Abstract
A Lyapunov theory-based controller is proposed in this paper for robustness against model uncertainties in the control of a missile. The controller design consists of two parts; in the first phase, an optimal nonlinear controller is designed with neural networks for tracking. This is based on the adaptive critic method that consists of one neural network called the supervisor or critic and a second network called an action network or a controller. Each network is trained through the output of the other network and equations related to optimal control. When their outputs are mutually consistent, the controller network output is optimal. In the second phase, we use this controller as a reference and formulate a Lyapunov theory-based controller for robustness to unmodeled dynamics or uncertainty. This formulation results in an expression for extra control. Combined with the control effort for the reference model, the extra control can keep the system stable in the presence of unmodeled uncertainty. We illustrate this approach through the design of a longitudinal autopilot for a nonlinear missile. © 2001 by the authors. Published by the American Institute of Aeronautics and Astronautics, Inc.
Recommended Citation
Z. Huang and S. N. Balakrishnan, "Robust Adaptive Critic based Neurocontrollers for Missiles with Model Uncertainties," AIAA Guidance, Navigation, and Control Conference and Exhibit, American Institute of Aeronautics and Astronautics, Jan 2001.
The definitive version is available at https://doi.org/10.2514/6.2001-4159
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 2001
