A route representation framework and its main implementation procedures are proposed for generating contextadaptive route directions

which could meet human cognitive habits

reflect user’s spatial knowledge

and is apt to be expressed in natural language.In the framework

a route is represented as a sequence of uniform temporal and various granular instruction units

which can be processed into route instruction phrases or sentences.For the implementation of context-adaptive route directions

landmark extraction

various granular instruction unit generation and most appropriate instruction unit sequence selection are introduced

while some contextual factors such as environmental structures

route characteristics and prior knowledge are also considered in these procedures.After compared with traditional route directions predominantly using distance-to-turn information

it can be found that the context-adaptive route directions based on spatial cognition is more conformable to the way people describe routes

and thus could decrease user’s cognitive workload and promote the efficiency of navigation systems.