Path planning far a fuzzy controlled autonomous mobile robot

Abstract

Path planning is a crucial task in navigation of autonomous mobile robots. The paper proposes a high-level path planning approach based on a fuzzy navigator in uncertain environments which is independent of crisp metric information. The navigator acquires information about the environment with eight ultrasonic sensors. The information is evaluated by the navigator utilizing fuzzy rules. In order to acquire the information about the environment around the mobile robot MORIA, the planner only uses computed state variables of the navigator combined with fuzzy metric information. The fuzzy state variables contain information about the actions of the robot, relative fuzzy distances since the last fuzzy state interaction and information according to the current situation. The roles of the navigator and planner are comparable with the behaviour of a car driver and his co-driver reading a map. The approach is developed in a series of simulations and tested on the robot MORIA.