文章快速检索 高级检索

Vision guide based teaching programming for industrial robot
NI Ziqiang, WANG Tianmiao , LIU Da
School of Mechanical Engineering and Automation, Beijing University of Aeronautics and Astronautics, Beijing 100083, China
Received: 2015-04-13; Accepted: 2015-05-08; Published online: 2015-06-17 15:17
Foundation items: National High-tech Research and Development Program of China (2013AA041201); National Natural Science Foundation of China (61175104)
Corresponding author. Tel.: 010-82338271 E-mail: itm@buaa.edu.cn
Abstract: Most industrial robots used in manufacture are based on teaching programming and offline programming. The shortcomings of these two programming methods limit the further application of industrial robots. A vision guide based programming method was introduced to solve the problem. The singular value decomposition (SVD) algorithm was used to calculate the registration matrix between computer vision space and robot space. The positions and orientations of robot's end-actuator were obtained by measuring the teaching tool, which is the key process to realize vision guide programming. Analytical the format of executable file which running on robot controller, and then transform the positions and orientations' data into executable file. An experiment was introduced to verify the feasibility and reliability of the programming method. The results indicate that the maximum error of trajectory tracking is -1.18 mm, and the root mean square error is 0.47 mm.
Key words: industrial robot     teaching programming     vision     weld     singular value decomposition (SVD)

1 双目视觉引导

1.1 双目视觉系统

 图 1 MicronTracker双目视觉系统 Fig. 1 MicronTracker stereo vision system
 图 2 识别模板 Fig. 2 Detection template
1.2 示教工具的识别

 图 3 工具识别和坐标系的定义 Fig. 3 Tool detection and coordinate definition
2 坐标映射

1) 计算P和Q的重心。

2) 构造PQ的协方差矩阵。

3) 设H的SVD为H=UΛVT,令

4) 可得到R=VSUT,t=p0-R×q0

3 示教程序自动生成

3.1 示教轨迹预处理

3.2 JOB文件生成

/JOB

//NAME**

//POS

///NPOS C,BC,EC,PO,BP,EX

///TOOL N

///POSTYPE**

///

PT***=X,Y,Z,Rx,Ry,Rz

BC****=X0,Y0,Z0

……

//INST

///DATE YYYY/MM/DD HH:MM

///ATTR SC,RW

///GROUP1 RB1

NOP

MOVL PT**,V=** PL=**

……

END

4 试验验证和误差分析

4.1 试验方案

 图 4 利用示教工具进行示教 Fig. 4 Teaching with teaching tool
 图 5 机器人执行示教程序 Fig. 5 Robot executing teaching program
4.2 求映射矩阵T

 坐标空间 x/mm y/mm z/mm 摄像头空间 91.903256 -96.66610 628.6399 126.583750 32.45904 538.6166 113.081520 -57.80070 580.7874 100.987710 -16.97080 664.8106 100.267250 -58.89560 692.2673 71.121134 -146.69400 748.0332 88.195925 -73.02570 776.2479 125.181000 15.28276 738.9809 机器人空间 594.063475 -157.225966 322.797628 581.325489 1.551304 348.461613 582.653762 -99.276822 350.217200 584.792773 -100.864280 256.164144 579.309419 -149.879246 250.264059 593.787355 -255.967798 236.468432 577.895234 -200.807907 180.335079 552.693035 -100.741871 177.916597

 图 6 基准点误差 Fig. 6 Fiducial pionts error
4.3 示教数据预处理

 图 7 轨迹示意图 Fig. 7 Schematic of trajectory
4.4 误差分析

 图 8 示教前后及细化后的轨迹 Fig. 8 Teaching trajectories under different situations

 图 9 示教编程的轨迹误差 Fig. 9 Error of teaching programming trajectory
5 结 论

1) 结合工业机器人目前常用的示教编程和离线编程的优缺点,利用双目视觉引导的方式实现示教编程,极大提高了示教编程效率。

2) 所采用的示教方法不但可以对目标轨迹点位置进行示教,还可以对轨迹点处的姿态进行示教,提高了机器人工作的灵活性。

3) 借助示教工具,减少了机器人工作内容对示教编程的影响,由于示教工具的特殊设计,也最大限度地降低了工作环境中光照对示教编程的影响。

4) 试验中,机器人在双目视觉引导下完成对特定轨迹的示教编程,轨迹跟踪误差最大为-1.18mm,均方根误差为0.47mm。通过分析,人手本身的抖动和偏移给整个系统带来了很大程度的误差。在高精度的应用场合,如实际焊接应用中,为了减少人为因素对示教工具末端精度的影响,可根据不同的焊缝宽度将示教工具末端设计成相应直径的球,以使得示教工具末端卡在焊缝从而达到提高精度的目的。

 [1] 许燕玲,林涛,陈善本. 焊接机器人应用现状与研究发展趋势[J].金属加工(热加工),2010(8):32-36. XU Y L,LIN T,CHEN S B.An overview on weld robot[J].MW Metal Forming,2010(8):32-36(in Chinese). Cited By in Cnki (70) [2] PAN Z, POLDEN J,LARKIN N,et al.Recent progress on programming methods for industrial robots[J].Robotics and Computer-Integrated Manufacturing,2012,28(2):87-94. Click to display the text [3] KOHRT C, STAMP R,PIPE A G,et al.An online robot trajectory planning and programming support system for industrial use[J].Robotics and Computer-Integrated Manufacturing,2013,29(1):71-79. Click to display the text [4] CHEN S B, QIU T,LIN T,et al.Intelligent technologies for robotic welding[M]//TZYH-JONG T,SHAN-BEN C,ZHOU C J.Robotic welding,intelligence and automation.Berlin:Springer,2004:123-143. [5] CHEN S B, ZHANG Y,LIN T,et al.Welding robotic systems with visual sensing and real-time control of dynamic weld pool during pulsed GTAW[J].International Journal of Robotics and Automation,2004,19(1):28-35. [6] 鞠益兰,程金松. 结构光式激光视觉传感器的焊缝跟踪系统[J].电焊机,2002,32(5):9-11. JU Y L,CHENG J S.Seam track system of laser optical sensor with structured light[J].Electric Welding Machine,2002,32(5):9-11(in Chinese). Cited By in Cnki (39) | Click to display the text [7] HUANG W, KOVACEVIC R.Development of a real-time laser-based machine vision system to monitor and control welding processes[J].International Journal of Advanced Manufacturing Technology,2012,63(1-4):235-248. Click to display the text [8] Claron Technology Inc. MicronTracker developer's manual[M].Toronto:Claron Technology Inc.,2006:25-36. [9] KALMAN D. A singularly valuable decomposition:The SVD of a matrix[J].College Math Journal,1996,27(1):2-23. Click to display the text [10] 李燕青,计时鸣. MOTOMAN机器人实时控制的方法研究[J].机电工程,2007,24(7):78-81. LI Y Q,JI S M.Research on real-time control of MOTOMAN robot[J].Mechanical & Electrical Engineering Magazine,2007,24(7):78-81(in Chinese). Cited By in Cnki (7) | Click to display the text [11] 胡中华,陈焕明,许明星,等. 弧焊机器人MOTOMAN示教编程方法[J].电焊机,2006,36(3):40-42. HU Z H,CHEN H M,XU M X,et al.Programming method for arc welding robot of MOTOMAN teaching[J].Electric Welding Machine,2006,36(3):40-42(in Chinese). Cited By in Cnki (16) | Click to display the text [12] WEST J B, FITZPATRICK J M,TOMS S A,et al.Fiducial point placement and the accuracy of point-based,rigid body registration[J].Neurosurgery,2001,48(4):810-816. >Click to display the text [13] SEGINER A. Rigid-body point-based registration:The distribution of the target registration error when the fiducial registration errors are given[J].Medical Image Analysis,2011,15(4):397-413. Click to display the text [14] RAFAEL C G, RICHARD E W.Digital image processing[M].3rd ed.New York:Pearson Education Inc.,2010:671-675. [15] National Instruments Corporation. NI vision concept manual[M].Texas:National Instruments Corporation,2007:155-186.

#### 文章信息

NI Ziqiang, WANG Tianmiao, LIU Da

Vision guide based teaching programming for industrial robot

Journal of Beijing University of Aeronautics and Astronsutics, 2016, 42(3): 562-568.
http://dx.doi.org/10.13700/j.bh.1001-5965.2015.0218