Field Deployment of the Simultaneous Localisation and Mapping Algorithm

Abstract

Autonomous localisation and mapping requires a vehicle to start in an unknown location in an unknown environment and then to incrementally build a map of landmarks present in this environment while simultaneously using this map to compute absolute vehicle location. The theoretical basis of the solution to this problem, known as Simultaneous Localisation and Mapping (SLAM), is now well understood. A number of approaches to SLAM have appeared in the recent literature. This paper presents results of deployment of the algorithm undertaken at the Australian Centre for Field Robotics in a variety of field applications. The algorithm has been used in indoor environments, using a high speed land vehicle travelling in a park and on a submersible vehicle.