DocumentCode
323376
Title
A neural network approach to controller-observer design for robots
Author
Fuchun, Sun ; Zengqi, Sun
Author_Institution
Dept. of Comput. Sci. & Technol., Tsinghua Univ., Beijing, China
Volume
1
fYear
1997
fDate
28-31 Oct 1997
Firstpage
444
Abstract
A neural network approach to controller-observer design is developed in discrete-time form for the trajectory tracking of robots. A robot manipulator with unknown dynamic nonlinearities is assumed to have only joint angle and position measurements. The main theoretical results for designing an observer-based neural controller are given
Keywords
angular measurement; control nonlinearities; control system synthesis; discrete time systems; manipulator dynamics; neurocontrollers; observers; position measurement; tracking; controller-observer design; discrete-time form; joint angle measurements; joint position measurements; neural network; observer-based neural controller; robot manipulator; trajectory tracking; unknown dynamic nonlinearities; Hafnium; Manipulator dynamics; Mathematics; Neural networks; Robot control; Symmetric matrices; Torque; Trajectory; Velocity control;
fLanguage
English
Publisher
ieee
Conference_Titel
Intelligent Processing Systems, 1997. ICIPS '97. 1997 IEEE International Conference on
Conference_Location
Beijing
Print_ISBN
0-7803-4253-4
Type
conf
DOI
10.1109/ICIPS.1997.672820
Filename
672820
Link To Document