Cheonan, South Korea
Ji-Hun Bae received the B.S. and M.S. degrees in electrical engineering from Myongji University, South Korea, in 1999 and 2001, respectively, and the Ph.D. degree in robotics from Ritsumeikan University, Japan, in 2004. He was a Postdoctoral Fellow of the JSPS 21st Century COE Program at Ritsumeikan University, Japan. He was a Senior Researcher at KIRO, from 2006 to 2008, and a Postdoctoral Fellow at KIST, from 2008 to 2009. He is currently a Principal Research Scientist in the Robotics R&D Group, Korea Institute of Industrial Technology, South Korea. His research interests include control algorithms for robotic hands and arms, coordinated hand–arm control, bimanual manipulation, and robotic assembly.
Talk # 1
Development and Usage of Allegro Hand
Recently, there has been a growing interest in grasping technology and gripper/hand for object manipulation due to the demand for manipulation technology in the field of industrial robots. In this talk, I would like to talk about ‘Allegro hand’, a representative robot hand that has been used as a research platform in various research institutes. As a designer of the ‘Allegro hand’, I talk about the development purpose, process, usage, and future improvement direction of the hand.
Marc Toussaint is full professor for Machine Learning and Robotics at the University of Stuttgart since 2012. In 2017/18 he spend a year as visiting scholar at MIT, and before that some months with Amazon Robotics. His research focuses on the combination of decision theory and machine learning, motivated by fundamental research questions in robotics. Reoccurring themes in his research are appropriate representations (symbols, temporal abstractions, relational representations) to enable efficient learning and manipulation in real world environments, and how to achieve jointly geometric, logic and probabilistic learning and reasoning. He currently is coordinator of the German research priority programme Autonomous Learning, member of the editorial board of the Journal of AI Research (JAIR), reviewer for the German Research Foundation, and programme committee member of several top conferences in the field (UAI, R:SS, ICRA, IROS, AIStats, ICML). His work was awarded best paper at R:SS'18, ICMLA'07 and runner up at R:SS'12, UAI'08.
Talk # 1
Physical Reasoning & Robot Manipulation
There recently is, again, substantial optimism about AI due to the great advances in machine learning and data-driven methods. However, a core challenge remains to capture and formalize essential structure in real-world decision making and control, and thereby provide the foundation for sample-efficient learning and strong generalization. To this end we need a united machine learning, probabilistic AI and robotics research approach. In this talk I will summarize my work on learning and reasoning in logic, geometric and uncertain domains, and highlight what I think are core research challenges towards real-world AI.