A comparison of methods for line extraction from range data

Abstract The representation of the environment of a models robot by line models is a popular alternative to occupancy grid maps. Line maps require significantly less memorythan occupancy grids and therefore scale better with the size of the environment. They furthermore are more accurate since they do not suffer from discretization problems. In thepast a variety of techniques for learning line maps from range data have been developed. These techniques differ in various aspects such as the way lines are extracted from rangescans, how the lines are updated upon sensory input. There furthermore are techniques that are able to operate online, whereas others postprocess the data. In this paper we comparethree different techniques for learning line models with respect to various parameters such as efficiency and quality of the resulting maps. Experimental results illustrate theadvantages and the disadvantages of the different techniques.

[1]  James L. Crowley,et al.  World modeling and position estimation for a mobile robot using ultrasonic ranging , 1989, Proceedings, 1989 International Conference on Robotics and Automation.

[2]  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.

[3]  John J. Leonard,et al.  Towards Robust Data Association and Feature Modeling for Concurrent Mapping and Localization , 2001, ISRR.

[4]  Bernhard Nebel,et al.  A fast, accurate and robust method for self-localization in polygonal environments using laser range finders , 2001, Adv. Robotics.

[5]  Wolfram Burgard,et al.  Using EM to learn motion behaviors of persons with mobile robots , 2002, IEEE/RSJ International Conference on Intelligent Robots and Systems.

[6]  Robert C. Bolles,et al.  Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography , 1981, CACM.

[7]  Sebastian Thrun,et al.  Learning Hierarchical Object Maps of Non-Stationary Environments with Mobile Robots , 2002, UAI.

[8]  John J. Leonard,et al.  Explore and return: experimental validation of real-time concurrent mapping and localization , 2002, Proceedings 2002 IEEE International Conference on Robotics and Automation (Cat. No.02CH37292).

[9]  Stergios I. Roumeliotis,et al.  Weighted line fitting algorithms for mobile robot map building and efficient data representation , 2003, 2003 IEEE International Conference on Robotics and Automation (Cat. No.03CH37422).

[10]  Richard O. Duda,et al.  Pattern classification and scene analysis , 1974, A Wiley-Interscience publication.

[11]  Sebastian Thrun,et al.  Real-time acquisition of compact volumetric 3D maps with mobile robots , 2002, Proceedings 2002 IEEE International Conference on Robotics and Automation (Cat. No.02CH37292).

[12]  Panos E. Trahanias,et al.  An iterative approach for building feature maps in cyclic environments , 2002, IEEE/RSJ International Conference on Intelligent Robots and Systems.

[13]  Aníbal Ollero,et al.  Map building for a mobile robot equipped with a 2D laser rangefinder , 1994, Proceedings of the 1994 IEEE International Conference on Robotics and Automation.

[14]  Wolfram Burgard,et al.  Using EM to Learn 3D Models of Indoor Environments with Mobile Robots , 2001, ICML.

[15]  Wolfram Burgard,et al.  Map building with mobile robots in dynamic environments , 2003, 2003 IEEE International Conference on Robotics and Automation (Cat. No.03CH37422).

[16]  Roland Siegwart,et al.  Feature extraction and scene interpretation for map-based navigation and map building , 1998, Other Conferences.

[17]  J.-S. Gutmann,et al.  RG mapping: learning compact and structured 2D line maps of indoor environments , 2002, Proceedings. 11th IEEE International Workshop on Robot and Human Interactive Communication.