A NEURAL ADAPTIVE APPROACH FOR RELATIVE GUIDANCE OF AIRCRAFT

ABSTRACT In this study a neural adaptive approach is examined for aircraft trajectory generation. The relative guidance of an aircraft, which is aimed to join in minimum time the track of a leader aircraft, is particularly considered. Neural networks are applied to generate on-line optimized aircraft trajectories associated to the current relative position. In a first place, the minimum time optimization problem is considered. Then the synthesis of a neural approximator of optimal trajectories is discussed. Trained neural networks are used in an adaptive manner to generate intent trajectories during operation. Finally simulation results involving two wide body aircraft are presented where the pursuit trajectory is generated with and without knowledge of the leading aircraft's flight plan.