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.

The estimation of the relative pose of an inactive spacecraft by an active servicer spacecraft is a critical task for close-proximity operations, such as In-Orbit Servicing and Active Debris Removal. Among all the challenges, the lack of available space images of the inactive satellite makes the on-ground validation of current monocular camera-based navigation systems a challenging task, mostly due to the fact that standard Image Processing (IP) algorithms, which are usually tested on synthetic images, tend to fail when implemented in orbit. In response to this need to guarantee a reliable validation of pose estimation systems, this paper presents the most recent advances of ESA's GNC Rendezvous, Approach and Landing Simulator (GRALS) testbed for close-proximity operations around uncooperative spacecraft. The proposed testbed is used to validate a Convolutional Neural Network (CNN)-based monocular pose estimation system on representative rendezvous scenarios with special focus on solving the domain shift problem which characterizes CNNs trained on synthetic datasets when tested on more realistic imagery. The validation of the proposed system is ensured by the introduction of a calibration framework, which returns an accurate reference relative pose between the target spacecraft and the camera for each lab-generated image, allowing a comparative assessment at a pose estimation level. The VICON Tracker System is used together with two KUKA robotic arms to respectively track and control the trajectory of the monocular camera around a scaled 1:25 mockup of the Envisat spacecraft. After an overview of the facility, this work describes a novel data augmentation technique focused on texture randomization, aimed at improving the CNN robustness against previously unseen target textures. Despite the feature detection challenges under extreme brightness and illumination conditions, the results on the high exposure scenario show that the proposed system is capable of bridging the domain shift from synthetic to lab-generated images, returning accurate pose estimates for more than 50% of the rendezvous trajectory images despite the large domain gaps in target textures and illumination conditions.

The estimation of the relative pose of an inactive spacecraft by an active servicer spacecraft is a critical task for close-proximity operations, such as In-Orbit Servicing and Active Debris Removal. Among all the challenges, the lack of available space images of the inactive satellite makes the on-ground validation of current monocular camera-based navigation systems a challenging task, mostly due to the fact that standard Image Processing (IP) algorithms, which are usually tested on synthetic images, tend to fail when implemented in orbit. In response to this need to guarantee a reliable validation of pose estimation systems, this paper presents the on-ground validation of a Convolutional Neural Network (CNN)-based monocular pose estimation system on representative rendezvous scenarios recreated in ESA's GNC Rendezvous, Approach and Landing Simulator (GRALS) testbed. Special focus is given on solving the domain shift problem which characterizes CNNs trained on synthetic datasets when tested on more realistic imagery. The validation of the proposed system is ensured by the introduction of a calibration framework, which returns an accurate reference relative pose between the target spacecraft and the camera for each lab-generated image, allowing a comparative assessment at a pose estimation level. The VICON Tracker System is used together with two KUKA robotic arms to respectively track and control the trajectory of the monocular camera around a scaled 1:25 mockup of the Envisat spacecraft. After an overview of the facility, this work describes a novel data augmentation technique focused on texture randomization, aimed at improving the CNN robustness against previously unseen target textures. Despite the feature detection challenges under extreme brightness and illumination conditions, the results on the high exposure scenario show that the proposed system is capable of bridging the domain shift from synthetic to lab-generated images, returning accurate pose estimates for more than 50% of the rendezvous trajectory images despite the large domain gaps in target textures and illumination conditions.