Provide a Global Tracking Feature for Person-Following Robot based on the Kinect Sensor

Abstract

Person-tracking with mobile robots is a very active research area which has found success in areas such as museum guidance and hospital assistance. The ability to track only the target user and ignore other people in the robot’s field of view is one of the main issues associated with the person tracking. This problem can be divided into two sub-problems: local tracking and global tracking. This paper introduces a solution to these problems by developing a body measurement identification system using the skeletal data from the Kinect sensor. The proposed solution to this problem is combined with a simple person-following method that enables the robot to follow the target person. 