Capturing Social Intelligence: Simulating Humans for Robots, Games, and Medicine
ABSTRACT: Artificial Intelligence (AI) has brought a high level of skill to computers in many challenging abstract problems. However, robots and other intelligent systems are increasingly expected to interact autonomously with humans in everyday settings, making it vital they also increase their social intelligence. Here we discuss techniques for moving AI past the realm of abstract problems and towards a more social form of intelligence. In this talk, we will look at our recent efforts to develop an understanding of key features of human interactions, including navigation in crowds and emotional expression. We will also discuss data-driven methods to allow AI systems to adapt in response to individual differences of the people with whom they interact.
BIO: Stephen J. Guy is an assistant professor in the Department of Computer Science and Engineering at the University of Minnesota. His research focuses on the areas of interactive computer graphics and multi-robot coordination. Stephen's work on motion planning has been licensed for use in games and virtual environments by Relic Entertainment, EA, and other companies; his work in crowd simulation has been recognized by best paper awards at international conferences. Prior to joining Minnesota, he received his Ph.D. in Computer Science in 2012 from the University of North Carolina - Chapel Hill with support from fellowships from Google, Intel, and the UNCF.