Politeness and fairness in human-robot interaction

Politeness was studied in human–robot interaction based on Lakoff’s politeness theory. A series of user studies were conducted to manipulate politeness, errors, and culture. In the first study manipulation of three different levels of politeness of non-humanoid robots and evaluated their effects. A table-setting task was developed for two different types of robots (a robotic manipulator and a mobile robot). The studies included two different populations (old and young adults) and were conducted in two conditions (video and live). Results revealed that polite robot behavior positively affected users' perceptions of the interaction with the robots and that participants were able to differentiate between the designed politeness levels.

The second study investigated the influence of robot politeness and erroneous behavior on users' perceptions. Correctness was manipulated as robot behavior without errors vs. behavior with errors. Participants provided higher ratings for robots operating in the correct-polite condition. However, politeness could not compensate for erroneous behavior, and the participants rated the correct yet strict robot better than the erroneous yet polite robot. It thus appears that at least in the context of this study (a utilitarian task, young users, specific culture), politeness cannot make up for errors, and a polite yet erring robot may even be annoying.