The article presents Deep Coherent Point Drift (DeepCPD), a neural-network approach for estimating the six-degrees-of-freedom pose of noncooperative spacecraft during autonomous rendezvous and docking through point cloud data. The method registers unorganized scan point clouds with their reference model point clouds. DeepCPD replaces the Expectation-Maximization procedure in the Gaussian Mixture Model registration algorithm with a neural network that learns point-to-component correspondence, achieving better estimation performance and acceleration of the registration process. The proposed method is also robust to perturbation, corruption, occlusion, and distance, as validated by simulated experimental results. Our code will be available at https://github.com/Zhang-CV/DeepCPD.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Neural-Network-Based Pose Estimation During Noncooperative Spacecraft Rendezvous Using Point Cloud


    Contributors:
    Zhang, Shaodong (author) / Hu, Weiduo (author) / Guo, Wulong (author) / Liu, Chang (author)

    Published in:

    Publication date :

    2023-08-01




    Type of media :

    Article (Journal)


    Type of material :

    Electronic Resource


    Language :

    English





    Position Awareness Network for Noncooperative Spacecraft Pose Estimation Based on Point Cloud

    Liu, Xiang / Wang, Hongyuan / Chen, Xinlong et al. | IEEE | 2023


    Robust Model-Based Monocular Pose Initialization for Noncooperative Spacecraft Rendezvous

    Sharma, Sumant / Ventura, Jacopo / D’Amico, Simone | AIAA | 2018



    Edge Detection Using Point Cloud Data for Noncooperative Pose Estimation

    Lim, Tae W. / Ramos, Pierre F. / O’Dowd, Matthew C. | AIAA | 2017