Simultaneous localization and map building for outdoor mobile robot navigation

Abstract

Simultaneous Localization and Map Building (SLAM) is currently an active re- search asea in autonomous ground vehicles (AGVs). The SLAM problem asks if it is possible for an autonomous vehicle to start at an unknown location in an unknown environment and then to incrementally build a map of this environment while simultaneously using this map to compute absolute vehicle location. Solving this problem would allow an AGV to be deployed easily, with very little initializa- tion requirement and enable it to be truly autonomous that can deal with changes in the environment.