Image-based attitude determination of co-orbiting satellites using deep learning technologies

Active debris removal missions pose demanding guidance, navigation and control requirements. We present a novel approach which adopts deep learning technologies to the problem of attitude determination of an uncooperative debris satellite of an a-priori unknown geometry. A siamese convolutional neural network is developed, which detects and tracks inherently useful landmarks from sensor data, after training upon synthetic datasets of visual, LiDAR or RGB-D data. The method is capable of real-time performance while improving upon conventional computer vision-based approaches, and generalises well to previously unseen object geometries, enabling this approach to be a feasible solution for safely performing guidance and navigation in active debris removal, satellite servicing and other close proximity operations. The performance of the algorithm, its sensitivity to model parameters and its robustness to illumination and shadowing conditions, are analysed via numerical simulation.

Active debris removal, Deep learning, Image processing, Spacecraft attitude determination

10.1016/j.ast.2021.107232

1270-9638

Guthrie, Benjamin, Felix

03652589-afe9-4d34-a4fd-831cb1562c73

Kim, Minkwan

18ed9a6f-484f-4a7c-bf24-b630938c1acc

Urrutxua, Hodei

b419b029-53d7-41aa-bd77-117ec584a972

Hare, Jonathon

65ba2cda-eaaf-4767-a325-cd845504e5a9

January 2022

Guthrie, Benjamin, Felix

03652589-afe9-4d34-a4fd-831cb1562c73

Kim, Minkwan

18ed9a6f-484f-4a7c-bf24-b630938c1acc

Urrutxua, Hodei

b419b029-53d7-41aa-bd77-117ec584a972

Hare, Jonathon

65ba2cda-eaaf-4767-a325-cd845504e5a9

Guthrie, Benjamin, Felix, Kim, Minkwan, Urrutxua, Hodei and Hare, Jonathon (2022) Image-based attitude determination of co-orbiting satellites using deep learning technologies. Aerospace Science and Technology, 120, [107232]. (doi:10.1016/j.ast.2021.107232).

Record type: Article

Abstract

Text

image_based_attitude - Author's Original

Available under License Creative Commons Attribution Non-commercial No Derivatives.

Download (4MB)

More information

Submitted date: 23 June 2021

Accepted/In Press date: 16 November 2021

e-pub ahead of print date: 19 November 2021

Published date: January 2022

Additional Information: Funding Information: This work was supported by the EPSRC Centre for Doctoral Training in Next Generation Computational Modelling Grant No. EP/L015382/1 . The authors acknowledge the use of the IRIDIS High Performance Computing Facility, and associated support services at the University of Southampton, in the completion of this work. Hodei Urrutxua wishes to acknowledge funding from grant PID2020-112576GB-C22 of the Spanish State Research Agency and the European Regional Development Fund , as well as from grant F663-AAGNCS by the “Dirección General de Investigación e Innovación Tecnológica, Consejería de Ciencia, Universidades e Innovación, Comunidad de Madrid” and “Universidad Rey Juan Carlos” . Funding Information: This work was supported by the EPSRC Centre for Doctoral Training in Next Generation Computational Modelling Grant No. EP/L015382/1. The authors acknowledge the use of the IRIDIS High Performance Computing Facility, and associated support services at the University of Southampton, in the completion of this work. Hodei Urrutxua wishes to acknowledge funding from grant PID2020-112576GB-C22 of the Spanish State Research Agency and the European Regional Development Fund, as well as from grant F663-AAGNCS by the ?Direcci?n General de Investigaci?n e Innovaci?n Tecnol?gica, Consejer?a de Ciencia, Universidades e Innovaci?n, Comunidad de Madrid? and ?Universidad Rey Juan Carlos?. Publisher Copyright: © 2021 Elsevier Masson SAS

Keywords: Active debris removal, Deep learning, Image processing, Spacecraft attitude determination

Learn more about Vision, Learning and Control research