A RECURRENT NEURAL-NETWORK-BASED ADAPTIVE VARIABLE-STRUCTURE MODEL-FOLLOWING CONTROL OF ROBOTIC MANIPULATORS

A novel scheme for integrating a neural network approach with an adaptive implementation of variable structure control for multijointed robotic manipulators in complex task executions is presented. The control strategy is developed within the general framework of nonlinear model-following control and attempts to minimize the total regulation time while ensuring a specified percentage of time on the sliding manifolds in order to exploit the disturbance attenuation features present during the sliding motions. These objectives are realized by tailoring an adaptation process that appropriately adjusts the controller gains to keep the motion on the sliding manifolds and also progressively updates the sliding manifold parameters. Rapid execution of the adaptation process is facilitated by a multilayer recurrent neural network. The resulting control scheme is decentralized, and permits design of independent joint controls, A quantitative performance evaluation of the neural network-based adaptive variable structure controller is given in several task scenarios, namely regulation, trajectory tracking and model-following.