Songhwai Oh received the B.S. (with highest honors), M.S., and Ph.D. degrees in electrical engineering and computer sciences from the University of California, Berkeley, in 1995, 2003, and 2006, respectively. He is currently an Associate Professor in the Department of Electrical and Computer Engineering, Seoul National University, Seoul, Korea. Before his Ph.D. studies, he was a Senior Software Engineer at Synopsys, Inc. and a Microprocessor Design Engineer at Intel Corporation. In 2007, he was a Postdoctoral Researcher in the Department of Electrical Engineering and Computer Sciences, University of California, Berkeley. From 2007 to 2009, he was an Assistant Professor of electrical engineering and computer science in the School of Engineering, University of California, Merced. His research interests include robotics, computer vision, cyber-physical systems, and machine learning.
With recent advances in hardware, sensing, and algorithms, we are witnessing the emergence of a new robotics industry. I will present a few examples of new services provided by upcoming service robots. With the introduction of new service robots in diverse domains, we can expect that more service robots will be assisting us in the near future in places, such as offices, malls, and homes. But, for a robot to coexist with humans and operate successfully in crowded and dynamic environments, a robot must be able to learn from experiences to act safely and harmoniously with human participants in the environment. I will discuss research challenges for service robots and our attempts to address those challenges.
In particular, I will present our recent work on learning with counterexamples to enhance safety and social acceptability of service robots. While existing learning from demonstration (LfD) algorithms assume that demonstrations are given from skillful experts, the proposed method alleviates such assumption by allowing demonstrations from casual or novice users. To learn from demonstrations of mixed quality, we present a sparse-constrained leveraged optimization algorithm using proximal linearized minimization. I will also present how the same concept can be applied to inverse reinforcement learning to improve performance.