Sigma Point Modified State Observer for Nonlinear Uncertainty Estimation

A neural network based novel state observer, known as the Sigma Point Modified State Observer, is presented. The Sigma Point Modified State Observer uses sigma point filtering techniques, similar to the Unscented Kalman Filter, in combination with a neural network to estimate system states, state error covariance, and system uncertainty in nonlinear systems online. Spacecraft atmospheric reentry simulation results are presented to show the validity of the Sigma Point Modified State Observer to highly nonlinear systems with significant uncertainty.