基于Kinect的机器人臂手系统的目标抓取

doi:10.3969/j.issn.1007-2861.2016.04.008

上海大学学报(自然科学版) ›› 2016, Vol. 22 ›› Issue (4): 421-431.doi: 10.3969/j.issn.1007-2861.2016.04.008

基于Kinect的机器人臂手系统的目标抓取

丁美昆, 徐昱琳, 蒋财军, 冉鹏

上海大学机电工程与自动化学院, 上海200072

收稿日期:2015-03-25 出版日期:2016-08-30 发布日期:2016-08-30
通讯作者: 徐昱琳(1964—), 女, 副教授, 博士, 研究方向为机器人、智能控制. E-mail: xuyulin@shu.edu.cn
作者简介:徐昱琳(1964—), 女, 副教授, 博士, 研究方向为机器人、智能控制. E-mail: xuyulin@shu.edu.cn
基金资助:
上海市产学研合作项目(CXY-2013-28)

Kinect-based object grasping by robot arm hand system

DING Meikun, XU Yulin, JIANG Caijun, RAN Peng

School of Mechatronics Engineering and Automation, Shanghai University, Shanghai 200072, China

Received:2015-03-25 Online:2016-08-30 Published:2016-08-30

摘要/Abstract

摘要：

为了实现机器人臂手系统的目标抓取, 采用Kinect对目标信息进行实时检测. 首先,采用张正友棋盘标定法完成对Kinect内外参数的标定. 其次, 利用深度信息进行深度分割, 滤除大部分干扰背景, 再通过颜色与形状特征实现目标的识别与定位. 将识别对象的3维坐标通过以太网发送至机械臂控制台, 随后机械臂移动至目标位置. 最后采用变积分PID算法控制灵巧手接触力, 保证响应的快速性及精密性, 实现灵巧手的精细抓取. 通过设计一套完整的实验系统验证了该方法的有效性.

关键词: 变积分PID , 灵巧手, 深度分割 , Kinect 标定

Abstract:

To realize automatic object grasping by a robot arm hand system, Kinect is used for real-time detection of the object. The Zhang Zhenyou chessboard method is applied to calibrate the intrinsic and external parameters of the Kinect. Depth segmentation is done to filter out most of the background interference, and identification and location of object are achieved based on the color and shape features. The object’s 3D coordinates is sent to the manipulator console to locate the target position through TCP/IP communication. A changing integration PID algorithm is applied to achieve fast and accurate grasp by controlling pressure on the dexterous hand. An experiment system is developed to verify effectiveness of the proposed methods.

Key words: changing integration PID , depth segmentation , dexterous hand, Kinect calibration

丁美昆, 徐昱琳, 蒋财军, 冉鹏. 基于Kinect的机器人臂手系统的目标抓取[J]. 上海大学学报(自然科学版), 2016, 22(4): 421-431.

DING Meikun, XU Yulin, JIANG Caijun, RAN Peng. Kinect-based object grasping by robot arm hand system[J]. Journal of Shanghai University（Natural Science Edition）, 2016, 22(4): 421-431.

参考文献

[1] Sakagami Y, Watanabe R, Aoyama C, et al. The intelligent ASIMO: system overview and integration [C]// Proceeding of the 2002 IEEE/RSJ International Conference on Intelligent Robots and Systems. 2002: 2478-2483.
[2] Stückler J, Steffens R, Holz D, et al. Efficient 3D object perception and grasp planning for mobile manipulation in domestic environments [J]. Robotics & Autonomous Systems, 2012, 61(10): 1106-1115.
[3] 尚倩, 阮秋琦, 李小利. 双目立体视觉的目标识别与定位[J]. 智能系统学报, 2011, 6(4): 303-311.
[4] 项荣. 开放环境中番茄的双目立体视觉识别与定位[D]. 杭州: 浙江大学, 2013: 216.
[5] 徐昱琳, 杨永焕, 李昕, 等. 基于双目视觉的服务机器人仿人机械臂控制[J]. 上海大学学报(自然科学版), 2012, 18(5): 506-512.
[6] 韩峥, 刘华平, 黄文炳, 等. 基于Kinect 的机械臂目标抓取[J]. 智能系统学报, 2013, 8(2): 149-155.
[7] Huang Z Y, Huang J T, Hsu C M. A case study of object identification using a Kinect sensor [C]// 2013 IEEE International Conference on Systems, Man, and Cybernetics (SMC). 2013: 1743-1747.
[8] 孙小凯. 基于RGB-D 信息的物体定位与识别[D]. 杭州: 浙江大学, 2014: 87.
[9] Parker M, Daniel H C, Echtler F, et al. Hacking the Kinect [M]. New York: Apress, 2012: 10-25.
[10] 李格格, 沈建强. 基于Kinect 的目标跟踪与避障[J]. 江南大学学报(自然科学版), 2014, 13(4): 427-432.
[11] Zhang Z Y. A flexible new technique for camera calibration [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2000, 22(11): 1330-1334.
[12] Zhang Z Y. Flexible camera calibration by viewing a plane from unknown orientations [C]//The Proceedings of the Seventh IEEE International Conference on Computer Vision. 1999: 666-673.
[13] 于仕琪, 刘瑞祯. 学习OpenCV [M]. 北京: 清华大学出版社, 2009: 406-429.
[14] Jiang L, Koch A, Scherer S A, et al. Multi-class fruit classification using RGB-D data for indoor robots [C]// 2013 IEEE International Conference on Robotics and Biomimetics (ROBIO). 2013: 587-592.
[15] Lai K, Bo L, Ren X, et al. A large-scale hierarchical multi-view RGB-D object dataset [C]//2011 IEEE International Conference on Robotics and Automation (ICRA). 2011: 1817-1824.
[16] 阮秋琦. 数字图像处理学[M]. 3 版. 北京: 电子工业出版社, 2007: 254-257.

基于Kinect的机器人臂手系统的目标抓取

Kinect-based object grasping by robot arm hand system

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 0

编辑推荐

Metrics

本文评价