IMMERSIVEXR: AN AI-DRIVEN ADAPTIVE AR/VR FRAMEWORK FOR COMPUTER SCIENCE ENGINEERING LABORATORIES AND INDUSTRIAL SKILL DEVELOPMENT

image: https://doi.org/10.65725/JCISE/2/4/010
JOURNAL OF COMPUTATIONAL INTELLIGENCE SCIENCE AND ENGINEERING (JCISE) 
ISSN: 3107-8168
Volume 2 Issue 4, Oct – Dec 2026

Abstract: 
Computer Science Engineering (CSE) laboratories and industry-facing technical training share a common constraint: hands-on practice is bounded by hardware availability, cost, safety, and instructor bandwidth. Extended Reality (XR) technologies have been associated with improved engagement and, in several domains, improved learning outcomes, yet existing AR/VR laboratory solutions remain largely static — they deliver the same content at the same pace to every learner and stop at procedural task completion rather than diagnostic reasoning. This paper presents ImmersiveXR, a proposed AI-driven adaptive AR/VR framework built around three functional layers: an XR Simulation Layer for immersive laboratory and industrial-scenario practice; an AI Adaptation Engine that models learner competency in real time to recalibrate task difficulty, hints, and sequencing; and an Analytics and Feedback Loop that logs mastery evidence for learners and instructors. The framework further introduces scenario-based industrial troubleshooting (symptom → hypothesis → test → resolve) to extend practice beyond procedural lab exercises toward authentic diagnostic and decision-making skill-building, and proposes a comparative, mixed-methods assessment design contrasting XR-based instruction against conventional laboratory teaching across cognitive, psychomotor, and affective outcome measures. The study follows a design-science research approach across five phases — requirements analysis, architectural design, prototype development, pilot deployment, and comparative evaluation — targeting core CSE domains including computer assembly, microprocessor architecture, computer networks, and embedded systems. This paper sets out the problem statement, research questions, objectives, literature gap, proposed methodology, and expected contributions of this doctoral research, positioning ImmersiveXR as a unified response to four presently unaddressed needs: adaptive personalization, shared-hardware feasibility, authentic industrial diagnostics, and validated comparative assessment.

Authors: Sriram S

Keywords: Extended Reality (XR); Adaptive Learning; Intelligent Tutoring Systems; Computer Science Engineering Laboratories; Virtual Reality (VR); Augmented Reality (AR); Industrial Skill Development; Instructional Design; Artificial Intelligence in Education; Comparative Assessment.