Convolutional neural network-based spacecraft attitude control for docking port alignment

This paper proposes the spacecraft attitude control algorithm based on Convolutional Neural Networks (CNNs) for spacecraft's docking port alignment. the CNN model is used in order to recognize the attitude of target spacecraft and the attitude controller aligns the docking port of the target spacecraft using the target spacecraft's attitude information obtained from CNN. Three-Dimensional spacecraft simulator is developed for training CNN model and testing the algorithm. Experiments are conducted for demonstrating the target spacecraft's attitude recognition and attitude control performances of the proposed algorithm.

[1]  Howard D. Curtis,et al.  Orbital Mechanics for Engineering Students , 2005 .

[2]  Shai Segal,et al.  Vision-based relative state estimation of non-cooperative spacecraft under modeling uncertainty , 2011, 2011 Aerospace Conference.

[3]  Fei-Fei Li,et al.  Large-Scale Video Classification with Convolutional Neural Networks , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[4]  Christopher G. Harris,et al.  A Combined Corner and Edge Detector , 1988, Alvey Vision Conference.

[5]  Douglas J. Zimpfer,et al.  Autonomous Rendezvous, Capture and In-Space Assembly: Past, Present and Future , 2005 .

[6]  Andrew Zisserman,et al.  Return of the Devil in the Details: Delving Deep into Convolutional Nets , 2014, BMVC.

[7]  Steve Ulrich,et al.  Spacecraft Pose Estimation using Principal Component Analysis and a Monocular Camera , 2017 .

[8]  Yoshua Bengio,et al.  Gradient-based learning applied to document recognition , 1998, Proc. IEEE.

[9]  David K. Geller.  Orbital Rendezvous: When is Autonomy Required? , 2007 .

[10]  Zhi Li,et al.  Autonomous rendezvous and docking of an unknown tumbling space target with a monocular camera , 2014, Proceedings of 2014 IEEE Chinese Guidance, Navigation and Control Conference.

[11]  John L. Junkins,et al.  Vision based navigation system for autonomous proximity operations: an experimental and analytical study , 2004 .

[12]  Raja J. Chari.  Autonomous Orbital Rendevous Using Angles-Only Navigation , 2001 .

[13]  Luc Van Gool,et al.  Speeded-Up Robust Features (SURF) , 2008, Comput. Vis. Image Underst..

[14]  John L. Junkins,et al.  " Vision-Based Navigation for Rendezvous , Docking and Proximity Operation " , 1999 .

[15]  Alessio Grompone,et al.  Vision-Based 3D Motion Estimation for On-Orbit Proximity Satellite Tracking and Navigation , 2015 .

[16]  Patricio A. Vela,et al.  Cooperative Relative Navigation for Space Rendezvous and Proximity Operations using Controlled Active Vision , 2016, J. Field Robotics.