Efficient Plane Detection in Multilevel Surface Maps

• Autores: Víctor Prieto Marañón, Jorge Cabrera Gámez , Antonio Carlos Domínguez Brito, Daniel Hernández Sosa , José Isern González, Enrique Fernández Perdomo
• Localización: JoPha: Journal of Physical Agents, ISSN-e 1888-0258, Vol. 5, Nº. 1, 2011, págs. 15-23
• Idioma: inglés
• DOI: 10.14198/jopha.2011.5.1.03
• Enlaces
  • Texto completo
• Resumen

  • An automatic system aimed at producing a compact tridimensional description of indoor environments using a mobile 3D laser scanner is described in this paper. The resulting description is made up of a Multi-Level Map (ML map) and a series of planar patches extracted from the map. We propose a novel plane detection algorithm, based on the efficient RANSAC algorithm, that operates directly over the data structures of an ML map and does not need to rely on the low level laser data cloud. The mobile 3D scanner is built from a Hokuyo laser range sensor attached to a 2DOF pan-tilt, which is installed on top of a 3DX Pioneer mobile robot. The 3D spatial information acquired by the laser sensor from different poses is used to build a large single map of the environment using the SLAM 6D library. Experimental results demonstrate that the system described is capable of efficiently building compact and accurate 3D representations of complex large indoor environments at multiple semantic levels.

• Referencias bibliográficas
  • [1] Josep Aulinas, Yvan Petillot, Joaquim Salvi, and Xavier Lladó. The SLAM problem: a survey. In Proceeding of the 2008 conference on Artificial...
  • [2] Rudolph Triebel, Patrick Pfaff, and Wolfram Burgard. Multi-level surface maps for outdoor terrain mapping and loop closing. In In Proc....
  • [3] Andreas Nüchter, Kai Lingemann, and Joachim Hertzberg. 6D SLAM with cached K-D tree search. In RA’07: Proceedings of the 13th IASTED International...
  • [4] Ruwen Schnabel, Roland Wahl, and Reinhard Klein. Efficient RANSAC for Point-Cloud Shape Detection. Computer Graphics Forum, 26(2):214–226,...
  • [5] Julian Ryde and Michael Brünig. Non-cubic occupied voxel lists for robot maps. In IROS’09: Proceedings of the 2009 IEEE/RSJ international...
  • [6] Shrihari Vasudevan, Fabio Ramos, Eric Nettleton, and Hugh Durrant-Whyte. Gaussian process modeling of large-scale terrain. J. Field Robot.,...
  • [7] Cesar Rivadeneyra, Isaac Miller, Jonathan R. Schoenberg, and Mark Campbell. Probabilistic estimation of multi-level terrain maps. In ICRA’09:...
  • [8] Zoltan Csaba Marton, Radu Bogdan Rusu, and Michael Beetz. On fast surface reconstruction methods for large and noisy point clouds. In...
  • [9] Kaustubh Pathak, Narunas Vaskevicius, and Andreas Birk. Revisiting uncertainty analysis for optimum planes extracted from 3D range sensor...
  • [10] GuruPrasad M. Hegde and Cang Ye. Extraction of planar features from swissranger sr-3000 range images by a clustering method using normalized...
  • [11] D. Hähnel, W. Burgard, and S. Thrun. Learning compact 3d models of indoor and outdoor environments with a mobile robot. Robotics and...
  • [12] Mariano Martin Nevado, Jaime Gomez Garcia-Bermejo, and Eduardo Zalama Casanova. Obtaining 3d models of indoor environments with a mobile...
  • [13] Martin Heracles, Bram Bolder, and Christian Goerick. Fast detection of arbitrary planar surfaces from unreliable 3D data. In IROS’09:...
  • [14] J. Denavit and R. S. Hartenberg. A kinematic notation for lower-pair mechanisms based on matrices. Trans ASME J. Appl. Mech, 23:215–221,...
  • [15] Andreas Nüchter and K. Lingemann. 6D Simultaneous Localization and Mapping, 2010. [http://slam6d.sourceforge.net](http://slam6d.sourceforge.net).
  • [16] I.T. Jolliffe. Principal Component Analysis. Springer, New York, NY, 1986.