Overview 1
Congestion Reduction 2
Urban Traffic Evacuation 3
Related Publications 4
Demos 5

Our research group has proposed an agent based-model for Intelligent Transportation Systems that we call Agent-ITS or ATS. ATS is based on the following premises:

  1. The traffic physical space is partitioned into areas called zones which are managed by specialized agents called zone managers. A zone manager is responsible for a) gathering and analyzing traffic data from its zone and extracting useful traffic information, b) informing vehicle and traffic devices of the current traffic condition, c) notifying other managers of changes that may affect their zones, and d) identifying appropriate global traffic management strategies to ensure that micro-level behaviors and interactions are consistent with the global system behavior.
  2. Context-Aware Intelligent (CAI) vehicles are equipped with agent-based systems and sensors that allow them to a) monitor the driver’s behavior, b) communicate with other vehicles, c) communicate with smart traffic control devices, and 4) interact with zone managers to obtain traffic information and guidance in real time.
  3. Novel digital traffic devices controlled by a traffic control agent which determines the traffic sign to be displayed based on traffic conditions.

Through the development of advanced traffic management algorithms for various configurations of ATS, our research has shown that decentralized, coordinated solutions improve on the state-or-the-art technologies for traffic reduction and urban evacuations.

The purpose of this project is to define multi-agent cooperative algorithms for coordinated traffic systems. Intersection controllers are equipped with agents, i.e., autonomous software systems which are capable of communicating and cooperating with one another to achieve an individual or global goal. Our approach is based on real-world traffic parameters and constraints, and is meant to be implemented in existing traffic systems with minimal changes. By default, agents execute a standard timing strategy. At the same time, they observe and analyze traffic at their intersections. At any given time, if an agent determines that its intersection is congested, it deliberates and defines a timing plan to alleviate congestion. The plan is then “discussed” with other intersection controllers agents and a final action plan is executed.

Experimental results on a traffic network consisting of 384 road segments, 133 nodes and 40 signalized intersections show that our agent-based approach outperforms the traditional pre-timed and actuated modes when traffic is heavy.

The purpose of this project is to define and evaluate traffic re-organization algorithms in the context of ATS.

Traffic re-organization refers to the modification of the traffic network topology to better utilize an existing network capacity. This is commonly achieved by applying a combination of road reversal and crossing elimination operations. In the transportation field, various models have been defined in the context of urban evacuation. These models are based on the definition of a traffic strategy then its execution. The main drawback of these models is that they do not account for the dynamic nature of real-world traffic networks.

Our research improves on the state-of-the-art by proposing agent-based self-organizing algorithms for traffic network operations that take into consideration current traffic conditions.

The traffic manager executes a three-step plan to re-organize the traffic environment in  an effort to maximize the evacuation effort. Based on the information exchanged with the intersection controller agents, the traffic manager determines the next set of roads to be reversed. Before reversing the directions, it is necessary to empty roads from traffic and prevent new traffic from entering. This responsibility is delegated to intersection controller agents who adapt their traffic control strategies to minimize the time required to clear the roads marked for reversal. Once the roads are empty from traffic, road reversal operations are applied.

Initial Network topology

Network after the Identification of Roads to be Reversed

Network after Planning for Safe Reversal

Network after Road Reversal is Applied

  • Behnam Torabi, Rym Wenkstern, and Robert Saylor. Agent-based decentralized traffic signal timing. In Proceedings of the 21th IEEE/ACM International Symposium on Distributed Simulation and Real Time Applications, DS-RT 17, October 2017.
  • Mohammad Al-Zinati and Rym Wenkstern. An agent-based self-organizing traffic environment for urban evacuations. In Proceedings of the The Sixteenth International Conference on Autonomous Agent and Multiagent Systems, AAMAS ‘2017, May 2017.
  • Mohammad Al-Zinati and Rym Wenkstern. Simulation of traffic network re-organization operations. In Proceedings of the 20th IEEE/ACM International Symposium on Distributed Simulation and Real Time Applications, DS-RT 16, pages 178-186, September 2016. 
  • Mohammad Al-Zinati and Rym Wenkstern. Matisse 2.0: a large-scale multi-agent simulation system for agent-based its. In Proceedings of the 2015 ieee/wiciacm international conference on intelligent agent technology, lAT’ 15, pages 328-335, December 2015.
  • Mohammad Al-Zinati and Rym Wenkstern. A self-organizing virtual environment for agent-based simulations. In Proceedings of the 2015 international conference on autonomous agents and multiagent systems, AAMAS ’15, pages 1031-1039, May 2015.

More publications available here


Traffic congestion reduction in the West End District of the City of Dallas, Texas


Urban Evacuation with Network Re-Organization Operations