A fuzzy logic based language to model autonomous mobile robots

Describes the BG language, which includes an underlying agent architecture based on the blackboard paradigm. The language is intended to follow these guidelines: flexibility, simplicity, and fault tolerance. These objectives are accomplished by means of an extensive use of fuzzy logic at all software levels: agents behaviour definition, behaviour coordination, sensors filtering, and actuators control. In addition to this, the architecture is intended to be used in conjunction with learning techniques, to create or tune the fuzzy rule bases, and specially the fusion fuzzy rule bases. Some results, which have been obtained with our system, are presented.