Apache Helicopter Stabilization Using Neural Dynamic Programming

Abstract

A new form of neural control is introduced, neural dynamic programming (NDP), a model-free online learning control scheme. NDP is shown to perform exceedingly well as a learning controller for practical systems of higher dimension, such as helicopters. The discussion is focused on providing a viable alternative helicopter control system design approach rather than providing extensive comparisons among various available controllers. A comprehensive treatise of NDP and extensive simulation studies of NDP designs for controlling an Apache helicopter under different flight conditions is presented. Design robustness is addressed by performing simulations under various disturbance conditions. All of the designs are based on FLYRT, a sophisticated industry-scale nonlinear validated model of the Apache helicopter.