Advertisement

Autonomous Robots

, Volume 30, Issue 1, pp 25–39 | Cite as

Large scale graph-based SLAM using aerial images as prior information

  • Rainer Kümmerle
  • Bastian Steder
  • Christian Dornhege
  • Alexander Kleiner
  • Giorgio Grisetti
  • Wolfram Burgard
Article

Abstract

The problem of learning a map with a mobile robot has been intensively studied in the past and is usually referred to as the simultaneous localization and mapping (SLAM) problem. However, most existing solutions to the SLAM problem learn the maps from scratch and have no means for incorporating prior information. In this paper, we present a novel SLAM approach that achieves global consistency by utilizing publicly accessible aerial photographs as prior information. It inserts correspondences found between stereo and three-dimensional range data and the aerial images as constraints into a graph-based formulation of the SLAM problem. We evaluate our algorithm based on large real-world datasets acquired even in mixed in- and outdoor environments by comparing the global accuracy with state-of-the-art SLAM approaches and GPS. The experimental results demonstrate that the maps acquired with our method show increased global consistency.

Keywords

Mapping Localization Aerial images 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. Bay, H., Tuytelaars, T., & Van Gool, L. (2006). Surf: Speeded up robust features. In Proc. of the European conf. on computer vision (ECCV). Google Scholar
  2. Canny, J. (1986). A computational approach to edge detection. IEEE Transactions on Pattern Analysis and Machine Intelligence, 8(6), 679–698. CrossRefGoogle Scholar
  3. Chen, C., & Wang, H. (2007). Large-scale loop-closing by fusing range data and aerial image. International Journal of Robotics and Automation, 22(2), 160–169. CrossRefGoogle Scholar
  4. Davis, T. A. (2006). Direct methods for sparse linear systems. SIAM book series on the fundamentals of algorithms. Philadelphia: SIAM. zbMATHGoogle Scholar
  5. Dellaert, F., Fox, D., Burgard, W., & Thrun, S. (1998). Monte Carlo localization for mobile robots. In Proc. of the IEEE int. conf. on robotics & automation (ICRA). Google Scholar
  6. Ding, M., Lyngbaek, K., & Zakhor, A. (2008). Automatic registration of aerial imagery with untextured 3d lidar models. In Proc. of the IEEE conf. on computer vision and pattern recognition (CVPR). Google Scholar
  7. Dogruer, C. U., Bugra, K. A., & Dolen, M. (2007). Global urban localization of outdoor mobile robots using satellite images. In Proc. of the int. conf. on intelligent robots and systems (IROS). Google Scholar
  8. Doucet, A., de Freitas, N., & Gordan, N. (Eds.) (2001). Sequential Monte-Carlo methods in practice. Berlin: Springer. zbMATHGoogle Scholar
  9. Eustice, R., Singh, H., & Leonard, J. J. (2005). Exactly sparse delayed-state filters. In Proc. of the IEEE int. conf. on robotics & automation (ICRA) (pp. 2428–2435). Google Scholar
  10. Foley, J. D., Van Dam, A., Feiner, K., Hughes, J. F., & Phillips, R. L. (1993). Introduction to computer graphics. Reading: Addison-Wesley. Google Scholar
  11. Frese, U., Larsson, P., & Duckett, T. (2005). A multilevel relaxation algorithm for simultaneous localisation and mapping. IEEE Transactions on Robotics, 21(2), 1–12. CrossRefGoogle Scholar
  12. Früh, C., & Zakhor, A. (2004). An automated method for large-scale, ground-based city model acquisition. International Journal of Computer Vision, 60, 5–24. CrossRefGoogle Scholar
  13. Grisetti, G., Stachniss, C., & Burgard, W. (2005). Improving grid-based SLAM with Rao-Blackwellized particle filters by adaptive proposals and selective resampling. In Proc. of the IEEE int. conf. on robotics & automation (ICRA) (pp. 2443–2448). Google Scholar
  14. Grisetti, G., Stachniss, C., & Burgard, W. (2009, in press). Non-linear constraint network optimization for efficient map learning. IEEE Transactions on Intelligent Transportation Systems. Google Scholar
  15. Gutmann, J.-S., & Konolige, K. (1999). Incremental mapping of large cyclic environments. In Proc. of the IEEE int. symposium on computational intelligence in robotics and automation (CIRA). Google Scholar
  16. Howard, A. (2004). Multi-robot mapping using manifold representations. In Proc. of the IEEE int. conf. on robotics & automation (ICRA) (pp. 4198–4203). Google Scholar
  17. Julier, S., Uhlmann, J., & Durrant-Whyte, H. (1995). A new approach for filtering nonlinear systems. In Proc. of the american control conference (pp. 1628–1632). Google Scholar
  18. Korah, T., & Rasmussen, C. (2004). Probabilistic contour extraction with model-switching for vehicle localization. In IEEE intelligent vehicles symposium (pp. 710–715). Google Scholar
  19. Kümmerle, R., Steder, B., Dornhege, C., Kleiner, A., Grisetti, G., & Burgard, W. (2009). Large scale graph-based SLAM using aerial images as prior information. In Proc. of robotics: science and systems (RSS), Seattle, WA, USA, June 2009. Google Scholar
  20. Lee, K. W., Wijesoma, S., & Guzmán, J. I. (2007). A constrained slam approach to robust and accurate localisation of autonomous ground vehicles. Robotics and Autonomous Systems, 55(7), 527–540. CrossRefGoogle Scholar
  21. Leonard, J. J., & Durrant-Whyte, H. F. (1991). Mobile robot localization by tracking geometric beacons. IEEE Transactions on Robotics and Automation, 7(4), 376–382. CrossRefGoogle Scholar
  22. Leung, K. Y. K., Clark, C. M., & Huissoon, J. P. (2008). Localization in urban environments by matching ground level video images with an aerial image. In Proc. of the IEEE int. conf. on robotics & automation (ICRA). Google Scholar
  23. Lu, F., & Milios, E. (1997). Globally consistent range scan alignment for environment mapping. Journal of Autonomous Robots, 4, 333–349. CrossRefGoogle Scholar
  24. Montemerlo, M., & Thrun, S. (2004). Large-scale robotic 3-d mapping of urban structures. In Proc. of the int. symposium on experimental robotic (ISER) (pp. 141–150). Google Scholar
  25. Montemerlo, M., Thrun, S., Koller, D., & Wegbreit, B. (2003). FastSLAM 2.0: An improved particle filtering algorithm for simultaneous localization and mapping that provably converges. In Proc. of the int. conf. on artificial intelligence (IJCAI) (pp. 1151–1156). Google Scholar
  26. Olson, E. (2008). Robust and efficient robotic mapping. PhD thesis, Massachusetts Institute of Technology, Cambridge, MA, USA. Google Scholar
  27. Olson, E., Leonard, J., & Teller, S. (2006). Fast iterative optimization of pose graphs with poor initial estimates. In Proc. of the IEEE int. conf. on robotics & automation (ICRA) (pp. 2262–2269). Google Scholar
  28. Parsley, M., & Julier, S. J. (2009). Slam with a heterogeneous prior map. In SEAS-DTC conference. Google Scholar
  29. Press, W. H., Teukolsky, S. A., Vetterling, W. T., & Flannery, B. P. (1992). Numerical Recipes (2nd edn.). Cambridge: Cambridge University Press. Google Scholar
  30. Smith, R., Self, M., & Cheeseman, P. (1990). Estimating uncertain spatial relationships in robotics. In I. Cox & G. Wilfong (Eds.), Autonomous robot vehicles (pp. 167–193). Berlin: Springer. Google Scholar
  31. Sofman, B., Ratliff, E. L., Bagnell, J. A., Vandapel, N., & Stentz, T. (2006). Improving robot navigation through self-supervised online learning. In Proc. of robotics: science and systems (RSS), August 2006. Google Scholar
  32. Thrun, S., Liu, Y., Koller, D., Ng, A. Y., Ghahramani, Z., & Durrant-Whyte, H. (2004). Simultaneous localization and mapping with sparse extended information filters. International Journal of Robotics Research, 23(7/8), 693–716. Google Scholar
  33. Thrun, S., Burgard, W., & Fox, D. (2005). Probabilistic robotics. Cambridge: MIT Press. zbMATHGoogle Scholar
  34. Uhlmann, J. (1995). Dynamic map building and localization: new theoretical foundations. PhD thesis, University of Oxford. Google Scholar

Copyright information

© Springer Science+Business Media, LLC 2010

Authors and Affiliations

  • Rainer Kümmerle
    • 1
  • Bastian Steder
    • 1
  • Christian Dornhege
    • 2
  • Alexander Kleiner
    • 2
  • Giorgio Grisetti
    • 1
  • Wolfram Burgard
    • 1
  1. 1.Dept. of Computer ScienceUniversity of FreiburgFreiburgGermany
  2. 2.Dept. of Computer ScienceUniversity of FreiburgFreiburgGermany

Personalised recommendations