Skip to main content Accessibility help
×
Home

Relational FastSLAM: an improved Rao-Blackwellized particle filtering framework using particle swarm characteristics

  • Seung-Hwan Lee (a1), Gyuho Eoh (a1) and Beom H. Lee (a1)

Summary

This paper presents an improved Rao-Blackwellized particle filtering framework with consideration of the particle swarm characteristics in FastSLAM, called Relational FastSLAM or R-FastSLAM. The R-FastSLAM seeks to cope with the inherent problems of FastSLAM, i.e., a particle depletion problem and an error accumulation problem in large environments. The R-FastSLAM uses the particle swarm characteristics in calculating the importance weight and maintaining a particle formation. We assign more accurate weights to particles by clustering them using the Expectation-Maximization (EM) algorithm according to an adaptive weight compensation scheme. In addition, particles constitute an adaptive triangular mesh formation to maintain multiple data association hypotheses without any resampling step. Its outstanding accomplishments are verified on simulations and a test using the Victoria Park dataset by comparing the standard FastSLAM 2.0 with the particle swarm optimization based FastSLAM.

Copyright

Corresponding author

*Corresponding author. E-mail: leeyiri1@snu.ac.kr

References

Hide All
1.Durrant-Whyte, H. and Bailey, T., “Simultaneous localisation and mapping (SLAM): Part I - the essential algorithms,” Robot. Autom. Mag. 13 (2), 99110 (2006).
2.Murphy, K., “Bayesian Map Learning in Dynamic Environments,” Proceeding of Conference on Neural Information Processing Systems, Denver (1999) pp. 1015–1021.
3.Montemerlo, M., Thrun, S., Koller, D. and Wegbreit, B., “FastSLAM: A Factored Solution to the Simultaneous Localization and Mapping Problem,” Proceedings of the National Conference on Artificial Intelligence, Alberta, Canada (2002) pp. 593–598.
4.Montemerlo, M., Thrun, S., Koller, D. and Wegbreit, B., “Fastslam 2.0: An Improved Particle Filtering Algorithm for Simultaneous Localization and Mapping that Provably Converges,” Proceeding of International Joint Conference on Artificial Intelligence, Acapulco, Mexico (2003) pp. 1151–1156.
5.Kwak, N., Lee, B. H. and Yokoi, K., “Representation of the Results from Rao-Blackwellized Particle Filtering for SLAM,” Proceeding of International Conference on Control, Automation and Systems, Seoul, Republic of Korea (2008) pp. 698–703.
6.Kim, C., Sakthivel, R. and Chung, W. K., “Unscented FastSLAM: A robust and efficient solution to the SLAM problem,” IEEE Trans. Robot. 24 (4), 808820 (2008).
7.Kim, C., Kim, H. and Chung, W. K., “Exactly Rao-blackwellized Unscented Particle Filters for Slam,” Proceeding of IEEE International Conference on Robotics and Automation, Shanghai, China (2011) pp. 3589–3594.
8.Grisetti, G., Stachniss, C. and Burgard, W., “Improving Grid-Based SLAM with Rao-Blackwellized Particle Filters by Adaptive Proposals and Selective Resampling,” Proceeding of IEEE International Conference on Robotics and Automation, Barcelona, Spain (2005) pp. 2432–2437.
9.Kim, I., Kwak, N., Lee, H. and Lee, B., “Improved particle filter using geometric relation between particles in FastSLAM,” Robotica 27 (6), 853859 (2009).
10.Kwak, N., Kim, G. W. and Lee, B. H., “A new compensation technique based on analysis of resampling process n FastSLAM,” Robotica 26 (2), 205217 (2008).
11.Liu, D., Liu, G. and Yu, M., “An improved FastSLAM framework based on particle swarm pptimization and unscented particle filter,” J. Comput. Inf. Syst. 8 (7), 28592866 (2012).
12.Lee, G. and Chong, N. Y., “Self-configurable Mobile Robot Swarms with Hole Repair Capability,” Proceeding of IEEE/RSJ International Conference on Intelligent Robots and Systems, Nice, France (2008) pp. 1403–1408.
13.Havangi, R. and Taghirad, H. D., “A square root unscented FastSLAM with improved proposal distribution and resampling,” IEEE Trans. Ind. Electron. 61 (5), 23342345 (2014).
14.Lee, H. C., Park, S., Choi, J. S. and Lee, B. H., “PSO-FastSLAM: An Improved FastSLAM Framework using Particle Swarm Optimization,” Proceeding of IEEE International Conference on Systems, Man and Cybernetics, San Antonio, TX, USA (2009) pp. 2842–2847.
15.Zhu, G., Liang, D., Liu, Y., Huang, Q. and Gao, W., “Improving Particle Filter with Support Vector Regression for Efficient Visual Tracking,” Proceeding of International Conference on Image Processing, Genoa, Italy (2005) pp. 422–425.
16.Jiang, W., Yi, G. and Zeng, Q., “Application of Proximal Support Vector Regression to Particle Filter,” Proceeding of IEEE International Conference on Intelligent Computing and Intelligent Systems, Shanghai, China (2009) pp. 239–243.
17.Lee, S. H., Cho, Y. J. and Lee, B. H., “Adaptive weight compensation technique for improved FastSLAM,” Proceeding of IEEK Summer Conference, Jeju, Republic of Korea (2013) pp.1738–1741. (In Korean)
18.Lee, S. H. and Lee, B. H., “Selective Weight Controlling Technique in Rao-Blackwellized Particle Filter for SLAM,” Proceeding of KRoC 2012, Gangneung, Republic of Korea (2012) pp. 551–554. (In Korean)
19.Lee, S. H., Lee, H. C., Eoh, G. and Lee, B. H., “A new formation maintenance technique for particle diversity in RBPF-SLAM,” Appl. Mech. Mater. 330, 629634 (2013).
20.Lee, G., Chong, N. Y. and Christensen, H., “Adaptive Triangular Mesh Generation of Self-Configuring Robot Swarms,” Proceeding of IEEE International Conference on Robotics and Automation, Kobe, Japan (2009) pp. 2737–2742.
21.Lee, G. and Chong, N. Y., “Self-configurable Mobile Robot Swarms with Hole Repair Capability,” Proceeding of IEEE/RSJ International Conference on Intelligent Robots and Systems, Nice, France (2008) pp. 1403–1408.
22.Huang, S., Wang, Z. and Dissanayake, G., “Sparse local submap joining -lter for building large-scale maps,” IEEE Trans. Robot. 24 (5), 11211130 (2008).
23.Nebot, E., Victoria Park dataset, Website, http://www-personal.acfr.usyd.edu.au/nebot/dataset.htm, (2008).

Keywords

Metrics

Full text views

Total number of HTML views: 0
Total number of PDF views: 0 *
Loading metrics...

Abstract views

Total abstract views: 0 *
Loading metrics...

* Views captured on Cambridge Core between <date>. This data will be updated every 24 hours.

Usage data cannot currently be displayed