A Comparison of a New Neuroadaptive Controller Architecture with the σ- and e- Modification Architectures

This paper presents a neuroadaptive full-state feedback controller design for the Boeing unmanned combat aerial vehicle (UCAV), and a neuroadaptive output feedback controller design for a damped van der Pol oscillator model. The proposed neuroadaptive controllers employ a novel controller architecture involving additional terms in the update laws that are constructed using a moving window of the integrated system uncertainty. These terms can be used to identify the ideal system weights of the neural network as well as effectively suppress system uncertainty and actuator system failures.