NEURAL-NETWORK CONTROL OF SPACE-VEHICLE INTERCEPT AND RENDEZVOUS MANEUVERS

Neural networks are examined for use as optimal controllers. The effec t of the addition of noise to the neural network input measurements is investigated to determine the performance robustness of the neural ne twork controllers. These techniques are applied to the autonomous cont rol of interceptor-to target rendezvous missions. For this example, th e target lies in a circular orbit and remains passive throughout the m aneuver. The linearized Clohessy-Wiltshire equations with thrust are u sed to describe the relative motion of the two vehicles. Parameter opt imization is used to generate the training data for the neural network designs. A combination of open-loop and closed-loop control. is shown to work effectively for this problem.