Identification and control of a wheelchair using recurrent neural networks

This work involves the control of a wheelchair using a new model of radial base function (RBF) recurrent neural networks. The proposed architecture is made up of two blocks, each with one neural network: one to identify the p hysical system (plant)-the identifier, and another for control-the controll er. The identifier, running in parallel with the plant, is designed to obta in the system's Jacobian, which is used to adjust the weights of the contro ller. The stability conditions are obtained for the correct functioning of the system, and several tests are described in which the movements of a whe elchair are governed, thus confirming the correct Functioning of the contro l architecture used. (C) 1999 Elsevier Science Ltd. All rights reserved.