Efficient Multi-hypotheses Unscented Kalman Filtering for Robust Localization
Abstract
This paper describes an approach to Gaussian mixture filtering which combines the accuracy of the Kalman filter and the robustness of particle filters without sacrificing computational efficiency. Critical approximations of common Gaussian mixture algorithms are analyzed and similarities are pointed out to particle filtering with an extremely low number of particles. Known techniques from both fields are applied in a new combination resulting in a multi-hypotheses Kalman filter which is superior to common Kalman filters in its ability of fast relocalization in kidnapped robot scenarios and its representation of multi-modal belief distributions, and which outperforms particle filters in localization accuracy and computational efficiency.
Keywords
Mobile Robot Gaussian Mixture Model Humanoid Robot Sensor Model Goal PostPreview
Unable to display preview. Download preview PDF.
References
- 1.Alspach, D., Sorenson, H.: Nonlinear Bayesian Estimation using Gaussian Sum Approximations. IEEE Transactions on Automatic Control 17(4), 439–448 (1972)MATHCrossRefGoogle Scholar
- 2.Czarnetzki, S., Rohde, C.: Handling Heterogeneous Information Sources for Multi-Robot Sensor Fusion. In: Proceedings of the 2010 IEEE International Conference on Multisensor Fusion and Integration for Intelligent Systems, MFI 2010, Salt Lake City, Utah, pp. 133–138 (September 2010)Google Scholar
- 3.Duckett, T., Nehmzow, U.: Mobile Robot Self-Localisation using Occupancy Histograms and a Mixture of Gaussian Location Hypotheses. Robotics and Autonomous Systems 34(2-3), 117–129 (2001)MATHCrossRefGoogle Scholar
- 4.Gutmann, J.S., Fox, D.: An Experimental Comparison of Localization Methods continued. In: 2002 IEEE/RSJ International Conference on Intelligent Robots and Systems, vol. 1, pp. 454–459 (2002)Google Scholar
- 5.Kaune, R.: Gaussian Mixture (GM) Passive Localization using Time Difference of Arrival (TDOA). In: Fischer, S., Maehle, E., Reischuk, R. (eds.) GI Jahrestagung. LNI, vol. 154, pp. 2375–2381. GI (2009)Google Scholar
- 6.Krauthausen, P., Hanebeck, U.D.: Regularized Non-Parametric Multivariate Density and Conditional Density Estimation. In: Proceedings of the 2010 IEEE International Conference on Multisensor Fusion and Integration for Intelligent Systems, MFI 2010, Salt Lake City, Utah, pp. 180–186 (September 2010)Google Scholar
- 7.Lenser, S., Veloso, M.: Sensor Resetting Localization for Poorly Modelled Mobile Robots. In: Proceedings of IEEE International Conference on Robotics and Automation, ICRA 2000, vol. 2, pp. 1225–1232 (2000)Google Scholar
- 8.Nisticò, W., Hebbel, M.: Temporal Smoothing Particle Filter for Vision Based Autonomous Mobile Robot Localization. In: Proceedings of the 5th International Conference on Informatics in Control, Automation and Robotics, ICINCO, vol. RA-1, pp. 93–100. INSTICC Press (2008)Google Scholar
- 9.Pfaff, P., Plagemann, C., Burgard, W.: Gaussian Mixture Models for Probabilistic Localization. In: IEEE International Conference on Robotics and Automation, ICRA 2008, pp. 467 –472 (May 2008)Google Scholar
- 10.Quinlan, M.J., Middleton, R.H.: Multiple Model Kalman Filters: A Localization Technique for RoboCup Soccer. In: Baltes, J., Lagoudakis, M.G., Naruse, T., Ghidary, S.S. (eds.) RoboCup 2009. LNCS (LNAI), vol. 5949, pp. 276–287. Springer, Heidelberg (2010)CrossRefGoogle Scholar
- 11.Thrun, S., Burgard, W., Fox, D.: Probabilistic Robotics (Intelligent Robotics and Autonomous Agents). The MIT Press (2005)Google Scholar
- 12.Upcroft, B., Kumar, S., Ridley, M., Ong, L.L., Durrant-whyte, H.: Fast Re-parameterisation of Gaussian Mixture Models for Robotics Applications. In: Barnes, N., Austin, D. (eds.) Proceedings of the Australasian Conference on Robotics and Automation, ACRA. Australian Robotics and Automation Association (2004)Google Scholar