Autonomous aerial refueling technology is of great significance for improving the endurance of UAVs, expanding the combat radius, increasing the weight of the payload, and enhancing strategic deployment et al. It is an essential technology for future intelligent clustering UAV systems. In this paper, we studied the related aerial simulation docking technologies and strategies of the fixed-wing clustering UAVs for the Simulation Docking Race of UAV Challenge Competition. First, we designed the aerial simulation Docking pipeline of the clustering UAVs to deal with their fast speed, high formation density. The shortest time pursuit scheme based on Dubins path was also designed, and the nonlinear guidance law was used for route tracking. Second, we designed a set of weak classifiers to classify the target based on the prior information of the simulation drogue and accelerated the detection process by cascading these classifiers. Third, for the precise docking stage, we designed a strategy for precise docking along the course angle and computed the visual guidance parameters by integrating the attitudes prior of UAV and the size of the simulation drogue. Moreover, we designed a corresponding fixed-wing clustering UAVs system and participated the 2021 Simulation Docking Race of UAV Challenge Competition in a formation of 4 UAVs. Results demonstrated the feasibility and reliability of the pro-posed fixed-wing clustering UAVs system and simulation docking technologies.
[1] 刘多能. 固定翼无人机动态滑翔机理与航迹优化研究[D]. 长沙: 国防科学技术大学, 2016: 1?5.
Liu Duoneng. Research on Mechanism and Trajectory Optimization for Dynamic Soaring with Fiexed-wing Unmanned Aerial Vehicles [D]. Changsha: National University of Defense Technology, 2016: 1?5 (in Chi-nese).
[2] 钟德星, 李永强, 李严桵. 无人机自主空中加油技术现状及趋势[J]. 航空科学技术, 2014, 25(5): 1?6.
Zhong Dexing, Li Yongqiang, Li Yanrui. State-of-the-art and tendency of autonomous aerial refueling tech-nologies for unmanned aerial vehicles[J]. Aeronautical Science & Technology, 2014, 25(5): 1?6 (in Chinese).
[3] 马跃博. 基于卷积神经网络的自主空中加油识别测量技术研究[D]. 成都: 中国科学院光电技术研究所, 2020: 1?14.
Ma Yuebo. Research on Autonomous Aerial Refueling Recognition and Measureament Technology Based on Convolutional Neural Network[D]. Chengdu: Univer-sity of Chinese Academy of Sciences, 2020: 1?14 (in Chinese).
[4] Song X Q, Hu S Q. 2D Path Planning with Dubins-Path-Based A* Algorithm for a Fixed-wing UAV[C]// 2017 IEEE 3rd International Conference on Control Science and Systems Engineering, 2017, 69-73.
[5] Bares P, Lazarus S, Tsourdos A, et al. Adaptive guid-ance for UAV based on Dubins path[C]// Guidance, Navigation, and control and Co-located Conferences, Boston, MA, 2013, 19-22.
[6] Burns B, Blue P, Zollars M. Autonomous control for automated aerial refueling with minimum-time ren-dezvous[C]// AIAA Guidance, Navigation and Control Conference and Exhibit, 2007: 6739.
[7] Wilson D B, Soto M A T, G?kto?an A H, et al. Real-time rencezvous point selection for a nonholonomic vehicle[C]// 2013 IEEE International Conference on Robotics and Automation, 2013, 3941-3946.
[8] 龚全铨, 袁锁中, 张进. 基于Dubins路径的空中加油自主会合制导与控制[J]. 哈尔滨工程大学学报, 2016, 37(8): 1081-1088.
Gong Q Q, Yuan S H, Zhang J. Guidance and control of autonomous rendezvous in aerial refueling based on Dubins path planning[J]. Journal of Harbin Engi-neering University, 2016, 37(8): 1081-1088 (in Chi-nese).
[9] Guelman M. A qualitative study of proportional navi-gation[J]. IEEE Trans Aerosp Electron Syst, 1971, 7(4): 337-343.
[10] Austin L.Smith. Proportional Navigation with Adap-tive Terminal Guidance for Aircraft Rendezvous[J]. Journal of Guidance, Control, AND Dynamics, 2008, 31(6): 1832-1835.
[11] Park S, Deyst J, How J. A new nonlinear guidance logic for trajectory tracking[C]// AIAA guidance, nav-igation, and control conference and exhibit, 2004: 4900.
[12] Viola P, Jones M. Rapid Object Detection Using a Boosted Cascade of Simple Features[C]// Proceedings of the 2001 IEEE Computer Society Conference on Com-puter Vision and Pattern Recognition, 2001, pp. 1?1.
[13] Felzenszwalb P, Mcallester D, Ramanan D. A Discri-mi-natively Trained, Multiscale, Deformable Part Model [C]// Proceedings of the IEEE Computer Socie-ty Con-ference on Computer Vision &Pattern Recogni-tion. 2008, 8: 1?8.
[14] Liu W, Anguelov D, Erhan D, et al. SSD: Single Shot MultiBox Detector[C]// Proceedings of the European Conference on Computer Vision, Springer, Cham, 2016, 21?37.
[15] Bochkovskiy A, Wang C Y, Liao H. YOLOv4: Optimal Speed and Accuracy of Object Detection. arXiv pre-print arXiv:2004.10934, 2020.
[16] R. Girshick, J. Donahue, T. Darrell and J. Malik. Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation[C]// Proceedings of the Com-put-er Vision and Pattern Recognition, IEEE, 2014, 580?587.
[17] He K, Zhang X, Ren S, et al. Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recogni-tion[J]. IEEE Transactions on Pattern Analysis and Ma-chine Intelligence, 2015, 37(9): 1904?16.
[18] Ren S, He K, Girshick R, et al. Faster R-CNN: To-wards Real-Time ObjectDetection with Region Pro-posal Net-works[J]. IEEE Transactions on Pattern Analysis & Ma-chine Intelligence, 2017, 39(6): 1137?1149.
[19] Lin T Y, Dollar P, Girshick R, et al. Feature Pyramid Networks for Object Detection[C]// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2017, pp. 936?944.
[20] Law H, Deng J. CornerNet: Detecting Objects as Paired Keypoints[J]. International Journal of Computer Vision, 2020, 128(3): 642?656.
[21] K. Duan, S. Bai, L. Xie, H. Qi, Q. Huang and Q. Tian. CenterNet: Keypoint Triplets for Object Detection[C]// Proceedings of the 2019 IEEE/CVF International Con-ference on Computer Vision (ICCV), 2019, pp. 6568?6577.
[22] Z. Tian, C. Shen, H. Chen and T. He. FCOS: Fully Convolutional One-Stage Object Detection[C]// Pro-ceed-ings of the 2019 IEEE/CVF International Confer-ence on Computer Vision (ICCV), 2019, pp. 9626?9635.
[23] N. Carion, F. Massa, G. Synnaeve, N. Usunier, A. Kiril-lov and S. Zagoruyko. End-to-End Object Detection with Transformers. arXiv preprint arXiv:2005.12872, 2020.
[24] Michele Fornaciari, Andrea Prati, Rita Cucchiara. A fast and effective ellipse detector for embedded vision applications[J]. Pattern Recognition, 2014, 47(11): 3693?3708.
[25] C. Meng, Z. Li, X. Bai and F. Zhou. Arc Adjacency Matrix-Based Fast Ellipse Detection[J]. IEEE Transac-tions on Image Processing, 2020, 29: 4406?4420.
[26] Chen Q., Wu H., Wada T. Camera Calibration with Two Arbitrary Coplanar Circles[C]// In: Proceedings of the 2004 European Conference on Computer Vision (ECCV), Lecture Notes in Computer Science, 2004, 3023: 521?532.
[27] Paul Furgale, Jér?me Maye and J?rn Rehder. visual-inertial calibration toolbox Kalibr, available: https://github.com/ethz-asl/kalibr.
CJA