Developing an AI-Driven Virtual Lab Platform for Technical Skill Acquisition

Thesis Abstract

The rapid advancement of information and communication technologies has transformed the landscape of technical education, yet existing laboratory-based training often faces limitations related to resource constraints, accessibility, and safety concerns. This study addresses these challenges by developing an artificial intelligence (AI)-driven virtual laboratory platform designed to enhance technical skill acquisition among tertiary-level students in engineering and applied sciences. The primary aim is to create an interactive, adaptive, and scalable virtual lab environment that simulates real-world laboratory experiences, thereby improving learning outcomes and technical competence. The specific objectives of the study include (1) designing and developing an AI-enhanced virtual laboratory platform equipped with real-time feedback mechanisms; (2) evaluating the effectiveness of the platform in improving students’ technical skills compared to traditional laboratory approaches; (3) investigating students’ perceptions and engagement levels with the virtual lab; and (4) establishing a theoretical framework for the integration of AI technologies in technical education. The study adopts a mixed-methods research design, combining quantitative and qualitative approaches to provide a comprehensive assessment of the platform’s usability and pedagogical impact. The population for this research comprises undergraduate students enrolled in engineering programs at technical universities within the region, with a target sample size of 200 participants for quantitative analysis and 20 participants for in-depth interviews. Stratified random sampling ensures representative distribution across different engineering disciplines and academic years. Data collection instruments include a standardized technical skills assessment test, a Likert-scale usability and engagement questionnaire, and semi-structured interview guides. The technical skills test is validated through content expert review and pilot testing, achieving a reliability coefficient of 0.88 via Cronbach’s alpha. Data analysis involves descriptive statistics, paired t-tests to compare pre- and post-intervention performance, and thematic analysis for qualitative data, with NVivo software employed for coding and pattern identification. Expected findings include statistically significant improvements in students’ technical skills following interaction with the AI-driven virtual lab, higher engagement and satisfaction levels compared to conventional labs, and positive perceptions towards the platform’s usability and educational value. Additionally, the study anticipates that AI features such as adaptive assistance, intelligent feedback, and personalized learning pathways will contribute to improved learning efficiency. Theoretically, the study is grounded in Vygotsky’s Zone of Proximal Development and the cognitive load theory, providing a framework to interpret how AI technologies can scaffold student learning and reduce cognitive overload in complex technical tasks. This research contributes to knowledge by offering a robust model for integrating artificial intelligence into virtual laboratories, demonstrating its potential to democratize access to high-quality technical training and foster autonomous learning. It advances existing literature by empirically assessing the pedagogical effectiveness of AI-driven virtual labs in the context of technical education, which remains underexplored despite the proliferation of digital learning tools. The study concludes that the AI-driven virtual lab platform significantly enhances technical skill development and learner engagement. Recommendations include adopting the platform for wider implementation across engineering curricula, integrating AI features with existing learning management systems, and continuously refining the system based on user feedback. Future research should explore longitudinal effects of virtual lab usage, scalability in different educational contexts, and the integration of emerging technologies such as augmented reality to further innovate technical training methodologies.