Représentation ego‐centrée à base d’affordances de l’environnement pour la simulation multi‐agents de trafic

Abstract : To improve the validity of traffic simulations in urban and suburban areas, we propose to consider the driving context and the driver behavior in terms of space occupation. We endow agent driver with an ego‐centered representation of the environment based on the concept of affordances. We use the affordances to identify the possible actions, in terms of space occupation (virtual lanes), afforded by the environment. We use them, next, to build an ego‐centered representation of the situation. The proposed driver model was implemented with ArchiSim. The experiments allow to reproduce a real traffic situation and to compare simulated data to real ones.
Complete list of metadatas

Cited literature [46 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-01670597
Contributor : Arnaud Bonnard <>
Submitted on : Wednesday, March 14, 2018 - 8:57:25 AM
Last modification on : Thursday, March 21, 2019 - 12:59:12 PM
Long-term archiving on : Friday, June 15, 2018 - 12:38:24 PM

File

S0761898016004027a.pdf
Publisher files allowed on an open archive

Identifiers

Citation

Feirouz Ksontini, René Mandiau, Zahia Guessoum, Stéphane Espié. Représentation ego‐centrée à base d’affordances de l’environnement pour la simulation multi‐agents de trafic. Recherche Transports Sécurité, NecPlus, 2016, 2015 (03-04), pp.153-171. ⟨10.4074/S0761898016004027⟩. ⟨hal-01670597⟩

Share

Metrics

Record views

292

Files downloads

103