Adaptive learning approach of integrating evolution fuzzy-neural networks and Q-learning for mobile robots

Hong Jian Zhon, Wei Min Hsieh, Yih-Guang Leu, Chin-Ming Hong

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

In the paper, an adaptive learning approach of integrating evolution fuzzy-neural networks and Q-learning is developed so that a mobile robot can adapt itself to a real and complex environment. Specifically, based on Q-value and an evolution method that adjusts their parameter values of the fuzzy-neural networks, the mobile robot evolves better strategies to adapt to the environment. However, in most studies of evolution learning, the learning of mobile robots often requires a simulator and an enormous amount of evolution time so as to perform a task. Therefore, we are to integrate Q-learning into the evolution fuzzy-neural networks to avoid the requirement of the simulator. Experiment results of a mobile robot illustrate the performance of the proposed approach.

Original languageEnglish
Title of host publication2008 IEEE International Conference on Fuzzy Systems, FUZZ 2008
Pages1902-1906
Number of pages5
DOIs
Publication statusPublished - 2008 Nov 7
Event2008 IEEE International Conference on Fuzzy Systems, FUZZ 2008 - Hong Kong, China
Duration: 2008 Jun 12008 Jun 6

Other

Other2008 IEEE International Conference on Fuzzy Systems, FUZZ 2008
CountryChina
CityHong Kong
Period08/6/108/6/6

Fingerprint

Q-learning
Adaptive Learning
Fuzzy neural networks
Fuzzy Neural Network
Mobile Robot
Mobile robots
Simulators
Simulator
Integrate
Requirements
Experiments
Experiment

ASJC Scopus subject areas

  • Theoretical Computer Science
  • Software
  • Artificial Intelligence
  • Applied Mathematics

Cite this

Zhon, H. J., Hsieh, W. M., Leu, Y-G., & Hong, C-M. (2008). Adaptive learning approach of integrating evolution fuzzy-neural networks and Q-learning for mobile robots. In 2008 IEEE International Conference on Fuzzy Systems, FUZZ 2008 (pp. 1902-1906). [4630629] https://doi.org/10.1109/FUZZY.2008.4630629

Adaptive learning approach of integrating evolution fuzzy-neural networks and Q-learning for mobile robots. / Zhon, Hong Jian; Hsieh, Wei Min; Leu, Yih-Guang; Hong, Chin-Ming.

2008 IEEE International Conference on Fuzzy Systems, FUZZ 2008. 2008. p. 1902-1906 4630629.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Zhon, HJ, Hsieh, WM, Leu, Y-G & Hong, C-M 2008, Adaptive learning approach of integrating evolution fuzzy-neural networks and Q-learning for mobile robots. in 2008 IEEE International Conference on Fuzzy Systems, FUZZ 2008., 4630629, pp. 1902-1906, 2008 IEEE International Conference on Fuzzy Systems, FUZZ 2008, Hong Kong, China, 08/6/1. https://doi.org/10.1109/FUZZY.2008.4630629
Zhon HJ, Hsieh WM, Leu Y-G, Hong C-M. Adaptive learning approach of integrating evolution fuzzy-neural networks and Q-learning for mobile robots. In 2008 IEEE International Conference on Fuzzy Systems, FUZZ 2008. 2008. p. 1902-1906. 4630629 https://doi.org/10.1109/FUZZY.2008.4630629
Zhon, Hong Jian ; Hsieh, Wei Min ; Leu, Yih-Guang ; Hong, Chin-Ming. / Adaptive learning approach of integrating evolution fuzzy-neural networks and Q-learning for mobile robots. 2008 IEEE International Conference on Fuzzy Systems, FUZZ 2008. 2008. pp. 1902-1906
@inproceedings{cbc7a5fe9f134ae380c04c106ac98836,
title = "Adaptive learning approach of integrating evolution fuzzy-neural networks and Q-learning for mobile robots",
abstract = "In the paper, an adaptive learning approach of integrating evolution fuzzy-neural networks and Q-learning is developed so that a mobile robot can adapt itself to a real and complex environment. Specifically, based on Q-value and an evolution method that adjusts their parameter values of the fuzzy-neural networks, the mobile robot evolves better strategies to adapt to the environment. However, in most studies of evolution learning, the learning of mobile robots often requires a simulator and an enormous amount of evolution time so as to perform a task. Therefore, we are to integrate Q-learning into the evolution fuzzy-neural networks to avoid the requirement of the simulator. Experiment results of a mobile robot illustrate the performance of the proposed approach.",
author = "Zhon, {Hong Jian} and Hsieh, {Wei Min} and Yih-Guang Leu and Chin-Ming Hong",
year = "2008",
month = "11",
day = "7",
doi = "10.1109/FUZZY.2008.4630629",
language = "English",
isbn = "9781424418190",
pages = "1902--1906",
booktitle = "2008 IEEE International Conference on Fuzzy Systems, FUZZ 2008",

}

TY - GEN

T1 - Adaptive learning approach of integrating evolution fuzzy-neural networks and Q-learning for mobile robots

AU - Zhon, Hong Jian

AU - Hsieh, Wei Min

AU - Leu, Yih-Guang

AU - Hong, Chin-Ming

PY - 2008/11/7

Y1 - 2008/11/7

N2 - In the paper, an adaptive learning approach of integrating evolution fuzzy-neural networks and Q-learning is developed so that a mobile robot can adapt itself to a real and complex environment. Specifically, based on Q-value and an evolution method that adjusts their parameter values of the fuzzy-neural networks, the mobile robot evolves better strategies to adapt to the environment. However, in most studies of evolution learning, the learning of mobile robots often requires a simulator and an enormous amount of evolution time so as to perform a task. Therefore, we are to integrate Q-learning into the evolution fuzzy-neural networks to avoid the requirement of the simulator. Experiment results of a mobile robot illustrate the performance of the proposed approach.

AB - In the paper, an adaptive learning approach of integrating evolution fuzzy-neural networks and Q-learning is developed so that a mobile robot can adapt itself to a real and complex environment. Specifically, based on Q-value and an evolution method that adjusts their parameter values of the fuzzy-neural networks, the mobile robot evolves better strategies to adapt to the environment. However, in most studies of evolution learning, the learning of mobile robots often requires a simulator and an enormous amount of evolution time so as to perform a task. Therefore, we are to integrate Q-learning into the evolution fuzzy-neural networks to avoid the requirement of the simulator. Experiment results of a mobile robot illustrate the performance of the proposed approach.

UR - http://www.scopus.com/inward/record.url?scp=55249112487&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=55249112487&partnerID=8YFLogxK

U2 - 10.1109/FUZZY.2008.4630629

DO - 10.1109/FUZZY.2008.4630629

M3 - Conference contribution

AN - SCOPUS:55249112487

SN - 9781424418190

SP - 1902

EP - 1906

BT - 2008 IEEE International Conference on Fuzzy Systems, FUZZ 2008

ER -