Abstract. In recent years, the autonomous mobile robot has found diverse applications such as home/health care system, surveillance system in civil and military applications and exhibition robot. For surveillance tasks such as moving target pursuit or following and patrol in a region using mobile robot, this paper presents a fuzzy Q-learning, as an intelligent control for cost-based navigation, for autonomous learning of suitable behaviors without the supervision or external human command. The Q-learning is used to select the appropriate rule of interval type-2 fuzzy rule base. The initial testing of the intelligent control is demonstrated by simulation as well as experiment of a simple wall-following based patrolling task of autonomous mobile robot.