Artificial Chemical Reaction Optimization Algorithm and Neural Network Based Adaptive Control for Robot Manipulator

Abstract

In this paper, an artificial chemical reaction optimization algorithm (ACROA) and neural network based adaptive control scheme for robot manipulator is proposed to obtain the expected trajectory tracking. A radial basis function neural network (RBFNN) is applied to approximate the uncertainties. The network parameters in initial stage are optimized by utilizing ACROA. The RBFLN weights are achieved based on adaptive tuning law in Lyapunov stability theory. Thus, the system is convergent and stable, and the control performances of the system are improved. The simulation results of two-link robot manipulator are represented to validate the efficiency of the proposed control method.