Towards an Effective Generation of Functional Scenarios for AVs to Guide Sampling - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2023

Towards an Effective Generation of Functional Scenarios for AVs to Guide Sampling

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 sous embargo
Fichier sous embargo
1 1 29
Année Mois Jours
Avant la publication
dimanche 14 septembre 2025
Fichier sous embargo
dimanche 14 septembre 2025
Connectez-vous pour demander l'accès au fichier

Dates et versions

hal-04638461 , version 1 (10-07-2024)

Identifiants

Citer

Hugues Blache, Pierre-Antoine Laharotte, Nour-Eddin El Faouzi. Towards an Effective Generation of Functional Scenarios for AVs to Guide Sampling. SAFECOMP 2023 Workshop - Computer Safetty, Reliability and Security / workshop: International Workshop on Safety/Reliability/Trustworthiness of Intelligent Transportation Systems, Sep 2023, Toulouse, France. pp.260-270, ⟨10.1007/978-3-031-40953-0_22⟩. ⟨hal-04638461⟩
0 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Mastodon Facebook X LinkedIn More