Research of humanoid robot action acquisition

Song Hao Piao; Bing Rong Hong; Qiu Bo Zhong

Research of humanoid robot action acquisition

Song Hao Piao^*
, Bing Rong Hong
, Qiu Bo Zhong

^*Corresponding author for this work

School of Mechatronics Engineering, Harbin Institute of Technology

Research output: Contribution to journal › Article › peer-review

1 Scopus citations

Abstract

A kind of stable self-learning fuzzy neural networks control system based on genetic algorithm is proposed in this paper, and it is used to acquire humanoid robot action. The system is composed of two parts: A fuzzy neural networks controller which uses GA to search optimal fuzzy rules and membership function; A supervisor which uses gradient learning algorithm to train the network weights. The results of experiments show the effectiveness of the proposed controller.

Original language	English
Pages (from-to)	20-22
Number of pages	3
Journal	Journal of Harbin Institute of Technology (New Series)
Volume	15
Issue number	SUPPL. 2
State	Published - Jul 2008
Externally published	Yes

Keywords

Action acquisition
Genetic algorithm
Humanoid robot

Cite this

@article{12ed170a30bf469ab58131134bbb9e89,

title = "Research of humanoid robot action acquisition",

abstract = "A kind of stable self-learning fuzzy neural networks control system based on genetic algorithm is proposed in this paper, and it is used to acquire humanoid robot action. The system is composed of two parts: A fuzzy neural networks controller which uses GA to search optimal fuzzy rules and membership function; A supervisor which uses gradient learning algorithm to train the network weights. The results of experiments show the effectiveness of the proposed controller.",

keywords = "Action acquisition, Genetic algorithm, Humanoid robot",

author = "Piao, \{Song Hao\} and Hong, \{Bing Rong\} and Zhong, \{Qiu Bo\}",

year = "2008",

month = jul,

language = "英语",

volume = "15",

pages = "20--22",

journal = "Journal of Harbin Institute of Technology (New Series)",

issn = "1005-9113",

publisher = "Harbin Institute of Technology",

number = "SUPPL. 2",

}

TY - JOUR

T1 - Research of humanoid robot action acquisition

AU - Piao, Song Hao

AU - Hong, Bing Rong

AU - Zhong, Qiu Bo

PY - 2008/7

Y1 - 2008/7

N2 - A kind of stable self-learning fuzzy neural networks control system based on genetic algorithm is proposed in this paper, and it is used to acquire humanoid robot action. The system is composed of two parts: A fuzzy neural networks controller which uses GA to search optimal fuzzy rules and membership function; A supervisor which uses gradient learning algorithm to train the network weights. The results of experiments show the effectiveness of the proposed controller.

AB - A kind of stable self-learning fuzzy neural networks control system based on genetic algorithm is proposed in this paper, and it is used to acquire humanoid robot action. The system is composed of two parts: A fuzzy neural networks controller which uses GA to search optimal fuzzy rules and membership function; A supervisor which uses gradient learning algorithm to train the network weights. The results of experiments show the effectiveness of the proposed controller.

KW - Action acquisition

KW - Genetic algorithm

KW - Humanoid robot

UR - https://www.scopus.com/pages/publications/57749084580

M3 - 文章

AN - SCOPUS:57749084580

SN - 1005-9113

VL - 15

SP - 20

EP - 22

JO - Journal of Harbin Institute of Technology (New Series)

JF - Journal of Harbin Institute of Technology (New Series)

IS - SUPPL. 2

ER -

Research of humanoid robot action acquisition

Abstract

Keywords

Other files and links

Fingerprint

Cite this