VEDECOM is very pleased to announce the defense of the thesis of Laurène CLAUSSMANN

VEDECOM is very pleased to announce the defense of the thesis of Laurène CLAUSSMANN untitled « Motion Planning for Autonomous Highway Driving: A Unified Architecture for Decision-Maker and Trajectory Generator ».

For the first time, the defense took place at the mobiLAB, on Friday, September, 27th.

JURY
Pr. Michel BASSET Université de Haute Alsace Rapporteur
Dr. Fawzi NASHASHIBI,
INRIA, Rapporteur
Pr. Arnaud DE LA FORTELLE, 
Mines ParisTech, Examinateur
Dr. Vicente MILANES, 
Renault, Examinateur
Dr. Lydie NOUVELIERE, 
Université d’Evry-Val-d’Essonne, Examinateur
Pr. Sébastien GLASER, 
Queensland University of Technology, Directeur de thèse
Dr. Olivier ORFILA, IFSTTAR, 
Co-encadrant
Dr. Marc REVILLOUD, Institut VEDECOM, 
Co-encadrant

 RESUME

This thesis work is part of the development of a self-driving car in highway environments. More precisely, it aims to propose a unified architecture of trajectory planner and decision-maker taking into account the limitations of the environment and the available data within the current development of sensors technologies (distance limitations, uncertainties).
On the one hand, the method generates sigmoid trajectories in a continuous spatiotemporal representation of the evolution space, which is reduced beforehand by modeling collision-free intervals in nominal conditions of driving. The sigmoid parameters are subsequently optimized with a simulated annealing approach that uses the decision-maker algorithm as the evaluation function for the generated trajectory. It thus
makes it possible to elude both the discretization and position/speed decoupling problems. On the other hand, the aggregation of fuzzy logic and belief theory allows decision making on heterogeneous criteria and uncertain data. The proposed framework also handles personalization of the vehicle’s behavior, depending on the passengers’ risk perception and aggressive or conservative driving style.
The presented approach was finally evaluated and validated in a simulation environment and then in a test vehicle. The planning block was integrated into the existing vehicle’s architecture, interfaced with the localization, obstacles’ perception and control blocks.

 

Articles récents :