공과대학

- 제목: 로봇 비전 학습 (Visual Representation in Robot Learning)

- 일시: 7월 5일 (수) 10시

- 장소: 신공학관 4142호 (강당)

Title: Visual Representations in Robot Learning

Abstract:
We discuss the role of visual representations in robot learning. While particularly focusing on visuo-motor action policy learning, we describe how computer vision models (such as CNNs, Vision Transformers, vision-language models, and diffusion models) make robot learning more robust, adaptive, and accurate by supporting better representations. Multiple cases including Visionary (with neural architecture search), Robotics Transformer (RT-1), Token Turing Machines, as well as more recent efforts with diffusion models will be presented.

Bio:
Michael S. Ryoo is a SUNY Empire Innovation Associate Professor in the Department of Computer Science at Stony Brook University, and is also a staff research scientist at Robotics at Google. His research focuses on video representations, self-supervision, neural architectures, egocentric perception, as well as robot action policy learning. He previously was an assistant professor at Indiana University Bloomington, and was a staff researcher within the Robotics Section of NASA's Jet Propulsion Laboratory (JPL). He received his Ph.D. from the University of Texas at Austin in 2008, and B.S. from Korea Advanced Institute of Science and Technology (KAIST) in 2004. His paper on robot-centric activity recognition at ICRA 2016 received the Best Paper Award in Robot Vision. He provided a number of tutorials at the past CVPRs (including CVPR 2022/2019/2018/2014/2011) and organized previous workshops on Egocentric (First-Person) Vision.