Environment modelling in a multi-agent mobile system

The perception and world model building methods for multiple mobile robots operating in an industrial environment are discussed. The concept of geometrical database is associated with multiple classes of perception-based maps, to obtain the world model. Task-oriented maps are produced by grouped sensors. Two different representations of the environment are considered, namely vector-based and raster-based maps. Sensed maps are checked for consistency with the predefined model. The multi-agent approach has been applied with respect to the system architecture. As a consequence, world-model maintenance activity consists of a number of processes, which are driven by the team of agents. The results of experimental map building by using data from the optical range sensor combined with the predefined model are presented.