Blue phase: Optimal network traffic control for legacy and autonomous vehicles

• Published in: Transportation research. Part B: methodological Vol. 130; pp. 105 - 129
• Main Authors: Rey, David, Levin, Michael W.
• Format: Journal Article
• Language: English
• Published: Oxford Elsevier Ltd 01.12.2019; Elsevier Science Ltd
• Subjects: Autonomous vehicles; Communications traffic; Market penetration; Materials handling; Network control; Phases; Stochasticity; Traffic congestion; Traffic control; Traffic intersections; Traffic signals; Travel; Travel demand; Travel time; Vehicles
• ISSN: 0191-2615; 1879-2367
• DOI: 10.1016/j.trb.2019.11.001

•We propose a new, max-pressure based network traffic control policy for legacy and autonomous vehicles.•We introduce an autonomous vehicle-restricted phase, named the blue phase, to coordinate autonomous vehicles at network intersections.•We formulate a green signal phase model wherein movement capacities are endogenous to the choice of the activation matrix and lane FIFO blocking effects are accounted for.•We show that the proposed hybrid network traffic control policy is stable, i.e. maximizes throughout.•Our numerical experiments reveal considerable trade-offs in terms of vehicle-class travel time based on the level of congestion and the proportion of autonomous vehicles in the network. With the forecasted emergence of autonomous vehicles in urban traffic networks, new control policies are needed to leverage their potential for reducing congestion. While several efforts have studied the fully autonomous traffic control problem, there is a lack of models addressing the more imminent transitional stage wherein legacy and autonomous vehicles share the urban infrastructure. We address this gap by introducing a new policy for stochastic network traffic control involving both classes of vehicles. We conjecture that network links will have dedicated lanes for autonomous vehicles which provide access to traffic intersections and combine traditional green signal phases with autonomous vehicle-restricted signal phases named blue phases. We propose a new pressure-based, decentralized, hybrid network control policy that activates selected movements at intersections based on the solution of mixed-integer linear programs. We prove that the proposed policy is stable, i.e. maximizes network throughput, under conventional travel demand conditions. We conduct numerical experiments to test the proposed policy under varying proportions of autonomous vehicles. Our experiments reveal that considerable trade-offs exist in terms of vehicle-class travel time based on the level of market penetration of autonomous vehicles. Further, we find that the proposed hybrid network control policy improves on traditional green phase traffic signal control for high levels of congestion, thus helping in quantifying the potential benefits of autonomous vehicles in urban networks.