A Fuzzy Logic Based Navigation System for a Mobile Robot

Abstract

One of the problems associated with traditional behaviour based navigation systems for mobile robots is that of command arbitration. Having multiple behaviours which are all running concurrently leads to situations where several command outputs may be produced simultaneously. The decision about which output should be used to drive the robot is left to a separate command arbitrator. Using this method, however, does not always result in smooth motion control of the robot and may even cause the robot to move in a completely unintended direction. This paper describes the design of a fuzzy logic based navigation system for a mobile robot. The advantage of using fuzzy logic for navigation is that it allows for the easy combination of various behaviours’ outputs through a command fusion process. The navigation system in this case consists of two behaviours an obstacle avoidance behaviour and a goal seeking behaviour. The inputs to the fuzzy controller are the desired direction of motion and the readings from the sensor array. The outputs from each behaviour’s rule base are integrated using the command fusion process and made crisp using a modified defuzzification technique. The end result is very smooth motion control of the robot.