Using the robust statistics for travel time estimation on highways

Highway operators around the world are using automated vehicle identification (AVI)-based techniques as a technological input for travel time estimation on highways. Various AVI technologies provide various travel time measurement samples: some of them are able to identify only personal cars (e.g. tolling tags), while others provide mixed samples of all vehicle classes (e.g. license plate matching). As the adequate information on travel times should concern the personal cars, the influence of heavy vehicles (HVs) should be eliminated from the samples, which is not feasible with the use of existing travel time estimation algorithms. It was observed that also during congestion travel times of personal cars and HVs remain dispersed. The motivation for the present study was to introduce an algorithm that would be able to exclude the influence of slower HVs in travel time estimation for technologies, providing mixed samples of travel time measurements. This was achieved by the use of robust statistics. The results of the study could be used by all highway agencies and operators who are encountering problems with unreasonably extended estimations of travel times because of the presence of slow HVs in the traffic flow.