EAGER: TaskDCL: An Adaptive Extended Reality Embodied Cognition System to Assess Attention Deficit

University Of Texas At Arlington, Arlington TX

Investigators

Abstract

This EArly-concept Grant for Exploratory Research (EAGER) supports research that advances the understanding of attention deficit disorders and cognitive assessment through innovative extended reality technology. Attention deficit disorders affect millions of children and adults, impacting academic performance, social functioning, and overall quality of life. Traditional diagnostic methods often lack real-world applicability and engagement, leading to potential misdiagnosis or delayed intervention. This award funds the development of a novel extended reality system that leverages principles of embodied cognition to assess attention deficit and other cognitive functions in immersive, interactive environments. By creating standardized yet adaptable virtual scenarios, the system aims to provide more accurate and comprehensive cognitive profiles to support traditional assessments. The system's potential to improve access to cognitive evaluations could benefit underserved populations and remote areas lacking specialized expertise. Furthermore, the project's interdisciplinary approach, combining elements of cognitive science, computer engineering, and human-computer interaction, promotes collaboration across diverse fields and encourages broader participation in research. Ultimately, this work seeks to enhance early detection and targeted intervention for attention deficit disorders, potentially improving educational outcomes, workplace performance, and overall societal well-being. This grant supports research that utilizes extended reality technology, which includes virtual reality and mixed reality, to create immersive environments where users engage in cognitively demanding tasks designed to assess attention, executive function, and other cognitive abilities. Central to the system is a virtual avatar, which guides users through tasks and adapts its behavior based on real-time performance data. The research team will develop machine learning algorithms to analyze multimodal sensorimotor interactions, enabling dynamic task adaptation and personalized cognitive profiling. The project aims to validate the system through user studies comparing its performance to traditional assessment methods. By investigating the relationship between physical movements and cognitive processes in virtual environments, this research contributes to the emerging field of embodied cognition in extended reality contexts. The findings from this study have the potential to improve cognitive assessment methodologies and provide new insights into the intricate connections between mind, body, and machine interactions in cognitive tasks. This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.