SVA – Simulation of Autonomous Vehicule Safety
Project description
Meet the challenge posed by the complexity of the safety demonstration of the autonomous vehicle through the use of digital simulation
The autonomous vehicle, which interprets its environment via sensors such as cameras and radars, must be designed to ensure the safety of its occupants and other road users. Consequently, it must be designed to cope with technical failures, external disturbances (eg rain, glare, etc.) that could affect the efficiency of its sensors and the difficulties of interpreting its environment (e.g. erased markings on the ground). This represents a real challenge.
Launched in 2015 for a period of four years, the SVA project aims to address the issue of autonomous vehicle validation through digital simulation, by developing methods and tools to assist in the design and validation.
Expected results
- Provide manufacturers and equipment fitters with a methodology, a platform and simulation tools to design safe autonomous vehicles and to validate them;
- Specify, adapt or develop models of vehicle components and their environment in order to simulate the behaviour of the vehicle in the event of a failure of one of its components and the impact on its operation due to external disturbances.
Implemented skills
Data science and AI | |
Human-machine interaction | |
Systems Engineering and Safety | |
Safety of critical systems |
Targeted markets
- Automobile
Supervised theses in the framework of the project
Thesis #1: Application of formal methods to control the development of embedded systems on the autonomous vehicle (ENS Cachan – Université Paris-Saclay / Laboratoire Spécification et Vérification)
Thesis #2: Formal models for the conceptualization and the characterization of use cases for the autonomous vehicule (Université de Versailles Saint-Quentin-en-Yvelines / Laboratoire DAVID / STIC)