Abstract:
This paper describes a hands-off socially assistive therapist robot designed for monitoring, assisting, encouraging, and socially interacting with users engaged in rehabilitation exercises. We investigate the role of the robot's personality, empathy, and physiological signals in the hands-off therapy process, focusing mainly on the relationship between the level of extroversion-introversion of the robot and the user. We also demonstrate a behavior adaptation system capable of adjusting its social interaction parameters toward customized rehabilitation therapy based on the user's personality traits and task performance. The experiments validate our hypotheses of mapping the user's extroversionintroversion personality dimension to a spectrum of robot therapy styles that range from challenging to nurturing and of adapting the robot's therapy styles based on user personality and performance.