Methods using belief functions to manage imperfect information concerning events on the road in VANETs

Mira Bou Farah (1) , David Mercier (1) , François Delmotte (1) , Éric Lefèvre (1)

1 LGI2A - Laboratoire de Génie Informatique et d'Automatique de l'Artois

Different models using belief functions are proposed and compared in this article to share and manage imperfect information about events on the road in vehicular networks. In an environment without infrastructure, the goal is to provide to driver the synthesis of the situation on the road from all acquired information. Different strategies are considered: discount or reinforce towards the absence of the event to take into account messages agings, keep the original messages or only the fusion results in vehicles databases, consider the world update, manage the spatiality of traffic jams by taking into account neighborhood. Methods are tested and compared using a Matlab TM simulator. Two strategies are introduced to tackle fog blankets spatiality; they are compared through an example.

Keywords: Vehicular Ad-hoc Networks (VANET); Theory of belief functions; Transferable Belief Model (TBM); Events on the road; Decentralized data fusion; Imperfect information exchange

Domains: Artificial Intelligence [cs.AI]; Other

Mira Bou Farah, David Mercier, François Delmotte, Éric Lefèvre. Methods using belief functions to manage imperfect information concerning events on the road in VANETs. Transportation research. Part C, Emerging technologies, 2016, 67, pp.299-320. ⟨10.1016/j.trc.2016.02.014⟩. ⟨hal-03727894⟩