Date: 5/5/2022
Speaker: Daehyung Park
Location: 122 Gates Hall and Zoom
Time: 2:40 p.m.-3:30 p.m.
Abstract: There are now successful stand-alone or coexistence robotic systems in human environment. Yet robots are not intelligent enough to directly collaborate with humans, particularly potential non-expert users. In this talk, I will discuss how to develop highly-capable robotic teammates by bridging the knowledge gap between humans and robots. I will particularly show our cognitive architecture with learned knowledge models can produce three core capabilities: natural language grounding, transferable skill learning, and robust task planning-and-execution. I will show how to provide highly scalable and reliable assistance when situated in novel environments.
Bio:
Daehyung Park is an assistant professor at the School of Computing, KAIST, Korea, leading the Robust Intelligence and Robotics Laboratory (RIRO Lab). His research lies at the intersection of mobile manipulation, artificial intelligence, and human-robot interaction to advance collaborative robot technologies.
Prior to joining KAIST, he had been a postdoctoral associate in Computer Science and Artificial Intelligence Laboratory (CSAIL) at MIT. He received a Ph.D. in Robotics at Georgia Institute of Technology, an M.S. from the University of Southern California, and a B.S. from Osaka University. Prior to joining his Ph.D., he served as a Robotics Researcher at Samsung Electronics Inc from 2008-2012. He is a recipient of Google Research Scholar Award, 2022.