Incorporating safety relevance and realistic parameter combinations in test-case generation for automated driving safety assessment

Scenario Parameter Generation Method and Scenario Representativeness Metric for Scenario-Based Assessment of Automated Vehicles

“…• There is no assumption needed on a predetermined functional form of the time series data. For example, in an LVD scenario, the speed is often assumed to follow a polynomial function [10], a sinusoidal function, or a linear function [21]. In case of a predetermined functional form, parameters are fitted to the functional form.…”

“…Stepien et al [19] generate scenarios by sampling scenario parameter values from generalized extreme value distributions, where the distribution parameters are fitted using scenario parameter values extracted from safety-critical scenarios observed in naturalistic driving data. In [10,[20][21][22][23][24], also parameterized scenarios were generated and, in addition, importance sampling techniques were presented that automatically generate scenarios in which the system-under-test shows (safety-)critical behavior. Other approaches to generate scenarios in which the system-undertest shows (safety-)critical behavior are Monte Carlo tree search [25] and genetic programming [26].…”

“…• The scenarios are oversimplified. For example, a vehicle's speed profile follows a predetermined functional form [10,19,21].…”

“…of the metrics for the set of generated cut-in scenario parameters. [10,18,21]. Second, instead of using KDE to estimate the pdf of the parameters, a Gaussian distribution like in [29] is assumed.…”

Driver models for the definition of safety requirements of automated vehicles in international regulations. Application to motorway driving conditions

“…Therefore, the definition of sets of possible events is necessary. Those could be derived by observations in real data, by extracting correlations ( Thal et al, 2020 ), or sample high-risk situations ( Akagi et al, 2019 ). For the upcoming Level 3 ALKS, the riskiest cases will arguably be receiving a reckless cut-in by a slower vehicle, and a formulation to classify preventable and unpreventable cases is already in the text of the regulation [paragraph 5.2.5.2,( UNECE, 2021 )].…”