Search

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]

In recent years, the growing development of Connected Autonomous Vehicles (CAV), Intelligent Transport Systems (ITS), and 5G communication networks have led to the advent of Autonomous Intersection Management (AIM) systems. AIMs present a new paradigm for CAV control in future cities, taking control of CAVs in scenarios where cooperation is necessary and allowing safe and efficient traffic flows, eliminating traffic signals. So far, the development of AIM algorithms has been based on basic control algorithms, without the ability to adapt or keep learning new situations. To solve this, in this paper we present a new advanced AIM approach based on end-to-end Multi-Agent Deep Reinforcement Learning (MADRL) and trained using Curriculum through Self-Play, called advanced Reinforced AIM (adv.RAIM). adv.RAIM enables the control of CAVs at intersections in a collaborative way, autonomously learning complex real-life traffic dynamics. In addition, adv.RAIM provides a new way to build smarter AIMs capable of proactively controlling CAVs in other highly complex scenarios. Results show remarkable improvements when compared to traffic light control techniques (reducing travel time by 59% or reducing time lost due to congestion by 95%), as well as outperforming other recently proposed AIMs (reducing waiting time by 56%), highlighting the advantages of using MADRL. [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]

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]

Advances in autonomous vehicular technology facilitate the development of intelligent traffic regulation systems. Such a system aims to configure and regulate vehicular mobility patterns to enhance in-road transportation safety and efficiency. To effectively function, the autonomous system must enable high-rate communications and rapid dissemination of vehicle-to-vehicle messaging flows. Instead of applying classical mobility models to capture human driver behaviors, the use of autonomously controlled driverless vehicles brings up another design dimensionality: the regulation and shaping of vehicular flows. The induced joint impact of the vehicular flow process on the message communications networking system, on the vehicular throughput rate, and on on-ramp waiting times for highway systems, has not been addressed by the existing studies. In this paper, we investigate the integrated design of these aspects. We synthesize and study methods that are used to optimally group autonomously controlled vehicles to travel along a highway in platoons. Vehicular formations are structured to yield effective autonomous mobility operation and to realize high-performance multihop dissemination of multiclass messaging flows. We then investigate an on-ramp traffic flow control mechanism that serves to regulate the admission of vehicles into the highway. We characterize the tradeoffs available to the system's designer in attaining high message communication throughput rates, accounting for time delays experienced by on-ramp waiting vehicles, while also striving to enhance the highway's capacity for accommodating high vehicular flow rate levels. [ABSTRACT FROM PUBLISHER]

Platooning has been identified as a promising framework to improve road capacity, on-road safety, and energy efficiency. Enabling communications among vehicles in platoons is expected to enhance platoon control by keeping constant intervehicle and interplatoon distances. Characterizing the performance of intra- and interplatoon communications in terms of throughput and packet transmission delays is crucial for validating the effectiveness of information sharing on platoon control. In this paper, we introduce an IEEE 802.11p-based communication model for multiplatooning (a chain of platoons) scenarios. We present a probabilistic performance analysis of distributed-coordination-function-based intra- and interplatoon communications. Expressions for the transmission attempt probability, collision probability, packet delay, packet-dropping probability, and network throughput are derived. Numerical results show that the performance of interplatoon communications is affected by the transmissions of the first and last vehicles in a multiplatoon. This effect is reduced with an increase of the platoon number in the multiplatoon. In addition, the communication performance for three typical multiplatooning application scenarios is investigated, indicating that the IEEE 802.11p-based communication can support the timely delivery of vehicle information among platoons for diverse on-road applications. [ABSTRACT FROM PUBLISHER]

Transportation cyber–physical systems (TCPSs) require simulation-based testing and evaluation due to the prohibitive cost of building realistic test beds. Given the transdisciplinary nature of TCPSs, various simulation models and frameworks have been proposed in civil engineering, computer science, and related fields. Traditionally, researchers in different areas have developed their own set of simulation tools, which provide limited capability for TCPS research. In recent years, we have witnessed a growing interest of combining two or more features of traditional simulators to capture the unique characteristics of TCPSs. In this paper, we describe several mainstream simulation models used in transportation, communication, and human-factor studies in TCPS research. Moreover, we present our unique design and implementation of an integrated traffic–driving–network simulator (ITDNS). Finally, we discuss future enhancements that will promote best simulation practices for TCPS research. [ABSTRACT FROM AUTHOR]

Platooning, which is the idea of cars autonomously following their leaders to form a road train, has huge potential to improve traffic flow efficiency and, most importantly, road traffic safety. Wireless communication is a fundamental building block: It is needed to manage and maintain the platoons. To keep the system stable, strict constraints in terms of update frequency and communication reliability must be met. We investigate different communication strategies by explicitly taking into account the requirements of the controller, exploiting synchronized communication slots, and transmit power adaptation. As a baseline, we compared the proposed approaches to two state-of-the-art adaptive beaconing protocols that have been designed for cooperative awareness applications, namely, the European Telecommunications Standards Institute (ETSI) Decentralized Congestion Control (DCC) and Dynamic Beaconing (DynB). Our simulation models have been parameterized and validated by means of real-world experiments. Our results demonstrate that the combination of synchronized communication slots with transmit power adaptation is perfectly suited for cooperative driving applications, even on very crowded freeway scenarios. [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]

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]

In this paper, we investigate the performance of networks built from single-channel devices that use wireless access in vehicular environment protocols. We consider several traffic combinations, each of which presents a mix of traffic classes, over control and service channels. Our results show that time switching between the channels causes synchronization of backoff processes, which increases the frame collision probability, in particular for small sizes of contention windows. We also evaluate the impact of the interruption of the backoff process by inactive channel time, which gives rise to a probability distribution with repeated tails and a coefficient of variation larger than 1. Our model can also be used to evaluate different sets of enhanced distributed channel access parameters and to select the channel duty cycle according to the policy of the network operator. [ABSTRACT FROM PUBLISHER]

The automation of driving tasks is of increasing interest for highway traffic management. The emerging technologies of global positioning and intervehicular wireless communications, combined with in-vehicle computation and sensing capabilities, can potentially provide remarkable improvements in safety and efficiency. We address the problem of designing intelligent intersections, where traffic lights and stop signs are removed, and cars negotiate the intersection through an interaction of centralized and distributed decision making. Intelligent intersections are representative of complex hybrid systems that are increasingly of interest, where the challenge is to design tractable distributed algorithms that guarantee safety and provide good performance. [ABSTRACT FROM PUBLISHER]

To facilitate the dissemination of a time-critical information in a vehicular ad hoc network (VANET), immediate network connectivity is needed. In other words, a time-critical message from a source should be able to propagate and reach all of the vehicles on the road segment without any delay due to the unavailability of the vehicles to forward the message. Clearly, this requires the road segment to have a certain number of vehicles equipped with communication devices. It is the task of a system designer to determine the minimum number of vehicles (i.e., the minimum penetration) necessary to form a connected network as well as the critical transmission range required to provide such connectivity. In this paper, we present an analytical framework for determining the connectivity requirements in distributing the traffic information in a self-organizing vehicular network. One- and two-way street scenarios are considered. In addition to the conventional perspective on connectivity, where the characteristics of the wireless channel are often neglected, our analysis offers a new view by taking important physical-layer parameters, such as fading, propagation path loss, transmit power, and transmission data rate, into consideration. [ABSTRACT FROM AUTHOR]

Presents an a real-time intelligent decision making system for urban traffic control applications. Background and motivations that influence intelligent highway vehicle systems; Architecture of the proposed system; Mapping of the application to the system.

The special section presents a collection of high quality research papers on the state-of-the-art in the emerging technologies for connected vehicles, the latest development in standardizations and regulations, as well as the potential services and applications for connected vehicle (CV) and autonomous vehicle (AV) systems. [ABSTRACT FROM AUTHOR]