Adaptive AI-Supported Learning Environments in Engineering Education: Effects on Learning Outcomes, Engagement, and Digital Competence Development
TL;DR
Comparative analysis with traditional instructional methods demonstrates that the AI-driven control framework significantly improves knowledge acquisition, promotes active participation, and enhances students’ confidence in using digital technologies.
Abstract
In modern engineering education, the integration of artificial intelligence (AI) with intelligent control systems (ICS) is creating fundamentally new opportunities to transform the teaching and learning process. These technologies enable the personalization of educational pathways, support the continuous development of students’ digital competence, and contribute to improving overall educational effectiveness. Unlike traditional instructional models that apply uniform teaching strategies, AI-driven systems can dynamically respond to the individual needs, learning pace, and cognitive characteristics of each student, thereby fostering a more student-centered learning environment.This study proposes a novel AI-driven control architecture specifically designed for higher engineering education. The architecture is based on adaptive algorithms capable of analyzing learner behavior, performance data, and interaction patterns in real time. By processing these data streams, the system continuously adjusts instructional content, feedback mechanisms, and task complexity to optimize learning trajectories. Such an approach allows the educational process to function as a closed-loop intelligent control system, where monitoring, analysis, and pedagogical adjustment occur automatically and continuously.To validate the proposed framework, we designed and implemented a working prototype of the system and deployed it within a pilot group of engineering students. The effectiveness of the approach was evaluated using a combination of quantitative and qualitative metrics, including measurable learning gains, levels of student engagement, and self-reported development of digital competence. Comparative analysis with traditional instructional methods demonstrates that the AI-driven control framework significantly improves knowledge acquisition, promotes active participation, and enhances students’ confidence in using digital technologies.