Paper:
Views over last 60 days: 326
Learning Control Method for Robotic Dynamical System
Tohru Kumagai***, Mitsuo Wada**, Sadayoshi Mikami**, Ryoichi Hashimoto*
*National Institute of Bioscience and Human-Technology, 1-1, Higashi, Tsukuba, 305, Japan
**Faculty of Engineering Hokkaido University, N13-W8, Kita-ku, Sapporo 060, Japan
***Graduate School of Hokkaido University, N13-W8, Kita-ku, Sapporo 060, Japan
Received:November 1, 1996Accepted:December 20, 1996Published:February 20, 1997
Keywords:Adaptive control, Learning control, Neural network, Inverted pendulum, Multi output system
Abstract
We present a new learning control method to control a single input multi output system. In conventional learning controllers using a neural network, it is difficult to treat a multi-output system because of the difficulty in designing reference models. Hence, we propose to divide a complex plant into sub-plants and to use a learning controller for each one. We use our method to the regulation problem of the inverted pendulum that is a oneinput, two-output system. In the simulation and the experimental system, we regulate the inverted pendulum and show the effectiveness of this method. We also show that our learning control system can regulate a system that has a time lag between the input and the output signals. Moreover, we show that a reference model of order lower than the plant order is available.
Cite this article as:T. Kumagai, M. Wada, S. Mikami, and R. Hashimoto, “Learning Control Method for Robotic Dynamical System,” J. Robot. Mechatron., Vol.9 No.1, pp. 57-64, 1997.Data files:
