Fuzzy supervisory sliding-mode and neural-network control for robotic manipulators

Abstract

Highly nonlinear, highly coupled, and time-varying robotic manipulators suffer from structured and unstructured uncertainties. Sliding-mode control (SMC) is effective in overcoming uncertainties and has a fast transient response, while the control effort is discontinuous and creates chattering. The neural network has an inherent ability to learn and approximate a nonlinear function to arbitrary accuracy, which is used in the controllers to model complex processes and compensate for unstructured uncertainties. However, the unavoidable learning procedure degrades its transient performance in the presence of disturbance. A novel approach is presented to overcome their demerits and take advantage of their attractive features of robust and intelligent control. The proposed control scheme combines the SMC and the neural-network control (NNC) with different weights, which are determined by a fuzzy supervisory controller. This novel scheme is named fuzzy supervisory sliding-mode and neural-network control (FSSNC). The convergence and stability of the proposed control system are proved by using Lyapunov's direct method. Simulations for different situations demonstrate its robustness with satisfactory performance.