SimSpace: A Tool to Interpret Route Instructions with Qualitative Spatial Knowledge.

Abstract

This paper describes our work on using qualitative spa-tial interpretation and reasoning to achieve a natural and efficient interaction between a human and an intelli-gent robot on navigation tasks. The Conceptual Route Graph, which combines conventional route graphs and qualitative spatial orientation calculi, serves as an in-ternal model of human spatial knowledge on top of the robot’s quantitative representation, such that humans’ qualitative route instructions can be interpreted accord-ing to the model. The tool SimSpace then visualizes and proves the interpretation using qualitative spatial reasoning. Furthermore, SimSpace will generate appro-priate natural feedback if a route instruction cannot be interpreted properly.