Social robotics aims at designing robots capable of joint interaction with humans. On a conceptual level, sufficient mutual understanding is usually said to be a necessary condition for joint interaction. Against this background, the following questions remain open: in which sense is it legitimate to speak of human–robot joint interaction? What exactly does it mean to speak of humans and robots sufficiently understanding each other to account for human–robot joint interaction? Is such joint interaction effectively possible by reference, e.g., to the mere ascription or simulation of understanding? To answer these questions, we first discuss technical approaches which aim at the implementation of certain aspects of human–human communication and interaction in social robots in order to make robots accessible and understandable to humans and, hence, human–robot joint interaction possible. Second, we examine the human tendency to anthropomorphize in this context, with a view to human understanding of and joint interaction with social robots. Third, we analyze the most prominent concepts of mutual understanding and their implications for human–robot joint interaction. We conclude that it is—at least for the time being—not legitimate to speak of human–robot joint interaction, which has relevant implications both morally and ethically.