Urban Evacuation

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 the state-of-the-art by proposing agent-based self-organizing algorithms for traffic network operations that considers current traffic conditions.
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.

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 performed.

Initial Network topology

Network after the Identification of Roads to be Reversed

Network after Planning for Safe Reversal

Network after Road Reversal is Applied

• 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