Global Optimal Solution to SLAM Problem with Unknown Initial Estimates

Usman Qayyum, Jonghyuk Kim

Abstract

The paper presents a practical approach for finding the globally optimal solution to SLAM. Traditional methods are based upon local optimization based strategies and are highly susceptible to local minima due to non-convex nature of the SLAM problem. We employed the nonlinear global optimization based approach to SLAM by exploiting the theoretical limit on the numbers of local minima. Our work is not reliant on good initial guess, whereas existing approaches in SLAM literature assume good starting point to avoid local minima problem. The paper presents experimental results on different datasets to validate the robustness of the approach, finding the global basin of attraction with unknown initial guess.

References

  1. A. Doucet, N. Freitas, K. M. and Russel, S. (2002). Blackwellized particle filtering for dynamic bayesian networks. In International Conference on Uncertainty in Artificial Intelligence, pp. 17618.
  2. Bailey, T. and Durrant-Whyte, H. (2006). Simultaneous localization and mapping (slam): part ii. In IEEE Robotics and Automation Magazine, vol. 13, issue 3, pp. 108-117.
  3. C. Olsson, F. K. and Oskarsson, M. (2008). Branch and bound methods for euclidean registration problems. In IEEE Transactions on Pattern Analysis and Machine Intelligence.
  4. C.Blum and A.Roli (2003). Metaheuristics in combinatorial optimization: Overview and conceptual comparison. In ACM Computing Surveys, vol.35, no. 3.
  5. Dellaert, F. and Kaess, M. (2006). Square root sam: simultaneous localization and mapping via square root information smoothing. In Journal of Robotics Research, vol. 25, no. 12, pp. 1181-1203.
  6. E. Olson, J. L. and Teller, S. (2006). Fast iterative optimization of pose graphs with poor initial estimates. In IEEE International Conference on Robotics and Automation (ICRA), pp. 2262-2269.
  7. Freund, R. and Jarr, F. (2001). Solving the sum-of-ratios problem by an interior-point method. In Journal of Global Optimization.
  8. Iser, R. and Wahl, F. (2010). Antslam: global map optimization using swarm intelligence. In IEEE International Conference on Robotics and Automation (ICRA), pp. 265-272.
  9. J. Kurlbaum, U. F. (2010). A benchmark data set for data association. In Technical Report, University of Bremen, Data Available on http://cres.usc.edu/radishrepository/.
  10. K. Astrom, O. Enqvist, C. O. F. K. and Hartley., R. (2007). An l¥ approach to structure and motion problems in 1d-vision. In International Conference on Computer Vision (ICCV).
  11. K. Ni, D. Steedly, F. D. (2007). Tectonic sam: exact, out-of-core, submap-based slam. In IEEE International Conference on Robotics and Automation (ICRA), pp.16781685.
  12. Lu, F. and Milios, E. (1997). Globally consistent range scan alignment for environment mapping. In Journal of Autonomous Robots, pp.333349.
  13. R. Kummerle, G. Grisetti, H. S. K. K. and Burgard, W. (2011). g2o: A general framework for graph optimization. In IEEE International Conference on Robotics and Automation (ICRA).
  14. Resende, M. and Ribeiro., C. (2003). Greedy randomized adaptive search procedures. In Handbook of Metaheuristics, pp. 219249.
  15. S. Huang, Z. Wang, G. D. and Frese, U. (2008). Iterated slsjf: A sparse local submap joining algorithm with improved consistency. In Australiasan Conference on Robotics and Automation (ACRA).
  16. S. Huang, H. Wang, U. F. and Dissanayake, G. (2012). On the number of local minima to the point feature based slam problem. In IEEE International Conference on Robotics and Automation (ICRA), pp. 265-272.
  17. S. Huang, Z. W. and Dissanayake, G. (2008). Sparse local submap joining filter for building large-scale maps. In IEEE Transactions on Robotics, vol. 24, no. 5, pp. 1121-1130.
  18. T. Duckett, S. M. and Shapiro, J. (2002). Fast, on-line learning of globally consistent map. In Journal of Global Optimization, pp. 287300.
  19. U. Frese, P. L. and Duckett, T. (2005). A multilevel relaxation algorithm for simultaneous localization and mapping. In IEEE Transactions on Robotics, vol. 21, no. 2, pp. 196-207.
Download


Paper Citation


in Harvard Style

Qayyum U. and Kim J. (2012). Global Optimal Solution to SLAM Problem with Unknown Initial Estimates . In Proceedings of the 9th International Conference on Informatics in Control, Automation and Robotics - Volume 1: ICINCO, ISBN 978-989-8565-21-1, pages 76-83. DOI: 10.5220/0004040100760083


in Bibtex Style

@conference{icinco12,
author={Usman Qayyum and Jonghyuk Kim},
title={Global Optimal Solution to SLAM Problem with Unknown Initial Estimates},
booktitle={Proceedings of the 9th International Conference on Informatics in Control, Automation and Robotics - Volume 1: ICINCO,},
year={2012},
pages={76-83},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0004040100760083},
isbn={978-989-8565-21-1},
}


in EndNote Style

TY - CONF
JO - Proceedings of the 9th International Conference on Informatics in Control, Automation and Robotics - Volume 1: ICINCO,
TI - Global Optimal Solution to SLAM Problem with Unknown Initial Estimates
SN - 978-989-8565-21-1
AU - Qayyum U.
AU - Kim J.
PY - 2012
SP - 76
EP - 83
DO - 10.5220/0004040100760083