Comparing Spoken Language Route Instructions for Robots across Environment Representations

Matthew Marge and Alexander Rudnicky
Carnegie Mellon University


Spoken language interaction between humans and robots in natural environments will necessarily involve communication about space and distance. The current study examines people’s close-range route instructions for robots and how the presentation format (schematic, virtual or natural) and the complexity of the route affect the content of instructions. We find that people have a general preference for providing metric-based instructions. At the same time, presentation format appears to have less impact on the formulation of these instructions. We conclude that understanding of spatial language requires handling both landmark-based and metric-based expressions.