Multimodal human-humanoid interaction using motions, brain NIRS and spike trains

Author

Matsuyama, Yasuo ; Ochiai, Nimiko ; Hatakeyama, Takashi ; Noguchi, Keita

Author_Institution

Dept. of Comput. Sci. & Eng., Waseda Univ., Tokyo, Japan

fYear

2010

fDate

2-5 March 2010

Firstpage

173

Lastpage

174

Abstract

Heterogeneous bio-signals including human motions, brain NIRS and neural spike trains are utilized for operating biped humanoids. The Bayesian network comprising Hidden Markov Models and Support Vector Machines is designed for the signal integration. By this method, the system complexity is reduced so that that total operation is within the scope of PCs. The designed system is capable of transducing original sensory meaning to another. This leads to prosthesis, rehabilitation and gaming. In addition to the supervised mode, the humanoid can act autonomously for its own designed tasks.

Keywords

belief networks; brain; control engineering computing; hidden Markov models; human-robot interaction; humanoid robots; legged locomotion; neural nets; Bayesian network; biped humanoids; brain NIRS; gaming; heterogeneous bio-signals; hidden Markov models; human motions; multimodal human-humanoid interaction; neural spike trains; original sensory meaning; prosthesis; rehabilitation; signal integration; support vector machines; system complexity; Bayesian methods; Computer science; Hidden Markov models; Humans; Motion measurement; Neural prosthesis; Personal communication networks; Prosthetics; Signal design; Support vector machines; Brain NIRS; HMM/SVM-Embedded BN; Human-Humanoid Interaction; Motion Recogntion; Multimodal; Neural Spike Train; Non-Verbal; Sensory Transducing;

fLanguage

English

Publisher

ieee

Conference_Titel

Human-Robot Interaction (HRI), 2010 5th ACM/IEEE International Conference on

Conference_Location

Osaka

Print_ISBN

978-1-4244-4892-0

Electronic_ISBN

978-1-4244-4893-7

Type

conf

DOI

10.1109/HRI.2010.5453208

Filename

5453208