[1]孙自飞,钱堃,马旭东,等.多传感器的移动机器人可定位性估计与自定位[J].智能系统学报,2017,(04):443-449.[doi:10.11992/tis.201607007]
 SUN Zifei,QIAN Kun,MA Xudong,et al.Self-localization of mobile robot in dynamic environments based onlocalizability estimation with multi-sensor observation[J].CAAI Transactions on Intelligent Systems,2017,(04):443-449.[doi:10.11992/tis.201607007]
点击复制

多传感器的移动机器人可定位性估计与自定位(/HTML)
分享到:

《智能系统学报》[ISSN:1673-4785/CN:23-1538/TP]

卷:
期数:
2017年04期
页码:
443-449
栏目:
出版日期:
2017-08-25

文章信息/Info

Title:
Self-localization of mobile robot in dynamic environments based onlocalizability estimation with multi-sensor observation
作者:
孙自飞1 钱堃12 马旭东12 戴先中12
1. 东南大学 自动化学院, 江苏 南京 210096;
2. 复杂工程系统测量与控制教育部重点实验室, 江苏 南京 210096
Author(s):
SUN Zifei1 QIAN Kun12 MA Xudong12 DAI Xianzhong12
1. School of Automation, Southeast University, Nanjing 210096, China;
2. Key Laboratory of Measurement and Control of Complex Systems of Engineering, Ministry of Education, Nanjing 210096, China
关键词:
动态环境自主定位RGB-D传感器Fisher信息矩阵人体检测可定位性在线估计移动机器人
Keywords:
dynamic environmentself-localizationRGB-D sensorFisher information matrixpeople-detectinglocalizabilityonline estimationmobile robot
分类号:
TP24
DOI:
10.11992/tis.201607007
摘要:
针对有人干扰的动态室内环境,利用可定位性估计理论提出一种RGB-D传感器辅助激光传感器的移动机器人可靠自定位方法。利用RGB-D传感器信息快速检测人的位置区域,并通过坐标转换计算激光扫描数据中的动态障碍物影响因子,结合离散化Fisher信息矩阵在线估计观测信息的可定位性矩阵;同时通过预测模型协方差矩阵评价里程计信息的可靠性,从而动态补偿观测信息对粒子集的影响。在典型含多人运动的动态室内环境中实验,结果验证了本文方法能够提高机器人自定位的准确性和可靠性。
Abstract:
Based on the localizability estimation theory, in this paper, we propose a new method for the reliable self-localization of mobile robots in a disturbed dynamic indoor environment by the adoption of an RGB-D sensor to assist the laser scanner. People’s location areas are rapidly detected in RGB-D data, which are then transformed to the laser sensor coordinate to compute the influence of the dynamic obstacles on the laser data. In combination with the discrete Fisher information matrix, we estimate the localizability matrix of the observation information online. In addition, we assess the reliability of the information in odometers by the covariance matrix of the prediction model, thereby dynamically compensating for the effect of the observation information on the particle set. We conducted experiments in a dynamic indoor environment and the results confirm the accuracy and reliability of the proposed robot localization method.

参考文献/References:

[1] SAARINEN J, ANDREASSON H, STOYANOV T, et al. Normal distributions transform Monte-Carlo localization(NDT-MCL)[C]//2013 IEEE/RSJ International Conference on Intelligent Robots and Systems. Tokyo, Japan, 2013:382-389.
[2] VALENCIA R, SAARINEN J, ANDREASSON H, et al. Localization in highly dynamic environments using dual-timescale NDT-MCL[C]//2014 IEEE International Conference on Robotics and Automation (ICRA). Hong Kong, China, 2014:3956-3962.
[3] RÖWEKÄMPER J, SPRUNK C, TIPALDI G D, et al. On the position accuracy of mobile robot localization based on particle filters combined with scan matching[C]//2012 IEEE/RSJ International Conference on Intelligent Robots and Systems. Vilamoura, Portugal, 2012:3158-3164.
[4] DELLAERT F, FOX D, BURGARD W, et al. Monte Carlo localization for mobile robots[C]//Proceedings of the 1999 IEEE International Conference on Robotics and Automation. Detroit, USA, 1999:1322-1328.
[5] CENSI A. An ICP variant using a point-to-line metric[C]//2008 IEEE International Conference on Robotics and Automation. Pasadena, USA, 2008:19-25.
[6] 王炜. 移动机器人的可定位估计及其应用[D].上海:上海交通大学, 2012:21-43.WANG Wei. Localizability estimation for mobile robot and its application[D]. Shanghai:Shanghai JiaoTong University, 2012:21-43.
[7] 苗少帅,周峰. IMM迭代无迹Kalman粒子滤波目标跟踪算法[J]. 重庆邮电大学学报:自然科学版, 2015, 27(01):44-48.MIAO Shaoshuai, ZHOU Feng. IMM iterated unscented Kalman particle filter algorithm for target tracking[J]. Journal of Chongqing university of posts and telecommunications:natural science edition, 2015, 27(01):44-48.
[8] 张闯,郭晨. 二阶自适应权值粒子滤波的多传感器信息融合[J]. 哈尔滨工程大学学报, 2016, 37(10):1347-1352.ZHANG Chuang, GUO Chen. Multi-sensor information fusion of a particle filter on the basis of a two-stage adaptive weight[J]. Journal of Harbin engineering university, 2016, 37(10):1347-1352.
[9] 段鹏. 与人共融的家庭服务机器人定位与导航[D].济南:山东大学, 2015:39-58.DUAN Peng. Localization and navigation of home service robot in considering of human-robot harmony[D]. Ji’nan, China:Shandong University, 2015:39-58.
[10] CHOI W, PANTOFARU C, SAVARESE S. Detecting and tracking people using an RGB-D camera via multiple detector fusion[C]//2011 IEEE International Conference on Computer Vision Workshops. Barcelona, Spain, 2011:1076-1083.
[11] SPINELLO L, ARRAS K O. People detection in RGB-D data[C]//2011 IEEE/RSJ International Conference on Intelligent Robots and Systems. San Francisco, USA, 2011:3838-3843.
[12] 王勇, 陈卫东, 王景川,等. 面向拥挤环境的移动机器人改进粒子滤波定位[J]. 机器人, 2012, 34(5):596-603.WANG Yong, CHEN Weidong, WANG Jingchuan, et al. Improved particle filter localization in crowded environments for mobile Robots[J]. Robot, 2012, 34(5):596-603.
[13] CENSI A. On achievable accuracy for range-finder localization[C]//2007IEEE International conference on Robotics and Automation. Roma, Italy, 2007:4170-4175.
[14] DALAL N, TRIGGS B. Histograms of oriented gradients for human detection[C]//2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. San Diego, USA, 2005:886-893.
[15] ROS[EB/OL].[2016-05-14].http://wiki.ros.org/.
[16] RUSU R B, COUSINS S. 3D is here:Point Cloud Library (PCL)[C]//2011 IEEE International Conference on Robotics and Automation (ICRA). Shanghai, China, 2011:1-4.
[17] MUNARO M, et al. News articles[EB/OL].[2016-04-26]. http://www.pointclouds.org/news/.
[18] GERKEY B. Gmapping[EB/OL].[2016-06-18]. wiki.ros.org/gmapping.

相似文献/References:

[1]冷静,刘健,徐红丽.实时避碰的无人水面机器人在线路径规划方法[J].智能系统学报,2015,(03):343.[doi:10.3969/j.issn.1673-4785.201405012]
 LENG Jing,LIU Jiang,XU Hongli.Online path planning of an unmanned surface vehicle for real-time collision avoidance[J].CAAI Transactions on Intelligent Systems,2015,(04):343.[doi:10.3969/j.issn.1673-4785.201405012]

备注/Memo

备注/Memo:
收稿日期:2016-07-08。
基金项目:国家自然科学基金项目(61573100,61573101);中央高校基本科研业务费专项基金(2242013K30004).
作者简介:孙自飞,男,1990年生,硕士研究生,主要研究方向为移动机器人定位;钱堃,男,1982年生,副教授,IEEE会员、中国自动化学会会员,主要研究方向为服务机器人技术,主持国家自然科学基金项目2项并参与多项省部级科研项目,发表学术论文40余篇;马旭东,男,1962年生,教授,主要研究方向为网络化移动机器人、工业机器人与工业自动化,先后承担或参加国家、省部级科研项目15项,横向合作课题20项,发表学术论文80余篇。
通讯作者:钱堃,E-mail:kqian@seu.edu.cn.
更新日期/Last Update: 2017-08-25