Search Results

The potential of determining the change of injury severity in the accident event taking passive as well as active measures into account at the vehicle (integral systems) are at present limited to pedestrian protective systems. Therefore, an extension of the existing methods for the application with common integral systems (front protection, side protection, etc.) is suggested. Nowadays the effectiveness of passive safety systems is determined in crash tests with very high accident severities. However, approximately 90% of real-world accidents have a lower accident severity as the required crash tests. Thus, this paper will present a method calculating the effectiveness of such an integral system based on real-world accident data. For these reasons, this paper is presenting a method for a more valid prediction of injury severity. The German In-Depth Database GIDAS allows clustering the accident event in relevant car-to-car scenarios.

A reliable environment perception is a requirement for safe automated driving. For evaluating and demonstrating the reliability of the vehicle’s environment perception, field tests offer testing conditions that come closest to the vehicle’s driving environment. However, establishing a reference ground truth in field tests is time-consuming. This motivates the development of a procedure for learning the vehicle’s perception reliability from fleet data without the need for a ground truth, which would allow learning the perception reliability from fleet data. In Berk et al. (2019), a method based on Bayesian inference to determine the perception reliability of individual sensors without the need for a ground truth was proposed. The model utilizes the redundancy of sensors to learn the sensor’s perception reliability. The method was tested with simulated data.