Generation of Realistic Traffic Scenarios for Virtual and Real Test Drives Based on a Hybrid Machine Learning Framework

Realistic test scenarios are an indispensable tool in all development phases of automated driving functions. This paper presents a hybrid method that combines the advantages of data-driven methods with the modeling of realistic driving behavior using vehicle dynamics models. A neural network autoregressively generates a wide variety of starting configurations. A scenario planner within a ROS environment, which can be used to generate both virtual and real test scenarios, creates test cases from these starting configurations. The procedure is illustrated using three test scenarios, which can be found at https://doi.org/10.5281/zenodo.14002640. The neural network presented here slightly outperforms state-of-the-art models in replicating the distribution of road users in the real-world dataset. Moreover, it significantly reduces the number of scenarios where road users are positioned in the starting configuration in such a way that a collision with other road users can no longer be prevented, even if emergency braking is applied. The presented approach can play a key role in the scenario-based validation process of automated vehicles.