Spatio-Temporal Reasoning about Traffic Scenarios

A model of spatial relations between automobiles changing over time needs to trade off expressivity, computational complexity, type of measured data, and closeness to human cognition. We present a common sense theory for reasoning about distances between cars based on two temporal distances between pairs of cars, net time gap and time to collision. We give an axiomatization in the situation calculus which allows reasoning about car-to-car relations and how they are affected by time and acceleration. We also discuss experimental results in a plan recognition scenario.