Practical indoor mobile robot navigation using hybrid maps

Abstract

This paper presents a practical navigation scheme for indoor mobile robots using hybrid maps. The method makes use of metric maps for local navigation and a topological map for global path planning. Metric maps are generated as 2D occupancy grids by a range sensor to represent local information about partial areas. The global topological map is used to indicate the connectivity of the `places-of-interests' in the environment and the interconnectivity of the local maps. Visual tags on the ceiling to be detected by the robot provide valuable information and contribute to reliable localization. The navigation scheme based on the hybrid metric-topological maps is scalable and adaptable since new local maps can be easily added to the global topology, and the method can be deployed with minimum amount of modification if new areas are to be explored. The method is implemented successfully on a physical robot and evaluated in a hospital environment.