3D map building method with mobile mapping system in indoor environments

This paper presents three dimensional (3D) map building method for the intelligent vehicles based on accurate indoor localization using a mobile mapping system (MMS) that is equipped with perception sensors consist of a wheel odometer, a laser range finder (LRF), and two projected texture stereo (PTS) cameras. The environmental data measured by perception sensors are stored in the node units according to a certain distance interval. In order to estimate the positions of the MMS using the relationship among nodes, the localization method is divided into two parts, front-end (map-based scan matching) and back-end (graph-based optimization). The estimated positions are used to build the grid-based map and the point cloud dataset, respectively as the 2D and the 3D maps through the mapping process (Bayesian model). An experiment has been performed in office environment (indoor) to verify the effectiveness of the proposed method. Experimental results show the high precision of 3D point cloud dataset that can be used for various applications including navigation of intelligent vehicles and pedestrians in indoor evironments.

[1]  Jong Hwan Lim,et al.  Sonar Map Construction for Autonomous Mobile Robots Using a Data Association Filter , 2009, Adv. Robotics.

[2]  Lindsay Kleeman,et al.  Fast Laser Scan Matching using Polar Coordinates , 2007, Int. J. Robotics Res..

[3]  Evangelos E. Milios,et al.  Robot Pose Estimation in Unknown Environments by Matching 2D Range Scans , 1994, 1994 Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.

[4]  Hugh F. Durrant-Whyte,et al.  Simultaneous localization and mapping: part I , 2006, IEEE Robotics & Automation Magazine.

[5]  Joachim Hertzberg,et al.  Indoor and outdoor localization for fast mobile robots , 2004, 2004 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) (IEEE Cat. No.04CH37566).

[6]  Wolfram Burgard,et al.  A Tutorial on Graph-Based SLAM , 2010, IEEE Intelligent Transportation Systems Magazine.

[7]  Timothy S. Bailey,et al.  Mobile Robot Localisation and Mapping in Extensive Outdoor Environments , 2002 .

[8]  Paul Newman,et al.  Navigating, Recognizing and Describing Urban Spaces With Vision and Lasers , 2009, Int. J. Robotics Res..

[9]  Paul J. Besl,et al.  A Method for Registration of 3-D Shapes , 1992, IEEE Trans. Pattern Anal. Mach. Intell..

[10]  Nico Blodow,et al.  Real-time compression of point cloud streams , 2012, 2012 IEEE International Conference on Robotics and Automation.

[11]  Hugh Durrant-Whyte,et al.  Simultaneous localization and mapping (SLAM): part II , 2006 .

[12]  Impyeong Lee,et al.  Precise Geometric Registration of Aerial Imagery and LIDAR Data , 2011 .

[13]  Dong-Woo Cho.  Certainty Grid Representation for Robot Navigation by a Bayesian Method , 1990, Robotica.