Practical validation of synthetic pre-crash scenarios

The representativeness of synthetic pre-crash scenarios is crucial for assessing the safety impact of Driving Automation Systems through virtual simulations. However, a gap remains in the robust evaluation of synthetic pre-crash scenarios' practical equivalence to their real-world counterparts; that is, whether they are similar enough for the intended assessment purpose. Conventional significance testing is inadequate, as it focuses on detecting differences rather than establishing practical equivalence. This study addresses the research gap by extending our previous work on a Bayesian Region of Practical Equivalence (ROPE)-based equivalence testing framework by introducing a binning-based approach to define appropriate statistics and equivalence criteria. Two binning-based statistics are proposed to measure practically meaningful distributional differences between datasets in the context of safety impact assessment. The framework's applicability is demonstrated through a case study, which tests the practical equivalence of two synthetic rear-end pre-crash datasets with a previously developed reference dataset in the context of the safety impact assessment of an Automatic Emergency Braking system. The results show that the framework provides informative quantitative assessments of practical equivalence as well as diagnostic insights into the divergence of datasets. Although the demonstration focuses on rear-end pre-crash scenarios, the framework is generic and extensible to broader validation contexts, providing an interpretable and principled basis for practical equivalence assessment across diverse synthetic data applications.

Practical Equivalence Testing and Its Application in Synthetic Pre-Crash Scenario Validation

The use of representative pre-crash scenarios is critical for assessing the safety impact of driving automation systems through simulation. However, a gap remains in the robust evaluation of the similarity between synthetic and real-world pre-crash scenarios and their crash characteristics. Without proper validation, it cannot be ensured that the synthetic test scenarios adequately represent real-world driving behaviors and crash characteristics. One reason for this validation gap is the lack of focus on methods to confirm that the synthetic test scenarios are practically equivalent to real-world ones, given the assessment scope. Traditional statistical methods, like significance testing, focus on detecting differences rather than establishing equivalence; since failure to detect a difference does not imply equivalence, they are of limited applicability for validating synthetic pre-crash scenarios and crash characteristics. This study addresses this gap by proposing an equivalence testing method based on the Bayesian Region of Practical Equivalence (ROPE) framework. This method is designed to assess the practical equivalence of scenario characteristics that are most relevant for the intended assessment, making it particularly appropriate for the domain of virtual safety assessments. We first review existing equivalence testing methods. Then we propose and demonstrate the Bayesian ROPE-based method by testing the equivalence of two rear-end pre-crash datasets. Our approach focuses on the most relevant scenario characteristics. Our analysis provides insights into the practicalities and effectiveness of equivalence testing in synthetic test scenario validation and demonstrates the importance of testing for improving the credibility of synthetic data for automated vehicle safety assessment, as well as the credibility of subsequent safety impact assessments.

Model-based generation of representative rear-end crash scenarios across the full severity range using pre-crash data

Generating representative rear-end crash scenarios is crucial for safety assessments of Advanced Driver Assistance Systems (ADAS) and Automated Driving systems (ADS). However, existing methods for scenario generation face challenges such as limited and biased in-depth crash data and difficulties in validation. This study sought to overcome these challenges by combining naturalistic driving data and pre-crash kinematics data from rear-end crashes. The combined dataset was weighted to create a representative dataset of rear-end crash characteristics across the full severity range in the United States. Multivariate distribution models were built for the combined dataset, and a driver behavior model for the following vehicle was created by combining two existing models. Simulations were conducted to generate a set of synthetic rear-end crash scenarios, which were then weighted to create a representative synthetic rear-end crash dataset. Finally, the synthetic dataset was validated by comparing the distributions of parameters and the outcomes (Delta-v, the total change in vehicle velocity over the duration of the crash event) of the generated crashes with those in the original combined dataset. The synthetic crash dataset can be used for the safety assessments of ADAS and ADS and as a benchmark when evaluating the representativeness of scenarios generated through other methods.