Behavior based Mobile Robot Navigation Technique using AI System: Experimental Investigations

A key issue in the research of an autonomous mobile robot is the design and development of a navigation technique that enables the robot to navigate in a real world environment. This paper is focused on the (a) Establishment of a methodology to model the control system that optimizes the behavior rules using Fuzzy Associative Memory (FAM) for mobile robot navigation. The existing methods focuses on mainly to map certain portion of the input space to the outputs, whereas the method proposed in the research is mainly based on mapping of the entire input space to the outputs. The proposed FAM approach reduces the number rules significantly. (b) Experimental investigations of mobile robot using the proposed Alpha level fuzzy logic system are discussed and evaluated. These methodologies are tested and evaluated using Active Media Pioneer, Nomad Scout and Khepera II Robots. The results are analyzed, evaluated and compared with the most accepted methods. This approach provides a formal methodology for representing and implementing the human expert heuristic knowledge and perception-based action in robot navigation without needing of any analytical model.