May 6, 2008 10:45 WSPC - Proceedings Trim Size: 9in x 6in 20080505_clawar 1 Merging Topological Maps for Localisation in Large Environments F. Ferreira * and J. Dias Institute of Systems and Robotics- Coimbra, Portugal Coimbra, 3030-290 Coimbra, Portugal * E-mail: {cfferreira * | jorge}@isr.uc.pt http://paloma.isr.uc.pt V. Santos Department of Mechanical Engineering, Aveiro, 3810-193 Aveiro, Portugal E-mail: vitor@ua.pt This article presents a method for the creation of a topological map without having to previously create a geometric map. Independently obtained topological paths are compared pairwise to search for possible overlap in the view sequence. Each individual topological path is created from a sequence of raw data views that are sampled by leading the robot along a path in the environment. The multiple topological paths are ’stitched together’ into a generic Topological map by identifying overlapping segments in the individual sequences. A general topological map can be created by considering all the multiple sequences or separate runs through the environment. Results on the merger of upto 8 seperate paths indicate that this method of mapping large environments, by selective touring through the environment, can generate robust topological maps. Keywords: topological localisation, map merging. 1. Introduction The merging of smaller maps to create larger maps is a relevant topic in map building for Robot Navigation. There are various reasons why it might required to merge two or more smaller maps. One recent application of map merging tech- niques has been to integrate individual maps from cooperating robots. 1 The use of topological information to robustly merge maps is reported in a number of other recent works in the literature. Within Geometric maps, Simultaneous Localisation and Mapping (SLAM) al- gorithms and their variants maintain the relation between features through the use of the relative positions and error correlation matrices. 2 SLAM is well suited to the process of incrementally mapping the environment. An extension of the map