The Robotics Institute

Carnegie Mellon Robotics Institute

Copyright notice: This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. These works may not be reposted without the explicit permission of the copyright holder.

Abstract

Real-time optimization of the dynamic ﬂow of vehicle traf-ﬁc through a network of signalized intersections is an im-portant practical problem. In this paper, we take a decentral-ized, schedule-driven coordination approach to address the challenge of achieving scalable network-wide optimization.To be locally effective, each intersection is controlled inde-pendently by an on-line scheduling agent. At each decision point, an agent constructs a schedule that optimizes move-ment of the observable trafﬁc through the intersection, and uses this schedule to determine the best control action to take over the current look-ahead horizon. Decentralized coordina-tion mechanisms, limited to interaction among direct neigh-bors to ensure scalability, are then layered on top of these asynchronously operating scheduling agents to promote over-all performance. As a basic protocol, each agent queries for newly planned output ﬂows from its upstream neighbors to obtain an optimistic projection of future demand. This projec-tion may incorporate non-local inﬂuence from indirect neigh-bors depending on horizon length. Two additional mecha-nisms are then introduced to dampen “nervousness” and dy-namic instability in the network, by adjusting locally deter-mined schedules to better align with those of neighbors. We present simulation results on two trafﬁc networks of tightly-coupled intersections that demonstrate the ability of our ap-proach to establish trafﬁc ﬂows with lower average vehicle wait times than both a simple isolated control strategy and other contemporary coordinated control strategies that use moving average forecast or traditional offset calculation.

Notes

Associated Center(s) / Consortia: Center for Integrated Manfacturing Decision Systems

Associated Lab(s) / Group(s): Intelligent Coordination and Logistics Laboratory

Associated Project(s): Adaptive Traffic Light Signalization

Text Reference

Xiao-Feng Xie, Stephen Smith , and Gregory Barlow, "Schedule-Driven Coordination for Real-Time Trafﬁc Network Control," Proceedings 22nd International Conference on Automated Planning and Scheduling, Atibaia, Sao Paulo, Brazil, June 2012., June, 2012.

BibTeX Reference

@inproceedings{Xie_2012_7044,
   author = "Xiao-Feng Xie and Stephen {Smith } and Gregory Barlow",
   title = "Schedule-Driven Coordination for Real-Time Trafﬁc Network Control",
   booktitle = "Proceedings 22nd International Conference on Automated Planning and Scheduling, Atibaia, Sao Paulo, Brazil, June 2012.",
   month = "June",
   year = "2012",
   number= "CMU-RI-TR-",
}

The Robotics Institute

Menu