Sampling Safety-Critical Traffic Scenarios for Connected and Automated Vehicles - Archive ouverte HAL
Communication Dans Un Congrès Année : 2023

Sampling Safety-Critical Traffic Scenarios for Connected and Automated Vehicles

Résumé

Numerous methods have been developed for testing Connected and Automated Vehicles (CAV). The scenario-based approach is considered the most promising as it reduces the number of scenarios required to certify the CAV system. In this study, we propose a refined six-step methodology that includes two additional steps to compute a critical index for scenarios and use it to guide the sampling process The methodology starts with the generation of functional scenarios using a 5-layer ontology. Next, the driving data is processed to determine the criticality indices of the functional scenarios. This is achieved by using a latent Dirichlet Allocation technique and a Least Means Squares method. Finally, the sampling process is built on a scenario reduction based on clustering and a specific metric related to the a priori criticality indices. Overall, our refined approach enhances the scenario-based methodology by incorporating criticality indices to guide the sampling process, which can reduce drastically the number of scenarios needed for certification of CAV systems.
Fichier non déposé

Dates et versions

hal-04638478 , version 1 (08-07-2024)

Identifiants

  • HAL Id : hal-04638478 , version 1

Citer

Hugues Blache, Pierre-Antoine Laharotte, Nour-Eddin El Faouzi. Sampling Safety-Critical Traffic Scenarios for Connected and Automated Vehicles. International Symposium on Transportation Data & Modelling (ISTDM2023), Jun 2023, Ispra, Italy. ⟨hal-04638478⟩
18 Consultations
0 Téléchargements

Partager

More