Development of a Robotic Nanny for Children and a Case Study of Emotion Recognition in Human-Robotic Interaction

Abstract

A robotic nanny which can care for and play with children is desirable for many practical applications. In this study, I first design a robotic nanny named Dorothy Robotubby with a caricatured appearance, which consists of a head, a neck, a body, two arms, two hands, and a touch screen in its belly. Then, I develop two main user interfaces which are local control-based and remote control-based for the child and parents, respectively. Since emotion recognition can make important contributions towards achieving a believable and acceptable robot, I also study facial expression-based emotion recognition to address two problems which are important to drive facial expression recognition into real-world applications: misalignment-robust facial expression recognition and cross-dataset facial expression recognition. Then, I design a pilot study to evaluate whether the children like the appearances and functions of Dorothy Robotubby and collect the parent's opinions on the remote user interface designs. To analyze the performance of Robotubby and the interaction between the child and the robot, I employ questionnaires and videotapes. Correspondingly, evaluation results are obtained by questionnaire analysis, behavioral analysis, and case studies. Lastly, several valuable and helpful suggestions have been obtained from the result analysis phase.