Presentation | 2015-06-11 Reinforcement Learning-Based Fall-Prevention Control with Firm Standing for a Humanoid Robot Model Tomoyuki Yamaguchi, Tatsuya Kai, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | This study deals with a fall-prevention control problem for a humanoid robot model based on reinforcement learning. The main aim is to prevent a fall of a humanoid robot model with firm standing action when the robot is subjected to an external force, and we develop a control strategy that the behavior of the robot in the fall-prevention action is limited and learning time is reduced by decreasing of the number of the control inputs. We also consider an estimation method of the control input by using previous data for fall-prevention control to unknown external forces. By numerical simulations, it is confirmed that fall-prevention control with only firm standing is achieved and hence the new method is effective. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | Humanoid Robot / Reinforcement Learning / Fall-Prevention Control / Firm Standing / Zero Moment Point |
Paper # | NLP2015-39,CCS2015-1 |
Date of Issue | 2015-06-04 (NLP, CCS) |
Conference Information | |
Committee | NLP / CCS |
---|---|
Conference Date | 2015/6/11(2days) |
Place (in Japanese) | (See Japanese page) |
Place (in English) | Waseda Univerisity |
Topics (in Japanese) | (See Japanese page) |
Topics (in English) | |
Chair | Kenya Jinno(Nippon Inst. of Tech.) / Hiroo Sekiya(Chiba Univ.) |
Vice Chair | Naoto Fujisaka(Hiroshima City Univ.) / Yasuhiro Tsubo(Ritsumeikan Univ.) / Naoki Wakamiya(Osaka Univ.) |
Secretary | Naoto Fujisaka(Tokyo Univ. of Science) / Yasuhiro Tsubo(Konan Univ.) / Naoki Wakamiya(Kagawa National College of Tech.) |
Assistant | Hidehiro Nakano(Tokyo City Univ.) / Hiroyuki Asahara(Okayama Univ. of Science) / Takayuki Kimura(Nippon Inst. of Tech.) / Song-Ju Kim(NIMS) / Ryo Takahashi(Kyoto Univ.) / Junnosuke Teramae(Osaka Univ.) |
Paper Information | |
Registration To | Technical Committee on Nonlinear Problems / Technical Committee on Complex Communication Sciences |
---|---|
Language | JPN |
Title (in Japanese) | (See Japanese page) |
Sub Title (in Japanese) | (See Japanese page) |
Title (in English) | Reinforcement Learning-Based Fall-Prevention Control with Firm Standing for a Humanoid Robot Model |
Sub Title (in English) | |
Keyword(1) | Humanoid Robot |
Keyword(2) | Reinforcement Learning |
Keyword(3) | Fall-Prevention Control |
Keyword(4) | Firm Standing |
Keyword(5) | Zero Moment Point |
1st Author's Name | Tomoyuki Yamaguchi |
1st Author's Affiliation | Tokyo University of Science(Tokyo Univ. of Science) |
2nd Author's Name | Tatsuya Kai |
2nd Author's Affiliation | Tokyo University of Science(Tokyo Univ. of Science) |
Date | 2015-06-11 |
Paper # | NLP2015-39,CCS2015-1 |
Volume (vol) | vol.115 |
Number (no) | NLP-77,CCS-78 |
Page | pp.pp.1-6(NLP), pp.1-6(CCS), |
#Pages | 6 |
Date of Issue | 2015-06-04 (NLP, CCS) |