Sensor Fusion for Mobile Robot navigation: Fuzzy Associative Memory

The mobile robot navigation with complex environment needs more input space to match the environmental data into robot outputs in order to perform a realistic task. At the same time, the number of rules at the rule base needs to be optimized to reduce the computing time and to provide the possibilities for real time operation. In this paper, a sensor fusion technique is proposed to enhance the navigation rules using a Modified Fuzzy Associative Memory. In the proposed method, the rule base uses fuzzy compositional rule of inference and fuzzy associativity. This technique provides good flexibility to use multiple input space and reduction of rule base for robot navigation. The behavior rules obtained from Modified Fuzzy Associative Memory model are tested using simulation and real world experiments, and the results are discussed in the paper and compared with the existing methods.