Leveraging neural network uncertainty in adaptive unscented Kalman Filter for spacecraft pose estimation

Leveraging neural network uncertainty in adaptive unscented Kalman Filter for spacecraft pose estimation

Pasqualetto Cassinis, L. (TU Delft Space Systems Egineering)
Park, Tae Ha (Stanford University)
Stacey, Nathan (Stanford University)
D'Amico, Simone (Stanford University)
Menicucci, A. (TU Delft Space Systems Egineering)
Gill, E.K.A. (TU Delft Space Systems Egineering)
Ahrns, Ingo (AirBus Defence and Space GmbH)
Sanchez-Gestido, Manuel (European Space Agency (ESA))

2023

This paper introduces an adaptive Convolutional Neural Network (CNN)-based Unscented Kalman Filter for the pose estimation of uncooperative spacecraft. The validation is carried out at Stanford's robotic Testbed for Rendezvous and Optical Navigation on the Satellite Hardware-In-the-loop Rendezvous Trajectories (SHIRT) dataset, which simulates vision-based rendezvous trajectories of a servicer spacecraft to PRISMA's Tango spacecraft. The proposed navigation system is stress-tested on synthetic as well as realistic lab imagery by simulating space-like illumination conditions on-ground. The validation is performed at different levels of the navigation system by first training and testing the adopted CNN on SPEED+, Stanford's spacecraft pose estimation dataset with specific emphasis on domain shift between a synthetic domain and an Hardware-In-the-Loop domain. A novel data augmentation scheme based on light randomization is proposed to improve the CNN robustness under adverse viewing conditions, reaching centimeter-level and 10 degree-level pose errors in 80% of the SPEED+ lab images. Next, the entire navigation system is tested on the SHIRT dataset. Results indicate that the inclusion of a new scheme to adaptively scale the heatmaps-based measurement error covariance based on filter innovations improves filter robustness by returning centimeter-level position errors and moderate attitude accuracies, suggesting that a proper representation of the measurements uncertainty combined with an adaptive measurement error covariance is key in improving the navigation robustness.

Active debris removal
Adaptive filtering
Convolutional neural networks
Domain adaptation
On-ground validation
Relative pose estimation

http://resolver.tudelft.nl/uuid:991b4cee-257e-4635-96af-fe17a84acf5b

https://doi.org/10.1016/j.asr.2023.02.021

0273-1177

Advances in Space Research, 71 (12), 5061-5082

Institutional Repository

journal article

© 2023 L. Pasqualetto Cassinis, Tae Ha Park, Nathan Stacey, Simone D'Amico, A. Menicucci, E.K.A. Gill, Ingo Ahrns, Manuel Sanchez-Gestido