<title>Environment model for mobile robots indoor navigation</title>

摘要

An autonomous mobile robot must be able to combine uncertain sensory information with prior knowledge of the world. Moreover these operations have to be performed fast enough to be able to react to the changes in the world. This paper presents a model-driven system for a real-time indoor mobile robot. As the robot is constantly in motion information from an Environment Model is used to anticipate information-rich features and to direct selective sensing. Uncertain sensor information is combined with prior World Model knowledge to reduce uncertainty and the remaining uncertainty is directly represented by flexible ranges of values. We present a hall-following robot based on this system which exhibits real-time navigation performance. It does this despite primitive and relatively slow sensing motor control and communications capabilities. This system combines sensing action and cognition which are the major building blocks for any autonomous system.