Skip to Main content Skip to Navigation
Conference papers

A Risk-Driven Model for Traffic Simulation

Abstract : With the advent of the autonomous vehicle and the transformation appearing in the automobile sector in the next decade, road traffic simulation has taken off again. In particular, it is one of the few ways to test an autonomous vehicle in silico [6]. To achieve this, current traffic generators must increase their realism. We argue here that one of the major points of this realism concerns the consideration of risk in driving models. We propose here an individual and self-organizing driving model based on customisable risk-taking factors. In this model, interactions create accidents. Each driver, individually, does not generate any accident, but the collectivity does. Accidents here are unpredictable emerging phenomena resulting from individual deterministic behaviours. Thanks to this model, the risk-taking factor of vehicles improves the realism of the simulations.
Complete list of metadata
Contributor : Antoine Nongaillard Connect in order to contact the contributor
Submitted on : Monday, August 31, 2020 - 9:56:10 AM
Last modification on : Thursday, March 24, 2022 - 3:43:01 AM



Antoine Nongaillard, Philippe Mathieu. A Risk-Driven Model for Traffic Simulation. Distributed Computing and Artificial Intelligence, 17th International Conference, 2020,, Jun 2020, L'Aquila, Italy. pp.1--10, ⟨10.1007/978-3-030-53036-5\_1⟩. ⟨hal-02925891⟩



Record views