Robots in the Wild

Human-robot interaction (HRI) research to date has been dominated by laboratory studies, largely examining a single human interacting with a single robot. This research has helped establish a fundamental understanding about people as they interact with robots, how specific design choices affect interactions with robots, and how novel mechanisms or computational tools can be used to improve HRI. The predominant focus of this growing body of work, however, stands in stark contrast to the complex social contexts in which robots are increasingly placed. Developments in machine learning and tele-robotics, as well as compliant and social robotics, have occasioned more robots in closer proximity and even direct contact with people. Robots, especially mobile autonomous robots, are now deployed across work contexts and "sociable robots" such as Jibo, Cozmo, Kuri, and M.A.X. are increasingly becoming staples of household technology. These robots interact with people in everyday contexts across a wide range of tasks and situations, yet our research reflects a time when studies of HRI were possible almost exclusively only in laboratory settings. As a result, we have a limited understanding of how people will respond to robots in complex social settings and how robots will affect social dynamics in situ. In particular, our theories reflect an oversimplified view of HRI. The time is ripe for studies that tackle HRI in these complex settings and build generalizable theories about what to expect of HRI in the wild.