Autonomous control of human-robot spacing

Abstract

To enable socially situated human-robot interaction, a robot must both understand and control proxemics, the social use of space, to employ communication mechanisms analogous to those used by humans. In this work, we investigate speech and gesture production and recognition as a function of social agent spacing during both human-human and human-robot interactions. These models were used to implement an autonomous proxemic robot controller. The controller utilizes a sampling-based method, wherein each sample represents inter-agent pose, as well as agent speech and gesture production and recognition estimates; a particle filter 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 literature. This work contributes to the understanding of the underlying pre-cultural processes that govern proxemic behavior, and has implications for robust proxemic controllers for robots in complex interactions and environments.