LEARNING FEEDFORWARD CONTROLLER FOR A MOBILE ROBOT VEHICLE

This paper describes the design and realisation of an on-line learning pose-tracking controller for a three-wheeled mobile robot vehicle, Th e controller consists of two components, The first is a constant-gain feedback component, designed on the basis of a second-order model. The second is a learning feedforward component, containing a singlelayer neural network, that generates a control contribution on the basis of the desired trajectory of the vehicle. The neural network uses B-splin e basis functions, enabling a computationally fast implementation and fast learning, The resulting control system is able to correct for err ors due to parameter mismatches and classes of structural errors in th e model used for the controller design. After sufficient learning, an existing static gain controller designed on the basis of an extensive model has been outperformed in terms of tracking accuracy.