Online corrections to neural policy guidance for pinpoint powered descent
File(s)
Accepted version
Author(s)
Cho, Namhoon
Shin, Hyo-Sang
Tsourdos, Antonios
Amato, Davide
Type
Journal Article
Abstract
This study presents incremental correction methods for refining neural network parameters or control functions entering into a continuous-time dynamic system to achieve improved solution accuracy in satisfying the interim point constraints placed on the performance output variables. The proposed approach is to linearize the dynamics around the baseline values of its arguments and then to solve for the corrective input required to transfer the perturbed trajectory to precisely known or desired values at specific time points, in other words, the interim points. Depending on the type of decision variables to adjust, parameter correction and control function correction methods are developed. These incremental correction methods can be used as a means to compensate for the prediction errors of pretrained neural networks in real-time applications where high accuracy of the prediction of dynamical systems at prescribed time points is imperative. In this regard, the online update approach can be useful for enhancing overall targeting accuracy of finite-horizon control subject to point constraints using a neural policy. A numerical example demonstrates the effectiveness of the proposed approach in an application to a powered descent problem on Mars.
Date Issued
2024-05
Date Acceptance
2023-12-05
Citation
Journal of Guidance, Control, and Dynamics: devoted to the technology of dynamics and control, 2024, 47 (5), pp.945-963
ISSN
0731-5090
Publisher
American Institute of Aeronautics and Astronautics
Start Page
945
End Page
963
Journal / Book Title
Journal of Guidance, Control, and Dynamics: devoted to the technology of dynamics and control
Volume
47
Issue
5
Copyright Statement
Copyright © 2024 by the American Institute of Aeronautics and Astronautics, Inc. All rights reserved. All requests for copying and permission to reprint should be submitted to CCC at www.copyright.com; employ the ISSN 1533-3884 to initiate your request. See also AIAA Rights and Permissions www.aiaa.org/randp.
Identifier
http://dx.doi.org/10.2514/1.g007234
Publication Status
Published
Date Publish Online
2024-02-03