Logo: University of Southern California

USC Joins $10 Million Effort to Build Social Robots

The work will be funded by the National Science Foundation's Expeditions in Computing.

April 05, 2012 —

On Tuesday, April 3, the National Science Foundation’s Directorate for Computer and Information Science and Engineering awarded a USC partnered research team $10 million as one of four new Expeditions in Computing awards.

Team logo for the NSF-funded "Making Socially Assistive Robots."

Over the next five years, the Yale-led team will work to develop a new breed of sophisticated “socially assistive” robots to help young children learn to read, overcome cognitive disabilities, and appreciate and perform physical exercise.

The purpose of the federally funded effort, part of one of the largest grants awarded by the National Science Foundation, is to create self-adapting machines capable of cultivating long-term interpersonal relationships and assisting preschool-age children with educational and therapeutic goals.

Robots used in the project will not replace human caregivers or teachers, but instead supplement them, working directly with children in need of individualized attention. Scientists will attempt to model the dynamic nature of social interaction and develop novel algorithms that endow the robots with a vast array of behavioral options.

USC Viterbi professor and Vice Dean for Research Dr. Maja Matarić will serve as Co-PI (principal investigator) on the project with Dr. Cynthia Breazeal from the Massachusetts Institute of Technology and Dr. Brian Scassellati from Yale University, who will serve as lead PI. USC Viterbi’s Dr. Fei Sha will provide expertise on machine learning and Dr. Gisele Ragusa, of USC Viterbi and USC Rossier School of Education, will work on bringing the results of the project directly to preschool classrooms.

"I am thrilled to have the importance and promise of this work recognized by the Expedition award," Matarić said.  "The term 'socially assistive robots' was defined in our Interaction Lab at USC in 2004 (by David Feil-Seifer, who is now a postdoctoral fellow at Yale with the PI on this project); less than a decade later, it has grown into a recognized and expanding research community attracting top-notch computer scientists, roboticists and human-machine interaction researchers."

In total, the team comprises 17 principal investigators from four universities - USC, Yale, MIT and Stanford – representing a diverse group of disciplines, including computer science, robotics, educational theory, and developmental psychology.