Hyeonwoo Yu is an assistant professor of the Department of Electrical Engineering and Graduate School of AI at Ulsan National Institute of Science and Technology (UNIST), South Korea from Feb. 2022.
He received Ph.D and B.S from Electrical and Computer Engineering at Seoul National University, Korea in Feb. 2021 and Feb. 2014, respectively (advisor: Prof. Beomhee Lee). Before joining UNIST, he was a postdoctoral research fellow at Robotics Institute, Carnegie Mellon University from Mar. 2020 to Dec. 2021 (PI: Prof. Jean Oh).
His research focuses on how to bridge the gap between the artificial intelligence (AI) and the robotics. By exploiting robot perception and navigation, he contributes to make AI and robotics mutually beneficial. The ultimate goal is to develop adaptive robots that can automatically explore unknown environments and learn for their own purposes. To achieve this goal, he pursues the fusion of robot navigation and probabilistic perception model. The specific research areas involve multi-object and semantic scene understanding, deep generative model for probabilistic observation, visual navigation and exploration, zero-shot learning and continual learning.