Step estimation method for dance partner robot "MS DanceR" using neural network

Author

Hirata, Yasuhisa ; Hayashi, Tomohiro ; Takeda, Takahiro ; Kosuge, Kasuhiro ; Wang, Zhi-dong

Author_Institution

Dept. of Bioeng. & Robotics, Tohoku Univ., Sendai

fYear

0

fDate

0-0 0

Firstpage

523

Lastpage

528

Abstract

In this paper, we propose a dance partner robot referred to as MS DanceR (mobile smart dance robot) which has been developed as platform for realizing the effective human-robot coordination with physical interaction. MS DanceR consists of an omni-directional mobile base and body force sensor, which is a force/torque sensor installed between the mobile base and the body of the robot. A human could dance a ballroom dance together with MS DanceR based on a control architecture referred to as CAST (control architecture based-on step transition), in which the estimation method for the dance step is designed using neural network. CAST is applied to MS DanceR and a human dances a waltz together with MS DanceR experimentally

Keywords

force sensors; humanoid robots; man-machine systems; mobile robots; neurocontrollers; torque; user interfaces; MS DanceR; body force sensor; control architecture based-on step transition; dance partner robot; human-robot coordination; mobile smart dance robot; neural network; step estimation method; torque sensor; Biomedical engineering; Force sensors; Human robot interaction; Intelligent robots; Medical robotics; Mobile robots; Neural networks; Robot kinematics; Robot sensing systems; Torque;

fLanguage

English

Publisher

ieee

Conference_Titel

Robotics and Biomimetics (ROBIO). 2005 IEEE International Conference on

Conference_Location

Shatin

Print_ISBN

0-7803-9315-5

Type

conf

DOI

10.1109/ROBIO.2005.246322

Filename

1708799