Volume 24 Issue 8 - Publication Date: 1 August 2005
Topological Map Merging
W.H. Huang and K. R. Beevers Rensselaer Polytechnic Institute, Department of Computer Science, 110 8th Street, Troy, NewYork 12180, USA
When multiple robots cooperatively explore an environment, maps from individual robots must be merged to produce a single globally consistent map. This is a challenging problem when the robots do not have a common reference frame or global positioning. In this paper, we describe an algorithm for merging embedded topological maps. Topological maps provide a concise description of the navigability of an environment, and, with measurements easily collected during exploration, the vertices of the map can be embedded in a metric space. Our algorithm uses both the structure and the geometry of topological maps to determine the best correspondence between maps with single or multiple overlapping regions. Experiments with simulated and real-world data demonstrate the efficacy of our algorithm.
Return to Contents