Abstract
A fuzzy-Gaussian neural network (FGNN) controller is described by applying a Gaussian function as an activation function. A specialized learning architecture is used so that membership function can be tuned without using expert's manipulated data. As an example of the application, a tracking control problem for the speed and azimuth of a mobile robot driven by two independent wheels is solved by using the FGNN controller. To simplify the implementation of the FGNN controller for the two-input/two-output controlled system, a learning controller is utilized consisting of two FGNN's based on independent reasoning and a connection net with fixed weights. The effectiveness of the proposed method is illustrated by performing the simulation of a circular or square trajectory tracking control.
| Original language | English |
|---|---|
| Pages (from-to) | 193-199 |
| Number of pages | 7 |
| Journal | IEEE Transactions on Control Systems Technology |
| Volume | 4 |
| Issue number | 2 |
| DOIs | |
| Publication status | Published - 1996 |
| Externally published | Yes |
Fingerprint
ASJC Scopus subject areas
- Control and Systems Engineering
- Electrical and Electronic Engineering
Cite this
A fuzzy-Gaussian neural network and its application to mobile robot control. / Watanabe, Keigo; Tang, Jun; Nakamura, Masatoshi; Koga, Shinji; Fukuda, Toshio.
In: IEEE Transactions on Control Systems Technology, Vol. 4, No. 2, 1996, p. 193-199.Research output: Contribution to journal › Article
}
TY - JOUR
T1 - A fuzzy-Gaussian neural network and its application to mobile robot control
AU - Watanabe, Keigo
AU - Tang, Jun
AU - Nakamura, Masatoshi
AU - Koga, Shinji
AU - Fukuda, Toshio
PY - 1996
Y1 - 1996
N2 - A fuzzy-Gaussian neural network (FGNN) controller is described by applying a Gaussian function as an activation function. A specialized learning architecture is used so that membership function can be tuned without using expert's manipulated data. As an example of the application, a tracking control problem for the speed and azimuth of a mobile robot driven by two independent wheels is solved by using the FGNN controller. To simplify the implementation of the FGNN controller for the two-input/two-output controlled system, a learning controller is utilized consisting of two FGNN's based on independent reasoning and a connection net with fixed weights. The effectiveness of the proposed method is illustrated by performing the simulation of a circular or square trajectory tracking control.
AB - A fuzzy-Gaussian neural network (FGNN) controller is described by applying a Gaussian function as an activation function. A specialized learning architecture is used so that membership function can be tuned without using expert's manipulated data. As an example of the application, a tracking control problem for the speed and azimuth of a mobile robot driven by two independent wheels is solved by using the FGNN controller. To simplify the implementation of the FGNN controller for the two-input/two-output controlled system, a learning controller is utilized consisting of two FGNN's based on independent reasoning and a connection net with fixed weights. The effectiveness of the proposed method is illustrated by performing the simulation of a circular or square trajectory tracking control.
UR - http://www.scopus.com/inward/record.url?scp=0030109549&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=0030109549&partnerID=8YFLogxK
U2 - 10.1109/87.486346
DO - 10.1109/87.486346
M3 - Article
VL - 4
SP - 193
EP - 199
JO - IEEE Transactions on Control Systems Technology
JF - IEEE Transactions on Control Systems Technology
SN - 1063-6536
IS - 2
ER -