PRISSMA

The PRISSMA project is the response proposed by the autonomous mobility sector to Pillar 2 issued by the Grand Défi in partnership with the Ministry of Ecological and Inclusive Transition (notably through the DGITM and DGEC), focusing on the security, reliability, and ultimately the certification of AI-based systems.
This project aims to provide a platform that will overcome the technological barriers preventing the deployment of secure AI-based systems, and to integrate all the elements necessary for the approval activities of autonomous vehicles and their validation in their environment for a given use case.
Three main objectives can be listed for this project.
- Identify and list the safety and security objectives for AI-based autonomous mobility systems and develop complete reliability validation processes with a view to the commercial deployment of autonomous mobility services.
- Ensure the availability of shared concepts to address the complexity of AI-based autonomous mobility systems, which can be used internationally.
- Contribute to the implementation of prerequisites enabling France to position itself at the European level to host one of the Testing Facilities for autonomous mobility that will be developed in the coming years.
The PRISSMA project focuses on two main use cases, namely shuttles and automated robots (Droids).

An ambitious project
- PRISSMA addresses AI in the approval of Automated Mobility by considering the entire chain: Vehicle(s), Infrastructure (augmented or not), and Supervision.
- PRISSMA will propose a complementary methodological framework to the existing approval framework related to AI issues, with the objective of establishing a reference framework or label.
- By relying either on an existing approval strategy (shuttles) or by generating a new approval strategy (droids), PRISSMA aims in particular to:
- Extract as much information as possible from tests in a simulated environment, especially for the identification of critical scenarios,
- Enrich tests in a controlled environment and in a real environment, particularly in connection with supervision and infrastructures,
- Adapt and develop technologies/tools/testing and simulation means for the implementation of proofs of concept (POC) validating the adequacy of the process and tools with the needs of the approval strategy.

Contact

GuillaumePERRIN
Chercheur en apprentissage statistique et quantification des incertitudes
guillaume.perrin@univ-eiffel.fr
+33 (0)1 81 66 81 83Marne-la-Vallée