ADAPTIVE-CRITIC-BASED NEURAL NETWORKS FOR AIRCRAFT OPTIMAL-CONTROL

A dual neural network architecture for the solution of aircraft contro l problems is presented. The neural network structure, consisting of a n action network and a critic network, is used to approximately solve the dynamic programming equations associated with optimal control with a high degree of accuracy. Numerical results from applying this metho dology to optimally control the longitudinal dynamics of an aircraft a re presented. The novelty in this synthesis of the optimal controller network is that it needs no external training inputs; it needs no a pr iori knowledge of the form of control. Numerical experiments with neur al-network-based control as well as other pointwise optimal control te chniques are presented. These results show that this network architect ure yields optimal control over the entire range of training. In other words, the neural network can function as an autopilot. A scalar prob lem is also used in this study for easier illustration of the solution development.