Experiments in subsymbolic driving pattern prediction

Using vehicles for transportation is a convenient way to improve speed or reduce strain and thus to enable much larger distances to be traveled. The use of place based positioning and navigation techniques could provide support for navigation tasks which are not well supported by conventional car navigation systems. Although driving is a very complex process, there are a number of regularities which could be exploited by place based navigation techniques. Neural networks are well known for their prediction capabilities and the paper explores possibilities of short-term prediction of vehicle movement by various neural network architectures.