Simulation of connected driving in hazardous weather conditions: General and extensible multiagent architecture and models. (September 2021)

• Record Type: Journal Article
• Authors: Outay, Fatma; Galland, Stéphane; Gaud, Nicolas; Abbas-Turki, Abdeljalil
• Is Part Of: Engineering applications of artificial intelligence. Volume 104(2021)
• Publication Date: 2021-09
• Subjects: Agent-based simulation -- Microscopic simulation -- Traffic simulation -- Foggy weather condition; Engineering -- Data processing -- Periodicals; Artificial intelligence -- Periodicals; Expert systems (Computer science) -- Periodicals; Ingénierie -- Informatique -- Périodiques; Intelligence artificielle -- Périodiques; Systèmes experts (Informatique) -- Périodiques; Artificial intelligence; Engineering -- Data processing; Expert systems (Computer science); Periodicals; 620.00285
• DOI: 10.1016/j.engappai.2021.104412
• Languages: English
• ISSNs: 0952-1976

Abstract

Abstract: Based on historical records, driving in hazardous weather conditions is one of the most serious causes that lead to fatal accidents on roads in general and in United Arab Emirates (UAE) highways in particular. One solution for improving road safety is to equip the vehicles and infrastructure with connected and smart devices. Before deploying a concrete solution to the field, it must be validated by simulation, and more specifically agent-based simulation. Several key features are expected for the simulation framework, such as the reproduction of different and detailed behaviors for the components of the road infrastructure and for the drivers, simulate specific weather conditions and forecast their impacts on the global system behavior. Additionally, several technological features are related to recent advancements in agent software engineering and simulation. This paper proposes an agent-based model for the modeling and simulation of traffic in foggy weather conditions that covers the above features and technological requirements. The architecture is used and validated on two scenarios of traffic on UAE highways in foggy weather conditions. The first scenario does not include an intelligent transport system, and the second considers smart speed limit panels. From the experiments, the proposed model supports the expected key features, i.e., microscopic simulation of intelligent transport systems, including infrastructure and connected cars, and of different driving behaviors (human or autonomous car). Even if the included weather condition model is basic, a proof of concept is provided regarding the connection of an agent model and a weather condition model. Highlights: We define an architecture for agent-based simulation of intelligent transport system. We define the models for reproducing the driving behavior. We define the models for reproducing the behavior of connected devices in intelligent transport systems. We apply the proposed architecture models into two different simulation scenarios, and we compare the results. We discuss the advantages and disadvantages of the proposed architecture in regard to the related works.