Agent navigation under linguistic instructions of a route using contextual information

We propose a route planning algorithm for agent navigation under linguistic instructions of a route, aiming at man-agent flexible communication by a natural language. Instructions given to the agent describe a route in terms of landmarks like intersections, for example, “turn right at the second intersection”. The contextual information in instructions of a route provides some constraints on the interpretation of landmarks and their geometric relationships. This information helps to reduce ambiguities in landmark recognition