Footing in human-robot conversations

Abstract

During conversations, speakers establish their and others' participant roles (who participates in the conversation and in what capacity)-or "footing" as termed by Goffman-using gaze cues. In this paper, we study how a robot can establish the participant roles of its conversational partners using these cues. We designed a set of gaze behaviors for Robovie to signal three kinds of participant roles: addressee, bystander, and overhearer. We evaluated our design in a controlled laboratory experiment with 72 subjects in 36 trials. In three conditions, the robot signaled to two subjects, only by means of gaze, the roles of (1) two addressees, (2) an addressee and a bystander, or (3) an addressee and an overhearer. Behavioral measures showed that subjects' participation behavior conformed to the roles that the robot communicated to them. In subjective evaluations, significant differences were observed in feelings of groupness between addressees and others and liking between overhearers and others. Participation in the conversation did not affect task performancemeasured by recall of information presented by the robot-but affected subjects' ratings of how much they attended to the task.While Aiko and Robovie talk about how to get to the Muji store, another shopper, Yukio, approaches Robovie's booth. Yukio wants to get a program of this month's shows at the amphitheater. When Yukio approaches the information booth, Robovie acknowledges Yukio's presence with a short glance, but turns back to Aiko, signaling to Yukio that he has to wait until its conversation with Aiko is over and to Aiko that it is attending to her.This scenario differs with the addition of a non-participant [11] into the social situation who is playing the role of a bystander [19].After Robovie's conversation with Yukio is over, a couple, Katsu and Mari, approach the booth, inquiring about Korean restaurants. Robovie asks the couple a few questions on their dining preferences and leads them to a suitable restaurant.

Impacts of Robot Head Gaze on Robot-to-Human Handovers

“…Therefore, much work (e.g. [3,30,32,36]) in HRI has focused on the functions of robot gaze in conversations. Mutlu et al [36] explored the use of robot gaze behaviors to signal participant roles and manage turn-exchanges in a triadic conversation.…”

“…[3,30,32,36]) in HRI has focused on the functions of robot gaze in conversations. Mutlu et al [36] explored the use of robot gaze behaviors to signal participant roles and manage turn-exchanges in a triadic conversation. Andrist et al [3] investigated gaze aversion and its functions of signaling cognitive effort, modulating intimacy level and managing turn-taking in human-robot conversations.…”

Timing in Multimodal Turn-Taking Interactions: Control and Analysis Using Timed Petri Nets

“…In robotics, there has been study of how speaker-listener roles can be strongly shaped by controlling the single modality of eye gaze (Mutlu, Shiwa, Ishiguro, & Hagita, 2009). There has also been related work on conversational engagement.…”

Measuring Human Workload in a Collaborative Human-Robot Team

“…Collaborative interactions can be improved by including nonverbal communication, such as having the robot partner recognize head nodding and respond by nodding back (Sidner Lee, Morency, & Forlines, 2006). Employing mutual gaze and gazing at objects that are the subjects of conversation can improve the conversation (Mutlu, Shiwa, Kanda, Ishiguro, & Hagita, 2009;Sidner, Kidd, Lee, & Lesh, 2004). Taking appropriate turns in verbal dialogue by using gaze, verbal cues, body language, and robot learning also makes an H-R conversation easier for the human partner (Chao & Thomaz, 2010).…”