IEEE/RSJ International Conference on
Intelligent Robots and Systems
Vancouver, BC, Canada
September 24–28, 2017

Menu

Special Tutorial for Young Researchers

Date and time Monday, September 25, 14:30 - 17:30
Room Room 301
Fee Free
Lecturer Tetsuya Ogata (Waseda University)
Title Deep Learning for Robotics toward Deep Cognitive Systems

Tetsuya Ogata received the B.S., M.S., and D.E. degrees in mechanical engineering from Waseda University, Tokyo, Japan, in 1993, 1995, and 2000, respectively. He was a Research Associate with Waseda University from 1999 to 2001. From 2001 to 2003, he was a Research Scientist with the RIKEN Brain Science Institute, Saitama, Japan. From 2003 to 2012, he was an Associate Professor with the Graduate School of Informatics, Kyoto University, Kyoto, Japan. Since 2012, he has been a Professor with the Faculty of Science and Engineering, Waseda University. From 2009 to 2015, he was a JST (Japan Science and Technology Agency) PREST Researcher. He is currently an Invited Researcher with the Artificial Intelligence Research Center, National Institute of Advanced Industrial Science and Technology, Tokyo. His current research interests include deep learning for robot motion control, human–robot interaction, and dynamics of human–robot mutual adaptation.

Abstract:

In recent years, image recognition, speech recognition, and language processing systems, etc., particularly systems using deep learning are developed, and their greatly improved performance, which is beyond what was previously possible, is attracting attention. However, most of these systems use large-scale data that is already in the computerized cloud, and application to the real world is at an embryonic stage. There are already examples of applications of deep learning in real world systems, such as robots, but these are mainly centered on only the use of image processing such as object recognition, position recognition, etc.

In this tutorial, we first outline the basic methods of deep learning and introduce some tools. In addition, after introducing examples of application in each field such as image recognition and speech recognition, we will explain the application of multi-modal application etc.

In addition, we will introduce regarding the essential discussion of intelligence, the "cognitive developmental robotics" which is the process of development of a real-world cognition mechanism based on "embodiment" and a model explaining the cognition process of human beings.

Then we will show the concept of "deep cognitive system" which enhances the concept of "cognitive developmental robotics" with deep learning, with our robot's studies such as a language learning model and the application to flexible object handling of humanoid robots etc.

 

 

The Robotics Society of Japan
https://www.rsj.or.jp/en