在轨加注是一种典型的在轨服务操作，它对于降低空间运输成本和任务风险起着重要的作用，视觉感知系统可以感知操作任务周围环境并提供给控制系统。目前在轨加注依赖于人，在人员监控下完成或通过遥操作完成，缺乏自主性。本文围绕未来高自主性的基于深度强化学习的在轨加注方法，对基于深度学习的视觉感知方法展开了研究，针对基于深度学习的方法对相似实例的检测存在精确率低、对光照变化敏感等缺点，提出了基于深度图推理的卫星背板部件检测方法。提出的方法可以有效地检测复杂形状的目标，不依赖于手工设计的特征；提高了复杂光照环境下部件的检测正确率；可以有效区分外形相似的不同部件；其有效性在数学仿真和物理仿真中均得到了验证。
On-orbit refueling is a typical on-orbit service operation, and plays an important role in reducing space transportation costs and mission risks. The visual perception system can perceive the surrounding environment of the operation task, and provide the information to the control system. Nowadays, on-orbit refueling relies on human labor, and is done under the supervision of personnel or by remote operation, lacking autonom. Centered around the future high autonomy on-orbit refueling method based on deep reinforcement learning, this paper conducts research on deep learning based visual perception. Because of the problems of low accuracy of detection of similar instances and being sensitive to changes in illumination, deep learning based methods cannot be directly used for on-orbit refueling. A deep graph reasoning method is proposed for satellite component detection in this paper. The proposed method can effectively detect complex-shaped targets without relying on manually-designed features. It can improve the detection accuracy of parts under complex illumination, and effectively distinguish different parts with similar appearances. Its effectiveness has been verified by mathematical simulation and physical simulation.
[1] 解永春, 王勇, 陈奥, 等. 基于学习的空间机器人在轨服务操作技术[J]. 空间控制技术与应用, 2019, 45(4):25-37. XIE Y C, WANG Y, CHEN A, et al. Leaning based on-orbit servicing manipulation technology of space robot[J]. Aerospace Control and Application, 2019, 45(4):25-37(in Chinese).
[2] ROTENBERGER S, SOOHOO D, ABRAHAM G. Orbital express fluid transfer demonstration system[C]//SPIE Defense and Security Symposium. Proc SPIE 6958, Sensors and Systems for Space Applications II, 2008:695808.
[3] NASA's Exploration & In-space Services. Robotic refueling mission[EB/OL]. https://nexis.gsfc.nasa.gov/RRM3.html.
[4] 郝颖明, 付双飞, 范晓鹏, 等. 面向空间机械臂在轨服务操作的视觉感知技术[J]. 无人系统技术, 2018, 1(1):54-65. HAO Y M, FU S F, FAN X P, et al. Vision perception technology for space manipulator on-orbit service operations[J]. Unmanned Systems Technology, 2018, 1(1):54-65(in Chinese).
[5] SCHAAL S, ATKESON C G. Learning control in robotics[J]. IEEE Robotics & Automation Magazine, 2010, 17(2):20-29.
[6] LI P X, ZHAO H C, LIU P F, et al. RTM3D:Real-time monocular 3D detection from object keypoints for autonomous driving[M]//Computer Vision-ECCV 2020. Cham:Springer International Publishing, 2020:644-660.
[7] WANG X B, ZHANG S F, WANG S, et al. Mis-classified vector guided softmax loss for face recognition[J]. Proceedings of the AAAI Conference on Artificial Intelligence, 2020, 34(7):12241-12248.
[8] HE K M, ZHANG X Y, REN S Q, et al. Deep residual learning for image recognition[C]//2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Piscataway:IEEE Press, 2016:770-778.
[9] REN S Q, HE K M, GIRSHICK R, et al. Faster R-CNN:Towards real-time object detection with region proposal networks[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017, 39(6):1137-1149.
[10] HE K M, GKIOXARI G, DOLLAR P, et al. MRCNN[C]//2017 IEEE International Conference on Computer Vision (ICCV). Piscataway:IEEE Press, 2017:2961-2969.
[11] DAI J F, HE K M, SUN J. Instance-aware semantic segmentation via multi-task network cascades[C]//2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Piscataway:IEEE Press, 2016:3150-3158.
[12] SHELHAMER E, LONG J, DARRELL T. Fully convolutional networks for semantic segmentation[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017, 39(4):640-651.
[13] WU L, SUN P J, HONG R C, et al. SocialGCN:An efficient graph convolutional network based model for social recommendation[DB/OL]. arXiv preprint:1811.02815,2018.
[14] WANG H W, ZHAO M, XIE X, et al. Knowledge graph convolutional networks for recommender systems[C]//The World Wide Web Conference on-WWW'19. New York:ACM Press, 2019:3307-3313.
[15] ADAM S, DAVID R, DAVID B et al. Learning annotated hierarchies from relational data[M]//Advances in Neural Information Processing Systems 19. Cambridge:The MIT Press, 2007.
[16] ZHANG Z W, CUI P, ZHU W W. Deep learning on graphs:A survey[J]. IEEE Transactions on Knowledge and Data Engineering, 2020:1-20.
[17] CHEN T S, LIN L, CHEN R Q, et al. Knowledge-embedded representation learning for fine-grained image recognition[C]//Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence. California:International Joint Conferences on Artificial Intelligence Organization, 2018.
[18] MARINO K, SALAKHUTDINOV R, GUPTA A. The more You know:Using knowledge graphs for image classification[C]//2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Piscataway:IEEE Press, 2017:20-28.
[19] CHEN Z M, WEI X S, WANG P, et al. Multi-label image recognition with graph convolutional networks[C]//2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Piscataway:IEEE Press, 2019:5172-5181.
[20] LIU Z, JIANG Z D, FENG W. OD-GCN:Object detection by knowledge graph with GCN[DB/OL]. arXiv preprint:1908.04385, 2019.
[21] CHEN A, XIE Y C, WANG Y, et al. Knowledge graph based satellite component detection method for on-orbit refueling[C]//71st International Astronautical Congress (IAC 2020)-The Cyberspace Edition, 2020.
[22] LIN T Y, DOLLÁR P, GIRSHICK R, et al. Feature pyramid networks for object detection[C]//2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Piscataway:IEEE Press, 2017:936-944.
[23] KIPF T N, WELLING M. Semi-supervised classification with graph convolutional networks[DB/OL]. arXiv preprint:1609.02907, 2016.
CJA