导航

ACTA AERONAUTICAET ASTRONAUTICA SINICA ›› 2021, Vol. 42 ›› Issue (11): 524959-524959.doi: 10.7527/S1000-6893.2021.24959

• Article • Previous Articles     Next Articles

Long-range relative pose estimation and optimization of a failure satellite

MU Jinzhen1,2,3, LIU Zongming1,2, HAN Fei1,2, ZHOU Yan4, LI Shuang3   

  1. 1. Shanghai Aerospace Control Technology Institute, Shanghai 201109, China;
    2. Shanghai Key Laboratory of Space Intelligent Control Technology, Shanghai 201109, China;
    3. College of Astronautics, Nanjing University of Aeronautics and Astronautics, Nanjing 211106, China;
    4. College of Automation & Electronic Information, Xiangtan University, Xiangtan 411100, China
  • Received:2020-11-10 Revised:2020-12-03 Published:2021-02-24
  • Supported by:
    National Key Research and Development Program (2016YFB0501003); National Natural Science Foundation of China (61690214, 11972182); Shanghai Scientific Research Program (19511120900, 19YF1420200)

Abstract: To improve the accuracy of pose estimation of long-range non-cooperative targets with slow rotation, a method for relative pose estimation is proposed based on fusion of image super-resolution and visual Simultaneous Localization And Mapping (SLAM). The method mainly includes three steps. First, a gradient guidance Generative Adversarial Network (GAN)-based super-resolution model is utilized to improve the quality of images, so as to obtain more and higher quality feature points. Second, a feature database is constructed to match the current frame with the feature database, so as to improve tracking stability of the rotating target. Thirdly, pose graph optimization is carried out in multiple frames to optimize the joint pose, so as to eliminate the cumulative error and obtain more accurate estimation results. To stablize the training of GAN, an evolutionary algorithm is introduced. To enhance the generalization and robustness of the model, the dataset is obtained by semi-physical simulation. Experimental results show that when the imaging distance is equivalent to 25 m and the target is rotating at 25 (°)/s, our algorithm can realize continuous stable measurement after the images are enhanced by the super-resolution model.

Key words: non-cooperative target, failure rotating satellite, simultaneous localization and mapping (SLAM), relative pose estimation, generative adversarial network (GAN), image super-resolution

CLC Number: