The ability to generate accurate travel time predictions for road freight transport is important when, for example, estimating the arrival times for heavy goods vehicles (HGVs) in order to plan terminal activities. We present a micro-level sampling method for road travel time prediction. The method makes use of historical GPS-data in order to determine the movement of a vehicle from an origin to a destination along a specific route. The method generates a travel time distribution, which can be used to obtain the expected travel time and probabilities for deviations. The method has been illustrated and evaluated in an experiment where the effective travel time was predicted for transport between two terminals. The experiment made use of GPS data that was recorded for two HGVs during a period of two months. An important feature of the method is that it does not need road network information, such as speed limits and number of lanes.