适用于非合作目标捕获的轻量级位姿估计网络

doi:10.19678/j.issn.1000-3428.0060882

摘要/Abstract

摘要： 空间非合作目标的增多导致太空安全受到严重威胁，对非合作目标进行捕获回收具有维护空间安全、节约资源等现实意义。非合作目标捕获回收需要进行位姿估计，而目前在硬件资源有限的航天器平台上，现有的大多数非合作目标位姿估计算法无法同时满足及时性和准确性的要求。设计一种超轻量级目标检测网络YOLO-GhostECA，利用GhostBottleneck网络减少特征图冗余，并使用高效注意力机制提取核心特征图，以降低模型参数，在提升运算速度的同时保证精度水平几乎不下降。根据YOLO-GhostECA网络的检测结果粗略估计姿态，以协助机械臂更加合理地执行智能捕获任务，解决2D识别算法无法检测出物体姿态的问题。在7自由度冗余机械臂上开展的空间非合作目标捕获地面模拟的实验结果表明，与YOLOv5s网络相比，该网络模型大小减小了80.4%，运算复杂度降低了78.9%，而精度基本保持不变，可准确快速地对非合作目标进行位姿估计，能够引导机器人成功捕获非合作物体。

关键词: 非合作目标, 神经网络, 目标检测, 智能捕获, 轻量级, 位姿估计

Abstract: The increase in non-cooperative targets in space has led to a serious threat to space security.Therefore, the capture and recovery of non-cooperative targets have practical significance in maintaining space security and resource-saving.Non-cooperative target acquisition and recovery require pose estimation.On a spacecraft platform with limited hardware resources, most existing non-cooperative target pose estimation algorithms cannot simultaneously meet the requirements of timeliness and accuracy.An ultra-lightweight target detection network YOLO-GhostECA is proposed. The Ghostbottleneck network reduces the redundancy of the feature map, and an efficient attention mechanism extracted the core feature map to reduce the model parameters and ensure that the accuracy level was not compromised while improving the operation speed.Using the detection results of the YOLO-GhostECA network to estimate the attitude to assist the manipulator in a sensibly intelligent acquisition task and solve the problem that the 2D recognition algorithm cannot detect the object attitude.The experimental results of the ground simulation of space non-cooperative target acquisition on a 7-DOF redundant manipulator show that compared with the algorithm based on the YOLOv5s network, the model size was reduced by 80.4%, the computational complexity was reduced by 78.9%, and the accuracy remained constant.It accurately and quickly estimates the pose of non-cooperative targets and guidesthe robot to successfully capture non-cooperative objects.

Key words: non-cooperative target, neural network, target detection, intelligent capture, lightweight, pose estimation

中图分类号:

TP391.41

蒋明, 陈雨, 周青华, 袁媛, 何世琼. 适用于非合作目标捕获的轻量级位姿估计网络[J]. 计算机工程, 2022, 48(6): 235-242.

JIANG Ming, CHEN Yu, ZHOU Qinghua, YUAN Yuan, HE Shiqiong. Lightweight Pose Estimation Network for Non-Cooperative Target Acquisition[J]. Computer Engineering, 2022, 48(6): 235-242.

http://www.ecice06.com/CN/Y2022/V48/I6/235

图/表 13

20220625180102

20220625180106

20220625180110

20220625180113

20220625180116

20220625180121

20220625180124

20220625180128

20220625180132

20220625180136

20220625180140

20220625180144

20220625180148

参考文献

[1] 孙康.空间机械臂抓捕非合作目标的辨识、规划及控制策略研究[D].哈尔滨:哈尔滨工业大学, 2020. SUN K.Research on identification, kinematic planning and control strategy in capture of non-cooperative target by space manipulator[D].Harbin:Harbin Institute of Technology, 2020.(in Chinese)
[2] 梁斌, 杜晓东, 李成, 等.空间机器人非合作航天器在轨服务研究进展[J].机器人, 2012, 34(2):242-256. LIANG B, DU X D, LI C, et al.Advances in space robot on-orbit servicing for non-cooperative spacecraft[J].Robot, 2012, 34(2):242-256.(in Chinese)
[3] KRIZHEVSKY A, SUTSKEVER I, HINTON G E.ImageNet classification with deep convolutional neural networks[J].Communications of the ACM, 2017, 60(6):84-90.
[4] GIRSHICK R, DONAHUE J, DARRELL T, et al.Rich feature hierarchies for accurate object detection and semantic segmentation[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C., USA:IEEE Press, 2014:580-587.
[5] 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.
[6] HE K M, GKIOXARI G, DOLLÁR P, et al.Mask R-CNN[C]//Proceedings of IEEE International Conference on Computer Vision.Washington D.C., USA:IEEE Press, 2017:2980-2988.
[7] REDMON J, DIVVALA S, GIRSHICK R, et al.You only look once:unified, real-time object detection[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C., USA:IEEE Press, 2016:779-788.
[8] LIU W, ANGUELOV D, ERHAN D, et al.SSD:single shot multibox detector[C]//Proceedings of European Conference on Computer Vision.Berlin, Germany:Springer, 2016:21-37.
[9] 刘帅.空间机器人抓捕非合作目标的智能控制与识别[D].大连:大连理工大学, 2019. LIU S.Intelligent control and recognition of space robot capturing non-cooperative targets[D].Dalian:Dalian University of Technology, 2019.(in Chinese)
[10] LI Y W, BO Y M, ZHAO G P.Survey of measurement of position and pose for space non-cooperative target[C]//Proceedings of the 34th Chinese Control Conference.Washington D.C., USA:IEEE Press, 2015:5101-5106.
[11] 余玉琴, 魏国亮, 王永雄.基于改进YOLOv2的无标定3D机械臂自主抓取方法[J].计算机应用研究, 2020, 37(5):1450-1455. YU Y Q, WEI G L, WANG Y X.3D uncalibrated robotic grasping method based on improved YOLOv2[J].Application Research of Computers, 2020, 37(5):1450-1455.(in Chinese)
[12] REDMON J, FARHADI A.YOLO9000:better, faster, stronger[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C., USA:IEEE Press, 2017:6517-6525.
[13] REDMON J, FARHADI A.YOLOv3:an incremental improvement[EB/OL].[2021-01-02].https://arxiv.org/abs/1804.02767.
[14] BOCHKOVSKIY A, WANG C Y, LIAO H Y M.YOLOv4:optimal speed and accuracy of object detection[EB/OL].[2021-01-02].https://arxiv.org/abs/2004.10934.
[15] JOCHER G, STOKEN A, BOROVEC J.Ultralytics yolov5:v3.0(Versionv3.0).[EB/OL].[2021-01-02].https://github.com/ultralytics/yolov5/releases/tag/v3.0.
[16] ZHANG S, WU Y X, MEN C G, et al.Tiny YOLO optimization oriented bus passenger object detection[J].Chinese Journal of Electronics, 2020, 29(1):132-138.
[17] PURKAIT P, ZHAO C, ZACH C.SPP-net:deep absolute pose regression with synthetic views[EB/OL].[2021-01-02].https://arxiv.org/abs/1712.03452.
[18] WANG C Y, MARK LIAO H Y, WU Y H, et al.CSPNet:a new backbone that can enhance learning capability of CNN[C]//Proceedings of IEEE/CVF Conference on Computer Vision and Pattern Recognition.Washington D.C., USA:IEEE Press, 2020:1571-1580.
[19] LIU S, QI L, QIN H F, et al.Path aggregation network for instance segmentation[C]//Proceedings of IEEE/CVF Conference on Computer Vision and Pattern Recognition.Washington D.C., USA:IEEE Press, 2018:8759-8768.
[20] HAN K, WANG Y H, TIAN Q, et al.GhostNet:more features from cheap operations[C]//Proceedings of 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition.Washington D.C., USA:IEEE Press, 2020:1580-1589.
[21] WANG Q L, WU B G, ZHU P F, et al.ECA-net:efficient channel attention for deep convolutional neural networks[C]//Proceedings of IEEE/CVF Conference on Computer Vision and Pattern Recognition.Washington D.C., USA:IEEE Press, 2020:11531-11539.
[22] ZHENG Z H, WANG P, LIU W, et al.Distance-IoU loss:faster and better learning for bounding box regression[J].Proceedings of the AAAI Conference on Artificial Intelligence, 2020, 34(7):12993-13000.
[23] ZHANG Z Y.Flexible camera calibration by viewing a plane from unknown orientations[C]//Proceedings of the 7th IEEE International Conference on Computer Vision.Washington D.C., USA:IEEE Press, 1999:666-673.
[24] TSAI R.A versatile camera calibration technique for high-accuracy 3D machine vision metrology using off-the-shelf TV cameras and lenses[J].IEEE Journal on Robotics and Automation, 1987, 3(4):323-344.

选择文件类型/文献管理软件名称

选择包含的内容