Drogue detection for autonomous aerial refueling based on convolutional neural networks  

作　　者：Wang Xufeng Dong Xinmin Kong Xingwei Li Jianmin Zhang Bo 

机构地区：[1]School of Aeronautics and Astronautics Engineering, Air Force Engineering University [2]State Key Laboratory of Intelligent Technology and Systems, Tsinghua National Laboratory for Information Science and Technology, Department of Computer Science and Technology, Tsinghua University

出　　处：《Chinese Journal of Aeronautics》2017年第1期380-390,共11页中国航空学报（英文版）

基　　金：co-supported by the National Basic Research Program of China (Nos. 2012CB316301, 2013CB329403);the National Natural Science Foundation of China (Nos. 61473307, 61304120, 61273023, 61332007)

摘　　要：Drogue detection is a fundamental issue during the close docking phase of autonomous aerial refueling（AAR）. To cope with this issue, a novel and effective method based on deep learning with convolutional neural networks（CNNs） is proposed. In order to ensure its robustness and wide application, a deep learning dataset of images was prepared by utilizing real data of ‘‘Probe and Drogue＂ aerial refueling, which contains diverse drogues in various environmental conditions without artificial features placed on the drogues. By employing deep learning ideas and graphics processing units（GPUs）, a model for drogue detection using a Caffe deep learning framework with CNNs was designed to ensure the method＇s accuracy and real-time performance. Experiments were conducted to demonstrate the effectiveness of the proposed method, and results based on real AAR data compare its performance to other methods, validating the accuracy, speed, and robustness of its drogue detection ability.Drogue detection is a fundamental issue during the close docking phase of autonomous aerial refueling（AAR）. To cope with this issue, a novel and effective method based on deep learning with convolutional neural networks（CNNs） is proposed. In order to ensure its robustness and wide application, a deep learning dataset of images was prepared by utilizing real data of ‘‘Probe and Drogue＂ aerial refueling, which contains diverse drogues in various environmental conditions without artificial features placed on the drogues. By employing deep learning ideas and graphics processing units（GPUs）, a model for drogue detection using a Caffe deep learning framework with CNNs was designed to ensure the method＇s accuracy and real-time performance. Experiments were conducted to demonstrate the effectiveness of the proposed method, and results based on real AAR data compare its performance to other methods, validating the accuracy, speed, and robustness of its drogue detection ability.

关 键 词：Autonomous aerial refueling Computer vision Convolutional neural net-works Deep learning Drogue detection 

分 类 号：V279[航空宇航科学与技术—飞行器设计] TP391.41[自动化与计算机技术—计算机应用技术]