Optimal reusable rocket landing guidance: a cutting-edge approach integrating scientific machine learning and enhanced neural networks

dc.contributor.authorÇelik, Ugurcan
dc.contributor.authorDemirezen, Mustafa Umut
dc.date.accessioned2024-03-19T14:22:57Z
dc.date.available2024-03-19T14:22:57Z
dc.date.issued2024-01-29
dc.description.abstractThis study presents an innovative approach that utilizes scientific machine learning and two types of enhanced neural networks for modeling a parametric guidance algorithm within the framework of ordinary differential equations to optimize the landing phase of reusable rockets. Our approach addresses various challenges, such as reducing prediction uncertainty, minimizing the need for extensive training data, improving convergence speed, decreasing computational complexity, and enhancing prediction accuracy for unseen data. We developed two distinct enhanced neural network architectures to achieve these objectives: Adaptive (AQResNet) and Rowdy Adaptive (RAQResNet) Quadratic Residual Neural Networks. These architectures exhibited outstanding performance in our simulations. Notably, the RAQResNet model achieved a validation loss approximately 300 times lower than the standard architecture with an equal number of trainable parameters and 50 times lower than the standard architecture with twice the number of trainable parameters. Furthermore, these models require significantly less computational power, enabling real-time computation on modern flight hardware. The inference times of our proposed models were measured in approximately microseconds on a single-board computer. Additionally, we conducted an extensive Monte Carlo analysis that considers a wide range of factors, extending beyond aerodynamic uncertainty, to assess the robustness of our models. The results demonstrate the impressive adaptability of our proposed guidance policy to new conditions and distributions outside the training domain. Overall, this study makes a substantial contribution to the field of reusable rocket landing guidance and establishes a foundation for future advancements.en_UK
dc.identifier.citationÇelik U, Demirezen MU. (2024) Optimal reusable rocket landing guidance: a cutting-edge approach integrating scientific machine learning and enhanced neural networks. IEEE Access, Volume 12, January 2024, pp. 16805-16829en_UK
dc.identifier.eissn2169-3536
dc.identifier.urihttps://doi.org/10.1109/ACCESS.2024.3359417
dc.identifier.urihttps://dspace.lib.cranfield.ac.uk/handle/1826/21042
dc.language.isoen_UKen_UK
dc.publisherIEEEen_UK
dc.rightsAttribution-NonCommercial-NoDerivatives 4.0 International*
dc.rights.urihttp://creativecommons.org/licenses/by-nc-nd/4.0/*
dc.subjectAdaptive activation functionsen_UK
dc.subjectguidanceen_UK
dc.subjectnavigationen_UK
dc.subjectoptimal controlen_UK
dc.subjectscientific machine learningen_UK
dc.subjectquadratic residual neural networksen_UK
dc.titleOptimal reusable rocket landing guidance: a cutting-edge approach integrating scientific machine learning and enhanced neural networksen_UK
dc.typeArticleen_UK
dcterms.dateAccepted2024-01-25

Files

Original bundle
Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
Optimal_reusable_rocket_landing_guidance-2024.pdf
Size:
2.52 MB
Format:
Adobe Portable Document Format
Description:
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
1.63 KB
Format:
Item-specific license agreed upon to submission
Description: