Perceptions of affective expression in a minimalist robotic face

Abstract

This study explores deriving minimal features for a robotic face to convey information (via facial expressions) that people can perceive/understand. Recent research in computer vision has shown that a small number of moving points/lines can be used to capture the majority of information (~95%) in human facial expressions. Here, we apply such findings to a minimalist robot face; recognition rates were similar to more complex robots. The project aims to answer a number of fundamental questions about robotic face design, as well as to develop inexpensive/replicable robotic faces for experimental purposes.