Understanding social robots: A user study on anthropomorphism

Anthropomorphism is one of the keys to understand the expectations people have about social robots. In this paper we address the question of how a robot's actions are perceived and represented in a human subject interacting with the robot and how this perception is influenced only by the appearance of the robot. We present results of an interaction-study in which participants had to play a version of the classical Prisoners' Dilemma Game (PDG) against four opponents: a human partner (HP), an anthropomorphic robot (AR), a functional robot (FR), and a computer (CP). As the responses of each game partner were randomized unknowingly to the participants, the attribution of intention or will to an opponent (i.e. HP, AR, FR or CP) was based purely on differences in the perception of shape and embodiment. We hypothesize that the degree of human-likeness of the game partner will modulate what the people attribute to the opponents - the more human like the robot looks the more people attribute human-like qualities to the robot. © 2008 IEEE.