Decentralized Traffic Management: A Synchronization-Based Intersection Control

Mohamed Tlig 1 Olivier Buffet 1 Olivier Simonin 2
1 MAIA - Autonomous intelligent machine
Inria Nancy - Grand Est, LORIA - AIS - Department of Complex Systems, Artificial Intelligence & Robotics
2 DYNAMID - Dynamic Software and Distributed Systems
CITI - CITI Centre of Innovation in Telecommunications and Integration of services
Abstract : Controlling the vehicle traffic in large networks remains an important challenge in urban environments and transportation systems. Autonomous vehicles are today considered as a promising approach to deal with traffic control. In this paper, we propose a synchronization-based intersection control mechanism to allow the autonomous vehicle-agents to cross without stopping, i.e., in order to avoid congestions (delays) and energy loss. We decentralize the problem by managing the traffic of each intersection independently from others. We define control agents which are able to synchronize the multiple flows of vehicles in each intersection, by alternating vehicles from both directions. We present experimental results in simulation, which allow to evaluate the approach and to compare it with a traffic light strategy. These results show the important gain in terms of time and energy at an intersection and in a network.
Document type :
Conference papers
Complete list of metadatas

Cited literature [9 references]  Display  Hide  Download

https://hal.inria.fr/hal-00966575
Contributor : Mohamed Tlig <>
Submitted on : Thursday, June 26, 2014 - 7:00:04 AM
Last modification on : Tuesday, November 19, 2019 - 10:25:00 AM
Long-term archiving on : Friday, September 26, 2014 - 10:36:35 AM

File

article.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-00966575, version 1

Citation

Mohamed Tlig, Olivier Buffet, Olivier Simonin. Decentralized Traffic Management: A Synchronization-Based Intersection Control. International Conference on Advanced Logistics and Transport, May 2014, Hammamet, Tunisia. ⟨hal-00966575⟩

Share

Metrics

Record views

815

Files downloads

279