Are you an EPFL student looking for a semester project?
Work with us on data science and visualisation projects, and deploy your project as an app on top of Graph Search.
Over the past decade, the automotive industry has made many efforts to improve the comfort and first and foremost the safety of passenger cars. So-called driver assistance systems have been developed, which support the driver in his task of controlling (steer-ing, breaking …) a vehicle. Present-day assistance systems are entrusted with complex driving manoeuvres and are expected to operate correctly in the highly dynamic, non-linear and unpredictable domain of road traffic. The field of artificial intelligence (AI) pro-vides concepts and methods, which are well-suited for the development of intelligent systems, able to act adequately in such an environment. This paper starts with a defini-tion of the properties and abilities of modern, intelligent driver assistance systems and how they can be distinguished from more traditional, older approaches. We explain why there is a demand for artificial intelligence within their development and name the most relevant concepts and methods from this field. Afterwards, we present examples and general frameworks for intelligent driver assistance systems and the concrete application of AI methods within them.
Alexandre Massoud Alahi, Yang Gao, Kaouther Messaoud Ben Amor, Saeed Saadatnejad
Jürg Alexander Schiffmann, Tomohiro Nakade, Robert Fuchs