Virtual Agent Tutors in Sheltered Workshops: A Feasibility Study on Attention Training for Individuals with Intellectual Disabilities

TL;DR

This study addresses the feasibility of deploying a socially assistive virtual agent–based attention training for individuals with intellectual disabilities in sheltered workshops. It adapts the RoboCamp system, originally developed for children with ADHD, and evaluates feasibility across usability, technical reliability, attention-training capability, and novelty effects using gaze-based attention detection in 13 participants over five sessions. The findings indicate the approach is feasible in a real-world sheltered-workshop setting but highlight technical limitations (notably face/detection reliability) and the need for longer-term evaluation to assess training efficacy. The work provides a practical deployment blueprint and identifies concrete directions for future larger-scale, longer-duration studies and system refinements.

Abstract

In this work, we evaluate the feasibility of socially assistive virtual agent-based cognitive training for people with intellectual disabilities (ID) in a sheltered workshop. The Robo- Camp system, originally developed for children with Attention Deficit Hyperactivity Disorder (ADHD), is adapted based on the results of a pilot study in which we identified barriers and collected feedback from workshop staff. In a subsequent study, we investigate the aspects of usability, technical reliability, attention training capabilities and novelty effect in the feasibility of integrating the RoboCamp system.

Figures (7)

• Figure 1: Employee interacting with the RoboCamp
• Figure 2: The five visit phases in the sheltered workshop in 2024 and 2025.
• Figure 3: Verbal statements by the participants during and after the sessions.
• Figure 4: Mean x gaze angle over sessions for each participant
• Figure 5: Number of Submissions per participant outside of gaze angle x threshold