留言板

尊敬的读者、作者、审稿人, 关于本刊的投稿、审稿、编辑和出版的任何问题, 您可以本页添加留言。我们将尽快给您答复。谢谢您的支持!

姓名
邮箱
手机号码
标题
留言内容
验证码

基于全局稀疏地图的AGV视觉定位技术

张浩悦 程晓琦 刘畅 孙军华

张浩悦, 程晓琦, 刘畅, 等 . 基于全局稀疏地图的AGV视觉定位技术[J]. 北京航空航天大学学报, 2019, 45(1): 218-226. doi: 10.13700/j.bh.1001-5965.2018.0272
引用本文: 张浩悦, 程晓琦, 刘畅, 等 . 基于全局稀疏地图的AGV视觉定位技术[J]. 北京航空航天大学学报, 2019, 45(1): 218-226. doi: 10.13700/j.bh.1001-5965.2018.0272
ZHANG Haoyue, CHENG Xiaoqi, LIU Chang, et al. Visual localization technology of AGV based on global sparse map[J]. Journal of Beijing University of Aeronautics and Astronautics, 2019, 45(1): 218-226. doi: 10.13700/j.bh.1001-5965.2018.0272(in Chinese)
Citation: ZHANG Haoyue, CHENG Xiaoqi, LIU Chang, et al. Visual localization technology of AGV based on global sparse map[J]. Journal of Beijing University of Aeronautics and Astronautics, 2019, 45(1): 218-226. doi: 10.13700/j.bh.1001-5965.2018.0272(in Chinese)

基于全局稀疏地图的AGV视觉定位技术

doi: 10.13700/j.bh.1001-5965.2018.0272
详细信息
    作者简介:

    张浩悦  男, 硕士研究生。主要研究方向:机器视觉、三维重建

    孙军华  男, 博士, 教授, 博士生导师。主要研究方向:机器视觉、精密视觉测量

    通讯作者:

    孙军华, E-mail: sjh@buaa.edu.cn

  • 中图分类号: V249.325;TP242.2

Visual localization technology of AGV based on global sparse map

More Information
  • 摘要:

    为了实现自动导引车(AGV)在复杂工业环境下的高精度定位,克服环境变化给定位带来的影响,提出了基于全局稀疏地图的视觉定位方法。首先,设计了大容量二维编码点,作为人工路标铺设在工业环境的地面;然后,基于一种四边形识别算法,在复杂工业环境中准确分割和识别二维编码点;最后,利用二维编码点提供的编码信息,鲁棒匹配图像中的特征点,并以此为基础,使用一种分参数块优化的三维重建策略,实现了工业环境的大规模地图构建,为AGV视觉定位提供了一种稀疏电子地图。AGV视觉的定位通过匹配车载视觉传感器图像中的特征点和稀疏电子地图实现。停车重复定位精度小于0.5 mm,角度偏差小于0.5°,轨迹平均位移误差小于0.1%。实际应用结果表明,该方法能在复杂工业环境中实现AGV视觉的定位,定位的速度和精度方面都满足工业应用的要求,为AGV的视觉定位提供了新的思路。

     

  • 图 1  编码点

    Figure 1.  Coded points

    图 2  二维编码点的检测和识别

    Figure 2.  Detection and recognition of two-dimensional coded points

    图 3  全局稀疏地图重建流程图

    Figure 3.  Flowchart of global sparse map reconstruction

    图 4  坐标系转换关系

    Figure 4.  Transformation relationship of coordinate system

    图 5  用于重构的原始图像

    Figure 5.  Original image for reconstruction

    图 6  用于定位的稀疏地图

    Figure 6.  Sparse map for localization

    图 7  测量值和重建值结果的对比

    Figure 7.  Comparison of measurement and reconstruction results

    图 8  搭载视觉定位系统的AGV

    Figure 8.  AGV equipped with visual localization system

    图 9  静态定位实验

    Figure 9.  Experiment of static localization

    图 10  行驶轨迹

    Figure 10.  Travelling trajectory

    表  1  二维编码点边长重构统计结果

    Table  1.   Statistical results of two-dimensional code side length reconstitution

    mm
    参数 平均值 平均误差 标准差
    数值 27.98 0.05 0.08
    下载: 导出CSV

    表  2  动态定位结果

    Table  2.   Result of dynamic localization

    车位 测量次数 x坐标/mm y坐标/mm 角度/(°)
    B201 1 31 814.1 13 511.2 89.4
    2 31 813.9 13 512.1 89.5
    3 31 814.0 13 512.0 89.6
    4 31 813.9 13 511.8 90.3
    5 31 814.0 13 511.7 89.4
    6 31 813.8 13 511.9 89.9
    7 31 814.1 13 512.0 89.8
    8 31 813.9 13 511.9 89.8
    9 31 813.9 13 511.8 89.6
    10 31 813.7 13 511.8 89.6
    B104 1 34 600.7 1 154.9 270.5
    2 34 600.7 1 154.9 270.3
    3 34 601.6 1 155.3 270.5
    4 34 601.7 1 155.2 270.8
    5 34 601.3 1 155.4 271.1
    6 34 601.7 1 155.2 270.3
    7 34 601.5 1 154.9 270.8
    8 34 600.9 1 154.8 270.8
    9 34 600.9 1 154.7 270.7
    10 34 600.8 1 155.1 271.2
    下载: 导出CSV

    表  3  定位轨迹的误差

    Table  3.   Error of localization trajectory

    %
    比较次数 位移误差 平均位移误差
    1 0.071 0.082
    2 0.084
    3 0.082
    4 0.087
    5 0.082
    6 0.084
    下载: 导出CSV
  • [1] 张建鹏, 楼佩煌, 钱晓明, 等.多窗口实时测距的视觉导引AGV精确定位技术研究[J].仪器仪表学报, 2016, 37(6):1356-1365. doi: 10.3969/j.issn.0254-3087.2016.06.020

    ZHANG J P, LOU P H, QIAN X M, et al.Research on precise positioning technology by multi-window and real-time measurement for visual navigation AGV[J].Chinese Journal of Scientific Instrument, 2016, 37(6):1356-1365(in Chinese). doi: 10.3969/j.issn.0254-3087.2016.06.020
    [2] KIM J, CHUNG W.Localization of a mobile robot using a laser range finder in a glass-walled environment[J].IEEE Transactions on Industrial Electronics, 2016, 63(6):3616-3627. doi: 10.1109/TIE.2016.2523460
    [3] CESAR C, LUCA C, HENRY C, et al.Past, present, and future of simultaneous localization and mapping:Toward the robust-perception age[J].IEEE Transactions on Robotics, 2016, 32(6):1309-1332. doi: 10.1109/TRO.2016.2624754
    [4] RUBLEE E, RABAUD V, KONOLIG K, et al.ORB: An efficient alternative to SIFT or SURF[C]//International Conference on Computer Vision.Piscataway, NJ: IEEE Press, 2012: 2564-2571. https://www.researchgate.net/publication/221111151_ORB_an_efficient_alternative_to_SIFT_or_SURF
    [5] LOWE D G.Distinctive image features from scale-invariant keypoints[J].International Journal of Computer Vision, 2004, 60(2):91-110. doi: 10.1023/B:VISI.0000029664.99615.94
    [6] LU Y, SONG D.Visual navigation using heterogeneous landmarks and unsupervised geometric constraints[J].IEEE Transactions on Robotics, 2017, 31(3):736-749. http://d.old.wanfangdata.com.cn/NSTLQK/NSTL_QKJJ0234911156/
    [7] ROLAND S, ILLAH R N, DAVIDE S, et al.Introduction to sutonomous mobile robots[M].Cambridge:MIT Press, 2010:345-346.
    [8] 曹天扬, 蔡元浩, 东方明, 等.结合图像内容匹配的机器人视觉导航定位与全局地图构建系统[J].光学精密工程, 2017, 25(8):2222-2232. http://d.old.wanfangdata.com.cn/Periodical/gxjmgc201708030

    CAO T Y, CAI Y H, DONG F M, et al.Robot vision system for keyframe global map establishment and robot localization based on graphic content mathing[J].Optics and Precision Engineering, 2017, 25(8):2222-2232(in Chinese). http://d.old.wanfangdata.com.cn/Periodical/gxjmgc201708030
    [9] WULF O, LECKING D, WAGNER B.Robust self-localization in industrial environments based on 3D ceiling structures[C]//IEEE/RSJ International Conference on Intelligent Robots and Systems.Piscataway, NJ: IEEE Press, 2007: 1530-1534. https://www.researchgate.net/publication/224685066_Robust_Self-Localization_in_Industrial_Environments_Based_on_3D_Ceiling_Structures
    [10] DAVIDE R, ROBERTO O, CRISTIAN S, et al.AGV global localization using indistinguishable artificial landmarks[C]//IEEE International Conference on Robotics and Automation.Piscataway, NJ: IEEE Press, 2011: 287-292. https://www.researchgate.net/publication/221076429_AGV_global_localization_using_indistinguishable_artificial_landmarks
    [11] 杨剑, 韩建栋, 秦品乐.视觉测量中可纠错的编码点识别及提取[J].光学精密工程, 2012, 20(10):2293-2299. http://d.old.wanfangdata.com.cn/Periodical/gxjmgc201210024

    YANG J, HAN J D, QIN P L.Correcting error on recognition of coded points for photogrammetry[J].Optics and Precision Engineering, 2012, 20(10):2293-2299(in Chinese). http://d.old.wanfangdata.com.cn/Periodical/gxjmgc201210024
    [12] 段康容, 刘先勇.摄影测量中编码标记点检测算法研究[J].传感器与微系统, 2010, 29(8):74-77. doi: 10.3969/j.issn.1000-9787.2010.08.024

    DUAN K R, LIU X Y.Detection algorithm on circular encoded point in photogrammetry[J].Transducer and Microsystem Technologies, 2010, 29(8):74-77(in Chinese). doi: 10.3969/j.issn.1000-9787.2010.08.024
    [13] CANNY J.A computational approach to edge detection[J].IEEE Transactions on Pattern Analysis and Machine Intelligence, 1986, PAMI-8(6):679-698. doi: 10.1109/TPAMI.1986.4767851
    [14] HARRIS C, STEPHENS M.A combined corner and edge detector[C]//Proceedings of the 4th Alvey Vision Conference, 1988: 147-151.
    [15] ANDERSON K R.A reevaluation of an efficient algorithm for determining the convex hull of a finite planar set[J].Information Processing Letters, 1978, 7(1):53-55. doi: 10.1016/0020-0190(78)90041-8
    [16] RICHARD H, ANDREW Z.Multiple view geometry in computer vision[M].Cambridge:Cambridge University Press, 2004:159-173.
    [17] ANDREAS G, PHILIP L, RAQUEL U.Are we ready for autonomous driving The KITTI vision benchmark suite[C]//2012 IEEE Conference on Computer Vision and Pattern Recognition.Piscataway, NJ: IEEE Press, 2012: 3354-3361. https://www.researchgate.net/publication/261861888_Are_we_ready_for_autonomous_driving_The_KITTI_vision_benchmark_suite
  • 加载中
图(10) / 表(3)
计量
  • 文章访问数:  477
  • HTML全文浏览量:  3
  • PDF下载量:  514
  • 被引次数: 0
出版历程
  • 收稿日期:  2018-05-15
  • 录用日期:  2018-08-10
  • 刊出日期:  2019-01-20

目录

    /

    返回文章
    返回
    常见问答