We present a new topological/metric approach to solving the simultaneous localisation and mapping problem. The map is represented as a graph - nodes are local map frames, and edges are transformations between adjacent map frames. The underlying local mapping algorithm is FastSLAM. The local maps and transformations are modelled by sets of particles. There is no global map frame, each map's uncertainties are restricted to its own map frame. The loop dosing is achieved via efficient map matching. We demonstrate our algorithm running in real-time in an indoor environment using a laser range sensor.