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:
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.
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.
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.
Our approach to congestion reduction is based on multi-agent collaborative algorithmsfor 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.
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.
Execution of a DALI agent
Behnam Torabi, Rym Z. Wenkstern, and Robert Saylor. A Self-Adaptive Collaborative Multi-Agent based Traffic Signal Timing System. In Proceedings of the 4th IEEE International Smart Cities Conference, ISC2 2018, Kansas City, Missouri, USA, September 2018.
Behnam Torabi, Rym Z. Wenkstern, and Robert Saylor. A Collaborative Agent-Based Traffic Signal System For Highly Dynamic Traffic Conditions. In Proceedings of the 21st IEEE International Conference on Intelligent Transportation Systems, IEEEITSC 2018, Maui, Hawaii, USA, November 2018.
Behnam Torabi, Rym Z. Wenkstern, and Robert Saylor. A Multi-Hop Agent-Based Traffic Signal Timing System for the City of Richardson. In Proceedings of the 16th International Conference on Autonomous Agent and Multiagent Systems, AAMAS 2018, page 2094–2096, Stockholm, Sweden, July 2018.
Behnam Torabi, Rym Z. Wenkstern, and Robert Saylor. Agent-based decentralized traffic signal timing. In Proceedings of the 21st International Symposium on Distributed Simulation and Real Time Applications, DS-RT 17, page 123–126, Rome, Italy, October 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.