Finding people in home environments with a mobile robot

Mobile robots assisting people in their apartment are subject to recent research efforts. To provide useful services a robot must be aware of the position of the user. Since the sensors of a robot have a limited field-of-view, the user is easily lost once he or she leaves the robot´s vicinity. This paper proposes a method to search and locate a person that is distant- probably in another room- by driving through the apartment and checking for people. We apply restrictive as well as computationally expensive detection methods on-demand to verify the hypotheses of a real-time person tracker. Additionally, the search-tour of the robot is guided by an occurrence probability histogram of previous positions of the user. The system has been tested by evaluating accuracy and time the robot needs to find a user in a 3-room scenario.