Spacecraft pose estimation: Robust 2-D and 3-D structural losses and unsupervised domain adaptation by intermodel consensus

The accurate estimation of spacecraft pose is crucial for missions involving the navigation of two spacecraft in close proximity. Supervised algorithms are currently the state-of-the-art approach for spacecraft pose estimation. However, the absence of training data acquired in operational scenarios...

ver descrição completa

Detalhes bibliográficos
Autores: Bravo Pérez-Villar, Juan Ignacio, García Martín, Álvaro, Bescos Cano, Jesús, Escudero Viñolo, Marcos
Tipo de documento: artigo
Data de publicação:2023
País:España
Recursos:Universidad Autónoma de Madrid
Repositório:Biblos-e Archivo. Repositorio Institucional de la UAM
Idioma:inglês
OAI Identifier:oai:repositorio.uam.es:10486/715655
Acesso em linha:http://hdl.handle.net/10486/715655
https://dx.doi.org/10.1109/TAES.2023.3306731
Access Level:Acceso aberto
Palavra-chave:3-D loss
domain adaptation
point-n-perspective
spacecraft pose estimation
uncooperative
Telecomunicaciones
Descrição
Resumo:The accurate estimation of spacecraft pose is crucial for missions involving the navigation of two spacecraft in close proximity. Supervised algorithms are currently the state-of-the-art approach for spacecraft pose estimation. However, the absence of training data acquired in operational scenarios poses a challenge for the supervised algorithms. To address this issue, computer-aided simulators have been introduced to solve the issue of data availability but introduce a large gap between the training domain and test domain. We here describe an algorithm for unsupervised domain adaptation with robust pseudolabeling by model consensus. Moreover, the proposed method incorporates a 3-D structure into the spacecraft pose estimation pipeline to provide robustness against high illumination shifts between domains. Our solution has ranked second in the two categories of the 2021 Pose Estimation Challenge (SPEC2021) organized by the European Space Agency and the Stanford University, achieving the lowest average error over these two categories