Research Chair
RAIMo

A road toward safe artificial intelligence in mobility

Project

Recent progresses in machine learning in general and especially in deep learning make it possible to include this technology in more and more autonomous vehicles. However, before this possible future becomes reality and our roads are made safer with algorithms replacing human drivers, it is necessary to know how to prove the quality of the decisions made.

This project aims at strengthening local research dynamics about safety issues associated with the use of artificial intelligence in mobility. To achieve this goal, the project will endeavor to formalize the problem, to propose algorithms to solve it and to demonstrate its feasibility on real autonomous vehicles under real driving conditions.

Img

ORIGINALITY, PERSPECTIVES & METHODOLOGY

RAIMo is mainly concerned with the advance of enabling techniques for the certification to machine and deep learning systems. This is a challenging issue, owing to the black-box nature of deep neural networks and the lack of rigorous foundations. We have made this the starting point of our research proposal about artificial intelligence in mobility: how to keep it safe? Will roads be safer if algorithms replace human drivers? How can we trust deep learning based algorithms?

To answer these questions, RAIMo will explore new methods and systems which can ensure Artificial Intelligence systems such as deep neural networks are more robust, safe and interpretable for mobility applications by ensuring that deep networks and other machine learning systems do what its mint for them to do. Our research program focuses on these safety issues related to deep learning on three complementary aspects: theoretical foundations, algorithmic considerations and implementation for experimental validation.

View Works

FOLLOW OUR LATEST NEWS

Read more about our latest developments. Keep updated with our new results and publications. Don't miss our internal and external events.

News

Our Partners

The chair project intervenes, with the INSA and the University of Rouen Normandy as part of Normandy University, in all levels of engineering training and in training through research. To reach its ambitious goals, the Chair benefits from various fundings, the scientific support from local and national laboratories with research in AI domain, the facilities of the regional on-site calculation center CRIANN, and the support of an industrial partners with expertise on stereo vision.

LITIS Lab
Insa Rouen
Université de Rouen
Normandie
ANR
Normandie
CRIANN
Stereolabs
Meet our Team

Our Support

The chair benefits from the support of companies with a strong expertise in the design of autonomous vehicles.

Rouen Normandy Autonomous Lab
Transdev