Advertisement

Gaussian Process Occupancy Maps for Dynamic Environments

Chapter
Part of the Springer Tracts in Advanced Robotics book series (STAR, volume 109)

Abstract

We present a continuous Bayesian occupancy representation for dynamic environments. The method builds on Gaussian processes classifiers and addresses the main limitations of occupancy grids such as the need to discretise the space, strong assumptions of independence between cells, and difficulty to represent occupancy in dynamic environments. We develop a novel covariance function (or kernel) to capture space and time statistical dependencies given a motion map of the environment. This enables the model to perform predictions on how the occupancy state of the environment will be in the future given past observations. We show results on a simulated environment with multiple dynamic objects, and on a busy urban intersection.

Keywords

Covariance Function Gaussian Process Query Point Marginal Likelihood Underlying Function 
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.

References

  1. 1.
    Bohg, J., Johnson-Roberson, M., Björkman, M., Kragic, D.: Strategies for multi-modal scene exploration. In: Proceedings of the 2010 IEEE/RSJ International Conference on Intelligent Robots and Systems, October 2010Google Scholar
  2. 2.
    Brechtel, S., Gindele, T., Dillmann, R.: Recursive importance sampling for efficient grid-based occupancy filtering in dynamic environments. In: IEEE International Conference on Robotics and Automation (ICRA), pp. 3932–3938, May 2010Google Scholar
  3. 3.
    Chen, C., Tay, C., Laugier, C., Mekhnacha, K.: Dynamic environment modeling with gridmap: a multiple-object tracking application. In: 9th International Conference on Control, Automation, Robotics and Vision, 2006. ICARCV ’06, pp. 1–6, December 2006Google Scholar
  4. 4.
    Elfes, A.: Occupancy grids: a probabilistic framework for robot perception and navigation. PhD thesis, Carnegie Mellon University (1989)Google Scholar
  5. 5.
    Ellis, D., Sommerlade, E., Reid, I.: Modelling pedestrian trajectories with gaussian processes. In: Ninth International Workshop on Visual Surveillance (2009)Google Scholar
  6. 6.
    Fleet, D., Weiss, Y.: Optical Flow Estimation. Springer, Berlin (2005)Google Scholar
  7. 7.
    Gan, S., Yang, K., Sukkarieh, S.: 3d path planning for a rotary wing UAV using a Gaussian process occupancy map. In: Proceedings of the Australasian Conference on Robotics and Automation (2009)Google Scholar
  8. 8.
    Gindele, T., Brechtel, S., Schroder, J., Dillmann, R.: Bayesian occupancy grid filter for dynamic environments using prior map knowledge. In: IEEE Intelligent Vehicles Symposium, 2009, pp. 669–676, June 2009Google Scholar
  9. 9.
    Lucas, B.D., Kanade, T.: An iterative image registration technique with an application to stereo vision. In: Proceedings of the 7th International Joint Conference on Artificial Intelligence—Volume 2, pp. 674–679. Morgan Kaufmann Publishers Inc., San Francisco, CA, USA (1981)Google Scholar
  10. 10.
    Melkumyan, A., Ramos, F.: Multi-kernel gaussian processes. In: IJCAI, pp. 1408–1413 (2011)Google Scholar
  11. 11.
    Moras, J., Cherfaoui, V., Bonnifait, P.: Credibilist occupancy grids for vehicle perception in dynamic environments. In: IEEE International Conference on Robotics and Automation (ICRA), 2011, pp. 84–89 (2011)Google Scholar
  12. 12.
    O’Callaghan, S.T., Ramos, F.T.: Gaussian process occupancy maps. Int. J. Robot. Res. 31(1), 42–62 (2012)MathSciNetCrossRefGoogle Scholar
  13. 13.
    O’Callaghan, S.T., Singh, S.P.N., Alempijevic, A., Ramos, F.T.: Learning navigational maps by observing human motion patterns. In: IEEE International Conference on Robotics and Automation (ICRA), 2011, pp. 4333–4340, May 2011Google Scholar
  14. 14.
    Plagemann, C., Kersting, K., Burgard, W.: Nonstationary Gaussian process regression using point estimates of local smoothness. In: European Conference on Machine Learning (ECML) (2008)Google Scholar
  15. 15.
    Rasmussen, C.E.: Gaussian Processes for Machine Learning. MIT Press, Cambridge (2006)Google Scholar
  16. 16.
    Wang, C.C.: Simultaneous localization, mapping and moving object tracking. Ph.D. thesis, Robotics Institute, Carnegie Mellon University, Pittsburgh, PA, April 2004Google Scholar

Copyright information

© Springer International Publishing Switzerland 2016

Authors and Affiliations

  1. 1.NICTAEveleighAustralia
  2. 2.Australian Centre for Field Robotics, School of Information TechnologiesThe University of SydneySydneyAustralia

Personalised recommendations