Multi-robot mapping using manifold representations

This paper introduces a new method for representing two-dimensional maps, and shows how this representation may be applied to concurrent localization and mapping problems involving multiple robots. We introduce the notion of a manifold map; this representation takes maps out of the plane and onto a two-dimensional surface embedded in a higher-dimensional space. Compared with standard planar maps, the key advantage of the manifold representation is self-consistency: manifold maps do not suffer from the 'cross over' problem that planar maps commonly exhibit in environments containing loops. This self-consistency facilitates a number of important autonomous capabilities, including robust retro-traverse, lazy loop closure, active loop closure using robot rendezvous, and, ultimately, autonomous exploration. By way of validation, this paper also includes experimental results obtained using teams of two to four robots in environments ranging in size from 400 m(2) to 900 m(2).