Back to search

International Hellenic University

Teaching machine learning concepts through educational robotics

Abstract

dc:description

The rapid proliferation of Artificial Intelligence (AI) and Machine Learning (ML) makes their timely and meaningful integration into secondary education critical. Despite notable efforts, gaps persist in mature instructional design, appropriate materials, and targeted teacher professional development. This dissertation investigates how foundational ML concepts can be taught effectively through educational robotics, linking theory and practice in authentic classroom scenarios. Methodologically, the work adopts a Design-Based Research (DBR) approach across successive design–implementation–redesign cycles in the Greek school context. In an initial software-only phase, ML introductory activities were designed with a tooling focus. Subsequently, three open-design robotic platforms were developed; only two were integrated into classroom instructional scenarios. In parallel, digital twins for the BCN3D Moveo and SelfLearn platforms were built in ROS1/Gazebo and used for design, simulation, and preparation. The pedagogical design aligned with Experiential Learning Theory (ELT), Computational Thinking (CT), and the AI4K12 guidelines. Evaluation employed mixed methods (pre/post knowledge and attitude measures, qualitative observations, and reflective artifacts). Findings indicate that software-only activities support basic understanding of ML concepts and workflows, whereas integrating robotics (for the platforms implemented in class) is associated with increased student engagement, deeper conceptual understanding of the data–training–evaluation cycle, and richer metacognitive and ethical reflection on AI’s implications. Although not used in live instruction, the digital twins enhanced safety, preparation, and the reproducibility of the design. The main contributions of the dissertation are: (a) the development of a coherent instructional framework for ML-through-robotics for secondary education, (b) the production of documented andreproducible open-design builds and classroom materials, (c) the development of measurement tools for learning and attitudes, and (d) recommendations for teacher training and curriculum design.

Degree

thesis:*
Grantor dc:publisher
International Hellenic University
Year dc:date
2026

Author and committee

dc:creator, dc:contributor.*
Authors dc:creator
  • Karalekas, Georgios
  • Καραλέκας, Γεώργιος

Subjects

dc:subject × 16

Rights

Language dc:language
eng

Identifiers

dc:identifier.*
Identifier
10.12681/eadd/60911

Chain of custody

source
Harvested from
Greek National Archive of PhD Theses
Base URL
phdtheses.ekt.gr/eadd_oai/request
Last updated
2026-11-18
Source record
OAI-PMH GetRecord
citation

Karalekas, Georgios; Καραλέκας, Γεώργιος. Teaching machine learning concepts through educational robotics. International Hellenic University, 2026. http://hdl.handle.net/10442/hedi/60911