Leveraging neural network uncertainty in adaptive unscented Kalman Filter for spacecraft pose estimation
Advances in Space Research · 2023-06 · 71 (12) · 5061-5082
DOI: 10.1016/j.asr.2023.02.021 ↗Kurz gefasst
Fachartikel in der Zeitschrift Advances in Space Research, 2023-06. Verfasst von Lorenzo Pasqualetto Cassinis und 7 weiteren Autor:innen. Die Arbeit wurde bisher 20-mal zitiert (Crossref) und nennt 76 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Airbus Defence and Space, Stanford University, European Space Agency.
Abstract (Originalsprache)
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 ser-vicer 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.
Förderung
- Airbus Defence and Space
- Stanford University
- European Space Agency
- Airbus Defense and Space
Zitieren
APA
Cassinis, L. P., Park, T. H., Stacey, N., D’Amico, S., Menicucci, A., Gill, E., Ahrns, I., & Sanchez-Gestido, M. (2023). Leveraging neural network uncertainty in adaptive unscented Kalman Filter for spacecraft pose estimation. Advances in Space Research, 71(12), 5061-5082. https://doi.org/10.1016/j.asr.2023.02.021
Vancouver
Cassinis LP, Park TH, Stacey N, D’Amico S, Menicucci A, Gill E, et al. Leveraging neural network uncertainty in adaptive unscented Kalman Filter for spacecraft pose estimation. Advances in Space Research. 2023;71(12):5061-5082. doi:10.1016/j.asr.2023.02.021
BibTeX
@article{Cassinis2023,
author = {Cassinis, Lorenzo Pasqualetto and Park, Tae Ha and Stacey, Nathan and D’Amico, Simone and Menicucci, Alessandra and Gill, Eberhard and Ahrns, Ingo and Sanchez-Gestido, Manuel},
title = {Leveraging neural network uncertainty in adaptive unscented Kalman Filter for spacecraft pose estimation},
journal = {Advances in Space Research},
year = {2023},
volume = {71},
number = {12},
pages = {5061--5082},
doi = {10.1016/j.asr.2023.02.021}
}
EUVIMED