A System to Convey the Emotional Content of Text Using a Humanoid Robot

摘要

Soon we will have anthropomorphic robots that will assist us at home and at work and will be able to recite our text-based communications to us in an animated and engaging manner. This paper describes some steps taken to explore this idea with a simple humanoid robot, the NAO Aldebaran, which is capable of speech of varying pitch, speed and loudness, and has evocative color LED lights around its eyes. To convey the emotional content of text, the proposed system maps ASCII text to these capabilities. The extraction of emotion makes use of the Natural Language Toolkit (NLTK), an open-source tool for computational linguistics using Python. A two-dimensional emotion space is used to map the extracted emotion to robot action. The effectiveness of the system is explored with a simple example of emotional text and a video of the results is provided along with a time-plot of the actions.