A robust robotic tracking controller based on neural network

A neural-network-based robust tracking controller (NNBRTC) is proposed for robot systems under plant uncertainties. A robust controller and a neural network (NN) are combined into a hybrid robust control scheme. NN is used to approximate the modelling uncertainties in a robotic system. Then the disadvantageous effects on tracking performance, due to the approximating error of the NN and nonmeasurable external disturbances in robotic system, are attenuated to a prescribed level by robust controller. The robust controller and the adaptation law of neural network are designed based on Hamilton-Jacobi-Issacs (HJI) inequality theorem. The weights of NN are easily tuned online by a simple adaptation law, with no need of a tedious and lengthy offline training phase. A simulation example demonstrates the effectiveness of the proposed control strategy.