KI - Künstliche Intelligenz

, Volume 24, Issue 3, pp 249–254 | Cite as

Surface Representations for 3D Mapping

A Case for a Paradigm Shift
  • Andreas Birk
  • Kaustubh Pathak
  • Narunas Vaskevicius
  • Max Pfingsthorn
  • Jann Poppinga
  • Sören Schwertfeger
Fachbeitrag

Abstract

Point clouds, i.e., sets of 3D coordinates of surface point samples from obstacles, are the predominant form of representation for 3D mapping. They are the raw data format of most 3D sensors and the basis for state of the art algorithms for 3D scan registration. It is argued here that point clouds have severe limitations and a case is made for a necessary paradigm shift to surface based representations. In addition to several conceptual arguments, it is shown how a surface based approach can be used for fast and robust registration of 3D data without the need for robot motion estimates from other sensors. Concretely, a short overview on own work dubbed 3D Plane SLAM is presented. It features an extraction of planes with uncertainties from 3D range scans. Two scans can then be registered by determining the correspondence set that maximizes the global rigid body motion constraint while finding the related optimal decoupled rotations and translations with their underlying uncertainties. The registered scans are embedded in pose-graph SLAM for loop closing and relaxation.

Keywords

3D Mapping Registration Simultaneous localization and mapping (SLAM) 

References

  1. 1.
    Besl PJ, McKay ND (1992) A method for registration of 3-d shapes. IEEE Trans Pattern Anal Mach Intell 14(2):239–256 CrossRefGoogle Scholar
  2. 2.
    Chen Y, Medioni G (1991) Object modeling by registration of multiple range images. In: Proceedings of the 1991 IEEE international conference on robotics and automation, vol 3, pp 2724–2729 Google Scholar
  3. 3.
    Chen Y, Medioni G (1992) Object modeling by registration of multiple range images. Image Vis Comput 10(3):145–155 CrossRefGoogle Scholar
  4. 4.
    Duckett T, Marsland S, Shapiro J (2002) Fast on-line learning of globally consistent maps. Auton Robots 12(3):287–300 MATHCrossRefGoogle Scholar
  5. 5.
    Fischer D, Kohlhepp P (2000) 3D geometry reconstruction from multiple segmented surface descriptions using neuro-fuzzy similarity measures. J Intell Robot Syst 29:389–431 MATHCrossRefGoogle Scholar
  6. 6.
    Kohlhepp P, Bretthauer G, Walther M, Dillmann R (2006) Using orthogonal surface directions for autonomous 3d-exploration of indoor environments. In: IEEE/RSJ international conference on intelligent robots and systems, pp 3086–3092, October 2006 Google Scholar
  7. 7.
    Kohlhepp P, Pozzo P, Walther M, Dillmann R (2004) Sequential 3D-SLAM for mobile action planning. In: Proceedings of the 2004 IEEE/RSJ international conference on intelligent robots and systems (IROS 2004), vol 1, pp. 722–729 Google Scholar
  8. 8.
    Magnusson M, Lilienthal A, Duckett T (2007) Scan registration for autonomous mining vehicles using 3D-NDT. J Field Robot 24(10):803–827 CrossRefGoogle Scholar
  9. 9.
    Olson E, Leonard J, Teller S (2006) Fast iterative alignment of pose graphs with poor initial estimates. In: Proceedings of the 2006 IEEE international conference on robotics and automation (ICRA 2006), pp 2262–2269, May 2006 Google Scholar
  10. 10.
    Patrak K, Birk A, Poppinga J, Vaskevicius N (2009) Fast registration based on noisy planes with unknown correspondences for 3d mapping. Under review. Manuscript available online at http://robotics.jacobs-university.de/projects/3Dmap/PlaneMatching-UnderReview.pdf
  11. 11.
    Pathak K, Birk A, Vaskevicius N, Pfingsthorn M, Schwertfeger S, Poppinga J, (2010) Online 3D SLAM by registration of large planar surface segments and closed form pose-graph relaxation. J Field Robot 27(1):52–84 CrossRefGoogle Scholar
  12. 12.
    Patrak K, Birk A, Vaskevicius N, Poppinga J (2010) Fast registration based on noisy planes with unknown correspondences for 3D mapping. IEEE Trans Robot (2010). doi:10.1109/TRO.2010.2042989
  13. 13.
    Pathak K, Vaskevicius N, Birk A (2009) Revisiting uncertainty analysis for optimum planes extracted from 3D range sensor point-clouds. In: IEEE international conference on robotics and automation, Kobe, Japan Google Scholar
  14. 14.
    Pfingsthorn M, Birk A (2008) Efficiently communicating map updates with the pose graph. In: Proceedings of the international conference on intelligent robots and systems (IROS) Google Scholar
  15. 15.
    Pfingsthorn M, Slamet B, Visser A (2007) A scalable hybrid multi-robot slam method for highly detailed maps. In: RoboCup 2007: proceedings of the international symposium. LNAI. Springer, Berlin Google Scholar
  16. 16.
    Poppinga J, Vaskevicius N, Birk A, Pathak K (2008) Fast plane detection and polygonalization in noisy 3D range images. In: IEEE international conference on intelligent robots and systems (IROS), Nice, France Google Scholar
  17. 17.
    Vaskevicius N, Birk A, Pathak K Schwertfeger S Rathnam R (2010) Efficient representation in 3D environment modeling for planetary robotic exploration. Adv Robot 24(8–9) Google Scholar
  18. 18.
    Weingarten J, Siegwart R (2006) 3D SLAM using planar segments. In: IEEE/RSJ international conference on intelligent robots and systems (IROS), Beijing Google Scholar
  19. 19.
    Weingarten J (2006) Feature-based 3D SLAM. PhD thesis, EPFL, Lausanne, Switzerland Google Scholar

Copyright information

© Springer-Verlag 2010

Authors and Affiliations

  • Andreas Birk
    • 1
  • Kaustubh Pathak
    • 1
  • Narunas Vaskevicius
    • 1
  • Max Pfingsthorn
    • 1
  • Jann Poppinga
    • 1
  • Sören Schwertfeger
    • 1
  1. 1.Jacobs UniversityBremenGermany

Personalised recommendations