A Hybrid Approach to Finding Cycles in Hybrid Maps

One of the most difficult problems in Simultaneous Localisation and Mapping (SLAM) is that of identifying and closing cycles. While localisation methods exist that can provide local consistency in a map, residual errors can grow unbounded in global metric maps. Topological maps are favoured by some because they do not have the global consistency problems however they too have difficult correspondence problems due to perceptual aliasing. In this paper we discuss our approach to closing cycles in a topological map. We use both a global metric map and the topological map itself to identify cycles in the topological map.

[1]  Wai-Kiang Yeap,et al.  Computing a Representation of the Local Environment , 1999, Artif. Intell..

[2]  Sebastian Thrun,et al.  A Probabilistic On-Line Mapping Algorithm for Teams of Mobile Robots , 2001, Int. J. Robotics Res..

[3]  C R Gallistel,et al.  Computations on metric maps in mammals: getting oriented and choosing a multi-destination route. , 1996, The Journal of experimental biology.

[4]  Michael Bosse,et al.  An Atlas framework for scalable mapping , 2003, 2003 IEEE International Conference on Robotics and Automation (Cat. No.03CH37422).

[5]  Sebastian Thrun,et al.  Learning Metric-Topological Maps for Indoor Mobile Robot Navigation , 1998, Artif. Intell..

[6]  Joseph Modayil,et al.  Exploiting Local Perceptual Models for Topological Map-Building , 2003 .

[7]  M. E. JEFFERIES,et al.  BUILDING A MAP FOR ROBOT NAVIGATION USING A THEORY OF COGNITIVE MAPS , 2001 .

[8]  David Kortenkamp,et al.  Prototypes, Location, and Associative Networks (PLAN): Towards a Unified Theory of Cognitive Mapping , 1995, Cogn. Sci..

[9]  Roland Siegwart,et al.  Hybrid simultaneous localization and map building: closing the loop with multi-hypotheses tracking , 2002, Proceedings 2002 IEEE International Conference on Robotics and Automation (Cat. No.02CH37292).

[10]  Thomas Röfer,et al.  Using histogram correlation to create consistent laser scan maps , 2002, IROS.

[11]  Kurt Konolige,et al.  Incremental mapping of large cyclic environments , 1999, Proceedings 1999 IEEE International Symposium on Computational Intelligence in Robotics and Automation. CIRA'99 (Cat. No.99EX375).

[12]  Benjamin Kuipers,et al.  A Robust, Qualitative Method for Robot Spatial Learning , 1988, AAAI.

[13]  Benjamin Kuipers,et al.  Bootstrap learning for place recognition , 2002, AAAI/IAAI.

[14]  Benjamin Kuipers,et al.  The Spatial Semantic Hierarchy , 2000, Artif. Intell..

[15]  Wai-Kiang Yeap.  Towards a Computational Theory of Cognitive Maps , 1988, Artif. Intell..

[16]  Wolfram Burgard,et al.  A system for volumetric robotic mapping of abandoned mines , 2003, 2003 IEEE International Conference on Robotics and Automation (Cat. No.03CH37422).