Abstract

Service robots have seen rapid adoption in the industry, but their dependency on user-specific commands is a problem that limits their usefulness. To process user requests, the robot must control and manage reactions in unstable environments comprised of unreliable sensors. This talk aims to address these problems and presents a hybrid control architecture inspired by mirror neurons and ideas from the theory of mind (ToM), deployed on a humanoid service robot platform for demonstration. Robust reaction is achieved through behaviour selection networks which are affected by the goal-oriented characteristics of mirror neurons interacting with the environment. In order to resolve the frequent occurrence of conflicting goals within the mirror neurons, the proposed system accompanies hierarchical task network planning set forth by the ToM, by designing sub-goals with modular behaviour selection networks. Subsequent experimentation in various scenarios confirm the generation of proper systemic reactions as responses to actual user intention, showing the usefulness of the proposed control architecture.

Biography

Prof. Dr. Cho received the Ph.D. degree in computer science from KAIST (Korea Advanced Institute of Science and Technology), Korea, in 1993. He was an Invited Researcher of Human Information Processing Research Laboratories at Advanced Telecommunications Research (ATR) Institute, Japan from 1993 to 1995, and a Visiting Scholar at University of New South Wales, Australia in 1998. He was also a Visiting Professor at University of British Columbia, Canada from 2005 to 2006. Since 1995, he has been a Professor in Department of Computer Science, Yonsei University, Korea. Prof. Dr. Cho has been serving as an associate editor for several journals including IEEE Transactions on CI and AI on Games (2009-present) and IEEE Transactions on Fuzzy Systems (2013-present). He was also the chair of Games Technical Committee, IEEE CIS (2009-2010), and Student Games-based Competition Subcommittee, IEEE CIS (2011-2012). He is a member of Board of Government (BoG) of Asia Pacific Neural Networks Assembly (APNNA) (2011-present), and a member of three technical committees in IEEE CIS such as Emergent Technologies, Computational Finance and Economics, and Games. His research interests include hybrid intelligent systems, soft computing, evolutionary computation, neural networks, pattern recognition, intelligent man-machine interfaces, and games. He has published over 230 journal papers, and over 680 conference papers. According to google scholar, total citations are 11,842 (4,815 since 2014), h-index is 53 (31 since 2014), and i10-index is 220 (111 since 2014). The most cited publication was “Combining multiple neural networks by fuzzy integral for robust classification,” 1995 (447 citations).

Contact

Dr. Sung-Bae Cho, Professor
Yonsei University
50 Yonsei-ro, Sudaemoon-gu
Seoul 03722, South Korea
Email: sbcho@yonsei.ac.kr