Title :
An adaptive neurocontroller using RBFN for robot manipulators
Author :
Lee, Min-Jung ; Choi, Young-Kiu
Author_Institution :
Dept. of Electron. & Inf., Kyungnam Coll. of Inf. & Technol., Pusan, South Korea
fDate :
6/1/2004 12:00:00 AM
Abstract :
In recent years, neural networks have fulfilled the promise of providing model-free learning controllers for nonlinear systems; however, it is very difficult to guarantee the stability and robustness of neural network control systems. This paper proposes an adaptive neurocontroller for robot manipulators based on the radial basis function network (RBFN). The RBFN is a branch of neural networks and is mathematically tractable. Therefore, we adopt the RBFN to approximate nonlinear robot dynamics. The RBFN generates control input signals based on the Lyapunov stability that is often used in the conventional control schemes. A saturation function is also chosen as an auxiliary controller to guarantee the stability and robustness of the control system under the external disturbances and modeling uncertainties.
Keywords :
Lyapunov methods; adaptive control; learning systems; manipulator dynamics; neurocontrollers; nonlinear control systems; radial basis function networks; robust control; Lyapunov stability; RBFN; adaptive neurocontroller; control system stability; mathematically tractable; model-free learning controllers; modeling uncertainties; neural networks; nonlinear systems; radial basis function network; robot dynamics; robot manipulators; robust control; Control system synthesis; Manipulator dynamics; Neural networks; Neurocontrollers; Nonlinear control systems; Nonlinear systems; Radial basis function networks; Robots; Robust control; Robust stability; Lyapunov stability; RBFN; radial basis function network; robot manipulator; stability and robustness;
Journal_Title :
Industrial Electronics, IEEE Transactions on
DOI :
10.1109/TIE.2004.824878