SLAM Using Relational Trees and Semantics


Article Preview

This work attempts to develop a method for SLAM using semantics based on FastSLAM 2.0. Our approach to semantic mapping consists of segmenting images obtained from two sensors (optical and radar) aboard a UAV. We then identify landmarks within the segmented image, followed by the construction of relational trees with the landmarks; these trees are then used at consecutive time-steps of the robot’s motion for its localization as well as update of the landmarks. The term semantics has been used for region-landmarks which are validated with a look-up table (LUT) of the predefined surface type information, a superset of the robot’s actual environment. Finally, based on particle filters, the posterior density of the state of the robot is estimated and a 2-D semantics map is constructed. The methodology has been tested in a situation wherein the robot’s true environment and path have been simulated. For simulation we consider satellite images of optical and radar sensors of the robot’s environment. At different time-steps the robot’s images are cropped from these images, incorporating errors in the robot’s control information. Experiments carried out on the simulated environment have provided encouraging results.



Advanced Materials Research (Volumes 452-453)

Edited by:

Liu Pei




A. Sarkar et al., "SLAM Using Relational Trees and Semantics", Advanced Materials Research, Vols. 452-453, pp. 648-653, 2012

Online since:

January 2012




[1] J. Aulinas, Y. Petillot, J. Salvi, X. Lladό, in: The SLAM Problem: a Survey, Proceedings of the 2008 conference on Artificial Intelligence Research and Development: Proceedings of the 11th International Conference of the Catalan Association for Artificial Intelligence (2008).

[2] M. W. M. G. Dissanayake, P. Newman, S. Clark, H. F. Durrant-Whyte, M. Csorba, in: A Solution to the Simultaneous Localization and Map Building (SLAM) Problem, IEEE Transactions on Robotics and Automation (2001), Vol. 17, Issue 3.

DOI: 10.1109/70.938381

[3] M. Montemerlo, S. Thrun, D. Koller, B. Wegbreit, in: FastSLAM 2. 0: An Improved Particle Filtering Algorithm for Simultaneous Localization and Mapping that Provably Converges, Proceedings of the International Joint Conference on Artificial Intelligence (2003).

[4] M. Montemerlo, S. Thrun, in: FastSLAM: A Scalable Method for the Simultaneous Localization and Mapping Problem in Robotics, Springer Tracts in Advanced Robotics (2007), Vol. 27.

DOI: 10.1007/978-3-540-75388-9_3

[5] A. Sarkar, A. Banerjee, N. Banerjee, S. Brahma, B. Kartikeyan, M. Chakraborty, K. L. Majumdar, in: Land-cover Classification in MRF Context Using Dempster-Shafer Fusion for Multisensor Imagery, IEEE Transactions on Image Processing (2005).

DOI: 10.1109/tip.2005.846032

[6] R. Smith, P. Cheeseman, in: On the Representation and Estimation of Spatial Uncertainty, The International Journal of Robotics Research (1986), Vol. 5, no. 4.

[7] T. F. Smith, M. S. Waterman, in: Identification of Common Molecular Subsequences, J. Mol. Biol. (1981), Vol. 147, pp.195-197.

[8] S. Thrun, W. Burgard, D. Fox, in: Probabilistic Robotics, The MIT Press (2005).

Fetching data from Crossref.
This may take some time to load.