Tool-body assimilation model considering grasping motion through deep learning

doi:10.1016/j.robot.2017.01.002

Robotics and Autonomous Systems

Volume 91, May 2017, Pages 115-127

https://doi.org/10.1016/j.robot.2017.01.002 Get rights and content

Under a Creative Commons license

open access

Abstract

We propose a tool-body assimilation model that considers grasping during motor babbling for using tools. A robot with tool-use skills can be useful in human–robot symbiosis because this allows the robot to expand its task performing abilities. Past studies that included tool-body assimilation approaches were mainly focused on obtaining the functions of the tools, and demonstrated the robot starting its motions with a tool pre-attached to the robot. This implies that the robot would not be able to decide whether and where to grasp the tool. In real life environments, robots would need to consider the possibilities of tool-grasping positions, and then grasp the tool. To address these issues, the robot performs motor babbling by grasping and nongrasping the tools to learn the robot’s body model and tool functions. In addition, the robot grasps various parts of the tools to learn different tool functions from different grasping positions. The motion experiences are learned using deep learning. In model evaluation, the robot manipulates an object task without tools, and with several tools of different shapes. The robot generates motions after being shown the initial state and a target image, by deciding whether and where to grasp the tool. Therefore, the robot is capable of generating the correct motion and grasping decision when the initial state and a target image are provided to the robot.

Keywords

Tool-body assimilation

Motor babbling

Deep neural network

Recurrent neural network

Transfer learning

Cited by (0)

Kuniyuki Takahashi received the B.S. and M.S. degrees in mechanical engineering from Waseda University, Tokyo, Japan, in 2011 and 2013, respectively. He is currently pursuing the Ph.D. degree in Waseda University. He studied abroad to the Institute for Cognitive System, Technical University Munich, Munich, Japan from 2015 to 2016. He is currently Research Fellow of Japan Society for the Promotion of Science from 2015, and Graduate Program for Embodyment Informatics, Waseda University from 2014. His current research interests include machine learning for robotics. He is a Student Member of the Robotics Society of Japan (RSJ), and The Japanese Society for Artificial Intelligence (JSAI).

Kitae Kim received the B.E degrees from Waseda University, Tokyo, Japan, in 2016. He is currently pursuing the M.S. in Waseda University degree. His current research interests include machine learning for robotics. He is a Student Member of the Robotics Society of Japan, and the Information Processing Society of Japan (IPSJ).

Tetsuya Ogata (M’00) 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 a Visiting Researcher with the Artificial Intelligence Research Center, National Institute of Advanced Industrial Science and Technology, Tokyo. His current research interests include human–robot interaction, dynamics of human–robot mutual adaptation, and inter-sensory translation in robot systems with neuro-dynamical models.

Shigeki Sugano (M’94–SM’03–F’07) received the B.S., M.S., and D.Eng. in mechanical engineering from Waseda University, Tokyo, Japan, in 1981, 1983, and 1989, respectively. He was a Research Associate with Waseda University from 1986 to 1990. From 1993 to 1994, he was a Visiting Scholar with the Mechanical Engineering Department, Stanford University, USA. From 2001 to 2010, he was the President of the Japan Association for Automation Advancement. Since 1991, he has been a Faculty Member with the Department of Mechanical Engineering, Waseda University, where he is currently a Professor. Since 2014, he has served as the Dean of the School/Graduate School of Creative Science and Engineering with Waseda University. He has authored over 200 refereed journal and conference papers. His current research interests include anthropomorphic robot, dexterous manipulator, and humanrobot interaction. Dr. Sugano is a fellow of the Japan Society of Mechanical Engineers (JSME), the Society of Instrument and Control Engineers (SICE), and the Robotics Society of Japan (RSJ). He served as the Secretary of the IEEE Robotics and Automation Society (RAS) from 2006 to 2007. He served as an AdCom Member of the IEEE RAS from 2008 to 2013. He served as the Editor-in-Chief of the Journal of Advanced Robotics from 2007 to 2012. He served as the General Chair of the IEEE/ASME International Conference on Advanced Intelligent Mechatronics in 2003, and the IEEE/RSJ International Conference on Intelligent Robots and Systems in 2013. Since 2016, he has served as the Vice President of SICE.

¹: Research Fellow of the Japan Society for the Promotion of Science (JSPS Research Fellow).