Please wait a minute...
 首页  期刊介绍 期刊订阅 联系我们 横山亮次奖 百年刊庆
 
最新录用  |  预出版  |  当期目录  |  过刊浏览  |  阅读排行  |  下载排行  |  引用排行  |  横山亮次奖  |  百年刊庆
清华大学学报(自然科学版)  2015, Vol. 55 Issue (10): 1061-1066    DOI: 10.16511/j.cnki.qhdxxb.2015.22.017
  机械工程 本期目录 | 过刊浏览 | 高级检索 |
基于改进型粒子群算法的曲面匹配与位姿获取
罗磊1,2, 陈恳1, 杜峰坡2, 马振书2
1. 清华大学 机械工程系, 北京 100084;
2. 总装军械技术研究所, 石家庄 050000
Surface fitting and position-pose measurements based on an improved SA-PSO algorithm
LUO Lei1,2, CHEN Ken1, DU Fengpo2, MA Zhenshu2
1. Department of Mechanical Engineering, Tsinghua University, Beijing 100084, China;
2. Institute of Ordnance Technology, Shijiazhuang 050000, China
全文: PDF(1075 KB)  
输出: BibTeX | EndNote (RIS)      
摘要 有限散乱点模式匹配是机器视觉与模式识别领域中的一个基础问题和重要环节, 在目标识别、医学图像配准、遥感图像匹配、目标位姿获取等方面得到了广泛应用。该文提出了一种变概率密度分布的改进型模拟退火粒子群算法, 能够加速算法收敛并搜索到全局最优解, 提高匹配准确性。通过采集已知旋转体目标局部表面有限散乱点, 构造适应度函数并进行坐标变换, 实现散乱点与曲面的匹配和目标位姿获取, 讨论了误差影响因素和算法适用性。应用结果表明: 该方法与最小二乘曲面拟合方法相比, 所需散乱点数目少, 计算效率和精度高, 且具有对散乱点采集误差不敏感等优点, 能够满足排爆机器人抓取目标局部裸露情况下的位姿获取应用需求。
服务
把本文推荐给朋友
加入引用管理器
E-mail Alert
RSS
作者相关文章
罗磊
陈恳
杜峰坡
马振书
关键词 粒子群算法模拟退火曲面匹配排爆机器人    
Abstract:Scattered point pattern matching is an important issue in computer vision and pattern recognition, which is widely used for target recognition, medical and remote sensing image registration, and position and pose measurements. This paper describes an algorithm for use in an explosive ordnance disposal robot for when the target object is partial exposed. A simulated annealing-particle swarm optimization (SA-PSO) algorithm based on particle density distribution changes for scattered point pattern matching is developed. The algorithm is more accurate and faster than previous algorithms. The fitness function is constructed from a series of scattered points collected from the local surface of a rotated object. Accurate surface fitting and pose parameters are found using coordinate transforms. The factors that affect the accuracy and applicability are discussed in detail. Tests show that this method is accurate and efficient, with less points needed and less sensitivity to point errors compared with the traditional least squares method.
Key wordsparticle swarm optimization (PSO) algorithm    simulated annealing (SA)    surface fitting    explosive ordnance disposal (EOD) robot
收稿日期: 2014-01-11      出版日期: 2015-11-16
ZTFLH:  TP242.3  
基金资助:国家“八六三”高技术项目(2009AA043701)
通讯作者: 陈恳,教授,E-mail:kenchen@tsinghua.edu.cn     E-mail: kenchen@tsinghua.edu.cn
作者简介: 罗磊(1972-),男(汉),河北,博士研究生。
引用本文:   
罗磊, 陈恳, 杜峰坡, 马振书. 基于改进型粒子群算法的曲面匹配与位姿获取[J]. 清华大学学报(自然科学版), 2015, 55(10): 1061-1066.
LUO Lei, CHEN Ken, DU Fengpo, MA Zhenshu. Surface fitting and position-pose measurements based on an improved SA-PSO algorithm. Journal of Tsinghua University(Science and Technology), 2015, 55(10): 1061-1066.
链接本文:  
http://jst.tsinghuajournals.com/CN/10.16511/j.cnki.qhdxxb.2015.22.017  或          http://jst.tsinghuajournals.com/CN/Y2015/V55/I10/1061
  图1 最优适应度值随迭代次数变化曲线
  图2 匹配效果图
[1] 孔新立, 金丰年, 蒋美蓉. 恐怖爆炸袭击方式及规模分析[J]. 爆破, 2007, 24(3): 88-92.KONG Xinli, JIN Fengnian, JIANG Meirong. Analysis of way and scale of terroristic raid [J]. Blasting, 2007, 24 (3): 88-92. (in Chinese)
[2] 范路桥, 姚锡凡, 祁亨年. 排爆机器人的研究现状及其关键技术[J]. 机床与液压, 2008, 36(6): 139-143.FAN Luqiao, YAO Xifan, QI Hengnian. Research progress and key techniques of explosive ordnance disposal robot [J]. Machine Tool & Hydraulics, 2008, 36(6): 139-143. (in Chinese)
[3] 金周英, 白英. 我国机器人发展的政策研究报告[J]. 机器人技术与应用, 2009(2): 1-7.JIN Zhouying, BAI Ying. Policy research report of robot development [J]. Robot Technique and Application, 2009(2): 1-7. (in Chinese)
[4] Jean G V. New robots planned for bomb disposal teams [J]. National Defense, 2011, 96(692): 28-31.
[5] Dakis A. Human presence detection: The navy has tri-service responsibility for EOD-related science and technology development [J]. Chips, 2011, 29(4): 50-52.
[6] ZENG Jianjun, YANG Ruqing, ZHANG Weijun. Research on semi-automatic bomb fetching for an EOD robot [J]. International Journal of Advanced Robotic Systems, 2008, 4(2): 247-252.
[7] Homsup N, Jariyanorawiss T, Homsup W. A control of a bomb disposal robot using a stereo scope vision [C]//IEEE Southeast Con. Huntsville, AL, 2008: 293-294.
[8] 范路桥, 蒋梁中, 汪伟. 排爆机器人双目立体视觉系统的研究和开发[J]. 计算机工程, 2007, 33(7): 207-209.FAN Luqiao, JIANG Liangzhong, WANG Wei. Research and development on explosive-handling robot binocular visual system [J]. Computer Engineering, 2007, 33(7): 207-209. (in Chinese)
[9] 任同群, 赵悦含, 龚春忠. 自由曲面测量的三维散乱点云无约束配准[J]. 光学精密工程, 2013, 21(5): 1234-1243.REN Tongqun, ZHAO Yuehan, GONG Chunzhong. Unconstrained registration of 3-D scattered point clouds for free-form shape measurement [J]. Optics and Precision Engineering, 2013, 21(5): 1234-1243. (in Chinese)
[10] 李二涛, 张国煊, 曾虹. 基于最小二乘的曲面拟合算法研究[J]. 杭州电子科技大学学报, 2009, 29(2): 48-51.LI Ertao, ZHANG Guoxuan, ZENG Hong. Algorithm of surface fitting research based on least-squares methods [J]. Journal of Hangzhou Dianzi University, 2009, 29(2): 48-51. (in Chinese)
[11] Kennedy J, Eberhart R C. Particle swarm optimization [C]// Proc of IEEE International Conference on Neural Networks. Piscataway, NJ: IEEE Service Center, 1995: 1942-1948.
[12] Kirkpatrick S, Gelat C D, Veccbi M P. Optimization by simulated annealing [J]. Science, 1983, 220: 611-680.
[13] Clere M, Kennedy J. The particle swarm-explosion, stability and convergence in a multi-dimension complex space [J]. IEEE Transactions on Evolutionary Computation, 2002, 6(l): 58-73.
[14] 王东霞, 温秀兰, 赵艺兵. 基于CAD模型引导测量的自由曲面定位及轮廓度误差评定[J]. 光学精密工程, 2012, 20(12): 2720-2727.WANG Dongxia, WEN Xiulan, ZHAO Yibing. Localization and profile error evaluation of freeform surface based on CAD model-directed measurement [J]. Optics and Precision Engineering, 2012, 20(12): 2720-2727. (in Chinese)
[15] 廖平. 基于粒子群算法和分割逼近法的复杂曲面轮廓度误差计算[J]. 中国机械工程, 2010, 21(2): 201-205.LIAO Ping. Calculation of complex surface profile errors based on hybrid particle swarm optimization algorithm [J]. Mechanical Engineering of China, 2010, 21(2): 201-205. (in Chinese)
[16] Akemi G, Andres I. A new iterative mutually coupled hybrid GA-PSO approach for curve fitting in manufacturing [J]. Applied Soft Computing, 2013(13): 1491-1504.
[17] CHANG Fengcheng, Huang H C. A refactoring method for cache-efficient swarm intelligence algorithms [J]. Information Sciences, 2012(192): 39-49.
[18] Chang W A, Jinung A, Jae C Y. Estimation of particle swarm distribution algorithms: Combining the benefits of PSO and EDAs [J]. Information Sciences, 2012(192): 109-119.
[19] ZHAO Xiuyang, ZHANG Caiming, XU Li. IGA-based point cloud fitting using B-spline surfaces for reverse engineering [J]. Information Sciences, 2013(245): 276-289.
[20] Akemi G, Andres I. Particle swarm optimization for non-uniform rational B-spline surface reconstruction from clouds of 3D data points [J]. Information Sciences, 2012 (192): 174-192.
[21] Craig J. Introduction to Robotic: Mechanics and Control [M]. 3rd Ed. Englewood Cliffs, NJ: Prentice Hall, 2005: 48-71.
[22] 王建录, 刘学云, 廖平. 结合分割逼近和粒子群法的燃气轮机叶片轮廓度误差计算[J]. 西安交通大学学报, 2010, 40(7): 42-45.WANG Jianlu, LIU Xueyun, LIAO Ping. Profile error calculation for gas turbine blade based on subdivision approach algorithm and particle swarm optimization [J]. Journal of Xi'an Jiaotong University, 2010, 40(7): 42-45. (in Chinese)
[1] 陈冬青, 张普含, 王华忠. 基于MIKPSO-SVM方法的工业控制系统入侵检测[J]. 清华大学学报(自然科学版), 2018, 58(4): 380-386.
[2] 肖武, 王开锋, 姜晓滨, 贺高红. 遗传-模拟退火算法优化设计管壳式换热器[J]. 清华大学学报(自然科学版), 2016, 56(7): 728-734.
[3] 蔡东阳, 卓子寒, 王婕, 武建安, 唐劲天. 基于模拟退火算法的磁感应治疗热籽分布[J]. 清华大学学报(自然科学版), 2014, 54(2): 153-158.
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
版权所有 © 《清华大学学报(自然科学版)》编辑部
本系统由北京玛格泰克科技发展有限公司设计开发 技术支持:support@magtech.com.cn