Integrating Reinforcement Learning and AI Agents for Adaptive Robotic Interaction and Assistance in Dementia Care

2025-01-28

AI Summary

Dementia care faces critical challenges including scarce clinical data, insufficient personalization, and poor interpretability of automated decision-making. Method: We propose an adaptive human-robot collaborative system that jointly integrates (i) probabilistic cognitive-affective state modeling of persons living with dementia (PLWDs) and (ii) large language model (LLM)-driven behavioral simulation, both grounded in clinical knowledge to construct a realistic, domain-informed simulation environment. Decision policies are trained via sample-efficient, interpretable reinforcement learning—specifically PPO and SAC—enabling generalizable, low-data robot behavior planning. The system supports cross-platform deployment on Pepper robots and virtual agents. Contribution/Results: Experiments demonstrate significant improvements in interaction response accuracy and personalization fidelity. Generated care strategies align with clinical consensus, effectively reducing caregiver burden while enhancing patient autonomy—validating the system’s clinical utility and operational robustness.

Technology Category

• Cognitive Modeling & Cognitive Systems: Simulating Human Behavior
• Intelligent Robots: Human-Robot Interaction
• Humans and AI: Human-Aware Planning and Behavior Prediction

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• User Modeling, Personalization and Recommendation: User modeling and simulation for interactive and conversational systems
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems

Abstract

This study explores a novel approach to advancing dementia care by integrating socially assistive robotics, reinforcement learning (RL), large language models (LLMs), and clinical domain expertise within a simulated environment. This integration addresses the critical challenge of limited experimental data in socially assistive robotics for dementia care, providing a dynamic simulation environment that realistically models interactions between persons living with dementia (PLWDs) and robotic caregivers. The proposed framework introduces a probabilistic model to represent the cognitive and emotional states of PLWDs, combined with an LLM-based behavior simulation to emulate their responses. We further develop and train an adaptive RL system enabling humanoid robots, such as Pepper, to deliver context-aware and personalized interactions and assistance based on PLWDs' cognitive and emotional states. The framework also generalizes to computer-based agents, highlighting its versatility. Results demonstrate that the RL system, enhanced by LLMs, effectively interprets and responds to the complex needs of PLWDs, providing tailored caregiving strategies. This research contributes to human-computer and human-robot interaction by offering a customizable AI-driven caregiving platform, advancing understanding of dementia-related challenges, and fostering collaborative innovation in assistive technologies. The proposed approach has the potential to enhance the independence and quality of life for PLWDs while alleviating caregiver burden, underscoring the transformative role of interaction-focused AI systems in dementia care.

Problem

• Dementia Care
• Limited Data
• Personalization

Innovation

• Robotics-Assisted Dementia Care
• Machine Learning in Healthcare
• Emotionally Adaptive Nursing Services