A Framework for Autonomous Mobile Robot Exploration and Map Learning through the use of Place-Centric Occupancy Grids

The Autonomous Intelligent Knowledgebuilding Exploration (AIKE) system explores how an autonomous mobile robotic agent using sonar sensors and dead reckoning can learn a map of a completely unknown environment. AIKE generates grid-based maps based on the notion of a "place" (i.e., a location separated from other places by a confining gateway such as a door or entryway). Empirical trials show that the AIKE agent explores the environment with a faster rate of knowledge acquisition than random exploration, learning maps of higher accuracy by reducing error propagation. The algorithm produces a high level of similarity between maps of the same location created from different agent starting locations, making place recognition easier and providing consistency in mapping. We describe the AIKE system in the context of a proposed architecture for autonomous map learning, navigation, and map refinement. Our approach is best suited to operate effectively in large connected spaces such as office buildings using small mobile robots.