複数の教示パターンによるロボットの見真似学習法の検討

松田 雅博; 福村 直博

doi:10.11511/jacc.54.0.38.0

THE 54TH JAPAN JOINT AUTOMATIC CONTROL CONFERENCE

Session ID : 1C203

DOI https://doi.org/10.11511/jacc.54.0.38.0

Conference information

Host: The Society of Instrument and Control Engineers, The Japan Society of Mechanical Engineers, The Institute of Systems, Control and Information Engineers, The Society of Chemical Engineers, The Japan Society for Precision Engineering, The Japan Society for Aeronautical and Space Sciences

Co-host: Toyohashi University of Technology, Technically Cosponsored by 51 Societies and Institutes

Recognition Technology for Environment and Behavior and Human-Robot Interaction (2)

A study of imitation learning using multiple teaching patterns.

*Masahiro Matsuda, Naohiro Fukumura

Author information

CONFERENCE PROCEEDINGS FREE ACCESS

Details

Abstract

One of the motor learning method for robots is the imitation from human motion task.Since human's motion patterns, however, are not always same, the robot needs to choose a appropriate pattern from multiple human motion patterns. In this study, we investigate the imitation learning using multiple teaching patterns and experiment using a humanoid robot.

Corresponding author

Register with J-STAGE for free!