The challenge of a computational driver's model in transport engineering. Preprint

TATTEGRAIN-VESTE ; BELLET ; PAUZIE ; CHAPON

Type de document
OUVRAGE SCIENTIFIQUE (OS)
Langue
anglais
Auteur
TATTEGRAIN-VESTE ; BELLET ; PAUZIE ; CHAPON
Résumé / Abstract
Taking into account road safety issues, a deep understanding of the 'driver' as a logic system is crucial, in order to be able to predict his most probable behavior according to the contextual elements. Knowledge and data in human functional abilities exist, the problem would be now to organize and to structure them. This paper proposes to realize a computational approach in the driver's modeling. In the first part, a brief historical overview of available driver models in ergonomic and in psychological areas is made, with a specific focus on the description of the hierarchical risk model. And the respective advantages of predictive versus explicative models in an implementation perspective. In the second part, the computational aspect of the work is described, with the software concepts, the cognitive modeling needs, the implementation choices and the knowledge modeling. The object oriented techniques have been chosen because they allow a modular overview of the general system and they also offer a reliable representation of the cognitive processes. The objective is to check if there is a possibility to implement in a quite reliable way a driver's model using the techniques from artificial intelligence and based on the theoretical knowledge from cognisciences researches. This attempt to establish links between two scientific domains, requiring to build a common tool, is a real challenge. This paper describes the first step of a work that will have to be developed in a long term time scale, taking into account its quite ambitious objective

puce  Accès à la notice sur le portail documentaire de l'IFSTTAR

  Liste complète des notices publiques de l'IFSTTAR