| 摘要 |
A anticipatory monitoring and prediction system described in the present invention comprises methods for generating effective, accurate predictions of other traffic objects in the vicinity of an ego-car. To this end the invention proposes to combine approximate probability distributions (ADPs) of agent states with Attractor Functions (AFs) for generating distributed probabilistic representations of the potential future states of the observed traffic objects. For maximal accuracy, AFs are selected based on both the current road context, in which the ego-car is situated, and the current states of all participating objects. The generated predictions can be used to filter incoming sensory information for better object state estimations, to rate the normality or the hazardous nature of the behavior of other traffic objects by comparing generated predictions with actual perceived sensor information, or to infer accident likelihoods by comparing the predicted state distributions of objects and the ego-car. Further, warning and information signals in a driving assistance system or actual control commands for preventing accidents can be issued. |
