Cognitive Computation

, Volume 6, Issue 3, pp 496–509 | Cite as

Conjugate Unscented FastSLAM for Autonomous Mobile Robots in Large-Scale Environments

Article
First Online:
Received:
Accepted:

Abstract

Map learning and self-localization based only on a perception of an environment’s structure are fundamental cognitive capacities required for intelligent robot’s to realize true autonomy. Simultaneous localization and mapping (SLAM) is an effective technique for such robots, as it addresses the problem of incrementally building an environment map from noisy sensory data and tracking the robot’s pose with the built map. While the Rao-Blackwellized particle filter (RBPF) is a popular SLAM technique, it tends to accumulate errors introduced by inaccurate linearization of the SLAM nonlinear function. Accordingly, RBPF-SLAM will usually fail to close large loops when applied to large-scale environments. To overcome this drawback, a new Jacobian-free RBPF-SLAM algorithm is derived in this paper. The main contribution of the algorithm lies in the utilization of the 5th-order conjugate unscented transform, which calculates the SLAM transition density up to the 5th order, to give a better distribution of the particle filter and discover local features and landmarks. The performance of the proposed SLAM is investigated and compared with that of FastSLAM2.0 and UFastSLAM in both indoor and outdoor experiments. The results verify that the proposed algorithm improves the SLAM performance in large-scale environments.

Keywords

Simultaneous localization and mapping Particle filter Conjugate unscented transform Large-scale environments 
This is a preview of subscription content, log in to check access.

Notes

Acknowledgments

This work was jointly supported by State Key Laboratory of Robotics and System of Harbin Institute of Technology (Grant No. SKLRS-2009-ZD-04), National Nature Science Foundation of China (Grant Nos. 60909055, 61005070), China Postdoctoral Science Foundation Special Funded Project (Grant No. 201003144), and Fundamental Research Funds for the Central Universities of China (Grant No. 2014JBM014). The authors gratefully acknowledge T. Bailey for the SLAM simulator, The University of Sydney for the Victoria Park dataset, and the University of Bremen for the DLR dataset.

References

  1. 1.
    Haikonen POA. XCR-1: an experimental cognitive robot based on an associative neural architecture. Cogn Comput. 2011;3(2):360–6.CrossRefGoogle Scholar
  2. 2.
    Cutsuridis V, Taylor JG. Cognitive control architecture for the perception-action cycle in robots and agents. Cogn Comput. 2013;5:383–95.CrossRefGoogle Scholar
  3. 3.
    Mohan V, Morasso P, Sandini G, et al. Inference through embodied simulation in cognitive robots. Cogn Comput. 2013;5(3):355–82.CrossRefGoogle Scholar
  4. 4.
    Taylor JG, Cutsuridis V, Hartley M, et al. Observational learning: basis, experimental results and models, and implications for robotics. Cogn Comput. 2013;5(3):340–54.CrossRefGoogle Scholar
  5. 5.
    Samar R, Kamal WA. Optimal path computation for autonomous aerial vehicles. Cogn Comput. 2012;4(4):515–25.CrossRefGoogle Scholar
  6. 6.
    Jia ZJ, Song YD, Cai WC. Bio-inspired approach for smooth motion control of wheeled mobile robots. Cogn Comput. 2013;5(2):252–63.CrossRefGoogle Scholar
  7. 7.
    Chen FY, Jiang B, Tao G. Fault self-repairing flight control of a small helicopter via fuzzy feedforward and quantum control techniques. Cogn Comput. 2012;4(4):543–8.CrossRefGoogle Scholar
  8. 8.
    Zhao JJ, Du C, Sun H. Biologically motivated model for outdoor scene classification. Cognit Comput. 2013; published online.Google Scholar
  9. 9.
    Wei H, Li H. Shape description and recognition method inspired by the primary visual cortex. Cogn Comput. 2013; published online.Google Scholar
  10. 10.
    Pal A, Tiwari R, Shukla A. Multi-robot exploration in wireless environments. Cogn Comput. 2012;4(4):526–42.CrossRefGoogle Scholar
  11. 11.
    Tian B, Shim VA, Yuan ML, et al. RGB-D based cognitive map building and navigation. In: IEEE/RSJ international conference on intelligent robots and systems (IROS); 2013. p. 1152–6.Google Scholar
  12. 12.
    Milford M, Wyeth G. Mapping a suburb with a single camera using a biologically inspired SLAM system. IEEE Trans Rob. 2008;24(5):1038–53.CrossRefGoogle Scholar
  13. 13.
    Milford M, Wyeth G. Persistent navigation and mapping using a biologically inspired slam system. Int J Robot Res. 2010;29(9):1131–53.CrossRefGoogle Scholar
  14. 14.
    Steckel J, Peremans H. BatSLAM: simultaneous localization and mapping using biomimetic sonar. PLoS ONE. 2013;8(1):e54076.PubMedCentralPubMedCrossRefGoogle Scholar
  15. 15.
    Durrant WH, Bailey T. Simultaneous localization and mapping: part I. IEEE Robot Autom Mag. 2006;13(2):99–110.CrossRefGoogle Scholar
  16. 16.
    Bailey T, Durrant WH. Simultaneous localization and mapping: part II. IEEE Robot Autom Mag. 2006;13(3):108–17.CrossRefGoogle Scholar
  17. 17.
    Dellaert F, Kaess M. Square root SAM: simultaneous localization and mapping via square root information smoothing. Int J Robot Res. 2006;25(12):1181–203.CrossRefGoogle Scholar
  18. 18.
    Kuemmerle R, Grisetti G, Strasdat H, Konolige K, Burgard W. g2o: a general framework for graph optimization. In: IEEE international conference on robotics and automation; 2011. p. 3607–7.Google Scholar
  19. 19.
    Doucet A, Freitas ND, Murphy K. Rao-blackwellised particle filtering for dynamic Bayesian networks. In: Proceedings of the 16th conference on uncertainty in artificial intelligence; 2000. p. 176–8.Google Scholar
  20. 20.
    Montemerlo M. FastSLAM: a factored solution to the simultaneous localization and mapping problem with unknown data association. Tech. Report CMU-RI-TR-03-28. Carnegie Mellon University; 2003.Google Scholar
  21. 21.
    Grisetti G, Stachniss C. Improved techniques for grid mapping with rao-blackwellized particle filters. IEEE Trans Rob. 2007;23(1):34–46.CrossRefGoogle Scholar
  22. 22.
    Sim R, Elinas P, Little J. A study of the rao—blackwellised particle filter for efficient and accurate vision-based SLAM. Int J Comput Vis. 2007;74:303–18.CrossRefGoogle Scholar
  23. 23.
    Kim C, Sakthivel R. Unscented FastSLAM: a robust and efficient solution to SLAM problem. IEEE Trans Rob. 2008;24(4):808–20.CrossRefGoogle Scholar
  24. 24.
    Wang X, Zhang H. A UPF-UKF framework for SLAM. In: IEEE international conference on robotics and automation; 2007. p. 1664–6.Google Scholar
  25. 25.
    Julier SJ, Uhlmann JK. Unscented filtering and nonlinear estimation. Proc IEEE. 2004;92(3):401–22.CrossRefGoogle Scholar
  26. 26.
    Merwe R, Doucet A. The unscented particle filter. Tech. Report CUED/F INFENG/TR380. Cambridge: Cambridge University; 2000.Google Scholar
  27. 27.
    Song Y, Li QL, Kang YF, Song YD. CFastSLAM: a new Jacobian free solution to SLAM problem. In: IEEE international conference on robotics and automation; 2012. p. 3063–6.Google Scholar
  28. 28.
    Song Y, Li QL, Kang YF, Song YD. Square-root cubature FastSLAM algorithm for mobile robot simultaneous localization and mapping. In: IEEE international conference on mechatronics and automation; 2012. p. 1162–6.Google Scholar
  29. 29.
    Arasaratnam I, Haykin S. Cubature kalman filters. IEEE Trans Autom Control. 2009;54(6):1254–69.CrossRefGoogle Scholar
  30. 30.
    Adurthi N, Singla P, Singh T. The conjugate unscented transform-an approach to evaluate multi-dimensional expectation integrals. In: American control conference; 2012. p. 5556–6.Google Scholar
  31. 31.
  32. 32.
    Kurlbaum J, Frese U. A benchmark data set for data association. Tech. Report. University of Bremen. [Online] http://radish.sourceforge.net/.
  33. 33.
    Guivant J, Nebot E. Optimization of the simultaneous localization and map-building algorithm for real-time implementation. IEEE Trans Robot Autom. 2001;17(3):242–57.CrossRefGoogle Scholar
  34. 34.
    Huang SD, Wang H, Frese U, Dissanayake G. On the number of local minima to the point feature based SLAM problem. In: IEEE international conference on robotics and automation; 2012. p. 2074–6.Google Scholar

Copyright information

© Springer Science+Business Media New York 2014

Authors and Affiliations

  1. 1.School of Electronic and Information EngineeringBeijing Jiaotong UniversityBeijingChina
  2. 2.State Key Laboratory of Robotics and System of HITHarbin Institute of TechnologyHarbinChina
  3. 3.School of Mechanical Electronic and Information EngineeringChina University of Mining and TechnologyBeijingChina

Personalised recommendations