A Minimal Dataset Construction Method Based on Similar Training for Capture Position Recognition of Space Robot

Recognizing capture position for non-cooperative targets is an important component of on-orbit service. Traditional machine learning works could not satisfy the requirements of space mission, which demands universality, accuracy and real-time performance. To meet those requirements, an innovative job based on deep learning called Faster Region-based Convolutional Neural Network (Faster RCNN) is introduced for space robot capture position recognizing. Based on the principle of similar training, a minimal dataset construction trick is proposed in order to solve the problem of fewer training samples in space environment. Firstly, the Deep Neural Network is pre-trained through ImageNet training set. Then, using the trained weights as the initial weight of the network, the network is fine-tuned by 1000 training samples in space environment. Finally, a simulation experiment is designed, and the experimental results indicate that the similar training principle can solve the problem of capture position recognition of non-cooperative targets.

[1]  Huaizu Jiang,et al.  Face Detection with the Faster R-CNN , 2016, 2017 12th IEEE International Conference on Automatic Face & Gesture Recognition (FG 2017).

[2]  Giovanni B. Palmerini,et al.  Adaptive and robust algorithms and tests for visual-based navigation of a space robotic manipulator☆ , 2013 .

[3]  Antonio Morales,et al.  Using Experience for Assessing Grasp Reliability , 2004, Int. J. Humanoid Robotics.

[4]  Leonidas J. Guibas,et al.  Render for CNN: Viewpoint Estimation in Images Using CNNs Trained with Rendered 3D Model Views , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[5]  Ou Ma,et al.  A review of space robotics technologies for on-orbit servicing , 2014 .

[6]  Anis Sahbani,et al.  Handling Objects by Their Handles , 2008 .

[7]  Kate Saenko,et al.  Learning Deep Object Detectors from 3D Models , 2014, 2015 IEEE International Conference on Computer Vision (ICCV).

[8]  Xiao-Feng Liu,et al.  Dynamics modeling and control of a 6-DOF space robot with flexible panels for capturing a free floating target , 2016 .

[9]  丁庆海 Ding Qinghai,et al.  Monocular Vision Pose Measurement Based on Docking Ring Component , 2013 .

[10]  Shimon Edelman,et al.  Learning to grasp using visual information , 1996, Proceedings of IEEE International Conference on Robotics and Automation.

[11]  Kate Saenko,et al.  Exploring Invariances in Deep Convolutional Neural Networks Using Synthetic Images , 2014, ArXiv.

[12]  Gangqi Dong,et al.  Incremental inverse kinematics based vision servo for autonomous robotic capture of non-cooperative space debris , 2016 .

[13]  Tal Hassner,et al.  Age and gender classification using convolutional neural networks , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).

[14]  Panfeng Huang,et al.  A non-cooperative target grasping position prediction model for tethered space robot , 2016 .

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

[16]  Fan Zhang,et al.  Dexterous Tethered Space Robot: Design, Measurement, Control, and Experiment , 2017, IEEE Transactions on Aerospace and Electronic Systems.

[17]  Honglak Lee,et al.  Deep learning for detecting robotic grasps , 2013, Int. J. Robotics Res..

[18]  Yangsheng Xu,et al.  Autonomous rendezvous and robotic capturing of non-cooperative target in space , 2009, Robotica.

[19]  K Zetner,et al.  [The antibacterial effect of composites impregnated with chlorhexidine]. , 1976, ZWR.

[20]  K. Alfriend,et al.  Optimal Servicing of Geosynchronous Satellites , 2002 .

[21]  T. Aaron Gulliver,et al.  A Faster RCNN-Based Pedestrian Detection System , 2016, 2016 IEEE 84th Vehicular Technology Conference (VTC-Fall).

[22]  朱枫,et al.  Pose estimation of non-cooperative spacecraft based on collaboration of space-ground and rectangle feature , 2011 .

[23]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.