Bayesian Environment Representation, Prediction, and Criticality Assessment for Driver Assistance Systems

Zusammenfassung

This work deals with the questions i) how to represent the driving environment in an environment model, ii) how to obtain such a representation, and iii) how to predict the traffic scene for critica­lity assessment. Bayesian inference provides the common framework of all designed methods. First, Parametric Free Space (PFS) maps are introduced, which compactly represent the vehicle environment in form of relevant, drivable free space while suppressing irrelevant details of ­common occupancy grids. They are obtained by a novel method for grid mapping and tracking in dynamic environments. In addition, a maneuver-based, long-term trajectory prediction and criticality assessment system is introduced together with the Time-To-Critical-Collision-Probability (TTCCP) metric for uncertain, multi-object driving situations. Finally, the Advanced Driver Assistance System (ADAS) PRORETA 3 is described, which constitutes an integrated approach to collision avoidance and vehicle automation.

...