Brain, Digital, & Learning

 Open access, Peer Reviewed

Indexed in KCI

pISSN 2384-2474
eISSN 2586-7490

RESEARCH ARTICLE

A Qualitative Case Study on the Implementation of an AI-Powered Gait Rehabilitation Robot Program for Students with Severe and Multiple Disabilities

1Daegu Dongmoon High School
2Department of Earth Science Education and Science Education Research Institute, Kyungpook National University

Correspondence to Hyonyong Lee, hlee@knu.ac.kr

Brain, Digital, & Learning. Volume 16, Number 3, 281–303, September 2026. https://doi.org/10.31216/BDL.2026.16.3.5
Received on July 14, 2026, Revised on September 20, 2026, Accepted on September 21, 2026, Published on September 30, 2026.
Copyright © 2026 Institute of Brain·AI based Education, Korea National University of Education This is an Open Access article distributed under the terms of the Creative Commons Attribution Non-Commercial License (https://creativecommons.org/licenses/by-nc/4.0/) which permits unrestricted non-commercial use, distribution, and reproduction in any medium, provided the original work is properly cited.

Abstract

This qualitative case study explored how an AI-powered gait rehabilitation robot program was implemented over one semester in a special school and how its participants experienced and made sense of it. The bounded case was the program itself; its participants comprised three students with severe and multiple disabilities, the teacher-researcher (a special education teacher), a collaborating physical therapist, and three guardians. Data were collected from multiple sources, including health-management records and assessment sheets, class documents and Individualized Education Program (IEP) team minutes, robot-recorded gait data, semi-structured surveys and interviews, participant-observation logs, and the researcher’s reflexive journal. The data were analyzed through iterative coding, pattern identification, and cross-source comparison, with attention to discrepant data, and trustworthiness was strengthened through triangulation, member checking, and peer debriefing. Three themes were identified. First, the program was implemented within a co-teaching model that connected the special education teacher and the physical therapist across the boundary of education and therapy, and it was organized as a related service through IEP team consultation under the 2022 revised special education curriculum. Second, the participants moved from initial expectation and concern toward a more nuanced appreciation of the program, while also raising practical concerns about safety, sensor limitations, and the burden of responsibility. Third, the students showed uneven but meaningful changes. Although gains on the ordinal functional indicators (MMT, BBS, FAC) were partial or limited to maintenance, clearer changes appeared in confidence, self-efficacy, and social participation. Rather than verifying effectiveness, this case illustrates the possibilities and conditions of school-based AI gait-robot education and points to the need for a sustainable policy and institutional support framework, including the placement of rehabilitation professionals within schools.
Keywords

Students with severe and multiple disabilities, AI gait rehabilitation robot, gait education, qualitative case study, co-teaching

Section