Making a Socially Assistive Robot Companion Touch Sensitive

Abstract

Socially assistive robots are in the focus of research for a while. These robots are to be in close interaction with humans and try to communicate in a natural way. One intuitive modality for interaction is touch. This paper describes the design of our service robot intended for use in private homes of elderly people. We combined capacitive touch sensors at the stiff parts of the robot’s shell with a pressure sensitive textile array sensor on the flexible back of our robot. A detailed description of the construction and properties of our pressure sensitive matrix sensor is presented. Furthermore, a maximum likelihood classification algorithm is presented, which is capable of online classification without explicit segmentation of touch gesture events in before.