This is an archived version of CCC's website. Please visit the new ccc website for the latest information.

Relevant Links

Link to Original Paper
Media Contact


Stroke Detection, Robotics, Human-robot interaction


feed icon

feed icon

feed icon


Personalized Assistive Human-Robot Interaction for Socially-Assistive Post-Stroke Rehabilitation

An interdisciplinary project has developed an approach that uses a friendly robot and wearable sensors to monitor, coach, and assist people suffering from stroke. Principal Investigators Maja Mataric and Carolee Winstein of the University of Southern California have brought together expertise in the areas of assistive human-robot interaction, stroke diagnosis, and rehabilitation in an interdisciplinary project that is developing a novel technology based on a socially assistive robot SAR as the personalized rehabilitation coach. They have developed a humanoid robot capable of engaging the user and low-cost, lightweight non-invasive wearable sensors worn by the user that enable the robot to understand what the user is doing and offer appropriate coaching and encouragement.

The willingness of the user to train and follow instructions of the robot depends on the user's and the robot's personality. The PIs performed a study to determine an optimal matching of the user and robot personalities, and developed a learning algorithm that enables the robot to adjust its personality and coaching style to match the user's personality and effectively improve the user's performance on rehabilitation exercises. The developed technology is being validated on stroke pa tients interacting with the personalized physical therapist robot over multiple weeks of rehabilitation. The robot performs assessments of the user's movement abilities, and uses an appropriate personality style to motivate and coach the user in order to sustain the user's engagement in the rehabilitation process, and thereby improve the user's performance and strive to improve health outcomes.

Maja Mataric, USC
Carolee Winstein, USC

Agencies (that have supported the research):
University of Southern California


Current Highlight | Past Highlights

Computing Research Highlight of the Week is a service of the Computing Community Consortium and the Computing Research Association designed to highlight some of the exciting and important recent research results in the computing fields. Each week a new highlight is chosen by CRA and CCC staff and volunteers from submissions from the computing community. Want your research featured? Submit it!.