IMG receives its first NSF award! The project will advance autonomous reasoning about spatial patterns of group behavior that naturally emerge during social conversations.

Spatial patterns of behavior emerge during conversations as a result the interactants’ need to communicate. Prior work, including our own [HRI’17; IROS’15], has mainly focused on analyzing spatial behavior in open spaces, where circular conversational groups are often observed. But in physically constrained spaces, people’s position might be influenced by nearby elements, such as walls and other people, leading to variations in acceptable group structure. To enable robots to cope with this variability, the new project will provide empirical knowledge and methods to incorporate spatial constraints into the way robots reason about conversational spatial formations.