“…Experimental HRI work has validated the idea that spatial formations typical of human-human conversations naturally emerge in human-robot interactions (Hüttenrauch et al, 2006;Kuzuoka et al, 2010;Karreman et al, 2015;Vázquez et al, 2015aVázquez et al, , 2017. In turn, this research led to work on recognizing F-Formations in robotics, such as methods geared toward improving robot navigation (Rios-Martinez et al, 2011), generating multimodal nonverbal robot behavior (Vázquez et al, 2017), helping recognize the beginning and ending of human-robot interactions (Gaschler et al, 2012), joining groups (Barua et al, 2020), and other approaches for service robots (Hedayati et al, 2019;Swofford et al, 2020). Oftentimes, prior work on F-Formation detection in robotics builds on mathematical models of human F-Formations from the computer vision community, for example, (Cristani et al, 2011;Setti et al, 2013;Setti et al, 2015;Vascon et al, 2014).…”