world tasks. In this research, various models have been trained using object classes from benchmark datasets such as UC Merced, PatternNet, RESISC-45, and MDSv2. We detail techniques to scan broad swaths of the Earth with deep convolutional neural networks. We present algorithms for localizing object detection results, as well as a methodology for the evaluation of the results of broad-area scans. Our research explores the challenges of transitioning these models out of the training-validation laboratory setting and into the real-world application domain. We show a scalable approach to leverage state-of-the-art deep convolutional neural networks for the search, detection, and annotation of objects within large swaths of imagery, with the ultimate goal of providing a methodology for evaluating object detection machine learning models in real-world scenarios.

Actions, not Actor Identities, Affect Beliefs About Cooperation in Human-Machine Teaming

The efficacy of future human-machine teams will be determined by the ability of machine agents to work cooperatively with their human teammates. The ways teammates engage in cooperative teamwork behaviors might affect human beliefs about expressed cooperativity, and these changes in beliefs might depend on the identity of a teammate as a human or machine. In the current experiment we investigated how violations of cooperation expectations, presented to participants in a narrative vignette, influenced ratings on a measure of cooperation derived from social interdependence theory. As expected, participants rated vignette actors as less cooperative if the story included violated cooperation expectations, but consistent with previous research, the identities of the actors as humans or robots did not appear to influence ratings. Overall, this is a useful expansion on previous work describing the factors that influence perceptions of cooperation in human-machine teaming.

Applying the sidekick principles to the prototyping of human-machine teaming in collection planning

Collection planning for multi-domain operations is a complex task that is heavily manual, resource-intensive, and sub-optimally setup for collaboration. To solve these gaps and leverage advances in Artificial Intelligence and Machine Learning, which suggest that those are resolvable, our team employed the sidekick principles for human-machine teaming to design and prototype COGSWORTH, a system for Collection Optimization and Generation Synchronized with Optempo Reasoning Tailored to Humans. COGSWORTH is envisioned as a cognitive assistant to help collection planners. We report here on (1) our application of the sidekick principles to the prototyping of COGSWORTH, (2) how the sidekick principles are tangibly reflected in prototype artifacts, and (3) lessons learned and practical takeaways that may inform other researchers and practitioners in the human-machine teaming field.

Towards Joint Activity Design Heuristics: Essentials for Human-Machine Teaming

As machines increasingly behave more like active cognitive agents than passive tools, additional heuristics for supporting joint human-machine activity are urgently needed to complement existing usability heuristics. Despite the rich and extensive design guidance produced by forty years of cognitive systems engineering (CSE) and related fields, the lack of large-scale impact can be attributed, in part, to insufficient translation of CSE principles and guidelines to language and tools that are ready for designers and other decision-makers responsible for these automation-infused solutions. Towards this need, we synthesized a partial and preliminary list of ten machine requirements intended to capture some of the essentials of joint activity. We believe solidifying these essentials and their implications for machines is a first and necessary step towards deriving joint activity design heuristics that are valuable, practical, and sustainable for operational personnel. Through iterative refinement, we believe the combination of strong ideas and strong practicality in these tools can be the basis for a large-scale shift in the design and evaluation of human-machine teams.

Peripheral Eye Tracking for Measurement of Military Pilot Performance

Abstract Flying plays a crucial role in establishing both tactical and strategic superiority through direct engagement, facilitating logistics movement, and providing other essential supports. However, a concerning trend has been observed regarding pilot flight time, which has decreased from approximately 300 hours per year to 230 hours per year. This decline could potentially impact flight safety and training, particularly in situations requiring rapid decision-making. One of the critical factors affecting rapid decision-making is a pilot's ability to closely monitor the aircraft's systems and flight path. The objective of this paper is to review and synthesize a series of studies that investigated the impact of peripheral gaze behavior on flying performance. Pilots can process peripheral eye gaze information more quickly and effectively, and peripheral eye movements could be used to activate controls faster than typical motor reflexes. Mathematical models of visual attention related to peripheral eye tracking have proven to be valuable predictive tools for human-machine interfaces and can lay the groundwork for improved training of pilots. Understanding gaze behavior offers valuable insights into the human-machine interface in modern cockpits. Keywords: Peripheral eye tracking, Pilot decision making, Human-machine teaming.

Algorithmic loafing and mitigation strategies in Human-AI teams

Exercising social loafing – exerting minimal effort by an individual in a group setting – in human-machine teams could critically degrade performance, especially in high-stakes domains where human judgement is essential. Akin to social loafing in human interaction, algorithmic loafing may occur when humans mindlessly adhere to machine recommendations due to reluctance to engage analytically with AI recommendations and explanations. We consider how algorithmic loafing could emerge and how to mitigate it. Specifically, we posit that algorithmic loafing can be induced through repeated encounters with correct decisions from the AI and transparency may combat it. As a form of transparency, explanation is offered for reasons that include justification, control, and discovery. However, algorithmic loafing is further reinforced by the perceived competence that an explanation provides. In this work, we explored these ideas via human subject experiments (n = 239). We also study how improving decision transparency through validation by an external human approver affects performance. Using eight experimental conditions in a high-stakes criminal justice context, we find that decision accuracy is typically unaffected by multiple forms of transparency but there is a significant difference in performance when the machine errs. Participants who saw explanations alone are better at overriding incorrect decisions; however, those under induced algorithmic loafing exhibit poor performance with variation in decision time. We conclude with recommendations on curtailing algorithmic loafing and achieving social facilitation, where task visibility motivates individuals to perform better.

Modeling Team Interaction and Decision-Making in Agile Human–Machine Teams: Quantum and Dynamical Systems Perspective

In this study, we define team agility as a function of exploration and exploitation of team coordination. Based on these two coordination concepts, we examined interactive decision-making in a dynamic task environment by applying: first, the principles of quantum cognition for the decision-making processes at the confluence of teamwork and taskwork (to discern the effects of ontic uncertainty for each human team member in the case of having incomplete teamwork) and second, nonlinear dynamical systems modeling for the teamwork (to capture epistemic uncertainty). In this study, there were the following three conditions based on manipulation of the pilot role: first, synthetic condition—the pilot role was played by a synthetic agent, second, control condition—it was a randomly assigned participant, and third, experimenter condition—it was an expert who used a role-specific coordination script. Overall findings indicate that when teams in the experimenter condition come across the targets, they tend to explore alternatives by coordinating as a team rather than exploiting existing team strategies, which may not work best for the situation at hand. In contrast, teams in control and synthetic conditions tended more toward exploitation than exploration in coordination. We consider this a sign of agility in teamwork.

Team Situation Awareness-Based Augmented Reality Head-Up Display Design for Security Requirements

In the context of intelligent systems for human-vehicle collaboration, the fusion of information space, physical space, and user cognitive space has become a trend. This paper aims to address the challenges posed by information perception gaps and cognitive limitations experienced by drivers by leveraging Augmented Reality Head-up Displays (ie, AR-HUD) to compensate for perceptual deficiencies and enhance driver cognition. We introduce the innovative concept of the Human-Machine Team Situation Awareness (ie, TSA) loop model. Firstly, we analyze the cognitive characteristics of drivers and the spatiotemporal information elements within hazardous scenarios. Subsequently, AR-HUDs are employed to provide drivers with perceptual compensation and cognitive enhancement. Furthermore, we design AR-HUD interfaces for two representative scenarios. The results demonstrate that, with the support of AR-HUDs, the integration of dynamic interface elements proves to be more effective in compensating for perceptual deficiencies, and the inclusion of predictive information contributes to improved driving performance. Notably, in emergency situations, AR-HUDs play a crucial role in providing decision-enhancing information to drivers. The proposed theoretical framework offers opportunities for expanding the theoretical approaches and application domains of AR-HUDs.