# Transforming dementia caregiver support with AI-powered social robotics

**Authors:** Tyler Morris, Conor Brown, Xiaopeng Zhao, Linda Nichols, Jennifer Martindale-Adams, Sharon Bowland, Wenjun Zhou

PMC · DOI: 10.3389/frobt.2025.1704313 · Frontiers in Robotics and AI · 2026-01-27

## TL;DR

This paper introduces RISE, an AI-powered social robot system designed to support dementia caregivers by providing personalized training and stress management, showing promising results in usability and content accuracy.

## Contribution

The novel RISE system combines retrieval-augmented generative AI with social robotics to deliver scalable, evidence-based caregiver support.

## Key findings

- RISE's RAG-AI backend achieved 87% correctness and 92% relevancy in content delivery.
- User feedback showed high usability scores (3.6 to 4.6 out of 5) for all RISE components.
- The system is presented as a feasible and scalable solution for dementia caregiver support.

## Abstract

Informal dementia caregivers face significant emotional and physical burdens, yet evidence-based interventions like REACH are often limited by high labor costs and scalability constraints.

We design a Robot-based Information and Support to Enhance Alzheimer’s Caregiver Health (RISE) system, which uses novel social robotics and generative AI to deliver automated and personalized caregiver training and stress management. RISE uses retrieval-augmented generative AI (RAG-AI) grounded in the verified REACH Caregiver Notebook to ensure content safety and minimize hallucinations. It employs the social robot Pepper to deliver interactive presentations, Q&A sessions, review quizzes, and stress reduction activities. A technical evaluation and a two-phase user evaluation was conducted.

We found that the RISE’s RAG-AI backend achieved 87% correctness and 92% relevancy when compared to ground truth. User feedback indicated strong acceptance, with Likert-scale usability scores ranging from 3.6 to 4.6 out of 5 across all components.

These results suggest that combining verifiable AI architectures with embodied social robotics offers a feasible, scalable solution for enhancing caregiver support and wellbeing. Future work could include a larger scale user study involving real informal dementia caregivers.

## Linked entities

- **Diseases:** dementia (MONDO:0001627)

## Full-text entities

- **Diseases:** Alzheimer (MESH:D000544), hallucinations (MESH:D006212), dementia (MESH:D003704)

## Full text

_Full body text omitted from this summary view._ Fetch the complete paper as Markdown: https://tomesphere.com/paper/PMC12886016/full.md

## Figures

6 figures with captions in the complete paper: https://tomesphere.com/paper/PMC12886016/full.md

## References

37 references — full list in the complete paper: https://tomesphere.com/paper/PMC12886016/full.md

---
Source: https://tomesphere.com/paper/PMC12886016