Skip to main content

An improved particle filter for sparse environments

Abstract

In this paper, we combine a path planner based on Boundary Value Problems (BVP) and Monte Carlo Localization (MCL) to solve the wake-up robot problem in a sparse environment. This problem is difficult since large regions of sparse environments do not provide relevant information for the robot to recover its pose. We propose a novel method that distributes particle poses only in relevant parts of the environment and leads the robot along these regions using the numeric solution of a BVP. Several experiments show that the improved method leads to a better initial particle distribution and a better convergence of the localization process.

References

  1. 1.

    Amigoni F. Experimental evaluation of some exploration strategies for mobile robots. In:Proceedings of IEEE International Conference on Robotics and Automation; 2008; Pasadena, California. EUA: IEEE; 2008.

  2. 2.

    Angeli A, Doncieux S, Meyer JA and Filliat D. Incremental vision-based topological SLAM. In:Proceedings of IEEE/RSJ International Conference on Intelligent Robots and Systems; 2008; Nice, França. EUA: IEEE; 2008.

  3. 3.

    Begum M, Mann GKI and Gosine RG. Concurrent mapping and localization for mobile robot using soft computing techniques. In:Proceedings of IEEE/RSJ International Conference on Intelligent Robots and Systems; 2005; Alberta. Canada:IEEE; 2005.

    Google Scholar 

  4. 4.

    Blanco JL, Fernández-Madrigal JA and González J. Efficient probabilistic range-only SLAM. In:Proceedings of IEEE/RSJ International Conference on Intelligent Robots and Systems; 2008; Nice, França. EUA: IEEE; 2008.

  5. 5.

    Bourgault F, Makarenko AA, Williams SB, Grocholsky B and Durrant-Whyte HF. Information based adaptive robotic exploration. In: Proceedings of IEEE/RSJ International Conference on Intelligent Robots and Systems; 2002. Switzerland: IEEE; 2002.

    Google Scholar 

  6. 6.

    Dapper F, Prestes E, Idiart MAP and Nedel LP. Simulating pedestrian behavior with potential fields. In:Advances in Computer Graphics. New York: Springer; 2006. p. 324–335. (Lecture Notes in Computer Science, v. 4035).

    Chapter  Google Scholar 

  7. 7.

    Dapper F, Prestes E and Nedel LP. Generating steering behaviors for virtual humanoids using BVP control. In: Advances in Computer Graphics. New York: Springer; 2007. (Lecture Notes in Computer Science)

    Google Scholar 

  8. 8.

    Faria G, Prestes E, Idiart MAP and Romero RAF. Multi robot system based on boundary value problems. In:Proceedings of IEEE/RSJ International Conference on Intelligent Robots and Systems; 2006; Beijing, China. EUA: IEEE; 2006. p. 424-429.

  9. 9.

    Faria G, Romero RAF, Prestes E, and Idiart MAP. Comparing harmonic functions and potential fields in the trajectory control of mobile robots. In:Proceedings of IEEE Conference on Robotics, Automation and Mechatronics; 2004; Singapore. IEEE; 2004. p. 762–767. (v. 1).

    Google Scholar 

  10. 10.

    Fox D, Thrun S, Dellaert F and Burgard W. Particle filters for mobile robot localization. In: Doucet A, Freitas JFG and Gordon NJ. (Eds.).Sequential Monte Carlo in practice. New York: Springer; 2001.

    Google Scholar 

  11. 11.

    Freda L, Loiudice F and Oriolo G. A randomized method for integrated exploration. In:Proceedings of IEEE/RSJ International Conference on Intelligent Robots and Systems; 2006; Beijing, China. EUA: IEEE; 2006.

  12. 12.

    Gasparri A, Panzieri S, Pascucci F and Ulivi G. Monte carlo filter in mobile robotics localization: a clustered evolutionary point of view.Journal of Intelligent and Robotic Systems. 2006; 47(2):155–174.

    Article  Google Scholar 

  13. 13.

    Gonzalez R and Woods R.Digital image processing. Estados Unidos: Addison-Wesley Publishing Company; 1992.

    Google Scholar 

  14. 14.

    Jensfelt P and Kristensen S. Active global localisation for a mobile robot using multiple hypothesis tracking.IEEE Transactions on Robotics and Automation. 2001; 17(5):748–760.

    Article  Google Scholar 

  15. 15.

    Kwon TB and Song JB. Thinning-based topological exploration using position probability of topological nodes. In:Proceedings of IEEE/RSJ International Conference on Intelligent Robots and Systems; 2006; Beijing, China. EUA: IEEE; 2006.

  16. 16.

    Kwon TB, Yang JH, Song JB and Chung W. Efficiency improvement in Monte Carlo localization through topological information. In:Proceedings of IEEE/RSJ International Conference on Intelligent Robots and Systems; 2006; Beijing. China: IEEE; 2006. p. 424–429.

    Google Scholar 

  17. 17.

    Leonard JJ and Durrant-Whyte HF.Directed sonar sensing for mobile robot navigation. Norwell: Kluwer Academic; 1992.

    MATH  Google Scholar 

  18. 18.

    Leung C, Huang S and Dissanayake G. Active SLAM using model predictive control and attractor based exploration. In:Proceedings of IEEE/RSJ International Conference on Intelligent Robots and Systems; 2006; Beijing, China. EUA: IEEE; 2006.

  19. 19.

    Milstein A, Sanchez JN and Williamson ET. Robust global localization using clustered particle filtering. In:Proceedings of Innovative Applications of Artificial Intelligence; 2002; Edmonton, Canada. EUA: The AAAI Press; 2002. p. 581-586.

  20. 20.

    Mobile Robots.Mobilesim. [on the internet]. Available from http://robots.mobilerobots.com/wiki/MobileSim. Access in 10/09/2009.

  21. 21.

    Montemerlo M, Thrun S, Koller D and Wegbreit B. Fast SLAM: A factored solution to the simultaneous localization and mapping problem. In:Proceedings of Innovative Applications of Artificial Intelligence; 2002; Edmonton, Canada. EUA: The AAAI Press; 2002.

  22. 22.

    Silva-Junior EP, Engel PM, Trevisan M and Idiart MAP. Exploration method using harmonic functions.Robotics and Autonomous Systems. 2002; 40(1):25–42.

    Article  Google Scholar 

  23. 23.

    Roy N, Burgard W, Fox D and Thrun S. Coastal navigation: mobile robot navigation with uncertainty in dynamic environments. In:Proceedings of IEEE International Conference on Robotics and Automation; 1999; Detroit. EUA: IEEE ; 1999.

  24. 24.

    Schiele B and Crowley JL. A comparison of position estimation techniques using occupancy grids. In:Proceedings of IEEE International Conference on Robotics and Automation; 1994; San Diego. EUA: IEEE; 1994.

  25. 25.

    Smith L and Husbands P. Visual landmark navigation through large-scale environments. In:Proceedings of EPSRC/BBSRC International Workshop on Biologically Inspired Robotics: The Legacy of W. Grey Walter; 2002; Bristol. Londres: The Royal Society; 2002. p. 272–279.

    Google Scholar 

  26. 26.

    Stachniss C, Grisetti G and Burgard W. Information gain-based exploration using raoblackwellized particle filters. In:Proceedings of Robotics: Science and Systems; 2005; Massachusetts. Cambridge: The MIT Press; 2005.

    Google Scholar 

  27. 27.

    Thrun S, Burgard W, Fox D and Dellaert F. Robust Monte Carlo localization for mobile robots.Artificial Intelligence. 2000; 128(1/2):99–141.

    Google Scholar 

  28. 28.

    Thrun S, Burgard W and Fox D.Probabilistic Robotics. Cambridge: The MIT Press; 2005.

    MATH  Google Scholar 

  29. 29.

    Trevisan, M, Idiart MAP, Prestes E and Engel PM. Exploratory navigation based on dynamic boundary value problems.Jounal of Intelligent and Robotic Systems. 2006; 45(2):101–114.

    Article  Google Scholar 

Download references

Author information

Affiliations

Authors

Rights and permissions

Open Access This article is distributed under the terms of the Creative Commons Attribution 2.0 International License ( https://creativecommons.org/licenses/by/2.0 ), which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

Reprints and Permissions

About this article

Cite this article

Prestes, E., Ritt, M. & Führ, G. An improved particle filter for sparse environments. J Braz Comp Soc 15, 55–64 (2009). https://doi.org/10.1007/BF03194506

Download citation

Keywords

  • boundary value problems
  • autonomous navigation
  • environment exploration
  • global localization
  • Monte Carlo localization