Creating an Artificial Intelligence Tutor for Brain-Computer Interface Use – UROP Symposium

Creating an Artificial Intelligence Tutor for Brain-Computer Interface Use

Calvin Naimou

Research Mentor: Jane Huggins
Mentor Department: Physical Medicine and Rehabilitation, Medicine
Author(s): Calvin Naimou, Jane E. Huggins
Session: Session 4 (1:00 PM – 1:50 PM)
Presentation Type: Poster 122

Abstract

This project develops an AI-based tutor to assist users and caregivers in operating brain–computer interface (BCI) systems. Although BCIs function well in laboratories, independent home use remains challenging due to complicated procedures and difficult-to-understand documentation. To bridge this gap, we created a support tutor using Retrieval-Augmented Generation (RAG) on the University of Michigan’s Maizey platform, enabling the system to generate answers based on verified BCI documentation. The tutor provides structured, step-by-step guidance for device procedures and troubleshooting, while ensuring safety and adherence to device-specific constraints. This work serves as a proof of concept to demonstrate how an AI tutor can enhance accessibility and ease of use for real-world BCI operation.

lsa logoum logo