Please wait a minute...
浙江大学学报(工学版)
浙江大学学报(工学版)  2021, Vol. 55 Issue (1): 145-152    DOI: 10.3785/j.issn.1008-973X.2021.01.017
机械工程     
基于机器视觉的机器人装配位姿在线校正算法
董大钊1,2(),徐冠华1,4,*(),高继良3,徐月同1,傅建中1
1. 浙江大学 浙江省三维打印工艺与装备重点实验室，流体动力与机电系统国家重点实验室，浙江 杭州 310027
2. 浙江大学 工程师学院，浙江 杭州 310027
3. 苏州新智机电科技有限公司，江苏 苏州 215101
4. 苏州紫金港智能制造装备有限公司，江苏 昆山 215300
Online correction algorithm for posture by robot assembly based on machine vision
Da-zhao DONG1,2(),Guan-hua XU1,4,*(),Ji-liang GAO3,Yue-tong XU1,Jian-zhong FU1
1. Key Laboratory of 3D Printing Process and Equipment of Zhejiang Province, State Key Laboratory of Fluid Power and Mechatronic Systems, Zhejiang University, Hangzhou 310027, China
2. Polytechnic Institute, Zhejiang University, Hangzhou 310027, China
3. Suzhou Xinzhi Mechatronics Technology Limited Company, Suzhou 215101, China
4. Suzhou Zijingang Intelligent Manufacturing Equipment Limited Company, Kunshan 215300, China
 全文: PDF(1857 KB)   HTML
摘要：

为了解决柔性夹具夹取异形零件过程中工件与夹具相对位置具有不确定性的难题，提出基于机器视觉的机器人装配位姿在线校正算法. 通过图像预处理及零件表面特征提取，建立工件位姿向量. 通过系统建模、误差分析及函数拟合，将工件位姿校正量分解为原始位姿差、旋转引入位姿差及残余位姿差三部分，将三部分位姿差进行线性组合作为零件位姿误差补偿量反馈给机器人，以引导机器人完成装配. 为了验证算法的有效性，以涡旋式汽车空调压缩机动盘装配为例，设计机器人手眼装配系统进行实验. 实验结果表明，该系统能够保证校正后的零件位姿与目标位姿角度偏差和x及y方向位置偏差分别小于0.6°和0.6 mm，平均装配时间小于20 s，实验过程中装配成功率达到99.67%.
关键词： 工业机器人;  自动装配;  视觉引导;  位姿检测;  误差分析;  姿态校正    
Abstract:

A robot assembly posture online correction algorithm based on machine vision was proposed in order to solve the problem that the relative position between the workpiece and fixture was uncertain in the process of clamping special-shaped parts with flexible fixture. A workpiece pose vector was established by image preprocessing and surface feature extracting. The correction of posture was decomposed into the original posture error, the posture error introduced by rotation and the residual posture error by system modeling, error analysis and function fitting. Linear combination of these three corrections was fed back to the robot as an error compensation for the posture error of the workpiece in order to guide the robot to complete the assembly task. Experiment was conducted by taking the assembly process for the rotating scroll of automotive aircon scroll compressor, and a robot hand-eye assembly system was established in order to verify the effectiveness of the method. The experimental results showed that the angular deviation and the displacement deviation in the x and y directions between the corrected posture and target posture were less than 0.6 degrees and 0.6 mm, respectively. The average assembly time was less than 20 seconds, and the assembly success rate in the experiment was 99.67%.
Key words: industrial robot    automatic assembly    vision-guided    pose detection    error analysis    posture correction
收稿日期: 2020-06-17 出版日期: 2021-01-05
CLC:  TP 242  
基金资助: 国家自然科学青年基金资助项目（51805477）
通讯作者: 徐冠华     E-mail: dazhao_dong@163.com;xgh_zju@163.com
作者简介: 董大钊（1996—），男，硕士生，从事图像处理及机器人自动化应用的研究.orcid.org/0000-0002-0385-199X. E-mail： dazhao_dong@163.com
服务　　
把本文推荐给朋友
加入引用管理器
E-mail Alert
作者相关文章　　
董大钊
徐冠华
高继良
徐月同
傅建中

引用本文:

董大钊,徐冠华,高继良,徐月同,傅建中. 基于机器视觉的机器人装配位姿在线校正算法[J]. 浙江大学学报(工学版), 2021, 55(1): 145-152.

Da-zhao DONG,Guan-hua XU,Ji-liang GAO,Yue-tong XU,Jian-zhong FU. Online correction algorithm for posture by robot assembly based on machine vision. Journal of ZheJiang University (Engineering Science), 2021, 55(1): 145-152.

链接本文:

http://www.zjujournals.com/eng/CN/10.3785/j.issn.1008-973X.2021.01.017    或    http://www.zjujournals.com/eng/CN/Y2021/V55/I1/145

图 1  零件及装配示意图
图 2  手眼装配系统模型图
图 3  图像处理流程图
图 4  动盘表面特征图
图 5  手眼系统坐标关系图
图 6  旋转引入位姿差模型
$\Delta ^{{\rm{b}}}x$ $\Delta ^{ {\rm{b} } }{{y} }$ ${k_1}$ ${k_2}$
$\Delta ^{{\rm{b}}}x\geqslant 0$ $\Delta ^{ {\rm{b} } }{{y} }\geqslant 0$ 0 1
$\Delta ^{{\rm{b}}}x\geqslant 0$ $\Delta ^{ {\rm{b} } }{{y} } < 0$ 2 ?1
$\Delta ^{{\rm{b}}}x < 0$ $\Delta ^{ {\rm{b} } }{{y} }\geqslant 0$ 1 ?1
$\Delta ^{{\rm{b}}}x < 0$ $\Delta ^{ {\rm{b} } }{{y} } < 0$ 1 1
表 1   ${k}_{1}{\text{、}}{k}_{2}$的取值表
图 8  位姿校正算法流程图
图 7  旋转中心误差模型
图 9  手眼装配系统实例图
图 10  残余位姿差角度分量的测量结果
图 11  残余位姿差位置分量的测量结果
图 12   $\Delta {x_3}$随校正角度变化关系拟合结果
图 13   $\Delta {y_3}$随校正角度变化关系拟合结果
项目 ${a_i}$ ${b_i}$ ${\omega _i}$ ${c_i}$
拟合 $\Delta {x}_{3}(i=0)$ 1.161 ?0.3529 0.01923 0.2911
拟合 $\Delta { {{y} } }_{3}(i=1)$ 1.246 0.2909 0.02011 ?1.155
表 2  函数参数表
图 14  位置误差拟合标准化残差图
图 15  装配系统位置误差图
1 QIAN F Smart and optimal manufacturing: the key for the transformation and development of the process industry[J]. Engineering, 2017, 3 (2): 151
doi: 10.1016/J.ENG.2017.02.016
2 FELDMANN K, SLAMA S Highly flexible assembly–scope and justification[J]. CIRP Annals-Manufacturing Technology, 2001, 50 (2): 489- 498
doi: 10.1016/S0007-8506(07)62987-4
3 王田苗, 陶永 我国工业机器人技术现状与产业化发展战略[J]. 机械工程学报, 2014, 50 (9): 1- 13
WANG Tian-miao, TAO Yong Research status and industrialization development strategy of Chinese industrial robot[J]. Journal of Mechanical Engineering, 2014, 50 (9): 1- 13
doi: 10.3901/JME.2014.09.001
4 BONG G M, CAPSON D Vision-guided fixtureless assembly of automotive components[J]. Robotics and Computer-Integrated Manufacturing, 2003, 19 (1/2): 79- 87
5 JIANG J, HUANG Z, BI Z, et al State-of-the-art control strategies for robotic PiH assembly[J]. Robotics and Computer-Integrated Manufacturing, 2020, 65: 101894
doi: 10.1016/j.rcim.2019.101894
6 PAGANO S, RUSSO R, SAVINO S A vision guided robotic system for flexible gluing process in the footwear industry[J]. Robotics and Computer-Integrated Manufacturing, 2020, 65: 101965
doi: 10.1016/j.rcim.2020.101965
7 GOLNABI H, ASADPOUR A Design and application of industrial machine vision systems[J]. Robotics and Computer Integrated Manufacturing, 2007, 23 (6): 630- 637
doi: 10.1016/j.rcim.2007.02.005
8 CHANG W C Robotic assembly of Smartphone back shells with eye-in-hand visual servoing[J]. Robotics and Computer-Integrated Manufacturing, 2017, 50: 102- 113
9 WANG W Q, LOU Y, YANG K, et al. Multi-angle automotive fuse box detection and assembly method based on machine vision[J]. Measurement, 2019, 145: 234- 243
doi: 10.1016/j.measurement.2019.05.100
10 SEMIM R C, ROSSO R S U, SILVA A G, et al Engine head blocks handling robot guided by vision system[J]. IFAC Proceedings Volumes, 2012, 45 (6): 859- 864
doi: 10.3182/20120523-3-RO-2023.00244
11 BORANGIU T, IVANESCU N A, BARAD S Robotized flange assembling with line scan camera control[J]. IFAC Proceedings Volumes, 2003, 36 (23): 119- 124
doi: 10.1016/S1474-6670(17)37672-3
12 NERAKAE P, UANGPAIROJ P, CHAMNIPRASART K Using machine vision for flexible automatic assembly system[J]. Procedia Computer Science, 2016, 96: 428- 435
doi: 10.1016/j.procs.2016.08.090
13 钟德星, 杨元, 刘瑞玲, 等 基于单目视觉的装配机器人研究及应用[J]. 西安交通大学学报, 2018, 52 (5): 81- 87
ZHONG De-xing, YANG Yuan, LIU Rui-ling, et al Study and application of monocular vision-based assembly robot[J]. Journal of Xi'an Jiaotong University, 2018, 52 (5): 81- 87
14 JIANG T, CHENG X S, CUI H H, et al Dual-camera-based method for identification and location of scattered self-plugging rivets for robot grasping[J]. Measurement, 2019, 134: 688- 697
doi: 10.1016/j.measurement.2018.11.017
15 HUANG Y, LEE F F An automatic machine vision-guided grasping system for Phalaenopsis tissue culture plantlets[J]. Computers and Electronics in Agriculture, 2010, 70 (1): 42- 51
doi: 10.1016/j.compag.2009.08.011
16 GUO D, SUN F C, FANG B, et al Robotic grasping using visual and tactile sensing[J]. Information Sciences, Information Sciences, 2017, 417: 274- 286
17 刘毅, 丛明, 刘东, 等 基于改进遗传算法与机器视觉的工业机器人猪腹剖切轨迹规划[J]. 机器人, 2017, 39 (3): 377- 384
LIU Yi, CONG Ming, LIU Dong, et al Trajectory planning for porcine abdomen cutting based on an improved genetic algorithm and machine vision for industrial robot[J]. Robot, 2017, 39 (3): 377- 384
18 ZHANG G, YUN T J, OH W B, et al A study on seam tracking in robotic GMA welding process[J]. Materials Today: Proceedings, 2020, 22: 1771- 1777
doi: 10.1016/j.matpr.2020.03.010
19 ABDULLAH M W, ROTH H, WEYRICH M, et al An approach for peg-in-hole assembling using intuitive search algorithm based on human behavior and carried by sensors guided industrial robot[J]. IFAC PapersOnLine, 2015, 48 (3): 1476- 1481
doi: 10.1016/j.ifacol.2015.06.295
20 张思思, 李凤鸣, 杨旭亭, 等. 基于接触状态感知发育的机器人柔性装配方法[EB/OL]. [2020-10-22]. https://doi.org/10.13195/j.kzyjc.2019.1079.
ZHANG Si-si, LI Feng-ming, YANG Xu-ting, et al. Flexible assembly method based on contact state perception development [EB/OL]. [2020-10-22]. https://doi.org/10.13195/j.kzyjc.2019.1079.
21 JASIM I F, PLAPPER P W, VOOS H Position identification in force-guided robotic peg-in-hole assembly tasks[J]. Procedia CIRP, 2014, 23: 217- 222
doi: 10.1016/j.procir.2014.10.077
22 NIU L C, SAARINEN M, TUOKKO R, et al Integration of multi-camera vision system for automatic robotic assembly[J]. Procedia Manufacturing, 2019, 37: 380- 384
doi: 10.1016/j.promfg.2019.12.063
23 PINTO L, GUPTA A. Supersizing self-supervision: learning to grasp from 50k tries and 700 robot hours [C] // IEEE International Conference on Robotics and Automation. Stockholm: IEEE, 2016: 1544–1551.
24 孟少华, 胡瑞钦, 张立建, 等 一种基于机器人的航天器大型部件自主装配方法[J]. 机器人, 2018, 40 (1): 81- 88
MENG Shao-hua, HU Rui-qin, ZHANG Li-jian, et al A method of autonomous assembly of large spacecraft components using robot[J]. Robot, 2018, 40 (1): 81- 88
25 马春英, 杜鹃, 郑璟, 等 洪峰流量与流域面积幂函数关系最优拟合方法探讨[J]. 北京师范大学学报: 自然科学版, 2019, 55 (3): 408- 414
MA Chun-ying, DU Juan, ZHENG Jing, et al Optimal fitting for discharge-area power law relationship[J]. Journal of Beijing Normal University: Natural Science, 2019, 55 (3): 408- 414
[1] 郭英杰,顾钒,董辉跃,汪海晋. 压脚压紧力作用下的机器人变形预测和补偿[J]. 浙江大学学报(工学版), 2020, 54(8): 1457-1465.
[2] 冯毅雄,李康杰,高一聪,郑浩. 面向视觉伺服的工业机器人轮廓曲线角点识别[J]. 浙江大学学报(工学版), 2020, 54(8): 1449-1456.
[3] 毛晨涛,陈章位,张翔,祖洪飞. 基于相对精度指标的机器人运动学校准[J]. 浙江大学学报(工学版), 2020, 54(7): 1316-1324.
[4] 蒲陈阳,刘作军,庞爽,张燕. 知识继承型迭代学习控制的研究与应用[J]. 浙江大学学报(工学版), 2019, 53(7): 1340-1348.
[5] 黄梓亮, 欧阳小平, 赵天菲, 张建波, 周亮, 杨华勇. 飞机液压含气量检测系统特性[J]. 浙江大学学报(工学版), 2019, 53(1): 158-165.
[6] 陈星宇, 黄善和, 何昊哲. 探测频率对多频声学测沙技术测量误差的影响[J]. 浙江大学学报(工学版), 2018, 52(2): 307-316.
[7] 董辉跃, 孙强, 郭英杰, 赵安安, 朱伟东. 机器人孔口倒角加工振动及抑制[J]. 浙江大学学报(工学版), 2018, 52(12): 2243-2252.
[8] 何雪军, 王进, 陆国栋, 刘振宇, 陈立, 金晶. 基于三角网切片及碰撞检测的工业机器人三维头像雕刻[J]. 浙江大学学报(工学版), 2017, 51(6): 1104-1110.
[9] 何雪军,王进,陆国栋,陈立. 岛中含湖型截面的环切刀轨连接方法[J]. 浙江大学学报(工学版), 2016, 50(9): 1654-1661.
[10] 何雪军, 王进, 陆国栋, 陈立. 基于蚁群算法的机器人图像绘制序列优化[J]. 浙江大学学报(工学版), 2015, 49(6): 1139-1145.
[11] 董辉跃,朱灵盛, 章明, 李少波,罗水均. 飞机蒙皮切边的螺旋铣削方法[J]. 浙江大学学报(工学版), 2015, 49(11): 2033-2039.
[12] 王剑,胡锡幸,郭吉丰. 二自由度超声波电机位姿检测与控制[J]. 浙江大学学报(工学版), 2014, 48(5): 871-876.
[13] 骆永洁, 杨甬英, 田超, 韦涛, 卓永模. 非球面部分补偿检测系统的误差分析与处理[J]. J4, 2012, 46(4): 636-642.
[14] 林远芳, 黄强盛, 茹启田, 孙硕, 郑晓东. 椭偏参数测量误差对薄膜参数测试精度的影响[J]. J4, 2011, 45(8): 1485-1489.
[15] 刘楚辉, 姚宝国, 柯映林. 工业机器人切削加工离线编程研究[J]. J4, 2010, 44(3): 426-431.