Published: April 6, 2022
Robot turns to person entering the conversational group, even though she is not wearing a detectable hat like the other three members of the group.

To effectively participate in a group discussion, it's important to be able to identify who is present and direct your attention accordingly. For most people, this is not hard, but designing robots able to do the same thing is quite challenging. While robots are equipped with sensors for detecting the number of people in a group, they areÌýnot always accurate and, to date, there has been little research into how robots can confirm their assumptions and correct any errors they may have made.

However, last year, two researchersÌýin ATLAS Institute'sÌýIRON Lab* developed a solution to this problem that is described inÌýa paperÌýpublished in the March Proceedings of theÌýInternational Conference on Human-Robot Interaction Ìý(HRI '22). The authors,ÌýHooman HedayatiÌýÌý(PhD computer science '20) and Daniel Szafir, assistant professor of computer science at UNC Chapel HillÌýand the former director of the ATLAS IRON Lab, proposed a method to overcome situations when conversational group (F-formation) detection algorithms fail.

By studying different conversational groupÌýdata sets, the researchers observed that relative to the size of a conversation group, people tend to stand inÌýpredictable locations relative to each other. Hedayati and SzafirÌýthen developed a system for identifying high probability regions where people are likely to stand in a group relative to a single participant.ÌýUsing that system, the robot can reason when another person in theÌýconversation hasn't been detected and correct their error.Ìý

The first model estimates the true size of a conversational group, where only some participants were detected. TheÌýsecond model predicts the locations where any undetected participants are likely to be standing. Together, these models may improve detection algorithms and a robot's ability to detect members of a group and participate more seamlessly in a conversation.

*Following Szafir's departure last summer, the ATLASÌýIRON Lab was closed.

Ìý

Publication

Hooman Hedayati and Daniel Szafir. 2022. . In Proceedings of the 2022 ACM/IEEE International Conference on Human-Robot Interaction (HRI '22). IEEE Press, 402–411 (March 7-10, 2022—virtual, originally Hokkaido, Japan).