Jing Li

Parental involvement is crucial for the development of children's emotion regulation (ER) skills, yet navigating these complex emotional interactions remains challenging for many families. While Large Language Models (LLMs) offer unprecedented conversational flexibility, integrating them into embodied social robots to provide context-aware, multimodal support remains an open challenge. In this paper, we present the design and preliminary evaluation of an LLM-powered robotic system aimed at facilitating ER within parent-child dyads. Utilizing a supervised autonomy approach, our system bridges the gap between language-based reasoning and embodied robotic behavior, allowing the MiRo-E robot to engage in natural dialogue while performing empathetic physical actions. We detail the system's technical architecture and interaction design, which guides dyads through evidence-based ER strategies. Preliminary user tests with six parent-child dyads suggest positive user engagement and initial trust, with participants reporting that the robot showed potential as a supportive mediator. These findings offer early design insights into developing autonomous, LLM-driven social robots for family-centered mental health interventions.

Individuals prone to respiratory diseases such as asthma, chronic cough, and pneumonia often encounter considerable challenges in adhering to home-based pulmonary rehabilitation programs, largely due to limited engagement, low motivation, and the absence of interactive feedback. To address these barriers, we present Puffpuff Pals, an interdisciplinary self-assessment and rehabilitation tool designed for home use. The system integrates gamified training experiences with real-time respiratory monitoring to deliver biofeedback, featuring both a parkour mode and a boss battle mode to enhance user engagement. The ergonomically rounded design of the breathing trainer improves grip comfort, thereby increasing safety and usability. A pilot study with six participants was conducted, employing HRV-derived RMSSD as a key indicator of physiological response in conjunction with subjective evaluations of user experience. Preliminary findings indicate that Puffpuff Pals may facilitate more effective breathing training and show potential to improve adherence in home-based rehabilitation.

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.

Parental involvement is crucial for children’s stress management, and co-regulation of stress can have a positive effect. To facilitate parental involvement in children’s stress management in learning, we proposed an embodied connected system, which provides stress detection, stress information feedback, and encouragement prompts, aiming to help parents better understand and engage in children’s stress-regulation process. This article focuses on the impact of interactive encouragement prompts provided to parents on children’s stress management. The within-group experiment was used to collect stress data and scales from 36 parent–child groups during a controlled learning experiment, and semi-structured interviews were conducted with parents and children. The results indicate that the encouragement prompts provided to the parents enhance the effectiveness of stress relief in children facilitated by parental involvement. In particular, the psychological stress was reduced, and the communication between parents and children became more effective. In addition, active parental involvement and timely encouragement prompts can improve children’s stress-coping abilities, providing an interactive intervention approach for learning stress management.