Search Results

Within this work we demonstrate the implementation and evaluation of a vehicle-to-vehicle based intersection assistance system, relying only on communication between the vehicles and not requiring any communication with infrastructural components as it is the case with typical complex intersection assistance systems. It also requires no additional information like right-of-way or maps and works out-of-the-box for nearly all types of intersections. The intersection assistance system utilizes GPS, yaw rate, vehicle acceleration, speed and heading as indicators for a 3D path prediction. While the x-y layer aids in the detection of possible collisions, the z axis is used for detecting bridges and overpasses. By applying several sophisticated filter levels and algorithms, the amount of false positives can massively be reduced while the true positives can be maintained. Finally, the developed simple intersection assistance system is compared to a sophisticated intersection assistance system.

Highly Automated Driving (HAD) opens up new middle-term perspectives in mobility and is currently one of the main goals in the development of future vehicles. The focus is the implementation of automated driving functions for structured environments, such as on the motorway. To achieve this goal, vehicles are equipped with additional technology. This technology should not only be used for a limited number of use cases. It should also be used to improve Active Safety Systems during normal non-automated driving. In the first approach we investigate the usage of machine learning for an autonomous emergency braking system (AEB) for the active pedestrian protection safety. The idea is to use knowledge of accidents directly for the function design. Future vehicles could be able to record detailed information about an accident. If enough data from critical situations recorded by vehicles is available, it is conceivable to use it to learn the function design.