Traffic congestion causes unnecessary delay, pollution and increased fuel consumption. In this project we address this problem by creating a new Intelligent Transportation System which provides speed advice to car drivers. We design and analyze reinforcement learning algorithms to automatically learn policies dictating the optimal driving speed on the highway. Our algorithms take predictions of future traffic conditions into account, such that traffic flow can be controlled proactively. The resulting system is tested and evaluated in a real field test in the Netherlands.

Timeframe

October 2013 to December 2014

Collaborators

Cygnify BV, Traxpert, Locatienet, Tessa Bouw Communicatie

Funded by

Cityregion Eindhoven (SRE), the province of North Brabant and the Ministry of Infrastructure and the Environment, as part of the Brabant In-Car III program

More information

Please contact Matthijs Spaan