Home > TERATEC FORUM > Workshop 2

TERATEC Forum 2015
Workshop 2 - Wednesday, June 24 from 9:00 to 12:30
Big Data: Optimizing decision making through Data Analytics

SALSA, a tool for large-scale analysis of driving data
Clément VAL, Responsable du département Expérience en science du comportement, CEESAR (Centre Européen d’Etudes de Sécurité et d’Analyse des Risques)

Download the presentation

The even more widespread usage of driving assistance systems and the development of autonomous vehicles raise numerous safety concerns. These systems replace the driver in the execution of an increased number of tasks. Their performance relies on the automated perception and interpretation of the heterogeneous environment surrounding the vehicle. Wrong interpretation of uncommon driving situations could lead to tragic consequences.

The usual experimental approach in a controlled environment is insufficient to identify those situations. In an attempt to improve the decision performance, large data have been gathered throughout the world in realistic situations in the last few years. Vehicle fleets have been used to collect data describing typical driving behaviors over long time frames. However, the analysis and interpretation of these data entails many challenges.

CEESAR has developed a tool (called SALSA) which allows scientists to tackle these challenges by automating data and computation management, algorithm testing, visualization, data annotation and querying.

Clément VAL dirige depuis 2006 le département « Expérimentations en Science du Comportement » du CEESAR. Il y a été organisé de nombreux projets dédiés à l’analyse du comportement des automobilistes. A travers les projets de collecte à grande échelle EUROFOT (40 automobiles en France) puis UDRIVE (120 automobiles en Europe), il a organisé l’enregistrement puis l’exploitation à grande échelle de données particulièrement riches (capteurs, vidéo…).
Clément VAL est diplômé de l’Ecole Centrale de Lyon.

Download the presentation



© Ter@tec - All rights reserved - Lawful mention