Domain randomisation and CNN-based keypoint-regressing pose initialisation for relative navigation with uncooperative finite-symmetric spacecraft targets using monocular camera images

• Published in: Advances in space research 2023-10, Vol.72 (7), p.2824-2844
• Main Authors: Kajak, Karl Martin, Maddock, Christie, Frei, Heike, Schwenk, Kurt
• Format: Article
• Language: English
• Subjects: Close-range relative navigation; Convolutional network; Domain randomisation; Monocular camera; Pose estimation; Symmetric uncooperative target
• ISSN: 0273-1177; 1879-1948
• DOI: 10.1016/j.asr.2023.02.024

Vision-based relative navigation technology is a key enabler of several areas of the space industry such as on-orbit servicing, space debris removal, and formation flying. A particularly demanding scenario is navigating relative to a non-cooperative target that does not offer any navigational aid and is unable to stabilise its attitude. This research integrates a convolutional neural network (CNN) and an EPnP-solver in a pose initialisation system. The system’s performance is benchmarked on images gathered from the European Proximity Operations Simulator EPOS 2.0 laboratory. A synthetic dataset is generated using Blender as a rendering engine. A segmentation-based pose estimation CNN is trained using the synthetic dataset and the resulting pose estimation performance is evaluated on a set of real images gathered from the cameras of the EPOS 2.0 robotic close-range relative navigation laboratory. It is demonstrated that a synthetic-image-trained CNN-based pose estimation pipeline is able to successfully perform in a close-range visual relative navigation setting on real camera images of a 6-facet symmetrical spacecraft.