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. Furthermore the system behaviour can be evaluated for the recorded accidents.Active Safety Systems need to know if the driver is able to solve a critical situation or if an intervention of the vehicle is necessary. Driver behaviour is difficult to model. It is not feasible to compute every possible future state of the driver. Based on the work from Eidehall, a stochastic approach is implemented to calculate how long a driver is able to drive collision free, based on information about other traffic participants and a high-precision digital map. This approach is described in the second part of the paper.