Collaborative research: generative artificial intelligence integrated with role-responsive virtual reality for construction education

The National Science Foundation Division of Undergraduate Education awarded Kennesaw State University Research And Service Foundation, Inc. $250,000 on October 1, 2026, under the STEM Education program (CFDA 47.076) to develop and pilot-test a generative AI-integrated, role-responsive virtual reality learning environment for construction management students.

The project addresses workforce readiness in construction by creating realistic, immersive learning experiences that simulate the uncertainty, safety risks, time pressures, and interdependent responsibilities of active jobsites. The learning environment embeds expert personas powered by generative AI to support the development of professional judgment, situational awareness, situational awareness, and collaborative decision-making among undergraduate students. The research investigates how AI-supported immersive environments can represent and transfer tacit professional expertise—including the professional judgment, adaptive decision-making, and role awareness that practitioners develop through years of experience—while expanding access to experiential learning when direct jobsite access is limited. Findings are expected to advance understanding of how such AI-integrated systems can support workforce readiness across applied STEM disciplines beyond construction.

Performance occurs at Kennesaw, Georgia, with a period of performance from October 1, 2026, through September 30, 2029.

Abstract

The U.S. Construction industry faces a persistent shortage of skilled workers as experienced professionals retire, and new workers enter increasingly complex, technology-intensive workplaces. This transition threatens the loss of critical tacit professional expertise, including the professional judgment, situational awareness, role awareness, and adaptive decision-making abilities that practitioners develop through years of experience. Traditional classroom instruction and conventional simulations provide limited opportunities for students to practice under the uncertainty, safety risks, time pressures, and interdependent responsibilities that characterize real-world construction projects. This project investigates how generative artificial intelligence (AI), integrated with interactive, adaptive, and role-responsive virtual reality (VR), can support the development of professional judgment, situational awareness, and collaborative decision-making among undergraduate construction management students. By creating realistic learning experiences that can be deployed when access to active jobsites, equipment, or hands-on training opportunities is limited, the project has the potential to expand access to experiential learning for a broader range of students. The findings will advance understanding of how AI-supported immersive environments can represent and transfer tacit professional expertise while supporting workforce readiness in construction and other applied science, technology, engineering, and mathematics (stem) disciplines. The primary goal of this study is to develop and pilot-test a generative AI-integrated, role-responsive VR learning environment and investigate how AI-embedded expert personas influence learners? Behavioral adaptation, situational awareness, professional judgment, and other cognitive and affective outcomes compared with static VR. First, researchers will collaborate with construction subject-matter experts to develop authentic, high-stakes scenarios and characterize decision pathways, tacit heuristics, and interdependent responsibilities associated with four professional roles: safety manager, site engineer, equipment operator, and subcontractor. Second, the project will encode this professional expertise into a functional immersive learning environment that combines generative AI, structured role representations, adaptive scenario branching, and role-responsive interactions. Third, researchers will conduct a controlled experimental study with undergraduate construction management students and compare the generative AI-integrated environment with a static VR condition. The study will collect multimodal evidence through performance assessments, VR telemetry, biometric indicators, validated cognitive and affective measures, and usability assessments. Mixed-effects models and analysis of covariance will be used to examine differences in behavioral adaptation, situational awareness, decision quality, engagement, knowledge transfer, and role-responsive learning processes. This project will generate foundational knowledge about how AI-embedded expert guidance and adaptive immersive environments influence learning in applied stem domains. Project outcomes include an empirical comparison of generative AI-augmented and static VR learning environments, a validated taxonomy of professional roles and decision pathways, a pilot-tested genaivr prototype with documented technical performance and usability, and a replicable framework for capturing, representing, and transferring tacit professional expertise through AI-supported immersive learning systems. The study will contribute to the learning sciences by advancing understanding of how behavioral adaptation, situational awareness, and professional judgment develop through interaction with adaptive, role-responsive AI learning environments. This project is supported by NSF?s EDU core research (ECR) program and NSF's iuse: EDU program. The iuse: EDU program supports research and development projects to improve the effectiveness of stem education for all students. The ECR program emphasizes fundamental stem education research that generates foundational knowledge in the field. Investments are made in critical areas that are essential, broad and enduring. 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.- subawards are not planned for this award.