32th Congress of the International Council of the Aeronautical Sciences

06.1 - Flight Dynamics and Control (Control & Modelling)

LEARNING-BASED MIDCOURSE GUIDANCE FOR VELOCITY MAXIMIZATION WITH ANGULAR CONSTRAINT

T. Jin╣, H. Li╣, S. He╣, Y. Li╣; ╣Beijing Institute of Technology, China

This paper investigates the midcourse guidance problem for velocity maximization with angular constraint, and we propose a learning-based approach to solve it. A deep neural network is first trained offline by supervised learning approach, then utilized online to realize optimal performance. And transfer learning is also used to improve the generalization ability of the proposed algorithm.


View Paper