AI robots as learning companions in PBL - Effects on cognitive and self-regulatory outcomes

Oct 15, 2026

Upload by jayni

Robot-assisted problem-based learning (PBL) in higher education is evaluated through a quasi-experimental study lasting 16 weeks (48 hours) with two parallel branches. An educational Q&A-focused robot is integrated into project-based learning for the experimental group, while the control group receives the same content without robots. Outcomes cover self-directed learning (including self-management), problem-solving, and comprehension/discovery, using Bayesian comparisons and reporting posterior effect sizes with 95% confidence intervals. Robot-assisted PBL yields medium-strong evidence of benefits, especially improved self-management, and higher problem-solving and comprehension/discovery scores, provided feedback design and implementation fidelity are maintained.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages18

Reading Time45 min

AccessFree to download

Introduction

Study aim and research questions

Expected outcomes and Bayesian evidence

Contemporary Educational Technology, 2025, 17(4), ep603 ISSN: 1309-517X (Online) OPEN ACCESS Research Article AI robots as learning companions in PBL: Effects on cognitive and self-regulatory outcomes Jaitip Nasongkhla 1* 0000-0001-5306-7688 Chich-Jen Shieh 1 0000-0001-5889-4682 1 Excellent Center of Disruptive Innovative Technology for Education, Chulalongkorn University, Bangkok, THAILAND * Corresponding author: [jaitip. n@chula.ac.th](jaitip. n@chula.ac.th) Citation: Nasongkhla, J., & Shieh, C.-J. (2025) . AI robots as learning companions in PBL: Effects on cognitive and selfregulatory outcomes. Contemporary Educational Technology, 17(4), ep603. [https://doi.org/10.30935/cedtech/17417](https://doi.org/10.30935/cedtech/17417) ARTICLE INFO ABSTRACT | Received: 24 Jul 2025
Accepted: 13 Oct 2025
INTRODUCTION | This study examines the effect of robot-assisted problem-based learning (PBL) on learning outcomes in higher education. A quasi-experimental design was adopted, and the application was carried out over 16 weeks (48 hours) with two parallel branches. In the experimental group, a question-and-answer-focused educational robot was integrated into the project-based learning process, while in the control group, the same content was applied without robots. Measurements encompassed self-directed learning (including self-management), problemsolving, and comprehension/discovery dimensions. Bayesian comparisons showed that the level of evidence in favor of the experiment was in the medium-strong range for most variables; a significant increase was observed particularly in self-management. Problem-solving and comprehension/discovery scores were also higher in the experimental condition. Figures and tables report posterior effect sizes and 95% confidence intervals. The results indicate that robotassisted PBL, which offers timely and elucidative feedback, improves the metacognitive processes associated with PBL and aids students in adhering to their study goals more consistently. In conclusion, robot-assisted PBL can significantly improve self-management, problem-solving, and comprehension outcomes, provided that appropriate feedback design and application fidelity are maintained. Future research should examine its effects across various fields by integrating long-term follow-up periods and behavioral performance assessments. The study enhances the reproducibility of results by evaluating the strength of evidence through open Bayesian reporting. This method makes design choices more transparent and establishes clear guidelines on how educational technologies should be used responsibly.
Keywords: problem-based learning, AI robots, blended learning, learning outcomes, selfdirected learning | | --- | --- | Problem-based learning (PBL) is a student-centered methodology wherein learners assume responsibility for a tangible problem, seek information, formulate solutions, and engage in reflection (Albanese & Mitchell, 1993) . Recent syntheses indicate that PBL can enhance cognitive outcomes and motivation, especially in higher education. The magnitude of the effect can differ based on the context of application and design specifics. So, it’s important to be clear about when PBL works best (Su et al., 2025) . AI-powered feedback systems and teaching robots can enhance student learning by providing personalized and timely feedback. Multi-level meta-analyses indicate that educational robots can improve success and conceptual understanding in science, technology, engineering, and mathematics (STEM) disciplines; however, their effectiveness depends on factors such as role, quality of interaction, and duration of intervention. Automated feedback can also slightly improve writing performance. These results suggest that robot/AI-powered feedback can be a valuable resource in project-based learning (PjBL) contexts (Fleckenstein et al., 2023; Ouyang & Xu, 2024; Trapero-González et al., 2024) . This study is po

FAQs

What learning approach does the study focus on, and where are robots used?

The study focuses on robot-assisted problem-based learning (PBL) in higher education, integrating an educational Q&A-focused robot into the project-based learning process for the experimental group.

How was the study conducted and for how long?

A quasi-experimental design was used with two parallel branches. The intervention was implemented over 16 weeks (48 hours).

Which learning outcomes improved with robot-assisted PBL?

Bayesian comparisons show improved self-management, along with higher problem-solving and comprehension/discovery scores in the robot-assisted condition. Benefits depend on appropriate feedback design and implementation fidelity.

Oct 15, 2026

Upload by jayni