This paper deals with the advantages of incorporating memory-based reasoning capabilities in autonomous navigation algorithm. These features enhance the mobile robot's performance whereby the mobile robot's forthcoming decisions are also affected by its previous experiences during the navigation apart from the current range inputs. The feasibility of this strategy is applied to an intelligent low cost mobile robot with local sensors with 8 bits microcontroller. The environment of the mobile robot is modeled by classifying temporal sequences of spatial sensory patterns. Fuzzy-Kohonen Network (FKN) technique determines this strategy. A detailed comparison of the proposed technique with other recent approaches in the specific case of 'Local minimum' detection and obstacle avoidance is also presented.