Comparative study of hybrid fuzzy logic methods for mobile robot navigation in unknown environments

The navigation of non-holonomic mobile robot in unknown environments is one of the most important challenges in robotic. In order to accomplish that task of navigation, many techniques are used like fuzzy logic control, neural networks, etc. In this work, fuzzy logic controller is used and optimised by two soft computer techniques: genetic algorithm, and Particle Swarm Optimization (PSO). These methods are used to adjust the inputs and outputs of fuzzy logic controller in order to improve the mobile robot navigation. In this work, three methods have been presented: manually constructed fuzzy logic controller (M-Fuzzy), fuzzy logic controller optimised by genetic algorithm (GA-Fuzzy), and fuzzy logic controller optimized by PSO (PSO-Fuzzy). Simulation results are presented to compare the performances of these approaches. The results obtained prove that the evolutionary methods give more efficient mobile robot navigation in terms of distance travelled and/or traveling time.