[1]胡欢,孙汉旭,贾庆轩.基于在线重建的遥操作预测显示系统[J].东南大学学报(自然科学版),2015,45(3):448-454.[doi:10.3969/j.issn.1001-0505.2015.03.007]
 Hu Huan,Sun Hanxu,Jia Qingxuan.On-line reconstruction-based predictive display system for teleoperation[J].Journal of Southeast University (Natural Science Edition),2015,45(3):448-454.[doi:10.3969/j.issn.1001-0505.2015.03.007]
点击复制

基于在线重建的遥操作预测显示系统()
分享到:

《东南大学学报(自然科学版)》[ISSN:1001-0505/CN:32-1178/N]

卷:
45
期数:
2015年第3期
页码:
448-454
栏目:
自动化
出版日期:
2015-05-20

文章信息/Info

Title:
On-line reconstruction-based predictive display system for teleoperation
作者:
胡欢孙汉旭贾庆轩
北京邮电大学自动化学院, 北京100876
Author(s):
Hu Huan Sun Hanxu Jia Qingxuan
Automation School, Beijing University of Posts and Telecommunications, Beijing 100876, China
关键词:
预测显示 遥操作 同步定位与地图构建 机器视觉
Keywords:
predictive display teleoperation simultaneous localization and mapping(SLAM) robot vision
分类号:
TP242
DOI:
10.3969/j.issn.1001-0505.2015.03.007
摘要:
为了提高遥操作的操作效率,采用一种基于单目视觉的预测显示方法来解决时延导致的视觉反馈滞后问题.该方法通过基于地图的相机位姿估计算法来实时跟踪机器人的状态,在线构建机器人工作环境的三维几何结构模型,并结合多纹理映射技术进行渲染,将模型重投影到预测视点下,得到逼真的预测图像.搭建了一个基于客户端-服务器端模式的系统平台,用于未知环境下的遥操作.结果表明,在总长为7.112 m的摄像机运动轨迹中,位姿跟踪的平均误差约为0.015 m.该系统不仅能提供预测图像,而且支持生成任意视点的图像,有利于操作者从各个角度观察机器人工作场景.
Abstract:
To improve the operation efficiency of teleoperation, a predictive display method based on monocular vision is proposed for solving the visual feedback delay problem caused by time delay. In this method, the robot’s poses are tracked in real-time by the map-based camera pose estimation algorithm. The three-dimensional geometry model under robot working environments is reconstructed on-line with rendering by multiple texture mapping technology. Finally, the realistic predicted image is obtained by projecting the model into the predicted view. The system platform based on the client-server architecture is constructed which is suitable for teleoperation under unknown environments. The experimental results show that the average error of pose tracking is about 0.015 m over a camera journey of 7.112 m. The proposed system can not only supply the predicted images, but also support to generate the images of arbitrary views, which benefits the operator observing the working environments of the robot from all angles.

参考文献/References:

[1] 王永, 谢圆, 周建亮. 空间机器人大时延遥操作技术研究综述[J]. 宇航学报, 2010, 31(2): 299-306.
  Wang Yong, Xie Yuan, Zhou Jianliang. A research survey on teleoperation of space robot through time delay[J]. Journal of Astronautics, 2010, 31(2): 299-306.(in Chinese)
[2] 孙汉旭, 胡欢, 贾庆轩,等. 遥操作系统中预测显示技术研究[J]. 宇航学报, 2013, 34(11): 1502-1508.
  Sun Hanxu, Hu Huan, Jia Qingxuan, et al. Research on predictive display in teleoperation system[J]. Journal of Astronautics, 2013, 34(11): 1502-1508.(in Chinese)
[3] Xie T, Xie L J, He L S, et al. A general framework of augmented reality aided teleoperation guidance[J]. Journal of Information and Computational Science, 2013, 10(5): 1325-1335.
[4] Jägersand M. Image-based predictive display for high d.o.f. uncalibrated tele-manipulation using affine and intensity subspace models[J]. Advanced Robotics, 2001, 14(8): 683-701.
[5] Kelly A, Chan N, Herman H, et al. Real-time photorealistic virtualized reality interface for remote mobile robot control[J]. The International Journal of Robotics Research, 2011, 30(3): 384-404.
[6] Rachmielowski A, Birkbeck N, Jagersand M. Performance evaluation of monocular predictive display[C]//IEEE International Conference on Robotics and Automation. Anchorage, Alaska, USA, 2010: 5309-5314.
[7] Mair E, Hager G D, Burschka D, et al. Adaptive and generic corner detection based on the accelerated segment test[C]//11th European Conference on Computer Vision. Heraklion, Greece, 2010: 183-196.
[8] Wu F C, Hu Z Y. 5-point and 4-point algorithm to determine of the fundamental matrix[J]. Acta Automatica Sinica, 2003, 29(2): 175-180.
[9] Klein G, Murray D. Parallel tracking and mapping for small AR workspaces[C]//6th IEEE and ACM International Symposium on Mixed and Augmented Reality. Nara, Japan, 2007: 225-234.
[10] Szeliski R. 计算机视觉——算法与应用[M]. 艾海舟,等译. 北京:清华大学出版社, 2012: 575-581.
[11] Blanco J L. A tutorial on SE(3)transformations and on-manifold optimization[R]. Seville, Spain: University of Malaga, 2010.
[12] Miller G L, Pav S E, Walkington N. Fully incremental 3D delaunay refinement mesh generation[C]//Proceedings of the International Meshing Roundtable(IMR). Ithaca, NY, USA, 2002: 75-86.
[13] Cousins S. Exponential growth of ROS [ROS topics][J]. IEEE Robotics & Automation Magazine, 2011, 18(1): 19-20.
[14] Sturm J, Engelhard N, Endres F, et al. A benchmark for the evaluation of RGB-D SLAM systems[C]//2012 IEEE/RSJ International Conference on Intelligent Robots and Systems. Vilamoura, Portugal, 2012: 573-580.

相似文献/References:

[1]崔建伟,宋爱国,黄惟一.遥操作系统中MOTOMAN-SV3X机器人的运动建模研究[J].东南大学学报(自然科学版),2003,33(4):424.[doi:10.3969/j.issn.1001-0505.2003.04.011]
 Cui Jianwei,Song Aiguo,Huan Weiyi.Research on kinematics modeling of MOTOMAN-SV3X robot in teleoperate system[J].Journal of Southeast University (Natural Science Edition),2003,33(3):424.[doi:10.3969/j.issn.1001-0505.2003.04.011]
[2]刘威,宋爱国,李会军.力觉临场感机器人基于在线修正虚拟模型的远程控制[J].东南大学学报(自然科学版),2006,36(2):242.[doi:10.3969/j.issn.1001-0505.2006.02.013]
 Liu Wei,Song Aiguo,Li Huijun.Force-reflecting teleoperation of robot based on on-line correction of virtual model[J].Journal of Southeast University (Natural Science Edition),2006,36(3):242.[doi:10.3969/j.issn.1001-0505.2006.02.013]

备注/Memo

备注/Memo:
收稿日期: 2014-12-19.
作者简介: 胡欢(1986—),女,博士生;孙汉旭(联系人),男,博士,教授,博士生导师,hxsun@bupt.edu.cn.
基金项目: 国家自然科学基金资助项目(61175080)、国家重点基础研究发展计划(973计划)资助项目(2013CB733000).
引用本文: 胡欢,孙汉旭,贾庆轩.基于在线重建的遥操作预测显示系统[J].东南大学学报:自然科学版,2015,45(3):448-454. [doi:10.3969/j.issn.1001-0505.2015.03.007]
更新日期/Last Update: 2015-05-20