BézierVAE: Improved Trajectory Modeling using Variational Autoencoders for the Safety Validation of Highly Automated Vehicles

Krajewski, Robert; Moers, Tobias; Meister, Adrian; Eckstein, Lutz

doi:10.1109/itsc.2019.8917297

Cited by 16 publications

(5 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Regarding RQ 2, we focus on the potential and limitations of each approach to conclude characteristics of scenario generation techniques. Data-driven approaches derive scenarios from a database of real-world observation, e.g., by reconstruction [9], [10], applying clustering methods [11], machine learning [12] or statistical analysis [13], [14]. Optimization-based scenario generation approaches define a fitness function and generate scenarios to maximize or minimize it.…”

Section: Discussionmentioning

confidence: 99%

Feature-Interaction Sampling for Scenario-based Testing of Advanced Driver Assistance Systems✱

Lukas

Pett

Vogelsang

et al. 2022

Proceedings of the 16th International Working Conference on Variability Modelling of Software-Intensive Systems

View full text Add to dashboard Cite

Scenario-based testing is considered state-of-the-art to verify and validate Advanced Driver Assistance Systems. However, two essential unsolved challenges prevent the practical application of scenario-based testing according to the SOTIF-standard: (1) how to select a set of representative test scenarios, and (2) how to assess the effectiveness of a test scenario suite. In this paper, we leverage variability modelling techniques to select scenarios from a scenario space and assess the resulting scenario suites with a mutation score as metric. We capture the scenario space in a feature model and generate representative subsets with feature-interaction coverage sampling. The mutation score assesses the failure-finding effectiveness of these samples. We evaluate our concepts by sampling scenario suites for two independent Autonomous Emergency Braking function implementations and executing them on an industrialstrength simulator. Our results show that the feature model captures a scenario space that is relevant to identify all mutants. We show that sampling based on interaction coverage reduces the testing effort significantly while maintaining effectiveness in terms of mutation scores. Our results underline the potential of feature model sampling for testing in the automotive industry. CCS CONCEPTS• Software and its engineering → Software testing and debugging.

show abstract

Section: Discussionmentioning

confidence: 99%

Feature-Interaction Sampling for Scenario-based Testing of Advanced Driver Assistance Systems✱

Lukas

Pett

Vogelsang

et al. 2022

Proceedings of the 16th International Working Conference on Variability Modelling of Software-Intensive Systems

View full text Add to dashboard Cite

show abstract

“…While most datadriven approaches attempt to identify predefined logical scenarios, some approaches utilize machine-learning methods. For this purpose, unsupervised machine learning is used to identify scenario parameters without previously defined knowledge [16,17]. However, when applying machine learning, the completeness of the scenario catalog depends on the quality and completeness of the dataset.…”

Section: B Scenario Identificationmentioning

confidence: 99%

Logical Scenarios Parameterization for Automated Vehicle Safety Assessment: Comparison of Deceleration and Cut-In Scenarios From Japanese and German Highways

et al. 2022

View full text Add to dashboard Cite

This study compares real-traffic deceleration and cut-in scenarios, which were established as critical to automated vehicles (AVs) safety, between Japanese and German highway trajectory datasets. Both scenarios were extracted from two different traffic data previously collected in Japan with both instrumented vehicles and fixed cameras over highways (SAKURA dataset) and in Germany with drones (highD dataset). Five vehicle kinematic variables (lateral and longitudinal distances, velocities, and accelerations) were used to parameterize both scenarios and compared them between datasets using correlation and intersection objective measures and safety metrics: Time-to-Collision and Time Headway. Despite the differences in the rule of the road (e.g., speed limits, left-and right-hand traffic), road design, and data sources between the two countries, data comparison results revealed significant correlations and intersections of parameters distribution for both scenarios. The Time-to-Collision significantly overlapped between countries for both scenarios. However, differences in the Time Headway indicate that the safety distance varied across both countries, suggesting that safety assessment methodologies need to be tailored to different environments and regions to ensure safety. These results highlight the potential to develop safety indicators applicable at the international level and warrant further data collection and comparative studies that support the development of harmonized, widely applicable, and region-neutral AVs safety assessment methodologies.

show abstract

“…Nevertheless, the approach could perform poorly in covering high diversity if a bad database is used. While most of the data-driven approaches identify logical scenarios based on a parameterizable model [17], some are utilizing machine-learning methods [18], [19]. For this purpose, the method of unsupervised machine learning is used, which divides a data set into scenarios without previously defined knowledge.…”

Section: B Gathering Of Concrete Scenariosmentioning

confidence: 99%

The ConScenD Dataset: Concrete Scenarios from the highD Dataset According to ALKS Regulation UNECE R157 in OpenX

Tenbrock¹,

König²,

Keutgens³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

With Regulation UNECE R157 on Automated Lane-Keeping Systems, the first framework for the introduction of passenger cars with Level 3 systems has become available in 2020. In accordance with recent research projects including academia and the automotive industry, the Regulation utilizes scenario based testing for the safety assessment. The complexity of safety validation of automated driving systems necessitates system-level simulations. The Regulation, however, is missing the required parameterization necessary for test case generation. To overcome this problem, we incorporate the exposure and consider the heterogeneous behavior of the traffic participants by extracting concrete scenarios according to Regulation's scenario definition from the established naturalistic highway dataset highD. We present a methodology to find the scenarios in real-world data, extract the parameters for modeling the scenarios and transfer them to simulation. In this process, more than 340 scenarios were extracted. OpenSCENARIO files were generated to enable an exemplary transfer of the scenarios to CARLA and esmini. We compare the trajectories to examine the similarity of the scenarios in the simulation to the recorded scenarios. In order to foster research, we publish the resulting dataset called ConScenD together with instructions for usage with both simulation tools. The dataset is available online at https://www.levelXdata.com/scenarios.

show abstract

BézierVAE: Improved Trajectory Modeling using Variational Autoencoders for the Safety Validation of Highly Automated Vehicles

Cited by 16 publications

References 5 publications

Feature-Interaction Sampling for Scenario-based Testing of Advanced Driver Assistance Systems✱

Feature-Interaction Sampling for Scenario-based Testing of Advanced Driver Assistance Systems✱

Logical Scenarios Parameterization for Automated Vehicle Safety Assessment: Comparison of Deceleration and Cut-In Scenarios From Japanese and German Highways

The ConScenD Dataset: Concrete Scenarios from the highD Dataset According to ALKS Regulation UNECE R157 in OpenX

Contact Info

Product

Resources

About