Probabilistic Models of Proxemics for Spatially Situated Communication in HRI

Abstract

To enable socially situated human-robot interaction, a robot must both understand and control proxemics—the social use of space—in order to employ communication mechanisms analogous to those used by humans. In this work, we focus on social speech and gesture production and recognition during both human-human and human-robot interactions. We conducted a data collection to model these factors as a function of the relative distance and orientation between sociable agents. The resulting models were used to implement a spatially situated autonomous proxemic robot controller. The controller utilizes a samplingbased approach, wherein each sample represents interagent distance and orientation, as well as agent speech and gesture production and recognition estimates; a particle filter (with resampling) uses these estimates to maximize the performance of both the robot and the human during the interaction. This functional approach yields pose, speech, and gesture estimates consistent with related work in human-human and human-robot interactions. This work contributes to the understanding of the underlying pre-cultural processes that govern proxemic behavior, and has implications for the development of robust proxemic controllers for robots situated in complex interactions (e.g., with more than two agents, or with individuals with hearing or visual impairments) and environments (e.g., with loud noises, low light, or visual occlusions).