Pattern Recognition and Image Analysis

, Volume 26, Issue 1, pp 205–215 | Cite as

Robust world-centric stereo EKF localization with active loop closing for AUVs

  • M. Solbach
  • F. Bonin-Font
  • A. Burguera
  • G. Oliver
  • D. Paulus
Applied Problems
  • 65 Downloads

Abstract

Visual localization is a crucial task in Autonomous Underwater Vehicles (AUV) and it is usually complicated by the extreme irregularity of the natural aquatic environments, or by unfavorable water conditions. Visual Simultaneous Localization and Mapping (SLAM) approaches are widely used in land and represent the most precise techniques for localization, but applied underwater, they are still an open and ongoing challenge. This paper presents a general approach to visual 3D pose-based SLAM based on Extended Kalman Filters (EKF). This approach has a general design being applicable to any vehicle with up to 6 Degrees of freedom, so, it is particularly suitable for AUV. It uses only visual data coming from a stereo camera, all orientations involved in the system are represented in the quaternion space in order to avoid the gimbal lock singularities, and the sparsity of the covariance matrix is guaranteed during the whole trajectory since the state vector only includes the vehicle global pose. The vehicle pose is continuously predicted by means of a stereo visual odometer, and eventually corrected with the pose constraints given by a particularization of the Perspective N-Point problem (PNP) [1], applied to the registration of images that most likely close a loop. Experimental results show the important pose corrections given by the SLAM approach with respect to a ground truth, compared with the evident trajectory errors present in the visual odometer estimates.

Keywords

visual navigation underwater robots EKF SLAM 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    M. Bujnak, S. Kukelova, and T. Pajdla, Lecture Notes Comput. Sci. 6492, 11 (2011).CrossRefGoogle Scholar
  2. 2.
    M. Hildebrandt and F. Kirchner, in Proc. of Oceans (Sydney, 2010).Google Scholar
  3. 3.
    H. Durrant-Whyte and T. Bailey, IEEE Robot. Automation Mag. 13, 99 (2006).CrossRefGoogle Scholar
  4. 4.
    R. Schattschneider, G. Maurino, and W. Wang, in Proc. of Oceans (Waikoloa, 2011), pp. 1–8.Google Scholar
  5. 5.
    J. Salvi, Y. Petillot, and E. Batlle, in Proc. Int. Conf. on Intelligent Robots and Systems (Nice, 2008), pp. 1011–1016.Google Scholar
  6. 6.
    R. Eustice, O. Pizarro, and H. Singh, IEEE J. Ocean. Eng. 33, 103 (2008).CrossRefGoogle Scholar
  7. 7.
    R. Eustice, H. Singh, and J. Leonard, IEEE Trans. Robot. 22, 1100 (2006).CrossRefGoogle Scholar
  8. 8.
    A. Burguera, Y. González, and G. Oliver, in Proc. IEEE Int. Conf. on Intelligent Robots and Systems (IROS) (San Francisco, CA, 2011).Google Scholar
  9. 9.
    R. Smith, P. Cheeseman, and M. Self, in Proc. Int. Symp. on Robotic Research (MIT Press, 1987), pp. 467–474.Google Scholar
  10. 10.
    J. Pujol, Geophysics 8, 1 (2007).CrossRefGoogle Scholar
  11. 11.
    C. Mei, in Proc. IEEE Int. Conf. on Intelligent Robots and Systems (Vilamoura-Algarve, 2012), pp. 3165–3170.Google Scholar
  12. 12.
    M. Quigley, K. Conley, B. Gerkey, J. Faust, T. Foote, J. Leibs, R. Wheeler, and A. Ng, in Proc. ICRA Workshop on Open Source Software (Kobe, 2009).Google Scholar
  13. 13.
    A. Geiger, J. Ziegler, and C. Stiller, in Proc. IEEE Intelligent Vehicles Symp. (Baden-Baden, 2011).Google Scholar
  14. 14.
    D. Ribas, N. Palomeras, P. Ridao, M. Carreras, and A. Mallios, IEEE/ASME Trans. Mechatron. 17, 46 (2012).CrossRefGoogle Scholar
  15. 15.
    P. Negre, F. Bonin-Font, and G. Oliver, in Proc. of Int. Conf. on Intelligent Autonomous Systems (IAS) (Vancouver, 2014).Google Scholar

Copyright information

© Pleiades Publishing, Ltd. 2016

Authors and Affiliations

  • M. Solbach
    • 1
  • F. Bonin-Font
    • 2
  • A. Burguera
    • 2
  • G. Oliver
    • 2
  • D. Paulus
    • 3
  1. 1.Centre for Vision ResearchYork UniversityTorontoCanada
  2. 2.Systems, Robotics and Vision GroupUniversity of the Balearic IslandsPalma de MallorcaSpain
  3. 3.Computational Visualistics GroupUniversity Koblenz-LandauKoblenzGermany

Personalised recommendations