제목: Teaching Robots Everyday Tasks
강사: 이영운 교수님
장소: D504
Abstract:
Recent advancements in AI, exemplified by models like ChatGPT and Sora from OpenAI, have achieved expert-level performance with proper prompting. But, what about robots? Robots still struggle to attain a five-year-old-level dexterity in manipulation skills. In this talk, I will first talk about why you should start working on robot learning. Then, I will introduce the challenges in teaching robots everyday tasks. Lastly, I will present my recent research on (1) robotic benchmarks, (2) skill-based reinforcement learning, and (3) model-based reinforcement learning.
Bio:
Youngwoon Lee is an assistant professor in AI at Yonsei University. Previously, he was a postdoctoral scholar at the University of California, Berkeley working with Prof. Pieter Abbeel. Prior to joining UC Berkeley, he completed his Ph.D. in Computer Science at the University of Southern California in 2022, advised by Prof. Joseph J. Lim, and received his B.S. and M.S. degrees in Computer Science at KAIST. His research interests are in deep reinforcement learning and imitation learning for robotics. Particularly, his research focuses on solving complex long-horizon tasks with complex robotic systems, such as humanoid robots assembling furniture, which requires many aspects of intelligent robots from structural reasoning to long-term planning to sophisticated control. Youngwoon’s research has been recognized with the Best System Paper Award at RSS’23 and the Best Paper Presentation Award at CoRL’20.