Dense Map Inference with User-Defined Priors: From Priorlets to Scan Eigenvariations

  • Paloma de la Puente
  • Andrea Censi
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7463)


When mapping is formulated in a Bayesian framework, the need of specifying a prior for the environment arises naturally. However, so far, the use of a particular structure prior has been coupled to working with a particular representation. We describe a system that supports inference with multiple priors while keeping the same dense representation. The priors are rigorously described by the user in a domain-specific language. Even though we work very close to the measurement space, we are able to represent structure constraints with the same expressivity as methods based on geometric primitives. This approach allows the intrinsic degrees of freedom of the environment’s shape to be recovered. Experiments with simulated and real data sets will be presented.


Penalty Function Prior Constraint Inference Engine Unconstrained Optimization Problem Consecutive Point 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Beevers, K., Huang, W.: Inferring and Enforcing Relative Constraints in SLAM. In: Algorithmic Foundation of Robotics VII. Springer, Heidelberg (2008)Google Scholar
  2. 2.
    Censi, A.: On achievable accuracy for pose tracking (2009),
  3. 3.
    Chong, K., Kleeman, L.: Sonar based map building for a mobile robot (1997)Google Scholar
  4. 4.
    Grisetti, G., Stachniss, C., Burgard, W.: Improved techniques for grid mapping with Rao-Blackwellized particle filters 23(1), 34–46 (2007)Google Scholar
  5. 5.
    Julier, S., LaViola, J.: On Kalman filtering with nonlinear equality constraints  55(6) (2007)Google Scholar
  6. 6.
    Koller, D., Friedman, N.: Probabilistic Graphical Models: Principles and Techniques. MIT Press (2009)Google Scholar
  7. 7.
    Kümmerle, R., Steder, B., Dornhege, C., Kleiner, A., Grisetti, G., Burgard, W.: Large scale graph-based SLAM using aerial images as prior information. Journal of Autonomous Robots 30(1), 25–39 (2011)CrossRefGoogle Scholar
  8. 8.
    Le, H., Kendall, D.G.: The Riemannian structure of Euclidean shape spaces: A novel environment for statistics. Annals of Statistics 21(3), 1225–1271 (1993)MathSciNetzbMATHCrossRefGoogle Scholar
  9. 9.
    Michor, P.W., Mumford, D.: Riemannian geometries on spaces of plane curves. J. of the European Math. Soc. 8, 1–48 (2004)MathSciNetGoogle Scholar
  10. 10.
    Newman, P.: On the Structure and Solution of the Simultaneous Localisation and Map Building Problem. Ph.D. thesis, U. of Sydney (1999)Google Scholar
  11. 11.
    Nguyen, V., Harati, A., Siegwart, R.: A lightweight SLAM algorithm using orthogonal planes for indoor mobile robotics (2007)Google Scholar
  12. 12.
    Parsley, M.P., Julier, S.J.: Towards the exploitation of prior information in SLAM. In: Proc. of the IEEE Int. Conf. on Intelligent Robots and Systems, IROS (2010)Google Scholar
  13. 13.
    Plagemann, C., Kersting, K., Pfaff, P., Burgard, W.: Gaussian beam processes: A nonparametric bayesian measurement model for range finders. In: Robotics: Science and Systems, RSS (2007)Google Scholar
  14. 14.
    Rodríguez-Losada, D., Matía, F., Jiménez, A., Galán, R.: Consistency improvement for SLAM-EKF for indoor environments (2006)Google Scholar
  15. 15.
    Ruszczynski, A.P.: Nonlinear Optimization. Princeton U. Press (2006)Google Scholar
  16. 16.
    Thrun, S., Burgard, W., Fox, D.: Probabilistic Robotics. MIT Press (2005)Google Scholar
  17. 17.
    Trevor, A.J.B., Rogers, J.G., Nieto, C., Christensen, H.I.: Applying domain knowledge to SLAM using virtual measurements. In: Proc. of the IEEE Int. Conf. on Robotics and Automation, ICRA (2010)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2012

Authors and Affiliations

  • Paloma de la Puente
    • 1
  • Andrea Censi
    • 2
  1. 1.Intelligent Control GroupUniversidad Politecnica de MadridMadridSpain
  2. 2.Engineering and Applied ScienceCalifornia Institute of TechnologyPasadenaUSA

Personalised recommendations