The simulation of traffic scenes in the environment of an automated vehicle promises to make significant contribution to the validation of automated driving. The construction of models which describe traffic scenes in a generic manner is complicated, since the parameter space of the scenes is infinite. This paper introduces a statistical approach to generate traffic scenes in intersections. A generic model which allows us to represent the scenes is proposed. The concept of Bayesian networks is used to fit the model onto a publicly accessible dataset and to infer traffic scenes from the model. A quantitative evaluation of the results is achieved by the calculation of the total variation distance (TVD) between the distributions of several physical properties.
Generation of Scenes in Intersections for the Validation of Highly Automated Driving Functions
2019-06-01
591690 byte
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
A comprehensive validation system for highly automated driving
TIBKAT | 2019
|Scenario Identification for Validation of Automated Driving Functions
Springer Verlag | 2016
|Real World Scenarios for the Safety Validation and Development of Highly Automated Driving Functions
British Library Conference Proceedings | 2022
|SENSOR COVERAGE ANALYSIS FOR AUTOMATED DRIVING SCENARIOS INVOLVING INTERSECTIONS
Europäisches Patentamt | 2021
|