Coat of arms of the Republic of Colombia
ES
Image: Unsplash — Brooke Cagle

Research line

AI-enhanced engineering education

We research how artificial intelligence can improve teaching, learning and assessment in engineering.

How can artificial intelligence help educate better engineers? At PLaS we research how to integrate this technology into teaching, learning and assessment, with a particular focus on programming, software engineering, and analog and digital electronics.

We design and evaluate educational strategies and tools that draw on AI to improve engineering education, through solutions that support students, provide timely feedback and help instructors understand learning difficulties. We study how these experiences influence conceptual understanding, problem solving, motivation and the ability to self-regulate learning.

We promote a critical and responsible integration of AI that strengthens reasoning and the development of professional competencies, with attention to privacy, equity and academic integrity.

Topic map
Auto. assessmentFeedbackMotivationGamificationSelf-regulationLearning analyticsCollaborativeTEL / video gamesHDL / digitalLLM tutorsStudent codeCurriculum

Topics

Learning analytics and educational data mining5 works

We study the data generated during learning activities to understand how students learn and what difficulties they face. We combine data analysis and artificial intelligence to identify patterns, detect where support is needed, and provide useful information to improve teaching and help students steer their own learning.

Conversational agents, intelligent tutoring and adaptive learning3 works

We explore the design of AI assistants that students and instructors can talk to in everyday language to resolve questions, discuss concepts and explore solutions. We investigate how to adapt these agents to course content and how to evaluate the quality of their answers, their limitations and their educational value. We also research tools that support learning through guiding questions, hints and explanations tailored to each student's needs. Our goal is for this support to foster understanding, autonomy and the ability to review one's own reasoning.

Automated assessment and feedback on code12 works

We develop and study methods to analyze programming solutions and give feedback that helps students understand errors and improve their code. We are interested in assessing both the result and the problem-solving process, and in combining automated tests with explanations that guide learning and support instructors.

Self-regulated learning18 works

We study and promote self-regulated learning, motivation and study strategies in subjects such as computer programming, digital electronics, electronic control systems and analog electronics. We evaluate how different teaching strategies and classroom innovations affect self-regulation, including automatic and immediate feedback on practical assignments, collaborative learning environments, peer assessment, game dynamics and video game creation, and hybrid, remote and pocket labs.

Integrating transversal competencies1 work

We want to understand how to deliberately incorporate and strengthen transversal competencies, such as managing study time, critical thinking, decision making and teamwork, as an integral part of learning technical engineering subjects. As a starting point, we have explored the effect of project management methodologies such as Scrum on time management in project-based learning environments. Looking ahead, we aim to extend and scale these studies with AI tools that provide adaptive scaffolding, metacognitive monitoring and personalized feedback in the classroom.

Timeline

  1. 2026

  2. 2025

  3. 2024

  4. 2023

  5. 2022

  6. 2021

  7. 2020

  8. 2019

  9. 2018

  10. 2017

  11. 2016