Invited talk (1445h):
Why we're not ready to engineer good social systems

Brian Scassellati

Abstract

Despite remarkable success in the last decade in bringing autonomous systems into our homes, schools, and offices, I'll argue that we're not quite close to being ready to have a clear engineering specification for how to build successful human-robot social interactions. I'll argue that we don't yet understand how to quantify and characterize social interactions between humans, much less between humans and robots. Finally, I'll suggest that rather than looking for clear engineering guidelines, we should be viewing these systems as a methodology for uncovering the details of how humans and robots can successfully interact.

About the speaker

Brian Scassellati is an Associate Professor of Computer Science at Yale University. His research focuses on the construction of humanoid robots that interact with people using natural social cues.

These robots are used both to evaluate models of how infants acquire social skills and to assist in the diagnosis and quantification of disorders of social development (such as autism). His other research interests include active vision systems, visual-motor coordination, developmental models, social learning (imitation and mimicry), and applications of robotics as a tool for cognitive science.