■ Title: Towards Human-level Visual Manipulation Learning
■강연자 : 최창현 교수(미네소타대학)
○ 시간 : 8/2(화)~8/4(목) 오전 11:00 (3일간 진행)
○ 장소 : 온라인 Webex진행
https://skku-ict.webex.com/meet/ai.dept (미팅번호 170 418 1090)
Robotic object manipulation is currently one of the biggest challenges in robotics. Humans can effortlessly grasp and manipulate diverse objects in various challenging scenarios. Relatively, state-of-the-art robotic manipulation systems are less capable than humans. In this series of seminars, I will showcase my research in which the goal is to design computational learning models that enable robots to perceive the world, learn tasks, and perform manipulation skills. Specifically, I will talk about 1) context-aware object grasping, 2) object grasping via leveraging environments, 3) active object manipulation, and 4) language-driven object manipulation.
Changhyun Choi is an Assistant Professor in the Department of Electrical and Computer Engineering at the University of Minnesota (UofM), Twin Cities. Before joining the UofM, he was a Postdoctoral Associate in the Computer Science & Artificial Intelligence Lab (CSAIL) at Massachusetts Institute of Technology (MIT). He obtained a Ph.D. in Robotics at the School of Interactive Computing, College of Computing, Georgia Institute of Technology. His broad research interests are in visual perception for robotic manipulation, with a focus on deep learning for object grasping and manipulation, reinforcement learning, object pose estimation, visual tracking, and active perception. He is the recipient of the NSF CAREER Award, Sony Research Award, Russell J. Penrose Excellence in Teaching Award, and ICRA 2022 Outstanding Student Paper Award.