LIRIS Laboratory

Sainte-Foy-lès-Lyon, France

LIRIS Laboratory

Sainte-Foy-lès-Lyon, France
Time filter
Source Type

Monteil J.,University of Lyon | Billot R.,IFSTTAR | Sau J.,University of Lyon | Armetta F.,LIRIS Laboratory | And 2 more authors.
Transportation Research Record | Year: 2013

As cooperative systems (connected vehicles) enable communication and the exchange of information between vehicles and infrastructure, the communication capabilities are expected to lead to better active traffic management on urban motorways. Technological constraints must be the basis for any management strategy. If communication has been analytically proved to help stabilize traffic flow at a microscopic level, then realistic communication strategies should be evaluated by taking into consideration multiple perturbations such as sensor faults and driver cooperation. In this study, a three-layer multiagent framework was used to model and control the homogenization of traffic flow. The physical layer coordinated vehicle dynamics on the basis of a cooperative car-following model. This layer included cooperation derived from the communication and trust layers that, respectively, managed information and its reliability. Simulation results highlight the positive impacts of communication and control on the stability of traffic flow.

Gueriau M.,University of Lyon | Billot R.,University of Lyon | Hassas S.,University of Lyon | Hassas S.,LIRIS Laboratory | And 3 more authors.
2014 International Conference on Connected Vehicles and Expo, ICCVE 2014 - Proceedings | Year: 2014

We present a multi-agent based extension of a microscopic time continuous lane-based simulator designed to develop cooperative vehicle behaviors within a connected environment. We have chosen to extend the Multi-model Open-source Vehicular-traffic SIMulator (MovSim) which offers a complete traffic simulation platform. By integrating concepts coming from artificial intelligence and related intelligent distributed systems such as multi-agent systems, we aim to model complex individual interactions (including sensors measurements, communication between vehicles and with the infrastructure). © 2014 IEEE.

Malki A.,LIRIS Laboratory | Barhamgi M.,LIRIS Laboratory | Benslimane S.-M.,EEDIS Laboratory | Benslimane D.,LIRIS Laboratory | Malki M.,EEDIS Laboratory
IEEE Transactions on Knowledge and Data Engineering | Year: 2015

With the emergence of the open data movement, hundreds of thousands of datasets from various concerns are now freely available on the Internet. The access to a good number of these datasets is carried out through Web services which provide a standard way to interact with data. In this context, user's queries often require the composition of multiple data Web services to be answered. Defining the semantics of data services is the first step towards automating their composition. An interesting approach to define the semantics of data services is by describing them as semantic views over a domain ontology. However, defining such semantic views cannot always be done with certainty, especially when the service's outputs are too complex. In this paper, we propose a probabilistic approach to model the semantics uncertainty of data services. In our approach, a data service with an uncertain semantics is described by several possible semantic views, each one is associated with a probability. Services along with their possible semantic views are represented in a Block-Independent-Disjoint (noted BID) probabilistic service registry, and interpreted based on the Possible Worlds Semantics. Based on our modeling, we study the problem of interpreting an existing composition involving services with uncertain semantics. We also study the problem of compositing uncertain data services to answer a user query, and propose an efficient method to compute the different possible compositions and their probabilities. © 2014 IEEE.

Gueriau M.,University of Lyon | Billot R.,University of Lyon | El Faouzi N.-E.,University of Lyon | Hassas S.,University of Lyon | And 3 more authors.
Proceedings of the National Conference on Artificial Intelligence | Year: 2015

Cooperative Intelligent Transportation Systems (C-lTS) are complex systems well-suited to a multi-agent modeling. We propose a multi-agent based modeling of a C-ITS, that couples 3 dynamics (physical, informational and control dynamics) in order to ensure a smooth cooperation between non cooperative and cooperative vehicles, that communicate with each other (V2V communication) and the infrastructure (I2V and V2I communication). We present our multi-agent model, tested through simulations using real traffic data and integrated into our extension of the Multi-model Open-source Vehiculartraffic SIMulator (MovSim). © Copyright 2015, Association for the Advancement of Artificial Intelligence ( All rights reserved.

Loading LIRIS Laboratory collaborators
Loading LIRIS Laboratory collaborators