Künstliche Intelligenz verhindert Verkehrsunfälle (English shop)

Preview

Extract, PDF (370 KB)
Table of Contents, PDF (27 KB)

The safety assessment of driving situations is of central importance for collision warning systems, driver assistance systems and autonomously driving vehicles. This contribution presents a new method for reliably assessing complex driving situations. Part of the relationships governing vehicle movements is described by stochastic models. The knowledge still missing is generated by a method of artificial intelligence, so that a complete stochastic model is available for the safety assessment. This model provides statements about current driving situations, such as the probability of a collision with a preceding vehicle or the probability of a severe collision. From these determined quantities, hazard warnings can be generated or braking manoeuvres initiated, and new driving functions can also be analysed as early as the development phase. The application of the method is demonstrated using recorded vehicle movement data from a traffic simulation. A direct safety assessment in the vehicle while driving is likewise possible.