Abstract
A neural network-based synthesis of an optimal midcourse guidance law is presented in this study. We use a set of two-neural networks; the first network called 'a critic' outputs the Lagrange's multipliers arising in an optimal control formulation and second network called 'an action network' outputs the optimal guidance/control. In this so-called 'adaptive critic' approach, the inputs to the networks are the current values of the states. This approach needs no external training. System equations, optimality conditions and the costate equations are used in conjunction with the network outputs to provide the targets for the neural networks. When the critic and action network are mutually consistent, the output of the action network yields optimal guidance/control. A midcourse guidance problem is the first test bed (to our knowledge) for this approach where the input is vector-valued. Numerical results for a number of scenarios show that the network performance is excellent. Corroboration for optimality is provided by comparisons of the numerical solutions with a shooting method, for a number of scenarios. © 2000 by Balakrishnan. Published by the American Institute of Aeronautics and Astronautics, Inc.
Recommended Citation
D. Han and S. N. Balakrishnan, "Midcourse Guidance Law with Neural Networks," AIAA Guidance, Navigation, and Control Conference and Exhibit, American Institute of Aeronautics and Astronautics, Jan 2000.
The definitive version is available at https://doi.org/10.2514/6.2000-4072
Department(s)
Mechanical and Aerospace Engineering
Publication Status
Full Access
International Standard Book Number (ISBN)
978-156347978-6
Document Type
Article - Conference proceedings
Document Version
Citation
File Type
text
Language(s)
English
Rights
© 2024 American Institute of Aeronautics and Astronautics, All rights reserved.
Publication Date
01 Jan 2000
