Self-Organizing Fuzzy Radial Basis-Function Neural-Network Controller for Robotic Systems
碩士 === 華夏科技大學 === 智慧型機器人研究所 === 105 === This study developed intelligent controllers for the control of robotic systems. The application of model based classical control theories needs accurate system’s mathematical model for the design of controllers. However, the mathematical mod- els of robotic s...
| Main Authors: | , |
|---|---|
| Other Authors: | |
| Format: | Others |
| Language: | zh-TW |
| Published: |
2017
|
| Online Access: | http://ndltd.ncl.edu.tw/handle/35094652486239930551 |
| Summary: | 碩士 === 華夏科技大學 === 智慧型機器人研究所 === 105 === This study developed intelligent controllers for the control of robotic systems.
The application of model based classical control theories needs accurate system’s
mathematical model for the design of controllers. However, the mathematical mod-
els of robotic systems with nonlinearities and dynamic uncertain characteristics are
difficult to establish or estimate accurately. This study proposed model-free in-
telligent control strategies to control robotic systems. The theoretical analysis and
simulation for the control of a robotic system was performed to verify the availability
of the proposed intelligent control strategies. This study employed three different
intelligent control strategies,
(1) self-organizing fuzzy controller (SOFC)
(2) self-organizing fuzzy radial basis-function neural-network with steepest descent method(SFRBNC S )
(3) self-organizing fuzzy radial basis-function neural-network with
Levenberg-Marquardt algorithm (SFRBNC L ) for the control of robotic systems.
Simulation results showed that the proposed intelligent controllers achieved satis-
factory control performance for the trajectory tracking control of a robotic system.
|
|---|