Search

Strategic traffic management is crucial for combating traffic congestion at the macroscopic level. However, such a field is still relatively unexplored, particularly for microscopic control objects, such as intersections and coordinated intersection groups. This article proposes a human-in-the-loop recommendation system for strategic urban traffic management, which follows an agent-based structure. A regional agent dispatcher is defined to assign agents for operation whenever “operation on-demand” is required. Such a requirement is identified by a daily-dependent operational mode on strategic traffic operations at a control object level. The strategic management scheme for each control object is guided by a strategic agent (customized), which is essentially a deep recommender model with a specific architecture. By featuring the multiagent design, a customized operational scheme can be generated at the intersection level, which instructs the corresponding controller to take specific operations. The utility of the recommendation system is demonstrated via a case study using real-world traffic data. In both offline and online evaluations, the system performs consistently at traffic operational recommendations in different scenarios and has the potential to provide more reasonable traffic operational strategies than a human-operated system. [ABSTRACT FROM AUTHOR]

Traffic congestion alleviation around intersections has been a growing challenge, and a competent traffic signal control scheme plays a pivotal role in intelligent transportation systems. Recent studies using deep reinforcement learning techniques have shown promising results for traffic signal control, but they only focus on extracting features from traffic conditions of isolated or adjacent intersections. In this work, we employed navigation information for traffic signal control, greatly enriching the features for traffic signal control with deep reinforcement learning. In addition, we are the first to propose a novel scheme DeepNavi to exploit the temporal-spatial relations from numerous navigation routes and extract dynamic real-time and future traffic features. We tested our scheme on a challenging real-world traffic dataset with 16 intersections in a residential district of Hangzhou, China. Extensive experiments were conducted and the results demonstrated that our DeepNavi scheme achieves superior performance over five popular and state-of-the-art baseline methods on different metrics, including queue length, speed, travel time and accumulative waiting time. In addition, with our method, vehicles suffer the least red lights and enjoy the most green waves, which further validates that our scheme greatly relieves the congestion and provides excellent experience for drivers. Simulations with different penetration levels of navigation routes showed that even with only part of navigation routes available in the traffic network, our scheme can obtain superior performance, further demonstrating the effectiveness and feasibility of DeepNavi. [ABSTRACT FROM AUTHOR]

Intelligent traffic light control is one of the modern approaches to solve traffic congestion, where reinforcement learning is a widely used method. Conventionally, reinforcement learning is used to determine whether to change the current phase (or choose a traffic phase) after each small interval. One major drawback of these approaches is that it makes the current traffic light phase duration uncertain before the current phase terminates. Directly determining the duration of the traffic light phase can effectively avoid this shortcoming. An adaptive traffic light timing system is proposed in this paper which can directly control the phase duration. In the proposed system, the Q-learning algorithm is employed and the action space is defined as all possible phase durations. In addition, the reward function is redefined to guide the agent to balance more traffic metrics, and the state is redefined to reduce the state space. Finally, the proposed system is evaluated by equal, unequal, and complex traffic scenarios. Results show that the proposed system has a better performance compared with other methods in controlling traffic lights, even on complex traffic scenarios. [ABSTRACT FROM AUTHOR]

Improving the efficiency of traffic signal control is an effective way to alleviate traffic congestion at signalized intersections. To achieve effective management of the system-wide traffic flows, current research tends to focus on applying reinforcement learning (RL) techniques for collaborative traffic signal control in a traffic road network. However, the existing collaboration-based methods often ignore the impact of transmission delay for exchanging traffic flow information on the system. Most of the studies assume that the signal controllers can collect all instantaneous vehicular features without delay. To fill the gap, we propose an RL-based cooperative traffic signal control scheme considering the data transmission delay issue in a traffic road network. In this paper, we (1) design our new RL agents to cooperatively control the traffic signals by improving the reward and state representation based on the state-of-the-art max-pressure control theory; (2) propose a traffic state prediction method to address the data transmission delay issue by decreasing the discrepancy between the real-time and delayed traffic conditions; (3) evaluated the performance of our proposed work on both synthetic and real-world scenarios with a different range of data transmission delays. The results demonstrate that our method surpassed the performance of the previous max-pressure-based traffic signal control methods and addressed the data transmission delay issue. [ABSTRACT FROM AUTHOR]

In the era of internet of vehicles, both the traffic signal control and the rerouting of connected and autonomous vehicles (CAVs) are essential techniques to alleviate traffic congestion and improve traffic efficiency. However, these two schemes have been treated separately without a unified framework allowing for joint optimization in the previous studies. In the case of traffic congestion at the bottleneck intersections, either of the two schemes alone is not enough. To this end, we propose to jointly control the traffic lights and the CAVs under the reinforcement learning (RL) framework. To lower the dimensionality of this learning problem, we propose to control the route choices of the CAVs through a few common scalar parameters instead of controlling the CAVs individually. In particular, the rerouting ratios are dynamically adjusted. A model-based method is further proposed to estimate the expected travel time with reduced estimation error. We then exploit the tools from deep RL and put forth an efficient algorithm that is able to control the green time allocation of traffic signals and the rerouting of CAVs jointly. Comprehensive numerical experiments demonstrate the validity of our proposed models and show the traffic efficiency can be significantly improved with our proposed algorithm. [ABSTRACT FROM AUTHOR]

As urban traffic condition is diverse and complicated, applying reinforcement learning to reduce traffic congestion becomes one of the hot and promising topics. Especially, how to coordinate the traffic light controllers of multiple intersections is a key challenge for multi-agent reinforcement learning (MARL). Most existing MARL studies are based on traditional $Q$ -learning, but unstable environment leads to poor learning in the complicated and dynamic traffic scenarios. In this paper, we propose a novel multi-agent recurrent deep deterministic policy gradient (MARDDPG) algorithm based on deep deterministic policy gradient (DDPG) algorithm for traffic light control (TLC) in vehiclar networks. Specifically, the centralized learning in each critic network enables each agent to estimate the policies of other agents in the decision-making process and each agent can coordinate with each other, alleviating the problem of poor learning performance caused by environmental instability. The decentralized execution enables each agent to make decisions independently. We share parameters in actor networks to speed up the training process and reduce the memory footprint. The addition of LSTM is beneficial to alleviate the instability of the environment caused by partial observable state. We utilize surveillance cameras and vehicular networks to collect status information for each intersection. Unlike previous work, we have not only considered the vehicle but also considered the pedestrians waiting to pass through the intersection. Moreover, we also set different priorities for buses and ordinary vehicles. The experimental results in a vehicular network show that our method can run stably in various scenarios and coordinate multiple intersections, which significantly reduces vehicle congestion and pedestrian congestion. [ABSTRACT FROM AUTHOR]

Potential adversary and maliciously-behaved vehicles may cause traffic chaos or even lead to traffic accidents (particularly on traffic congestion crossroads). To address this issue, a novel security scheme is proposed for facilitating an efficient vehicular communication by employing a quantum secret sharing method. In the proposed scheme, the traffic control information is broadcasted regularly and shared among vehicles to reduce traffic congestion, and thus avoiding traffic accidents. Finally, we also demonstrate the superiority performance of our proposed scheme through theoretical and numerical simulation analysis. [ABSTRACT FROM AUTHOR]

Urban freeway traffic control is of great importance for traffic management and intelligent transportation systems. Various approaches have been proposed to relieve urban freeway traffic jam, among which, ALINEA, a ramp metering strategy, is commonly implemented with fixed triggering threshold and static controller parameter. However, such a strategy may not be able to effectively alleviate the traffic congestion while maintaining certain ramp throughput due to two reasons: i). the congestion threshold can be time-varying due to different factors, such as segment ID, weather condition, time, and etc. ii). The congestion evolution patterns are time-varying even for the same segment. In this paper, based on over 890 million records of vehicles collected on ramps in Hangzhou, China, we established dynamic congestion threshold for each road segment with external factors. Based on such dynamic congestion threshold, we further clustered the congestion evolution patterns, and designed adaptive ramp controller which could switch the controller parameter according to the predicted congestion evolution pattern. Finally, in order to show the performance among different strategies, we introduced three baseline groups, which are ‘without Controller’, ‘ALINEA controller’, and ‘Direct RBF(radial basis function)-neural network controller’, respectively.The evaluation of proposed controller design over real large-scale data indicated that our method achieves 8.4%(7.2%), 4.62%(9.48%) efficiency improvement in terms of average speed in km/h (average traffic flow in veh/h) than the performance with normal ALINEA controller and RBF-neural network controller respectively. [ABSTRACT FROM AUTHOR]

Major international automakers have considered the deployment of the 5.9 GHz dedicated short-range communications (DSRC) on their vehicle fleets for wireless connectivity. DSRC-enabled vehicle-to-vehicle (V2V) communication through broadcast of basic safety messages enables safety applications for crash warning and avoidance. However, in dense traffic conditions as the V2V deployment scales up, the resultant channel load increases and leads to channel congestion and may adversely affect the performance of the safety applications. The Society of Automotive Engineers J2945/1 standard that builds atop Institute of Electrical and Electronics Engineers (IEEE) 802.11p and IEEE 1609 standards provides the minimum performance requirements for V2V safety communications. Specifically, it provides a congestion control protocol for transmission rate and power adaptations to achieve robust performance in dense vehicular networks. The primary contribution of this paper is that using a congestion generation testbed that emulates channel congestion including a large number of remote vehicles, we can validate and test any V2V equipped vehicle for compliance with the J2945/1 standard. Our paper also demonstrates that under heavy congestion, even with 600 ms of inter-transmit time, a moving vehicle can be tracked to a lane-level accuracy. [ABSTRACT FROM AUTHOR]

The urban road networks undergo frequent traffic congestions during the peak hours and around the city center. Capturing the spatiotemporal evolution of the congestion scenario in real-time in an urban-scale can aid in developing smart traffic management systems, and guiding commuters in making informed decision about route choice. The congestion scenario is often represented by a set of distinguishable network partitions that have a homogeneous level of congestion inside them but are heterogeneous to others. Due to the dynamic nature of traffic, these partitions evolve with time in terms of their structure and location. In this paper, we propose a comprehensive framework to capture the evolution by incrementally updating the partitions in an efficient manner using a two-layer approach. The physical layer maintains a set of small-sized road network building blocks in a fine granularity, and performs low-level computations to incrementally update them, whereas the logical layer performs high-level computations in order to serve as an interface to query the physical layer about the congested partitions in a coarse granularity. We also propose an in-memory index called Bin that compactly stores the historical sets of building blocks in the main memory with no information loss, and facilitates their efficient retrieval. Our experimental results show that the proposed method is much efficient than the existing re-partitioning methods without significant sacrifice in accuracy. The proposed Bin consumes a minimum space with least redundancy at different time stamps. [ABSTRACT FROM AUTHOR]

This paper proposes a self-adaptive interactive navigation tool (SAINT), which is tailored for cloud-based vehicular traffic optimization in road networks. The legacy navigation systems make vehicles navigate toward their destination less effectively with individually optimal navigation paths rather than network-wide optimal navigation paths, particularly during rush hours. To the best of our knowledge, SAINT is the first attempt to investigate a self-adaptive interactive navigation approach through the interaction between vehicles and vehicular cloud. The vehicles report their navigation experiences and travel paths to the vehicular cloud so that the vehicular cloud can know real-time road traffic conditions and vehicle trajectories for better navigation guidance for other vehicles. With these traffic conditions and vehicle trajectories, the vehicular cloud uses a mathematical model to calculate road segment congestion estimation for global traffic optimization. This model provides each vehicle with a navigation path that has minimum traffic congestion in the target road network. Using the simulation with a realistic road network, it is shown that our SAINT outperforms the legacy navigation scheme, which is based on Dijkstra's algorithm with a real-time road traffic snapshot. On a road map of Manhattan in New York City, our SAINT can significantly reduce the travel delay during rush hours by 19%. [ABSTRACT FROM PUBLISHER]

Vehicular ad hoc networks (VANETs) allow vehicles to generate and broadcast messages to inform nearby vehicles about road conditions, such as traffic congestion and accidents. Neighboring vehicles can utilize this information, which may improve road safety and traffic efficiency. However, messages generated by vehicles may not be reliable. We propose a novel announcement scheme for VANETs based on a reputation system that allows evaluation of message reliability. We present a secure and efficient scheme that is robust and fault tolerant against temporary unavailability of the central server. [ABSTRACT FROM PUBLISHER]

Adaptive control of traffic lights is a key component of any intelligent transportation system. Many real-time traffic light control (TLC) algorithms are based on graded thresholds, because precise information about the traffic congestion in the road network is hard to obtain in practice. For example, using thresholds L1 and L2, we could mark the congestion level on a particular lane as “low,” “medium,” or “high” based on whether the queue length on the lane is below L1, between L1 and L2, or above L2, respectively. However, the TLC algorithms that were proposed in the literature incorporate fixed values for the thresholds, which, in general, are not optimal for all traffic conditions. In this paper, we present an algorithm based on stochastic optimization to tune the thresholds that are associated with a TLC algorithm for optimal performance. We also propose the following three novel TLC algorithms: 1) a full-state Q-learning algorithm with state aggregation, 2) a Q-learning algorithm with function approximation that involves an enhanced feature selection scheme, and 3) a priority-based TLC scheme. All these algorithms are threshold based. Next, we combine the threshold-tuning algorithm with the three aforementioned algorithms. Such a combination results in several interesting consequences. For example, in the case of Q-learning with full-state representation, our threshold-tuning algorithm suggests an optimal way of clustering states to reduce the cardinality of the state space, and in the case of the Q-learning algorithm with function approximation, our (threshold-tuning) algorithm provides a novel feature adaptation scheme to obtain an “optimal” selection of features. Our tuning algorithm is an incremental-update online scheme with proven convergence to the optimal values of thresholds. Moreover, the additional computational effort that is required because of the integration of the tuning scheme in any of the graded-threshold-based TLC algorithms is minimal. Simulation results show a significant gain in performance when our threshold-tuning algorithm is used in conjunction with various TLC algorithms compared to the original TLC algorithms without tuning and with fixed thresholds. [ABSTRACT FROM PUBLISHER]

A transition from free flow to congested traffic on highways often spontaneously originates, despite the fact that the road could satisfy a higher traffic demand. The reasons for such a traffic breakdown are perturbations caused by human drivers in dense traffic. We present a strategy to reduce traffic congestion with the help of vehicle-to-vehicle communication. Periodically emitted beacons are used to analyze traffic flow and to warn other drivers of a possible traffic breakdown. Drivers who receive such a warning are told to keep a larger gap to their predecessor. By doing so, they are less likely to be the source of perturbations, which can cause a traffic breakdown. We analyze the proposed strategy via computer simulations and investigate which fraction of communicating vehicles is necessary until a beneficial influence on traffic flow is observable. We show that penetration rates of 10\% and less can have significant influence on traffic flow and travel times. In addition to applying a realistic mobility model, we further increase the degree of realism by the use of empirical traffic data from loop detectors on a German Autobahn. [ABSTRACT FROM PUBLISHER]

While vehicular congestion is very often defined in terms of aggregate parameters, such as traffic volume and lane occupancies, based on recent findings, the interpretation that receives most credit is that of a state of a road where traversing vehicles experience a delay exceeding the maximum value typically incurred under light or free-flow traffic conditions. We here propose a new definition according to which a road is in a congested state (be it high or low) only when the likelihood of finding it in the same congested state is high in the near future. Based on this new definition, we devised an algorithm that, exploiting probe vehicles, for any given road 1) identifies if it is congested or not and 2) provides the estimation that a current congested state will last for at least a given time interval. Unlike any other existing approach, an important advantage of ours is that it can generally be applied to any type of road, as it neither needs any a priori knowledge nor requires the estimation of any road parameter (e.g., number of lanes, traffic light cycle, etc.). Further, it allows performing short-term traffic congestion forecasting for any given road. We present several field trials gathered on different urban roads whose empirical results confirm the validity of our approach. [ABSTRACT FROM PUBLISHER]

Vehicle density is one of the main metrics used for assessing road traffic condition. High vehicle density indicates that traffic is congested. Currently, most vehicle density estimation approaches are designed for infrastructure-based traffic information systems. These approaches require detection devices such as inductive loop detectors or traffic surveillance cameras to be installed at various locations. Consequently, they are not appropriate for an emerging self-organizing vehicular traffic information system, where vehicles have to collect and process traffic information without relying on any fixed infrastructure. In this paper, we consider a few methods for estimating vehicle density based on the number of vehicles in the vicinity of the probe vehicle and the number of vehicles in a communication cluster. [ABSTRACT FROM PUBLISHER]

Traffic systems are often highly populated discrete event systems that exhibit several modes of behavior such as free flow traffic, traffic jams, stop-and-go waves, etc. An appropriate closed loop control of the congested system is crucial in order to avoid undesirable behavior. This paper proposes a macroscopic model based on continuous Petri nets as a tool for designing control laws that improve the behavior of traffic systems. The main reason to use a continuous model is to avoid the state explosion problem inherent to large discrete event systems. The obtained model captures the different operation modes of a traffic system and is highly compositional. In order to handle the variability of the traffic conditions, a model predictive control strategy is proposed and validated. [ABSTRACT FROM AUTHOR]

In this paper, we investigate the problem of multipath traffic engineering in optical burst switching (OBS) networks. The main goal of this work is to minimize burst loss rate in the network by adaptively balancing the burst traffic among multiple paths based on the measurement and analysis of path congestion. We develop three distributed traffic splitting algorithms by considering the special features of OBS networks. Among these three algorithms, one algorithm considers burst level traffic distribution, and the other two algorithms consider flow level traffic distribution to avoid packet reordering problem. The proposed multipath traffic engineering algorithms achieve significant performance improvement in reducing burst loss probability in a distributed manner in OBS networks. Further, through theoretical analysis and simulations, we show that the proposed algorithms converge quickly on a sudden traffic increase in the network. [ABSTRACT FROM AUTHOR]

The authors consider the problem of scheduling automated traffic in a city. Such automatic scheduling can improve efficiency of the system by decreasing delays, increasing capacity, and easing congestion. The algorithms described in this paper can be thought of as which belongs to a layer in the corresponding control-communication-computational system, which is responsible for generating timed trajectories for individual vehicles [S. Graham, G. Baliga, and P. Kumar, ‘Issues in the convergence of control with communication and computing: Proliferation, architecture, design, services, and middleware,’ in Proceedings of CDC '04, Nassau, Bahamas, December 2004]. Each vehicle has a specified route from its origin to its destination, and the task of the scheduler is to provide timed trajectories for all vehicles, which follow the respective vehicles' routes and further ensure that no collisions or deadlock will result. The authors' approach reduces the problem to a discrete-time graph-scheduling problem, by defining an appropriate graph to model the road network. Their main result is a sufficient condition on the graph of the road network and on the initial distribution of vehicles, under which there exists a scheduling algorithm that is guaranteed to clear the system in finite time. The nature of this result allows the design of provably correct scheduling algorithms that require only a small portion of future routes of all vehicles to be known, and are consequently able to work in real time. The authors also address the optimization of performance with respect to delay, by focusing on the ‘one-step move’ problem. Finding an optimal solution for the one-step problem would provide a greedy solution of the original network-wide scheduling problem, but is itself NP-hard. They present a polynomial time heuristic algorithm and evaluate its performance through simulations. [ABSTRACT FROM AUTHOR]

An adaptive multiagent reinforcement learning method for solving congestion control problems on dynamic high-speed networks is presented. Traditional reactive congestion control selects a source rate in terms of the queue length restricted to a predefined threshold. However, the determination of congestion threshold and sending rate is difficult and inaccurate due to the propagation delay and the dynamic nature of the networks. A simple and robust cooperative multiagent congestion controller (CMCC), which consists of two subsystems: a long-term policy evaluator, expectation-return predictor and a short-term rate selector composed of action-value evaluator and stochastic action selector elements has been proposed to solve the problem. After receiving cooperative reinforcement signals generated by a cooperative fuzzy reward evaluator using game theory, CMCC takes the best action to regulate source flow with the features of high throughput and low packet loss rate. By means of learning procedures, CMCC can learn to take correct actions adaptively under time-varying environments. Simulation results showed that the proposed approach can promote the system utilization and decrease packet losses simultaneously. [ABSTRACT FROM AUTHOR]

Handling traffic dynamics in order to avoid network congestion and subsequent service disruptions is one of the key tasks performed by contemporary network management systems. Given the simple but rigid routing and forwarding functionalities in IP base environments, efficient resource management and control solutions against dynamic traffic conditions is still yet to be obtained. In this article, we introduce AMPLE - an efficient traffic engineering and management system that performs adaptive traffic control by using multiple virtualized routing topologies. The proposed system consists of two complementary components: offline link weight optimization that takes as input the physical network topology and tries to produce maximum routing path diversity across multiple virtual routing topologies for long term operation through the optimized setting of link weights. Based on these diverse paths, adaptive traffic control performs intelligent traffic splitting across individual routing topologies in reaction to the monitored network dynamics at short timescale. According to our evaluation with real network topologies and traffic traces, the proposed system is able to cope almost optimally with unpredicted traffic dynamics and, as such, it constitutes a new proposal for achieving better quality of service and overall network performance in IP networks. [ABSTRACT FROM AUTHOR]

Traffic congestion in urban areas is an acute problem which is getting worse with the increased urbanization of the world population. The existing approaches to increasing traffic flow in urban areas have proven inefficient as they are expensive and therefore not scalable. It is shown in this article that a biologically inspired new approach could solve some of the fundamental transportation problems via a self-organizing traffic management paradigm. [ABSTRACT FROM PUBLISHER]