Detecting and tracking people by mobile robot using structured light range sensor

Abstract

An effective human-robot interaction is essential for wide penetration of mobile home robots into the market. The ability to track human in the home environment is one of fundamental functions of home robots. In this paper, we introduce a prototype of Samsung home robot (SHR) developed by Samsung Advanced Institute of Technology (SAIT) and present a scheme of tracking user movement utilizing a structured light range sensor. The structured light range sensor is considered to be cost-effective and robust for a wide range of environment; however, its low resolution of range data tends to extract wrong features for the human tracking, such as table legs, trash cans, door-edges, etc. To compromise this weakness, we have developed an algorithm that excludes those features that do not come from human legs. Efficacy and robustness of this proposed system were examined through experiments in the real home environment.