The vehicle routing problem

In this paper, we propose a set of algorithms to design signal timing plans via deep reinforcement learning. The core idea of this approach is to set up a deep neural network (DNN) to learn the Q-function of reinforcement learning from the sampled traffic state/control inputs and the corresponding traffic system performance output. Based on the obtained DNN, we can find the appropriate signal timing policies by implicitly modeling the control actions and the change of system states. We explain the possible benefits and implementation tricks of this new approach. The relationships between this new approach and some existing approaches are also carefully discussed.

Traffic signal timing via deep reinforcement learning

Signalized intersections play an important role in transportation efficiency and vehicle fuel economy in urban areas. This paper proposes a cooperative method of traffic signal control and vehicle speed optimization for connected automated vehicles, which optimizes the traffic signal timing and vehicles’ speed trajectories at the same time. The method consists of two levels, i.e., roadside traffic signal optimization and onboard vehicle speed control. The former calculates the optimal traffic signal timing and vehicles’ arrival time to minimize the total travel time of all vehicles; the latter optimizes the engine power and brake force to minimize the fuel consumption of individual vehicles. The enumeration method and the pseudospectral method are applied in roadside and onboard optimization, respectively. Simulation studies are conducted to compare the proposed method with benchmark methods. The results show significant improvement of transportation efficiency and fuel economy by the cooperation method.

Cooperative Method of Traffic Signal Optimization and Speed Control of Connected Vehicles at Isolated Intersections

Vehicle headway distribution models are widely used in traffic engineering fields, since they reflect the fundamental uncertainty in drivers' car-following maneuvers and meanwhile provide a concise way to describe the stochastic feature of traffic flows. This paper presents a systematic review of vehicle headway distribution studies in the last few decades. Since it is impossible to enumerate the merits and drawbacks of all of existing distribution models, we emphasize four advances of headway distribution modeling in this paper. First, we highlight the chronicle of key assumptions on the existing distribution models and explain why this evolution occurs. Second, we show that departure headways measured for interrupted flows on urban streets and headways measured for uninterrupted flows on freeways have common features and can be simulated by a unified microscopic car-following model. The interesting finding helps gather two kinds of headway distribution models under one umbrella. Third, we review different approaches that aim to link microscopic car-following models and mesoscopic vehicle headway distribution models. Fourth, we show that both the point scattering on the density-flow plot and the shape of traffic flow breakdown curve implicitly depend on the vehicular headway distribution. These findings reveal pervasive connections between macroscopic traffic flow models and mesoscopic headway distribution. All these new insights bring new vigor into vehicle headway studies and open research frontiers in this field.

Vehicle headway modeling and its inferences in macroscopic/microscopic traffic flow theory: A survey

During peak hours in urban areas, unpredictable traffic congestion caused by en route events (e.g., vehicle crashes) increases drivers' travel time and, more seriously, decreases their travel time reliability. In this paper, an original and highly practical vehicle rerouting system, which is called Next Road Rerouting (NRR), is proposed to aid drivers in making the most appropriate next road choice to avoid unexpected congestions. In particular, this heuristic rerouting decision is made upon a cost function that takes into account the driver's destination and local traffic conditions. In addition, the newly designed multiagent system architecture of NRR allows the positive rerouting impacts on local traffic to be disseminated to a larger area through the natural traffic flow propagation within connected local areas. The simulation results based on both synthetic and realistic urban scenarios demonstrate that, compared with the existing solutions, NRR can achieve a lower average travel time while guaranteeing a higher travel time reliability in the face of unexpected congestion. The impacts of NRR on the travel time of both rerouted and nonrerouted vehicles are also assessed, and the corresponding results reveal its higher practicability.

/pdf/next-road-rerouting-a-multiagent-system-for-mitigating-jor9am8ueu.pdf

Next Road Rerouting: A Multiagent System for Mitigating Unexpected Urban Traffic Congestion

In this paper, we present an adaptive signal control scheme to prevent intersection traffic blockage resulted from vehicle queue spillover. A method to identify vehicle queue spillover condition through simplified shockwave analysis is developed. Instead of measuring the vehicle queue length or locating the end of queue directly, this method relies on the vehicle speed which is more feasible to measure in practice. The adaptive traffic signal control scheme is designed to prevent potential intersection traffic blockage, and adaptively allocates green time to appropriate signal phases. At the end, a simulation study is carried out to evaluate the proposed adaptive control scheme. The results show that the scheme can effectively prevent intersection traffic blockage and significantly improve the performance of the intersection in terms of vehicle delay.

An Adaptive Signal Control Scheme to Prevent Intersection Traffic Blockage

We formulate a joint dynamical traffic system that encompasses both route choice and traffic control in which the signal controller interacts with and adapts to the route choices of travelers, and vice versa. Travelers’ route choice dynamics are captured by a recurrence function, which governs the system evolution from day to day. Traffic control also adjusts its plan from day to day in response to the route choices of travelers. We show that this joint dynamical system has a set of fixed points in which both the user equilibrium is achieved and the traffic signal converges to a fixed-time plan. We address equilibrium stability and convergence of this joint dynamical system through analyzing the Jacobian matrix associated with each fixed point. We demonstrate the attraction domains of this joint problem and illustrate their importance and relevance for designing adaptive traffic control through some numerical examples.

Combined Route Choice and Adaptive Traffic Control in a Day-to-day Dynamical System

This paper develops an adaptive approach for vehicle navigation in a stochastic network with real-time en route traffic information. This stochastic and adaptive approach is formulated as a probabilistic dynamic programming problem and is solved through a backward recursive procedure. The formulation, as a modeling framework, is designed to be able to incorporate various sources of information and real-time traffic states to improve routing quality. In this paper, the authors prove that the approach outperforms deterministic instantaneous shortest paths in a statistical sense. They also analyze the algorithm's computational efficiency. The results from numerical examples are included to illustrate the performance of the adaptive routing policy that was generated by the formulation.

Adaptive Vehicle Navigation With En Route Stochastic Traffic Information

A joint control model for connected vehicle platoon and arterial signal coordination

This paper develops an adaptive navigation approach for risk-averse travelers in a stochastic network while considering on-time arrival reliability, in which travelers’ final utility is measured with the prospect theory. Instead of finding a route or a policy that simply minimizes the expected travel time or maximizes the on-time arrival reliability, this model optimizes the expected prospect of potential routing alternatives while ensuring that both the expected en route travel time and resultant on-time arrival reliability are acceptable to the traveler. Moreover, the formulation is designed to incorporate various sources of information and real time traffic states in an adaptive routing framework, offering flexibility to incorporate different information types deemed useful in future extensions.

Lin Xiao

Papers

An Adaptive Signal Control Scheme to Prevent Intersection Traffic Blockage

Combined Route Choice and Adaptive Traffic Control in a Day-to-day Dynamical System

Adaptive Vehicle Navigation With En Route Stochastic Traffic Information

A joint control model for connected vehicle platoon and arterial signal coordination

Adaptive Vehicle Routing for Risk-averse Travelers☆