요약
협동로봇(cobot)은 산업용 로봇에 비해 교시 및 안전 기능과 UI/UX 측면에서 진일보한 기술을 선보여 로봇자동화 시장의 경계를 넓혀가고 있다. 본 강연에서는 협동로봇의 핵심기능인 교시 및 안전 기능의 세대 진화를 위해 뉴로메카에서 진행 중인 기술 개발에 대해 설명한다. 산업용로봇에 비해 협동로봇의 약점으로 꼽히는 성능을 극복하기 위해 뉴로메카가 제안하는 새로운 형태의 협동로봇에 대해서도 소개한다.

이력

• 2005년5월~2007년12월: 포항지능로봇연구소 연구개발팀장
• 2007년12월~2013년 2월: ㈜심랩 CTO
• 2012년 12월~2013년 2월: 한국과학기술연구원 (KIST) 초빙연구원
• 2013년2월~현재: (주)뉴로메카 창업 및 대표이사
• 2014년3월~현재: 포항공대 기계공학과 겸임교수

요약
The intelligent vehicle has various types of sensors and actuators. There are similarities between mobile robots and intelligent vehicles regarding sensing, perception, decision, motion planning, and control. However, there are different fundamental features of the intelligent vehicle from those of mobile robots, especially speed. We discuss how control theories are applied to intelligent vehicle control systems. Motion planning and decision processes required for intelligent vehicles are introduced. The speaker likes to share his field experience with a camera, LiDAR, radar, power steering systems, and adaptive cruise systems. The speaker will also present how deep learning and machine learning are applied to intelligent vehicle control in his research team. Experimental results from automated parking, lane-keeping, and lane change systems are also presented.

이력
Chung Choo Chung received his Ph.D. degree in electrical and computer engineering from the University of Southern California, Los Angeles, CA, USA, in 1993. Before his Ph.D. program, he worked for LG Electronics and IBM Korea. From 1994 to 1997, Dr. Chung was with the Samsung Advanced Institute of Technology, Korea, where he was selected as a Samsung Group 21C Leader. He also finished the Samsung Advanced Management Program at the Wharton School of the University of Pennsylvania in 1996. In 1997, he joined the Faculty of Hanyang University, Seoul, South Korea. Dr. Chung was an Associate Editor for various international journals such as Asian Journal of Control, IEEE TRANSACTIONS ON CONTROL SYSTEM TECHNOLOGIE (TCST), IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS, IFAC Mechatronics, and an (Founding) Editor for the International Journal of Control, Automation and Systems. He was a guest editor for a special issue on advanced servo control for emerging data storage systems published by TCST, 2012 and also a guest editor for the IEEE Intelligent Transportation Systems Magazine, 2017. H He was a program co-chair of ICCAS-SICE 2009, and an organizing chair for the ICCAS 2011 and a program co-chair of the 2015 IEEE INTELLIGENT VEHICLES SYMPOSIUM (IV2015). He was the general chair of ICCAS 2019, and also a general co-chair of IEEE Conference on Decision and Control 2020. Dr. Chung was the 2019 President of the Institute of Control, Robotics and Systems(ICROS), Korea. He is a member of the National Academy of Engineering of Korea (NAEK).

요약
Human-automation interaction (HAI) has gained much attention in recent decades and been successfully applied to a wide range of cyber-physical human systems (CPHSs), such as an artificial intelligent tutor for human operators, driver assistance systems, robot-human collaborative task in manufacturing, teleoperation systems in robotics, and remotely piloted systems in aerospace applications. In this talk, a data-driven and model assisted HAI framework for the CPHS is proposed to turn novices into experts more effectively in a shorter time. This work is motivated to let human novices, who potentially have different skill-levels, learn the skills of human experts using automation as a medium. The proposed framework is composed of two main elements: data-driven human behavior modeling and skill-level-based shared control. A data-driven human behavior modeling scheme is proposed to develop a computable cognitive model, which can explicitly account for the variability in human behavior (i.e., intrinsic uncertainty in the human motor skill), for human behavioral prediction and skill-level inference. A skill-level is defined as a value indicating the degree to which a human adheres to the expert’s mission objective. Then, a skill-level-based shared control scheme is developed for assisting and training humans based on their inferred skill-levels to expedite the rate of learning. Automation takes more control authority when the novice’s skill-level is poor, or it allows the novice to have more control authority when one’s skill-level is close to that of the expert to let the novice learn from one’s own control experience. Via human subject experiments, it has been demonstrated that the proposed human behavior modeling and skill-level based shared control framework can improve the human learning rate by providing customized assistance according to one’s skill-level.

이력
Inseok Hwang is a professor in the School of Aeronautics and Astronautics and a University Faculty Scholar at Purdue University, Indiana, U.S.A. He received the B.S. and M.S. degrees in Aerospace Engineering from Seoul National University in 1992 and KAIST in 1994, respectively, and his PhD degree in Aeronautics and Astronautics from Stanford University in 2004. His research expertise lies in intelligent situational awareness and high assurance autonomy, with provable properties in safety, security, and performance, for Cyber-Physical Systems (CPS) and Cyber-Physical Human Systems (CPHS) which are complex systems with interacting cyber elements (e.g., automation and/or human) and physical components (e.g., vehicles or robots), such as autonomous vehicles, unmanned systems, and intelligent transportation systems. He received various awards, including the National Science Foundation (NSF) CAREER award in 2008, recognition as one of the nation’s brightest young engineers by the National Academy of Engineering (NAE) in 2008, the AIAA Special Service Citation in 2010, the University Faculty Scholar by Purdue University in recognition of outstanding scholarship in 2017, Outstanding Graduate Faculty Mentor award 2018, and the C.T. Sun Award in recognition of excellence in research in 2019. He is currently an Associate Editor of the IEEE Transactions on Aerospace and Electronic Systems and the AIAA Journal.