Constrained Sampling from a Kernel Density Estimator to Generate Scenarios for the Assessment of Automated Vehicles

Gelder, Erwin de; Cator, Eric; Paardekooper, Jan‐Pieter; Camp, Olaf Op den; Schutter, Bart De

doi:10.1109/ivworkshops54471.2021.9669213

Cited by 5 publications

(2 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…where A and b are a matrix and vector, respectively. In [40], an algorithm is provided for sampling from a pdf estimated using KDE such that the generated sample is subject to the constraint of (25). The main idea of [40] is to weight each parameter vector v i , i ∈ {1, .…”

Section: Discussionmentioning

confidence: 99%

“…where the latter equality follows from the orthonormality of V . 2 The advantage of the Gaussian kernel is that it gives the possibility to calculate a metric that quantifies the completeness of the data [39] and to apply conditional sampling when generating scenario parameters [40]. Both these topics are out of scope of this article.…”

Section: Estimating the Probability Density Functionmentioning

confidence: 99%

See 1 more Smart Citation

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

Gelder¹,

Hof

Cator

et al. 2022

IEEE Trans. Intell. Transport. Syst.

Self Cite

View full text Add to dashboard Cite

The development of assessment methods for the performance of Automated Vehicles (AVs) is essential to enable the deployment of automated driving technologies, due to the complex operational domain of AVs. One candidate is scenariobased assessment, in which test cases are derived from real-world road traffic scenarios obtained from driving data. Because of the high variety of the possible scenarios, using only observed scenarios for the assessment is not sufficient. Therefore, methods for generating additional scenarios are necessary.Our contribution is twofold. First, we propose a method to determine the parameters that describe the scenarios to a sufficient degree while relying less on strong assumptions on the parameters that characterize the scenarios. By estimating the probability density function (pdf) of these parameters, realistic parameters values can be generated. Second, we present the Scenario Representativeness (SR) metric based on the Wasserstein distance, which quantifies to what extent the scenarios with the generated parameter values are representative of real-world scenarios while covering the actual variety found in the realworld scenarios.A comparison of our proposed method with methods relying on assumptions of the scenario parameterization and pdf estimation shows that the proposed method can automatically determine the optimal scenario parameterization and pdf estimation. Furthermore, it is demonstrated that our SR metric can be used to choose the (number of) parameters that best describe a scenario. The presented method is promising, because the parameterization and pdf estimation can directly be applied to already available importance sampling strategies for accelerating the evaluation of AVs.

show abstract

Section: Discussionmentioning

confidence: 99%