Manon CESAIRE
Doctoral student
What is the topic of your PhD research ?
I am interested in the generation of scenarios for the learning and validation of a decision-making function for steering of autonomous vehicles. Scenario data collection driving in real-life situations (e.g. with regard to the number of lanes, surrounding vehicles or weather conditions) is very expensive. One solution is to automatically generate realistic scenarios, respecting the physical constraints of the environment and nearby vehicles, to meet the expectations of autonomous driving and cover as many situations as possible in order to anticipate potential hazards. To do this, I use adverse attack methods thanks to reinforcement learning algorithms. These methods refer to machine learning algorithms that attempt to “deceive” models (for example neural networks) by providing erroneous information. I am thus able, on the basis of existing scenarios, to generate new ones that can mislead the autonomous driver thanks to the various adverse attacks set up, while maximizing the loss function of the decision system taken between the two scenarios.
Why did you decide to do your PhD at IRT SystemX?
I did my Master 2 Data Science internship at the institute. It was therefore quite natural for me to want to continue my studies within the Data Science and AI team and to make the most of my skills in mathematics and computer science. The collaborations between the academic and industrial worlds within the institute are also very instructive. Moreover, autonomous driving is a cutting-edge area that I find particularly exciting because it is about to radically change the relationship between users and their vehicles. It is therefore essential to have enhanced safety and to avoid any failure of this type of vehicle. I wanted to make my contribution in this field by completing my doctorate at the institute.
Can you describe SystemX in 3 words ?
Collaboration, Competence, Conviviality.