Robust, marker-based head tracking for testing cognitive vehicles in the loop

Abstract

One of the great challenges for the release of automated vehicles is the verification and evaluation of their cognitive skills. Therefore, Vehicle-in-the-loop testing provides an adequate tool, combining real test drives with simulations. In this paper we present our innovative Vehiclein- the-loop framework: First, a marker-based head tracking is presented, which is able to track the driver’s head in presence of vehicle’s movement and illumination influences. Second, we present our realization based on the Open-Source framework ROS with an exemplary coupling to the professional simulation tool CarMaker. Finally, we evaluate our approach in different driving scenarios.