Tracing commodities in indoor environments for service robotics

Daily life assistance for elderly people is one of the most promising scenarios for service robots in the near future. In particular, the go-and-fetch task will be one of the most demanding tasks in these cases. In this paper, we present an informationally structured room that supports a service robot in the task of daily object fetching. Our environment contains different distributed sensors including a floor sensing system and several intelligent cabinets. Sensor information is sent to a centralized management system which processes the data and makes it available to a service robot which is assisting people in the room. We additionally present the first steps of an intelligent framework used to maintain information about locations of commodities in our informationally structured room. This information will be used by the service robot to find objects under request. One of the main goal of our intelligent environment is to maintain a small number of sensors to avoid interfering with the daily activity of people and to reduce as much as possible the invasion of their privacy. In order to compensate this limited available sensor information our framework aims to exploit knowledge about people's activity and their interaction with objects to infer reliable information about the location of commodities. This paper presents simulated results that demonstrate the suitability of this framework to be applied to a service robotic environment equipped with limited sensors. In addition we discuss some preliminary experiments using our real environment and robot.