Design of Self-Learning Hierarchical Fuzzy Logic for Guidance and Control of Multi-robot Systems

Increased application of fuzzy logic to complex control raises a need for a structured methodological approach to developing fuzzy logic systems, which are currently developed based on individualistic bases and cannot face the challenge of interacting with other (fuzzy) systems in a dynamic environment. We propose designing self-learning hierarchical fuzzy logic control based on the integration of evolutionary algorithms and fuzzy logic to provide an integrated knowledge base for intelligent control and collision avoidance among multiple robots. Robots are considered point masses moving in common work space. Evolutionary algorithms are used as an adaptive method for learning the fuzzy knowledge base of control systems and learning, mapping, and interaction between fuzzy knowledge bases of different fuzzy logic systems.