Efficiently communicating map updates with the pose graph

Abstract

Robot mapping is a task that can benefit a lot from cooperative multi-robot systems. In multi-robot simultaneous localization and mapping (SLAM), it becomes very important how efficiently a given map can be shared among the robot team. To this end, the recently proposed pose graph map representation is used, adapted for use in a particle filter based mapping algorithm, and compared to the standard occupancy grid representation. Through analysis of corner cases as well as experiments with real robot data, the two map representations are thoroughly compared. It is shown that the pose graph representation allows for much more efficient communication of map updates than the standard occupancy grid.