Reusable launch vehicle adaptive guidance and control using neural networks

For reusable launch vehicles, it is common to separate the guidance and flight control problem into an outer loop and an inner loop. The inner loop uses aerodynamic and propulsive controls to achieve a commanded attitude. The attitude commands are generated by an outer loop. This outer loop uses inner loop commands and control variables to achieve desired position/velocity. Recently, neural network adaptive flight control utilizing a novel pseudo-control hedging method has been extended into the outer loop. For reusable launch vehicles, a recoverable failure will generally lead to a reduction in total control authority. In this work, the outer-loop adapts to force perturbations, while the inner-loop adapts to moment perturbations. The outer-loop is "hedged" to prevent adaptation to inner-loop dynamics. The hedge also enables adaptation while at control limits. The contribution of this paper is to further mature this approach with the addition of accelerometer feedback components to improve performance. Numerical simulation results in representative failure scenarios for the X-33 vehicle are presented.