Charmet, Thibault (Renault, Université de technologie de Compiègne), Cherfaoui, Véronique (UNIVERSITE DE TECHNOLOGIE DE COMPIEGNE), Ibanez Guzman, Javier (Renault S.A.S,), Armand, Alexandre (Renault SA)

Operational Design Domain Monitoring with Uncertain Measurements

Scheduled for presentation during the Regular Session "Advanced Vehicle Safety Systems I" (WeBT8), Wednesday, September 25, 2024, 14:30−14:50, Salon 16

2024 IEEE 27th International Conference on Intelligent Transportation Systems (ITSC), September 24- 27, 2024, Edmonton, Canada

This information is tentative and subject to change. Compiled on October 3, 2024

Abstract

The increasing automation in Intelligent Vehicles (IVs) necessitates robust safety measures. This paper proposes a method to address this challenge using the concept of Operational Design Domains (ODDs) and real-time monitoring. We present a framework for calculating an Operational Domain (OD) membership degree that accounts for measurement uncertainties and fuzzy boundaries within the ODD. This method utilizes fuzzy sets to represent the vagueness of real-world driving environments. Additionally, we introduce a taxonomy-based approach for formally defining ODDs independent of the vehicle's architecture. Our approach is demonstrated in simulation, by monitoring the vehicle's OD in real-time and by determining when it exits its defined ODD. The results pave the way for verifiable safety rules based on OD membership degrees.