Knowledge Base Tuning using Genetic Algorithm for Fuzzy Behavior-based Autonomous Mobile Robot

The attractive research in the field of robotics as a main alternative to conventional robot in recent years is Behavior-based mobile robot. This control architecture should generate perfect behavior action and able to handle conflicting actions that are seemingly irreconcilable, those are known as Behaviour Design Problem and Action Selection Problem. This paper presents a new schema to overcome behavior-based problems based on Fuzzy Logic Controller (FLC) where the fuzzy knowledge bases are tuned automatically by Genetic Algorithm (GAs), known as Genetic Fuzzy System (GFS). The behaviors are controlled by GFS to generate individual command action. Later, a ContextDependent Blending (DBD) based on meta fuzzy rules coordinates the commands to produce final control action. The scheme is validated using parameters of MagellanPro mobile robot and tested by simulation using MATLAB/SIMULINK. Simulation results show that the proposed model offers hopeful advantages and has improved performance.