AN ANALYTICAL COMPARISON OF A NEURAL-NETWORK AND A MODEL-BASED ADAPTIVE CONTROLLER

A neural network inverse dynamics controller with adjustable weights is compared with a computed-torque type adaptive controller. Adaptive control techniques have been designed to accomplish the same objectives as neural network controllers, namely to achieve good performance when the system parameters are poorly known. Thus, a detailed comparison of the two approaches highlights some of the similarities and differences, both with respect to learning/adaptation laws and system performance. Lyapunov stability techniques, usually applied to adaptive systems, are used to derive a globally asymptotically stable adaptation law for a single-layer neural network controller that bears similarities to the well-known delta rule for neural networks. This alternative learning rule allows the learning rates of each connection weight to be individually adjusted to give faster convergence. The role of persistently exciting inputs to ensure parameter convergence, often mentioned in the context of adaptive systems, is emphasized in relation to the convergence of neural network weights. A coupled, compound pendulum system is used to develop inverse dynamics controllers based on adaptive and neural network techniques. Adaptation performance is compared for a model-based adaptive controller and a simple neural network utilizing both delta-rule learning and the alternative adaptation law.