Towards Emotion Co-regulation with LLM-powered Socially Assistive Robots: Integrating LLM Prompts and Robotic Behaviors to Support Parent-Neurodivergent Child Dyads

2025-07-14

AI Summary

This study addresses parent–child emotion coregulation difficulties in families of children with neurodevelopmental disorders (e.g., autism) by proposing a large language model (LLM)-driven social assistive robot (SAR) intervention framework. Built on the MiRo-E platform, the system integrates speech interaction, prompt-engineering-guided behavioral control, and semi-autonomous decision-making to enable deep LLM–robot co-processing and bidirectional, timely emotion regulation feedback. Its key contributions are twofold: (1) it pioneers the use of an LLM as the SAR’s central cognitive engine, dynamically generating stage-adapted linguistic and behavioral strategies via customized prompting; and (2) it establishes a “prompt–behavior” mapping design paradigm tailored for mental health applications. Preliminary empirical evaluation demonstrates significant improvements in parent–child interaction quality and emotional synchrony, offering a scalable technical pathway and actionable design insights for digital psychological interventions in home settings.

Technology Category

• Intelligent Robots: Human-Robot Interaction
• Cognitive Modeling & Cognitive Systems: Social Cognition And Interaction
• Natural Language Processing: Safety and Robustness

Application Category

• Search and Retrieval-Augmented AI: Assisted, interactive, and conversational search
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

Socially Assistive Robotics (SAR) has shown promise in supporting emotion regulation for neurodivergent children. Recently, there has been increasing interest in leveraging advanced technologies to assist parents in co-regulating emotions with their children. However, limited research has explored the integration of large language models (LLMs) with SAR to facilitate emotion co-regulation between parents and children with neurodevelopmental disorders. To address this gap, we developed an LLM-powered social robot by deploying a speech communication module on the MiRo-E robotic platform. This supervised autonomous system integrates LLM prompts and robotic behaviors to deliver tailored interventions for both parents and neurodivergent children. Pilot tests were conducted with two parent-child dyads, followed by a qualitative analysis. The findings reveal MiRo-E's positive impacts on interaction dynamics and its potential to facilitate emotion regulation, along with identified design and technical challenges. Based on these insights, we provide design implications to advance the future development of LLM-powered SAR for mental health applications.

Problem

• Integrate LLM and SAR for parent-child emotion co-regulation
• Support neurodivergent children with tailored robotic interventions
• Address design challenges in LLM-powered assistive robotics

Innovation

• LLM-powered social robot for emotion co-regulation
• Integration of LLM prompts and robotic behaviors
• Supervised autonomous system for tailored interventions