Robust Adaptive Backstepping Control Design for MIMO Electrically Driven Robot Manipulators Using RBF Neural Network With Disturbance

Abstract

In this paper, a robust adaptive (RA) radial basis function (RBF) neural network (NN) based backstepping control design is proposed for multi-input multi-output (MIMO) electrically driven robot manipulators (EDRM) with completely unmodeled dynamics, unknown nonlinearities, disturbance, and virtual control inputs. The proposed research methodology guarantees the controller’s resilience even in the presence of parameter changes. The main idea of the backstepping control design is to reduce the error to zero via the use of parameter adjustment rules and a virtual control technique. The recursive backstepping design method treats specific system signals as virtual inputs to smaller subsystems. This novel control strategy guarantees the boundedness of the trajectory tracking error and also weight updates of NN. The key advantage of our control strategy is that it eliminates the requirement for regression matrices, the linear in parameter (LIP) assumption, and an offline learning phase. The results of proposed robust adaptive control methodology with unknown disturbance are compared with conventional proportional-derivative (PD) control scheme, i.e., without backstepping.