A vision based guide robot system: Initiating proactive social human robot interaction in museum scenarios

This paper presents a guide robot system which observes people´s interest and intention towards paintings in museum scenarios and proactively offers guidance to them using a guide robot, if needed. To do that, we utilized multiple USB video camera sensors to support the guide robot in detecting and tracking people´s visual focus of attention (VFOA) toward paintings. In this study, we consider each person´s head orientation and profile information and compute importance values to identify a target-person that may be interested in a particular painting. After identifying the target-person, the guide robot moves autonomously through an appropriate motion path from the so called public-distance to his/her social-distance to explain details about the painting to which s/he is interested. Furthermore, we demonstrate the viability of our guide robot system by experimenting with the Robovie-R3 as a museum guide robot. Finally, we tested the system to validate its effectiveness.