Adaptive AI-Driven Animal-like Social Robots for Personalized Emotional Health: A Multicriteria Decision-Making Approach Using Self-Monitoring Data

Vollständiger Abstract

Worum geht es in dieser Arbeit?

Background: Population aging has increased the prevalence of cognitive impairment and dementia, highlighting the need for personalized non-pharmacological interventions. Although socially assistive robots have shown therapeutic benefits, most rely on predefined interactions with limited adaptability. This study proposes an AI-enabled framework integrating continuous self-monitoring and explainable multicriteria decision-making to personalize robot-assisted interventions. Methods: A 12-week longitudinal quasi-experimental study was conducted involving 78 older adults with mild-to-moderate cognitive impairment allocated to three groups: an adaptive AI-based robot (n = 26), a sensor-based robot (n = 26), and a control group receiving conventional care (n = 26). The proposed framework combined continous self-monitoring, AI-based emotional-state estimation, and an Analytic Hierarchy Process (AHP) model to adapt robot behaviour according to participants’ clinical and behavioural profiles. Results: The AI-based robot achieved the greatest improvements in emotional status, social interaction, and functional performance. Depressive symptoms decreased by 42.9%, anxiety decreased by 39.1%, social interaction increased by 60.7%, and functional independence improved by 20.1%. Although the sensor-based robot showed slightly higher adherence (97.2% vs. 95.6%), the AI-based intervention achieved the highest overall effectiveness (AHP global score = 0.90). Conclusions: Integrating continuous self-monitoring, AI-based emotional-state estimation, and explainable multicriteria decision-making enables personalized robot-assisted interventions that improve emotional well-being, social engagement, and functional independence. These findings support the potential of adaptive socially assistive robots as AI-driven clinical decision-support systems for dementia care.