基于机器视觉设施农业内移栽机器人的研究
详细信息    本馆镜像全文|  推荐本文 |  |   获取CNKI官网全文
摘要
基于机器视觉技术的机器人在设施农业中的应用已经越来越广泛。移栽机器人作为育苗工厂化生产的重要设备,在提高育苗工作效率上有着重要意义。本文应用机器视觉技术识别穴盘幼苗的生长情况,并利用多特征判断出适合移栽的幼苗,对其定位。同时设计了合理的末端执行器,利用计算机及PLC控制,实现对机械臂及末端执行器的定点控制。主要研究内容如下:
     1、综述了国内外设施农业中机器人的研究现状和机器视觉在机器人中的应用,特别阐述了国内外移栽机器人的研究现状,并指出了国内外研究中存在的问题。
     2、建立了适合本研究的机器视觉系统。该系统由CCD摄像头、图像采集卡、计算机、6支荧光灯,光照箱等组成。
     3、建立了适合本研究的试验平台。该试验平台由机器视觉系统、控制系统、传输系统及移栽系统四部分组成。
     4、基于机器视觉技术的番茄幼苗的识别和位置检测。通过对R、G、B三个分量的不同线性变换的研究,确定了适合本研究的图像分割的彩色特征变换,从背景中提出幼苗植株。然后采用单连通域分析算法提取每个穴孔中幼苗的叶片面积,并根据此特征对幼苗进行分类,判断出适合移栽的幼苗,并记录适合移栽幼苗的穴孔中心位置。实验验证,该机器视觉系统对于50孔穴盘番茄幼苗识别准确率为98.7%,对于72孔穴盘幼苗识别准确率为98.14%。
     5、研究了移栽机器人的控制系统,该系统由计算机、PLC、执行部件、反馈传感器等组成。计算机通过RS232串行通信器实现与PLC之间的通信,将视觉系统获取的位置信息传送至PLC,PLC发送信息驱动步进电机及电磁阀,运用电路控制和气路两路控制实现了对机械臂和末端执行器的运动控制。对移栽策略进行了分析,比较了几种不同的移栽路径,最后用贪心算法对路径进行了优化,缩短了总路径。
     6、根据穴盘幼苗的特性,开发了移栽机器人的末端执行器。末端执行器由气缸驱动,采用手指式抓取方式。用三种不同的手指分别作了比较试验,试验结果表明,采用两个铲式手指能更有效地抓取及释放幼苗块,完成移栽过程,移栽成功率为82.5%。
Robots based on machine vision have been widely applied in facility agriculture. As a basilicequipment in the nursery factory, the transplanting robot plays an important role in improving thenursery efficiency. This research studied the application of machine vision to recognition and location ofplug seedlings, which are suitable to transplant decided by the characters of the area and perimeter ofleaves. Also an end-effector was designed to grasp, hold, insert, and release a plug. The movement ofthe manipulator and the end-effector was controlled by the computer and PLC. Main content and resultswere as follows:
     1. The research achievements in the field of facility agriculture robot and the application ofmachine vision in agriculture robot were reviewed, especially the development of the transplantingrobot, and the existing problems were put forward.
     2. A suitable machine vision system was set up for this research, which is composed of a grabber,a CCD camera, 6 fluorescent lamps and an industrial computer.
     3. A suitable experiment system was set up for this research, which is composed of four parts:machine vision system, control system, convection system and grasp system.
     4. The algorithm of recognition and location of tomato plug seedling based on machine visionwas developed. Through the analyses of linear transformation Of R, G and B in image shot by colorCDD, the color image was transformed to grayscale by proper color feature, and then was segmented bythreshold. The seedlings were recognized from background. Then the area of seedling leaves wasextracted using the blob analysis of each cell. The seedlings which need transplanted were recognizedand the position was recorded. The result shows the accuracy of machine vision system for the seedlingsof 50 cells was 98.7% while for the seedlings of 72 cells was 98.14%.
     5. The control system of transplanting robot was established. This system was composed of acomputer, a PLC, executive instrument, sensor and so on. RS-232 was used to communicate betweencomputer and PLC. Computer sends the position of seedling got from machine vision system to PLC,and then PLC sends the control information to the actuator of step motor and the electromagnetic. Themovement of the manipulator and the end-effector was controlled through the circuit and the air circuit. At last, the strategy of transplanting was analyzed, and different ways of transplanting were compared.The path was optimized based on greedy algorithm, and the total path became short.
     6. The end-effector was developed based on the character. The end-effector with fingeredgrasping was drove by two cylinders, and three kinds of fingers used to grasp, hold, insert, and release aplug were compared in the experiment, the result shows that the shovel fingers play the best behave, thesuccess rate is 82.5%.
引文
1.李基明.韩国设施园艺的自动化.日韩交流农业工程研讨会论文集,1993.22~30
    2.张志斌.荷兰温室产业及发展我国设施园艺建议.设施园艺,1999,No.9
    3.于海业,马成林,陈晓光.发达国家温室设备自动化研究的现状.1997,Vol.13:253~258
    4.徐向峰,杨广林,王立舒,高晶晶.我国设施农业的现状及发展对策研究.东北农业大学学报,2005,36(4):520~522
    5.申川.基于双目立体视觉系统的设施农业作物位置信息获取.浙江大学硕士学位论文,2006.6
    6.中华人民共和国国家统计局.中国统计年鉴-2006
    7.刘宗立,应芳卿,李武高.蔬菜穴盘育苗方法.现代农业科技,2006.1
    8.赵匀,武传宇,胡旭东,俞高红.农业机器人的研究进展及存在的问题.农业工程学报,2003,Vol.19.No.1:20~24
    9. N. Kondo, K. C. Ting. Robotics for Bio-production Systems [M]. 1998. ASAE Publisher.
    10. AR Jimene, R Ceres, JL Pons. A Machine Vision System Using a Laser Radar Applied to Robotic Fruit Harvesting. Machine vision and Application, 2000
    11.应义斌,饶秀勤,赵匀,蒋亦元.机器视觉技术在农产品品质自动识别中的应用(Ⅰ).农业工程学报,Vol.16,No.1:103~108.
    12. Teruo Takahashi, Shuhuai Zhang, Hiroshi Fukuchi. Measurement of 3-D locations of fruit by binocular stereo vision for apple harvesting in an orchard. ASAE Annual International Meeting, 2002, Paper Number:021102.
    13. Kawamura, N., K. Namikawa, T. Fujiura, and M. Ura. Study om agriculture robot (Part 1). Jan. Soc. Agric. 1984. Mach.46(3):353~358.
    14. Okamoto, T., Y. Shirai, T. Fujura and N. Kondo. Constitution of bio-production robot. In robotics in bioproduction 1992:5~82. Tokyo: Jikkyo Publishing Co.
    15.胡桂仙,于勇,王俊.农业机器人的开发与应用.试验研究,2002,7:44~47.
    16.张品端.日本的蔬菜嫁接机器人.机器人技术与应用,1997,5:11~14.
    17. Kondo, N., Monta, M., Shibano, Y., mohri, K. Basic Mechanism of Robot adapted to physical properties of tomato plant. In Process Engineering, 1993a, Vol.3: 840~849.
    18. Okamoto, T., Y.Shirai, and N.Kondo. Biotechnology robot. In Robotics in Bioproduction, 1992.177
    19. M. Monta, N. Kondo,K. C. Ting. End-effectors for tomato harvesting robot. Artificial Intelligence Review, 1998, 12:11~25
    20. Ling, P., R. Ehsani, KC Ting, Y.Chi, N. Ramalingam, MH Klingman, and C. Draper.. Sensing and end-effector for a robotic tomato harvester. 2004, ASAE Paper No. 043088.
    21. Fujiura, T., J.Yamashita, and N.Kondo. Agricultural robots (1):Vision sensing system, 1992, ASAE Paper:92-3517.
    22. Naoshi Kondo, Kazunori Ninomiya, Shigehiko Hayashi, Tomohiko Ota, Kotaro Kubota. A New Challenge of Robot for Harvesting Strawberry Grown on Table Top Culture. 2005, An ASAE Meeting Presentation Paper Number: 053138 1~10.
    23. Arima, S., N.Kondo, Y.Shibano, J.Yamashita, T.Fujiura, and H.Akiyoshi. Study on cucumber harvesting robot(Part1). J.Jpn.Soc.Agric.Mach. 1994a, 56(1):45~53
    24. Arima, S., N.Kondo, Y.Shibano, J.Yamashita, T.Fujiura, and H.Akiyoshi. Study on cucumber harvesting robot(Part2).J.Jpn.Soc.Agric. 1994b, Mach.56(6):69~76
    25. L M Vail, KoUenburg-Crisan and J Bontsema and P W ermekes. Mechanical system for automatic harvesting of cucumbers. IFAC Control Application and Ergonomic in Agriculture, Athens, Greece, 1998:289~293,
    26. Shifigefiko Hayashi, Katsunobu GANNO, Yukitsugu ISHII, Itsuo TANAKA. Robotic Harvesting System for Eggplants. JARQ, 2002, 36(3): 163~168
    27. Reed, J.N.,W.He, and R.D.Tillett.Picking. Mushrooms by robot. In Proceedings of the International Symposium on Automation and Robotic in Bioproduction and Processing, 1995, Vol.1: 27~34.
    28. Kutz K C, Miles G A, Hammer P A, Krutz GW. Robotictransplanting of bedding plants. Transactions of the ASAE, 1987, 30(3), 586~590.
    29. Ting, K. C., G. A. Giacomelli, and S. J. Shen. Robot work cell for seeding transplanting Part Ⅰ-layout and materials flow. Trans. Am. Soc. Agric. Eng. 1990a.33: 1005-1010.
    30. Ting, K. C., G. A. Giacomelli, S. J. Shen, and W. P. Kabala. Robot work cell for seeding transplanting Part Ⅱ—end-effector development. Trans. Am. Soc. Agric. Eng. 1990b.33: 1013-1017.
    31. Ting, K. C., Y. A. Yang, and W. Fang. Stochastic modeling of robotic workcell for seeding plug transplanting. 1990c, ASAE paper 90-1539. St. Joseph, MI: Anerican Society of Agricultural Engineers.
    32. Ting, K.C., G.A.Giacomelli, and P.P.Ling. Workability and productivity of robotic plug transplanting workcell. Vitro Cell, 1992.28:5~10.
    33. K.H.Ryu, G.Kim, J.S,Han. Development of a Robotic Transplanter for Bedding Plants. J.agric.Engng. Res, 2001, 78(2): 141~146
    34. Tal.Y.W, Ling,P.P; Ting K C. Machine vision assistedrobotic seedling transplanting. Transactions of the ASAE, 1994, 37(2), 661~667.
    35. W.C.Choi, D.C.Kim, I.H.Ryu, K.U.Kim. Development of a seedling pick-up device for vegetable transplanters. Transactions of the ASAE, 2002, 45(1), 13~19
    36.徐丽明,张铁中,刘长青.蔬菜自动嫁接机器人系统——旋转切削机构的设计.中国农业大学学报,2002,5(2):34~36
    37.张铁中,陈利兵,宋健.草莓采摘机器人的研究:基于图像的草莓重心位置和采摘点的 确定.中国农业大学学报,2005,10(1):48~51
    38.陈晓光,周云山等.图像处理技术在蔬菜栽培中的应用.农业工程学报,1994.Vol.1,No.4:31~36.
    39.周云山,李强,李红英,王荣本.计算机视觉在蘑菇采摘机器人上的应用.农业工程学报,1995,Vol.11,No.4:27~32.
    40.张瑞合,姬长英,沈明霞,曹坤.计算机视觉技术在番茄收获中的应用,农业机械学报,2001,Vol.32,No.5:50-52.
    41.张健软,王秀等.基于机器视觉技术的叶面积测量系统实现.自然科学进展,2004.Vol.11:1304~1310.
    42.仲琴.基于机器视觉的番茄收获机器人目标定位技术研究.硕士学位论文,2005.
    43.谢志勇,张铁中.基于RGB彩色模型的草莓图像色彩分割算法.中国农业大学学报,2006,11(1):84~86.
    44. David A. Forsyth, Jean Ponce. Computer Vision[M]. Prentice Hall, Inc, 2003.
    45.[美]马尔.视觉计算理论.姚国政,刘磊,汪云九译.北京:科学出版社,1987.
    46.颜发根,丁少华,陈乐,刘建群.基于PC的机器视觉系统[J].PLC&FA,2004,7.
    47.王耀南,李树涛等.计算机图像处理与识别技术.高等教育出片社,2000:26-28.
    48. Gonzalez, R.C., Woods, R.E. Digital Image Processing. Second ed. 2002, Prentice-Hall, Reading. NJ. USA.
    49.边肇祺,张学工.模式识别.第二版,2000,清华大学出版社
    50. Freeman H. Computer processing of line—drawing images[J]. Computing Surveys, 1974, 6(1): 57~97
    51.李国强,张薇,顾国庆.用顶点链编码计算区域面积的方法.上海理工大学学报,2003,Vol.25,No.3:267~270
    52.陈士金,汤漾平.基于链码的轮廓跟踪技术在二值图像中的应用.华中理工大学学报,1998,Vol.26,No.12:26~28
    53.江秀汉.计算机控制原理及其应用[M].1995,高等教育出版社
    54.宋伯生.PLC编程理论、算法及技巧[M].2005,北京:机械工业出版社
    55.黄谊,章宏甲,王积伟.液压与气压传动[M].2000,北京:机械工业出版社
    56.余释宣.计算机算法基础[M].2000,高等学校电子信息类规划教材
    57.张远圻,张兴国.机器人末端执行件的系统研究.机械制造,1997,Vol.9:9-11
    58.郑莉,董渊.C++语言程序设计.2001,清华大学出版社

© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号

地址:北京市海淀区学院路29号 邮编:100083

电话:办公室:(+86 10)66554848;文献借阅、咨询服务、科技查新:66554700