基于形状先验模型的平面型工件抓取位姿检测

doi:10.13973/j.cnki.robot.2017.0099

摘要
图/表
参考文献
相关文章 (15)

全文: PDF (999 KB) HTML ( ) 输出: BibTeX \| EndNote (RIS)
引用本文:
郑晶怡, 李恩, 梁自泽. 基于形状先验模型的平面型工件抓取位姿检测[J]. 机器人, 2017, 39(1): 99-110.DOI: 10.13973/j.cnki.robot.2017.0099. ZHENG Jingyi, LI En, LIANG Zize. Grasping Posture Determination of Planar Workpieces Based on Shape Prior Model. ROBOT, 2017, 39(1): 99-110. DOI: 10.13973/j.cnki.robot.2017.0099.

摘要为了能够在复杂的工业环境中抓取平面型工件，提出一种图割法与形状先验模型结合的工件图像分割方法，并且对工件的位姿信息进行测量．首先，建立先验形状，提出基于最小包围矩形法将工件的形状模板与目标工件人工分割形状进行配准，得到先验形状．为了保证分割结果的准确性，采用单一的先验形状．图割模型中加入了目标形状先验知识．其次，通过自适应调整形状先验项的权重系数，使得图割法的能量函数形状先验项自适应于被分割的图像．第三，本文可以采用形状先验方法分割一幅图像中的多个工件，并且能够计算吸盘的最优抓取位置．最后，采用结构光视觉系统采集工件的点云信息，拟合工件平面，确定工件法向量，得到工件的抓取姿态．实验结果表明，本文算法能够适应遮挡、光照变化的工件图像，同时也能够分割复杂环境中的目标工件；平面型工件抓取位姿的计算结果有效，可以应用于遮挡、反光、复杂干扰背景条件下的工件抓取作业．

	服务

	把本文推荐给朋友
	加入我的书架
	加入引用管理器
	E-mail Alert
	RSS
	作者相关文章
	郑晶怡
	李恩
	梁自泽

关键词 ：工件分割, 形状先验, 抓取位姿, 结构光视觉系统

Abstract：A new shape prior segmentation method based on graph cuts is used to segment workpiece images and measure the workpiece posture for grasping workpieces in cluttered industry scene. Firstly, a prior shape is built. Minimum bounding rectangle method is proposed to register the workpiece shape model and the manual shape of the target workpiece to get the prior shape. In order to ensure the segmentation accuracy, a single prior shape is used. The target shape prior knowledge is added to the graph cut model. Secondly, the weight of the shape prior term is adjusted in a self-adaptive manner, so that the shape prior term of the energy function in graph cut method becomes adaptive to the image to be segmented. Thirdly, multiple workpieces in a image can be segmented by the shape prior method. Meanwhile, the optimal position of suction cup for grasping the workpiece is determined. Finally, the structured light vision system is used to acquire the point cloud of the workpiece. The plane of the workpiece is fitted and the normal vector is determined. Thus, the grasping orientation is obtained. The effectiveness of the proposed approach is demonstrated on the workpiece segmentation in the scene with occlusion, light variation and cluttered background. The posture of the planar workpiece acquired through calculation is accurate, and can be applied to the grasping operation in conditions of occlusion, reflection and complicated background.

Key words： workpiece segmentation shape prior grasp posture structured light vision system

收稿日期: 2016-07-22 录用日期: 2016-12-19

TP24

基金资助:国家863计划（2013AA041002-1）；国家科技支撑计划（2015BAK06B01）；国家自然科学基金（61403372，61403374）

通讯作者: 郑晶怡，jingyi.zheng@ia.ac.cn E-mail: jingyi.zheng@ia.ac.cn

作者简介: 郑晶怡（1987-），女，博士．研究领域：机器人视觉，机器人路径规划．
李恩（1979-），男，博士，研究员．研究领域：机器人系统，传感器技术，嵌入式系统．
梁自泽（1963-），男，硕士，研究员．研究领域：先进机器人，智能控制，传感器网络．

链接本文:

https://robot.sia.cn/CN/10.13973/j.cnki.robot.2017.0099 或 https://robot.sia.cn/CN/Y2017/V39/I1/99

[1] Rother C, Kolmogorov V, Blake A. "GrabCut"——Interactive foreground extraction using iterated graph cuts[J]. ACM Transactions on Graphics, 2004, 23(3):309-314.
[2] Liu X Q, Veksler O, Samarabandu J. Graph cut with ordering constraints on labels and its applications[C]//IEEE Conference on Computer Vision and Pattern Recognition. Piscataway, USA:IEEE, 2008:990-997.
[3] Lempitsky V, Kohli P, Rother C, et al. Image segmentation with a bounding box prior[C]//IEEE International Conference on Computer Vision. Piscataway, USA:IEEE, IEEE, 2009:277-284.
[4] Slabaugh G, Unal G. Graph cuts segmentation using an elliptical shape prior[C]//IEEE International Conference on Image Processing. Piscataway, USA:IEEE, 2005:1222-1225.
[5] Nhat V, Manjunath B S. Shape prior segmentation of multiple objects with graph cuts[C]//IEEE Conference on Computer Vision and Pattern Recognition. Piscataway, USA:IEEE, 2008:840-847.
[6] Kolmogorov V, Zabih R. What energy functions can be minimized via graph cuts?[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2004, 26(2):147-159.
[7] Veksler O. Star shape prior for graph-cut image segmentation[C]//10th European Conference on Computer Vision. Berlin, Germany:Springer, 2008:454-467.
[8] 刘陈,李凤霞,张艳.基于图割与泛形信息的对象分割方法[J].计算机辅助设计与图形学学报,2009,21(12):1753-1760. Liu C, Li F X, Zhang Y. An interactive object cutout algorithm based on graph-cut and generalized shape prior[J]. Journal of Computer-aided Design and Computer Graphics, 2009, 21(12):1753-1760.
[9] 朗咸鹏,朱枫.基于图割的矩形目标交互式分割方法[J].计算机应用研究,2010,27(11):4369-4372,4378. Lang X P, Zhu F. Interactive segmentation of rectangle object via graph cut[J]. Application Research of Computers, 2010, 27(11):4369-4372,4378.
[10] Blake A, Kohli P, Rother C. Markov random fields for vision and image processing[M]. Cambridge, USA:MIT Press, 2011.
[11] Oh J K, Baek K K, Kim D, et al. Development of structured light based bin-picking system using primitive models[M]//Frontiers of Assembly and Manufacturing. Berlin, Germany:Springer, 2010:141-155.
[12] Hema C R, Paulraj M P, Nagarajan R. Object localization using stereo sensors for adept SCARA robot[C]//IEEE Conference on Robotics, Automation and Mechatronics. Piscataway, USA:IEEE, 2006:517-521.
[13] 陈伯豪.基于机器视觉的二维复杂轮廓加工对象在线检测系统研究[D].广州:广东工业大学,2014. Chen B H. Online testing system research of two-dimensional complex contour processing object based on machine vision[D]. Guangzhou:Guangdong University of Technology, 2014.
[14] 管经纬.基于机器视觉的工件自动分拣系统研究[D].上海:东华大学,2015. Guan J W. The research on automatic workpiece sorting system based on machine vision[D]. Shanghai:Donghua University, 2015.
[15] 王红涛.基于视觉的工业机器人目标识别定位方法的研究[D].西安:西安理工大学,2007. Wang H T. Research on target recognition and location of industrial robot based on computer vision[D]. Xi'an:Xi'an University of Technology, 2007.
[16] 朱海波.基于视觉引导的工业机器人工件搬运技术研究[D].沈阳:沈阳工业大学,2013. Zhu H B. Research of industrial robot workpiece handling technology based on visual guidance[D]. Shenyang:Shenyang University of Technology, 2013.
[17] 傅卫平,秦川,刘佳,等.基于SIFT算法的图像目标匹配与定位[J].仪器仪表学报,2011,32(1):163-169. Fu W P, Qin C, Liu J, et al. Matching and location of image object based on SIFT algorithm[J]. Chinese Journal of Scientific Instrument, 2011, 32(1):163-169.
[18] 佐立营.面向机器人抓取的散乱零件自动识别与定位技术研究[D].哈尔滨:哈尔滨工业大学,2015. Zuo L Y. Research on automatic identification and location of scattered parts for robot bin-picking[D]. Harbin:Harbin Institute of Technology, 2015.
[19] 黄红艳,杨煌普.基于高阶神经网络的机械零件形状识别[J].上海交通大学学报,2001,35(8):1144-1147.Huang H Y, Yang Y P. Shape recognition of machined parts based on higher order neural network[J]. Journal of Shanghai Jiaotong University, 2001, 35(8):1144-1147.
[20] 查英,刘铁根,杜东.图像识别技术在零件装配自动识别中的应用[J].计算机工程,2006,32(10):178-179,185.Zha Y, Liu T G, Du D. Application of image recognition in automatic recognition system for part assembling[J]. Computer Engineering, 2006, 32(10):179-179,185.
[21] 王修岩,程婷婷.基于单目视觉的工业机器人智能抓取研究[J].机械设计与制造,2011(5):135-136.Wang X Y, Cheng T T. Research on industrial robot intelligent grasp based on monocular vision[J]. Machinery Design & Manufacture, 2011(5):135-136.
[22] Jia Y B, Guo F, Lin H. Grasping deformable planar objects:Squeeze, stick/slip analysis, and energy-based optimalities[J]. International Journal of Robotics Research, 2014, 33(6):866-897.
[23] Seo J, Kim S, Kumar V. Planar, bimanual, whole-arm grasping[C]//IEEE International Conference on Robotics and Automation. Piscataway, USA:IEEE, 2012:3271-3277.
[24] Yu Z, Gu J. Optimized planar grasping synthesis algorithm for multi-fingered robotic hand[C]//IEEE International Conference on Automation and Logistics. Piscataway, USA:IEEE, 2009:1052-1057.
[25] 徐德,谭民,李原.机器人视觉测量与控制[M].2版.北京:国防工业出版社,2010:51-56. Xu D, Tan M, Li Y. Visual measurement and control for robots[M]. 2nd ed. Beijing:National Defense Industry Press, 2010:51-56.
[26] 吕震.反求工程CAD建模中的特征技术研究[D].杭州:浙江大学,2012. Lü Z. Study on feature technology in reverse engineering CAD modeling[D]. Hangzhou:Zhejiang University, 2012.