Framework for Safety in Autonomous Vehicles

Matthieu Carre (1) , Ernesto Expósito (2) , Javier Ibañez-Guzman (3)

1 LIUPPA - Laboratoire Informatique de l'Université de Pau et des Pays de l'Adour
2 LAAS-SARA - Équipe Services et Architectures pour Réseaux Avancés
3 Multimedia and Driving Assistance Systems

The integration of the Safety dimension has been a critical requirement when developing and deploying Autonomous Vehicles (AV). While much progress has been achieved within the past years, most work has centred on providing vehicles with the ability to navigate autonomously. Safety has emerged as the major challenge. This paper proposes a reference architecture that incorporates the notion of self-safety into existing AV architectures. This architecture consists in a multi-layered control loop aimed at managing self-adaptation processes in order to ensure safety at run-time

Domains: Engineering Sciences [physics]; Automatic; Computer Science [cs]; Computational Engineering, Finance, and Science [cs.CE]

Matthieu Carre, Ernesto Expósito, Javier Ibañez-Guzman. Framework for Safety in Autonomous Vehicles. Conférence Francophone sur les Architectures Logicielles (CAL 2019), Oct 2019, Hammamet, Tunisia. ⟨hal-02416464⟩