Neural Control of Space Trajectories with Pseudolinear Models
摘要
This paper describes an approach to neural control of a satellite trajectory. A pseudolinear model is created to generate the necessary training data for the neural network. This model uses an H∞ to stabilize the relative motion of a satellite concerning another satellite. The purpose of this paper is to show the feasibility of such an approach and to better understand the benefits of using a previously trained neural network to control a satellite.