Development of an indoor patrol robot based on ultrasonic and vision data fusion

Abstract

In this paper we present the development and implementation of a patrol robot for indoor environments. First, we propose an indoor patrol strategy by using ultrasonic sensors. According to the gathered range information of the environment, we apply the wall-following strategy to design of patrol rules for determining the navigation commands of the patrol robot. Then we design a steering controller based on the potential field method to drive the patrol robot moving along the wall baselines. In addition, we propose another navigation strategy by using ultrasonic and vision data fusion to improve the accuracy and robustness of the sensing system. We implement a visual navigation controller to successfully steer the patrol robot following the wall and keeping a certain distance to the wall.