[1]黄晶晶,陶卫军,胡洋洋,等.一种基于视觉识别的按钮自主操作机械手[J].南京理工大学学报(自然科学版),2017,41(05):616.[doi:10.14177/j.cnki.32-1397n.2017.41.05.013]
 Huang Jingjing,Tao Weijun,Hu Yangyang,et al.Autonomous manipulator for button pressing based onvisual recognition[J].Journal of Nanjing University of Science and Technology,2017,41(05):616.[doi:10.14177/j.cnki.32-1397n.2017.41.05.013]
点击复制

一种基于视觉识别的按钮自主操作机械手()
分享到:

《南京理工大学学报》(自然科学版)[ISSN:1005-9830/CN:32-1397/N]

卷:
41卷
期数:
2017年05期
页码:
616
栏目:
出版日期:
2017-10-31

文章信息/Info

Title:
Autonomous manipulator for button pressing based onvisual recognition
文章编号:
1005-9830(2017)05-0616-07
作者:
黄晶晶陶卫军胡洋洋刘佳耀丁林祥
南京理工大学 机械工程学院,江苏 南京 210094
Author(s):
Huang JingjingTao WeijunHu YangyangLiu JiayaoDing Linxiang
School of Mechanical Engineering,Nanjing University of Science and Technology,Nanjing 210094,China
关键词:
自主操作机械手 视觉识别 按钮按压 支持向量机 视觉定位
Keywords:
autonomous manipulators visual recognition botton pressing support vector machine visual positioning
分类号:
TP241
DOI:
10.14177/j.cnki.32-1397n.2017.41.05.013
摘要:
针对机器人自主按压按钮的操作需求,设计了一种适于机器人安装的基于视觉识别的四自由度(Degree of freedom,DOF)按钮自主操作机械手。结合功能需求对该机械手的机械结构和控制系统进行设计,通过几何法求解了机械手的运动学正反解,并规划了其运动轨迹。采用支持向量机对按钮样本进行训练和预测,并通过视觉对按钮进行定位。最后制作了按钮自主操作机械手样机,并进行了按钮识别、机械手定位和按压按钮实验。实验结果表明,该文4-DOF自主操作机械手的按钮识别成功率达94%,控制定位精度达10 mm,能够自主完成按钮按压操作。
Abstract:
According to requirements of the autonomous button pressing of the robot,the four-degree of freedom(4-DOF)autonomous manipulator for button pressing of the robot is developed based on the visual recognition.The mechanical structure and control system of the manipulator are designed according to its functional requirements,the kinematic is solved by using the geometric method,and the movement trajectory is planned.The support vector machine(SVM)is used to train and predict the image samples of the buttons,and the buttons are positioned visually.Lastly,a prototype of the manipulator is developed.The experiment results of button recognition,manipulator positioning and button pressing show that,the success rate of the button recognition of the manipulator sample is 94%,the positioning accuracy of the manipulator control system is 10 mm,and the developed 4-DOF manipulator can press the target button autonomously.

参考文献/References:

[1] 林凯.自主服务机器人在智能楼宇系统中的应用研究[D].厦门:厦门大学航空航天学院,2014.
[2]王家超.医院病房巡视机器人定位与避障技术研究[D].济南:山东大学控制科学与工程学院,2012.
[3]郭杰.一种多功能酒店服务机器人[P].中国:CN201420842068.X.2015-07-08.
[4]新浪科技.谷歌投资的机器人投入使用:提供酒店客房服务[EB/OL].http://tech.sina.com.cn/it/2014-09-22/09089631592.shtml,2014-09-22.
[5]尚俊.基于HOG特征的目标识别算法研究[D].武汉:华中科技大学软件学院,2012.
[6]Vapnik V N.The nature of statistical learning theory[M].New York,US:Springer,1999.
[7]殷羽,郑宏,高婷婷,等.基于联合HOG特征的车牌识别算法[J].计算机工程与设计,2015(2):476-481.
Yin Yu,Zheng Hong,Gao Tingting,et al.Algorithm license plate recognition based on joint HOG feature[J].Computer Engineering and design,2015(2):476-481.
[8]唐灵洁,胡红萍.基于SVM的车牌数字识别方法[J].数学的实践与认识,2012,42(23):138-143.
Tang Lingjie,Hu Hongpin.Recognition method of vehicle license plate based on SVM[J].Mathematics in Practice and Theory,2012,42(23):138-143.
[9]张小琴,赵池航,沙月进,等.基于HOG特征及支持向量机的车辆品牌识别方法[J].东南大学学报(自然科学版),2013(s2):410-413.
Zhang Xiaoqin,Zhao Chihang,Sha Yuejin,et al.Vehicle brand recognition based on HOG feature and support vector machine[J].Journal of Southeast University(Natural Science Edition),2013(s2):410-413.
[10]郑英娟.基于八方向Sobel算子的边缘检测算法研究[D].石家庄:河北师范大学数学与信息科学学院,2014.
[11]宁赛男,朱明,孙宏海,等.一种改进的Sobel自适应边缘检测的FPGA实现[J].液晶与显示,2014,29(3):395-402.
Ning Sainan,Zhu Ming,Sun Honghai,et al.Realization of improved Sobel adaptive edge detection algorithm based on FPGA[J].Chinese Journal of Liquid Crystals and Displays,2014,29(3):395-402.
[12]杨静宇,魏兴国,孙怀江.一种快速 SVM 学习算法[J].南京理工大学学报,2003,27(5):530-535.
Yang Jingyu,Wei Xingguo,Sun Huaijiang.A fast SVM learning algorithm[J].Journal of Nanjing University of Science and Technology,2003,27(5):530-535.
[13]马颂德,张正友.计算机视觉——计算理论与算法基础[M].北京:科学出版社,1998.
[14]方帅,曹洋,徐心和.一种非标定摄像机的定位新算法[J].仪器仪表学报,2005,26(8):845-848.
Fang Shuai,Gao Yang,Xu Xinhe.A new vision localization algorithm for uncalibrated camera[J].Chinese Journal of Scientific Instrument,2005,26(8):845-848.

备注/Memo

备注/Memo:
收稿日期:2017-01-12 修回日期:2017-06-05
作者简介:黄晶晶(1992-),男,硕士生,主要研究方向:机器人与智能机械,E-mail:1134271775@qq.com; 通讯作者:陶卫军(1975-),男,博士,副教授,主要研究方向:机械电子工程,E-mail:taoweijun01@163.com。
引文格式:黄晶晶,陶卫军,胡洋洋,等.一种基于视觉识别的按钮自主操作机械手[J].南京理工大学学报,2017,41(5):616-622.
投稿网址:http://zrxuebao.njust.edu.cn
更新日期/Last Update: 2017-09-30