서울대학교 AI 연구원 로봇 및 인공지능 선도·혁신 연구센터(센터장: 박종우 교수) 세미나에 초대합니다.

주제: Towards a Natural Motion Generator
연사: 고려대학교 최성준 교수

일정: 1:00 - 2:00 pm, October 8, 2021
장소변경: Building 301, Room 105

온라인 참여 안내
Zoom: https://snu-ac-kr.zoom.us/j/86152728100
YouTube: youtube.com/서울대학교AI연구원

강연소개: As autonomous robots gradually permeate our daily lives, there is growing interest in generating natural robotic motions. However, research on natural motions is limited because of the difficulty of defining the 'naturalness' of a motion; this in turn limits the effectiveness of motion optimization methods. Throughout this talk, I will cover how AI technologies can be utilized to generate natural motions of both robots (e.g., legged robots and manipulators) and animated characters. AI methods require training data, and generating an abundant number of motions for human-like robots from scratch may take an excessive amount of time. Hence, we will first look at how motion capture data can be leveraged to generate humanoid motions, often referred to as motion retargeting. I will also present a robust motion retargeting method to handle noisy motion data estimated from RGB videos (e.g., YouTube). Then, a data-driven motion generation method for animated characters will be presented that can not only generate a natural motion but also stylize the motion. Finally, I would like to share our recent results on perceptive manipulation using reinforcement learning, emphasizing shared autonomy.

연사소개: Sungjoon Choi received the Ph.D. in Electrical and Computer Engineering from Seoul National University (2018) and B.S degree in Electrical Engineering and Computer Science from Seoul National University (2012). He is currently an assistant professor in the Department of AI at Korea University. Before joining Korea University, he was a postdoctoral researcher at Disney Research Los Angeles and a research scientist at Kakao Brain in Korea. His research interests include sample-efficient reinforcement learning and human robot interaction. He received the Best Conference Paper Finalist Award at the 2016 IEEE International Conference on Robotics and Automation (ICRA).