Discrete Time Variable Structure Control of Robotic Manipulators Based on Fully Tuned RBF Neural Networks

This paper presents a discrete-time variable structure control based on neural networks for a planar robotic manipulator. Radial basis function neural networks are used to learn about uncertainties affecting the system. The learning algorithm combines the growth criterion of the resource allocating network technique with an adaptive extended Kalman filter to update all network parameters. The analysis of the control stability is given and the controller is evaluated on the ERICC robot arm. Simulations show that the proposed controller produces good trajectory tracking performance and is robust in the presence of model inaccuracies.