Search Results

Advanced driver assistance systems like cooperative adaptive cruise control (CACC) are designed to exploit information provided by vehicle-to-vehicle (V2V) and/or infrastructure-to-vehicle (I2V) communication systems to achieve desired objectives such as safety, traffic fluidity or fuel economy. In a day to day traffic scenario, the presence of unknown disturbances complicates achieving these objectives. In particular, CACC benefits in terms of fuel economy require the prediction of the behavior of a preceding vehicle during a finite time horizon. This paper suggests an estimation method based on actual and past inter-vehicle distance data as well as on traffic and upcoming traffic lights. This information is used to train a set of nonlinear, autoregressive (NARX) models. Two scenarios are investigated, one of them assumes a V2V communication with the predecessor, the other uses only data acquired by on-board vehicle sensors.

It is well known that driver behavior can affect fuel consumption to a large extent hence modifying it can lead to reasonable reduction in the magnitude of 10 to 20%. However, it is also known that effects of training are short lived and therefore many authors and companies suggest the use of monitoring systems, sometimes called eco-driver, which allow recognizing opportunities for reduction. V2V is an emerging technology which has been widely studied especially for safety applications. In terms of fuel consumption, there has also been a significant effort for methods directed to coordinate the movement of vehicles, especially of trucks, to improve fuel consumption by platooning [1].