User Identification for Healthcare Service Robots: Multidisciplinary Design for Implementation of Interactive Services

Abstract

Human robot interaction (HRI) is core to the design of service robots. The interaction during a service application determines how a user perceives the robot, which affects the user’s experience and how well the user accepts the robot and its services. During the last decade, robotics service applications in close proximity to human users have been a popular research area. Research in related fields such as computer vision has also made significant advances to make available many interaction algorithms for HRI. However, we argue that there is only minimum utilization of these algorithms in the construction of HRI needed in actual service robots, despite their availability. This is partly because these algorithms have inherent limitations and only solve some of the HRI issues required in a complete service scenario in real environments. In this paper, a new general design approach is proposed to utilize modeling languages UML and UMLi to describe a service scenario and model the HRI required in a complete service. These models can be further used to elicit sometimes hidden HRI requirements from limitations in the interaction algorithms used. This approach helps multidisciplinary research to make HRI design decisions early at the design stage and guide implementation by software engineers. A user identification service scenario was designed, implemented and used as the case study of this design approach. It was integrated with a medication reminder application on a robot which was deployed and evaluated with the older people in a retirement village in New Zealand.