Autonomous Mobile Robot Navigation by Combining Local and Global Techniques

Abstract

The present article is devoted to develop an algorithm for obstacle avoidance of an autonomous mobile robot based on fuzzy logic/ The method of navigation proposed provides a way of blending the intelligence and optimality of global methods with the reactive dynamic behavior of local ones. This is achieved by using hybrid navigation system composed of two modules, one of which uses the apriori information and determines roughly the optimal route towards the goal, whereas the other carries out effective navigation decisions using the potential function based local approach. The fuzzy rules are constructed from intuitive and subjective human ways of collision avoidance. The results of the present study are compares favorably with those of well-established algorithms.