基于子图分割和自适应噪音方差的2D移动机器人定位方法

doi:10.11896/j.issn.1002-137X.2014.10.005

摘要/Abstract

摘要： 基于子图分割和自适应噪音方差的2D移动机器人定位方法,不仅能有效地检测闭环,而且能更精准地估计移动机器人的位姿。首先,子图分割能够有效提高移动机器人的定位效率,通过匹配局部子图也能提高闭环检测的准确性,减少测量噪音的影响。与之前工作不同的是,根据2D几何特征点的个数来分割子图,使得子图中有足够的特征点,进而提高闭环检测的准确性。其次,在利用unscented卡尔曼滤波(UKF)模型时,使用自适应的噪音方差来估计移动机器人运动路径,使得每次UKF的预测方差与移动机器人当前环境有关,当检测到闭环时,通过UKF融合闭环定位信息,可以更准确地估计机器人位姿。在实验中,首先使用两组经典的移动机器人地图数据来比较基于特征点分割子图的方法与基于帧数分割子图的方法在闭环检测时的准确性；然后使用真实的移动智能车在室内环境进行实验,证明了自适应方差比常量方差有更高的定位精度。

关键词: 2D移动机器人,子图分割,自适应方差,闭环检测,自主定位

Abstract: Submap and adaptive covariance based 2D SLAM solution can not only achieve efficient loop-closure detection but also accurate localization．Firstly,the loop-closure is detected by efficiently matching 2D geometric features between local submaps．Unlike the previous methods which often use the number of the measure frames as the criteria of the division,we employed the number of features as the main criteria．To achieve accurate localization,we proposed an adaptive Kalman filter to estimate the final pose．Moreover,the prediction and observation covariance are adaptive and estimated by the scan-matching algorithm．Finally,if a loop-closure is detected,the optimized transformation and covariance from the backend can be fused directly in the Kalman filter．In the first experiment,the comparison between the two kinds of submap division mechanism verifies the validity of the proposed method．The second experiment shows that the proposed method can accurately localize the robot only using a single lidar.

Key words: 2D mobile robot,Submap division,Adaptive covariance,Loop closure detection,Localization

张贺,刘国良,李南君,侯紫峰. 基于子图分割和自适应噪音方差的2D移动机器人定位方法[J]. 计算机科学, 2014, 41(10): 23-26. https://doi.org/10.11896/j.issn.1002-137X.2014.10.005

ZHANG He,LIU Guo-liang,LI Nan-jun and HOU Zi-feng. Submap and Adaptive Covariance Based Method for 2D Localization[J]. Computer Science, 2014, 41(10): 23-26. https://doi.org/10.11896/j.issn.1002-137X.2014.10.005

参考文献

[1] Bengtsson O,Baerveldt A J．Robot localization based on scan-matchingestimating the covariance matrix for the idc algorithm[J]．Robotics and Autonomous Systems,2003,44(1):29-40
[2] Blanco J L,Fern′andez-Madrigal J A,Gonzalez J．A new approach for large-scale localization and mapping:Hybrid metric-topological slam[C]∥2007 IEEE International Conference on Robotics and Automation．IEEE,2007:2061-2067
[3] Bosse M,Zlot R．Map matching and data association for large-scale two-dimensional laserscan-based slam[J]．The InternationalJournal of Robotics Research,2008,27(6):667-691
[4] Howard A,Mataric M J,Sukhatme G．Relaxation on a mesh:a formalism for generalized localization[C]∥2001 IEEE/RSJ International Conference on Intelligent Robots and Systems．IEEE,2001,2:1055-1060
[5] Bosse M C．Atlas:a framework for large scale automated mapping and localization[D]．Massachusetts Institute of Technology,2004
[6] Censi A．An accurate closed-form estimate of icp’s covariance[C]∥2007 IEEE International Conference on Robotics and Automation．IEEE,2007:3167-3172
[7] Censi A．An icp variant using a point-to-line metric[C]∥ICRA 2008.IEEE International Conference on Robotics and Automation．IEEE,2008:19-25 (下转第30页)(上接第26页)
[8] Schnabel R,Wahl R,Klein R．Efficient RANSAC for Point-Cloud Shape Detection[J]．Computer Graphics Forum,2007,26(2):214-226
[9] Kummerle R,Grisetti G,Stras-dat H,et al.g2o:A generalframework for graph optimization[C]∥2011 IEEE International Conference on Robotics and Automation (ICRA)．IEEE,2011:3607-3613
[10] Tipaldi G D,Arras K O．Flirt-interest regions for 2d range data[C]∥2010 IEEE International Conference on Robotics and Automation (ICRA)．IEEE,2010:3616-3622
[11] Van Der Merwe R,Wan E A．The square-root unscented kalman filter for state and parameter-estimation[C]∥2001 IEEE International Conference on Acoustics,Speech,and Signal Processing,2001(ICASSP’01)．IEEE,2001,6:3461-3464
[12] Zhang H,Hou Z,Li N,et al.A graph-based hierarchical slam framework for large-scale mapping[J]．Intelligent Robotics and Applications,2012,7507:439-448
[13] Zlot R,Bosse M．Place recognition using keypoint similarities in 2D lidar maps[C]∥Experimental Robotics．Springer Berlin Heidelberg,2009:363-372
[14] Guivant J,Nebot E．Optimization of the simultaneous localiza-tion and map building algorithm for real time implementation[J]．IEEE Transactions on Robotics and Automation,2001,17(3):242-257
[15] Nieto,Juan,Bailey T,et al.Scan-slam:Combining ekf-slam and scan correlation[C]∥Field and service robotics．Springer Berlin Heidelberg,2006:167-178
[16] Martinez-Cantin R,Castellanos J A．Unscented slam for large-scale outdoor environments[C]∥IEEE/RSJ Intl．Conf．on Intelligent Robots and Systems．2005:328-333
[17] Montemerlo M,Thrun S．Simultaneous localization and mappingwith unknown data association using FastSLAM[C]∥the Proceedings of the 2003 IEEE International Conference on Robotics & Automation (ICRA’03)．IEEE,2003:1985-1991
[18] Eliazar A,Parr R．Dp-slam:Fast,robust simultaneous localiza-tion and mapping without predetermined landmarks[C]∥International Joint Conference on Artificial Intelligence．Lawrence Erlbaum Associates LTD,2003,18:1135-1142
[19] Olson E B．Real-time correlative scan matching[C]∥IEEE International Conference on Robotics and Automation(ICRA’09)．IEEE,2009:4387-4393
[20] Olson E B．Robust and efficient robotic mapping[D]．Massachusetts Institute of Technology,Department of Electrical Engineering and Computer Science,2008
[21] Borges G A,Aldon M J．Line extraction in 2d range images for mobile robotics[J]．Journal of Intelligent & Robotic Systems,2004,40(3):267-297
[22] Nunez P,Vazquez-Martin R,del Toro J C,et al.Feature extrac-tion from laser scan data based on curvature estimation for mobile robotics[C]∥Proceedings 2006 IEEE International Conference on Robotics and Automation(ICRA 2006)．IEEE,2006:1167-1172
[23] Li Y,Olson E B．Extracting general-purpose features from lidar data[C]∥2010 IEEE International Conference on Robotics and Automation (ICRA)．IEEE,2010:1388-1393

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed