Socially assistive robotics for guiding motor task practice

Due to their quantitative nature, robotic systems are useful tools for systematically augmenting human behavior and performance in dynamic environments, such as therapeutic rehabilitation settings. The e cacy of human-robot interaction (HRI) in these settings will depend on the robot’s coaching style. Our goal was to investigate the influence of robot coaching styles designed to enhance motivation and encouragement on post-stroke individuals during motor task practice. We hypothesized that coaching styles incorporating user performance and preference would be preferred in a therapeutic HRI setting. We designed an evaluation study with seven individuals post stroke. A socially assistive robotics (SAR) system using three di erent coaching styles guided participants during performance of an upper extremity practice task. User preference was not significantly a ected by the di erent robot coaching styles in our participant sample (H(2) = 2.638, p = 0.267). However, trends indicated di erences in preference for the coaching styles. Our results provide insights into the design and use of SAR systems in therapeutic interactions aiming to influence user behavior.