Topological Map Merging
A key capability for teams of mobile robots is to cooperatively explore and map an environment. Maps created by one robot must be merged with those from another robot — a difficult problem when the robots do not have a common reference frame. This problem is greatly simplified when topological maps are used because they provide a concise description of the navigability of a space. In this paper, we formulate an algorithm for merging two topological maps that uses aspects of maximal subgraph matching and image registration methods. Simulated and real-world experiments demonstrate the efficacy of our algorithm.
KeywordsMobile Robot Image Registration Iterative Close Point Transformation Space Common Subgraph
Unable to display preview. Download preview PDF.
- 1.K. R. Beevers. Topological mapping and map merging with sensing-limited robots. Master’s thesis, Rensselaer Polytechnic Institute, Troy, NY, April 2004.Google Scholar
- 2.P. Besl and N. McKay. A method for registration of 3-D shapes. IEEE Trans. on Pattern Analysis and Machine Intelligence, 14(2):239–256, February 1992.Google Scholar
- 4.G. Dedeoglu and G.S. Sukhatme. Landmark-based matching algorithm for cooperative mapping by autonomous robots. In L. E. Parker, G. W. Bekey, and J. Barhen, editors, Distributed Autonomous Robotic Systems 4, pages 251–260. Springer-Verlag, 2000.Google Scholar
- 5.T. Duckett, S. Marsland, and J. Shapiro. Learning globally consistent maps by relaxation. In IEEE Intl. Conf. on Robotics & Automation, pages 3841–3846, 2000.Google Scholar
- 6.G. Dudek, M. Jenkin, E. Milos, and D. Wilkes. Topological exploration with multiple robots. In 7th Intl. Symp. on Robotics with Applications, 1998.Google Scholar
- 7.J. Fenwick, P. Newman, and J. Leonard. Cooperative concurrent mapping and localization. In IEEE Intl. Conf. on Robotics & Automation, 2002.Google Scholar
- 8.J.M. Fitzpatrick, D.L. Hill, and C.R. Maurer, Jr. Image registration. In M. Sonka and J. M. Fitzpatrick, editors, Handbook of Medical Imaging, volume 2: Medical Image Processing and Analysis, chapter 8. SPIE, 2000.Google Scholar
- 9.M. Golfarelli, D. Maio, and S. Rizzi. Elastic correction of dead-reckoning errors in map building. In Intl. Conf. on Intelligent Robots and Systems, pages 905–911, 1998.Google Scholar
- 10.J. Ko, B. Stewart, D. Fox, K. Konolige, and B. Limketkai. A practical, decisiontheoretic approach to multi-robot mapping and exploration. In Intl. Conf. on Intelligent Robots and Systems, 2003.Google Scholar
- 11.K. Konolige, D. Fox, B. Limketkai, J. Ko, and B. Stewart. Map merging for distributed robot navigation. In Intl. Conf. on Intelligent Robots and Systems, pages 212–217, 2003.Google Scholar
- 14.R. Wilson and E. Hancock. Structural matching by discrete relaxation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 19(6), June 1997.Google Scholar