Search

With the development of autonomous driving, a mixed traffic flow state composed of connected automated vehicles (CAVs) and human-driven vehicles (HVs) will last for an extended period. The abundant computing resources and CAVs with high compliance in the intelligent connected environment provide a good situation for variable speed limit control on highways, which helps even the traffic flow and improves traffic efficiency and safety. In this paper, we propose a variable speed limit control method for mixed traffic flow based on deep-reinforcement learning. First, the variable speed limit control problem is abstracted into a Markov decision process and the factors of real-time CAV penetration rates and predictions are considered in the state description. Different from variable message signs (VMS), CAVs are taken as the executive objects of the controller so that the variable speed limit control for mixed traffic flow is realized indirectly through the interaction with HVs. Next, double deep Q network (DDQN) is introduced to calculate the optimal speed limit in different states. Finally, the empirical study on US101-S proves the effectiveness of the proposed model. The results show that the variable speed limit control model based on the DDQN algorithm can effectively improve the efficiency and environmental benefits of mixed traffic flow. Moreover, the multi-objective reward function can achieve a better control effect than the single objective. Besides, the proposed model outperforms other models in this paper and predictive factors can further improve proactive control performance. In addition, with the increasing penetration of CAV, the proposed model achieves a better control effect. [ABSTRACT FROM AUTHOR]

In recent years, high-resolution traffic signal event data has provided valuable insights into understanding and managing congestion at signalized intersections. While existing applications primarily employ automated traffic signal performance monitoring (ATSPM) systems as postanalysis tools for identifying everyday congestion causes, traffic engineers are increasingly overwhelmed by the number of ATSPM-capable intersections. The workload increases extensively as the number of ATSPM-capable intersections rises mainly due to the necessity of manually checking and generating performance figures. Nonetheless, an advanced ATSPM system capable of automatically detecting time-of-day congestion bottlenecks among multiple intersections and suggesting "top intersections of interest" would significantly aid traffic managers in monitoring historical congestion and preventing future congestion occurrences. This paper introduces an efficient graphical automated congestion ranking method for capable intersections, leveraging high-resolution traffic signal event data as the basis for automated congestion ranking. To accomplish these objectives, we build upon ATSPM concepts by continuously generating ATSPM measures of effectiveness (MOEs). Utilizing continuously generated ATSPM performance measures in Frisco, Texas, over several months, we devise an efficient graphical method for ranking hourly congestion levels among the studied ATSPM-capable intersections. All intersections are assessed and ranked using a multiobjective optimization technique, the Pareto front method. The points on the Pareto front represent dominating intersections with at least one inferior performance measurement, warranting prioritized improvement. The dominating points identified from the test dataset were validated and further explained using Purdue coordination diagrams (PCD), along with another individual dataset--Wejo-connected vehicle data. The outcomes of this approach have proven the validity of the method. [ABSTRACT FROM AUTHOR]

This paper proposes a reinforcement learning (RL)-based traffic control strategy integrated with attention mechanism for large-scale adaptive traffic signal control (ATSC) system. The proposed attention RL integrates attention mechanism into a multiagent RL model, namely multiagent proximal policy optimization (MAPPO), so as to enable more effective, scalable, and stable learning in complex ATSC envi)ronments. In the attention RL, decentralized policies are trained using a centrally computed critic that shares an attention model, while the attention model selects relevant intersections for each agent to estimate the global critic. This framework effectively reduces the computa)tional complexity and stabilizes the training process, enhancing the ability of RL agents to control large-scale traffic networks. The proposed control strategy is tested in both a large synthetic traffic grid and a large real-world traffic network of Yangzhou city using the microscopic traffic simulation tool, SUMO. Experimental results demonstrate that the proposed approach learns stable and sustainable policies that achieve lower congestion level and faster recovery, which outperforms other state-of-art RL-based approaches, as well as a gap-based actuated controller. [ABSTRACT FROM AUTHOR]

Evaluating arterial operational performance plays a pivotal role in arterial system management and enhancement. As a fundamental reference guide for traffic engineers, the Highway Capacity Manual (HCM) provides a series of analysis methodologies for evaluating multimodal operations on urban streets, highways, freeways, and off-street pathways. However, the efficient use of the performance evaluation methodology of urban street facilities for motorized vehicles in the HCM can be restricted by a large amount of traffic volume collections at signalized and access point intersections, roadway segment geometric data inputs, and complicated calculation procedures on urban street segments. Further, the use of alternative tools, such as vehicle trajectory data, remains to be explored to supplement the urban street facility calculation framework in the HCM. To bridge the gap, this research utilizes vehicle trajectory data as an alternative tool and proposes a combined vehicle trajectory data and HCM calculation framework to implement and assess the existing performance evaluation methodology of urban street facilities for motorized vehicles in the HCM 7th Edition. A case study was carried out on three major signalized arterials in Sparks, Nevada, for HCM methodology implementation and performance evaluation. Based on evaluation results, it was found that vehicle trajectory data can be utilized as an alternative tool to implement the performance evaluation methodology of urban street facilities for motorized vehicles in the HCM 7th Edition. It is recommended to combine arterial through-vehicle trajectories, the time-space diagram, arterial level of service (LOS), and the poorest segment LOS for arterial operational performance evaluation and further enhancement. The proposed automobile traveler perception score (ATPS) in the HCM was found to be insensitive to reflecting traveler’s perception of service quality. Additional traveler perception-based factors are recommended to be included for further ATPS development and enhancement. [ABSTRACT FROM AUTHOR]

Evaluating arterial operational performance plays a pivotal role in arterial system management and enhancement. As a fundamental reference guide for traffic engineers, the Highway Capacity Manual (HCM) provides a series of analysis methodologies for evaluating multimodal operations on urban streets, highways, freeways, and off-street pathways. However, the efficient use of the performance evaluation methodology of urban street facilities for motorized vehicles in the HCM can be restricted by a large amount of traffic volume collections at signalized and access point intersections, roadway segment geometric data inputs, and complicated calculation procedures on urban street segments. Further, the use of alternative tools, such as vehicle trajectory data, remains to be explored to supplement the urban street facility calculation framework in the HCM. To bridge the gap, this research utilizes vehicle trajectory data as an alternative tool and proposes a combined vehicle trajectory data and HCM calculation framework to implement and assess the existing performance evaluation methodology of urban street facilities for motorized vehicles in the HCM 7th Edition. A case study was carried out on three major signalized arterials in Sparks, Nevada, for HCM methodology implementation and performance evaluation. Based on evaluation results, it was found that vehicle trajectory data can be utilized as an alternative tool to implement the performance evaluation methodology of urban street facilities for motorized vehicles in the HCM 7th Edition. It is recommended to combine arterial through-vehicle trajectories, the time-space diagram, arterial level of service (LOS), and the poorest segment LOS for arterial operational performance evaluation and further enhancement. The proposed automobile traveler perception score (ATPS) in the HCM was found to be insensitive to reflecting traveler’s perception of service quality. Additional traveler perception-based factors are recommended to be included for further ATPS development and enhancement. [ABSTRACT FROM AUTHOR]

Decentralized traffic signal controls, such as max-pressure (MP) control, also known as back-pressure (BP) control, have received increased attention recently. MP signal control has been analytically proven to maximize the network throughput and stabilize vehicle queue lengths whenever possible. However, previous work on MP signal control with cyclic and noncyclic phases did not include pedestrian access, which may increase pedestrians’ travel time, and delay or even encourage some dangerous behaviors like jaywalking. Because the movement of pedestrians is a nonnegligible factor in traffic management, and many urban planning researchers have found that walking space and walking continuously have significant health, safety, and environmental impacts, a pedestrian-friendly MP signal control policy is needed. Here, we propose a novel pedestrian-friendly MP signal control, Ped-MP, that considers pedestrian access in an urban network to achieve both maximum stability for private vehicles and a comfortable, safe walking experience. This study modifies the original MP control to include pedestrians’ access for the first time. Furthermore, this policy still inherits the decentralized property of original MP control, which means it only relies on the local information of individual intersections. Simulation studies are implemented on a popular benchmark network, the Sioux Falls network, with added pedestrians network. The results indicate that, although considering pedestrians’ access may reduce the stable region for vehicles, the pedestrians’ travel time and delay can be reduced significantly. [ABSTRACT FROM AUTHOR]