Article
Transportation
Xiao (Joyce) Liang, S. Ilgin Guler, Vikash V. Gayah
Summary: This paper proposes a decentralized signal control algorithm that leverages connected vehicle information to improve traffic operations. The algorithm optimizes signal timing based on real-time vehicle locations, speeds, and pedestrian waiting information, and facilitates coordination between adjacent intersections through sharing vehicle platoons information. Compared to the centralized algorithm and traditional strategy, the proposed algorithm is more computationally efficient and provides better operational performance, while being robust to different demand patterns.
JOURNAL OF INTELLIGENT TRANSPORTATION SYSTEMS
(2023)
Article
Ergonomics
Tarek Ghoul, Tarek Sayed
Summary: The study introduces a SVCC system incorporating ATSC and speed advisories to optimize safety in real-time, effectively reducing traffic conflicts and vehicle delay through real-time data collection and estimation of traffic conflict rates.
ACCIDENT ANALYSIS AND PREVENTION
(2021)
Article
Green & Sustainable Science & Technology
Zhongtai Jiang, Dexin Yu, Siliang Luan, Huxing Zhou, Fanyun Meng
Summary: This paper presents an integrated traffic control framework for traffic signal optimization and vehicle microscopic control of connected and automated vehicles (CAVs) at an isolated signalized intersection. The framework includes redesigned control models for CAVs' longitudinal and lateral behavior, an optimal control model for trajectory optimization, and a controlled optimization of phase model for signal timing plan determination. Experimental results show significant improvements in traffic and energy efficiency using the proposed framework.
JOURNAL OF CLEANER PRODUCTION
(2022)
Article
Transportation Science & Technology
Qinzheng Wang, Yun Yuan, Xianfeng (Terry) Yang, Zhitong Huang
Summary: This paper proposes an adaptive traffic signal control system in a CV environment, aiming to reduce vehicle delay, improve arterial performance, and show superior effectiveness under various CV penetration rates and demand levels.
TRANSPORTATION RESEARCH PART C-EMERGING TECHNOLOGIES
(2021)
Article
Transportation Science & Technology
Zhaobin Mo, Wangzhi Li, Yongjie Fu, Kangrui Ruan, Xuan Di
Summary: This paper presents a decentralized reinforcement learning scheme for multi-intersection adaptive traffic signal control system using data collected from connected vehicles. The proposed scheme demonstrates advantages in considering travel delays and coordinating agents, and its effectiveness is verified through experiments under various traffic demand patterns and penetration rates.
TRANSPORTATION RESEARCH PART C-EMERGING TECHNOLOGIES
(2022)
Article
Engineering, Civil
Xingju Wang, Rongqun Zhang, Yang Gou, Jiayu Liu, Lin Zhao, Yanting Li
Summary: This paper proposes a model for alleviating traffic congestion in freeway bottleneck areas using a variable speed limit control method in an intelligent connected environment. The results show that the VSL online control method in an intelligent connected environment has better control effect, especially with an increasing penetration rate of intelligent connected vehicles (ICV).
JOURNAL OF ADVANCED TRANSPORTATION
(2021)
Review
Chemistry, Multidisciplinary
Vittorio Astarita, Vincenzo Pasquale Giofre, Giuseppe Guido, Alessandro Vitale
Summary: This paper reviews the latest developments in traffic signal control methods based on data from smartphones or connected vehicles, highlighting the potential benefits such as the utilization of real-time positional data and better-regulated intersections. The use of scientometric tools provides insights into trending ideas and concepts in the field, helping scientists and professionals identify relevant documents for further development of new traffic signal control systems.
APPLIED SCIENCES-BASEL
(2021)
Article
Engineering, Civil
Yiheng Feng, Shihong Ed Huang, Wai Wong, Qi Alfred Chen, Z. Morley Mao, Henry X. Liu
Summary: This study proposes a comprehensive analysis framework to address the cybersecurity problem in the traffic signal control system with connected vehicle technology. A case study is conducted to demonstrate the impact of data spoofing attacks and the corresponding mitigation measures.
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
(2022)
Article
Transportation Science & Technology
Hossein Moradi, Sara Sasaninejad, Sabine Wittevrongel, Joris Walraevens
Summary: This paper proposes a hierarchical framework to address the challenges in network-wide traffic control using connected vehicles. By incorporating real-time information into intersection and network control, it enables accurate estimation and control of traffic conditions, leading to competitive performance indicators.
TRANSPORTATION RESEARCH PART C-EMERGING TECHNOLOGIES
(2022)
Article
Engineering, Civil
Felipe de Souza, Rodrigo Castelan Carlson, Eduardo Rauh Mueller, Konstantinos Ampountolas
Summary: This study develops a real-time traffic management policy that integrates traffic signal control and multi-commodity routing of connected vehicles in networks with multiple destinations. By exchanging information, vehicles are able to optimize signal timings and specific routing information to improve traffic efficiency throughout the network.
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
(2022)
Article
Engineering, Civil
Azadeh Emami, Majid Sarvi, Saeed Asadi Bagloee
Summary: The study proposes an innovative method to adaptively optimize traffic signal plans based on the estimation of various penetration rates of Connected Vehicles (CVs). By using Kalman filter and Neural Network algorithms to predict and update traffic situation, the methodology outperforms conventional actuated-coordinated traffic signal plans at lower than 100% penetration rates. The results show that the proposed method can achieve maximum benefits even at 60% penetration rate, indicating its effectiveness in traffic signal optimization.
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
(2022)
Article
Chemistry, Analytical
Saeed Maadi, Sebastian Stein, Jinhyun Hong, Roderick Murray-Smith
Summary: Adaptive traffic signal control is an effective method to reduce traffic congestion. This study develops a reinforcement learning-based adaptive traffic signal control that optimizes signal plans and guides vehicle speed to minimize total stop delays and queue length. Experimental results show that the proposed method outperforms traditional actuated control and fixed timing plans under saturated and oversaturated conditions.
Article
Computer Science, Artificial Intelligence
Yi Wang, Yangsheng Jiang, Yunxia Wu, Zhihong Yao
Summary: This paper proposes a control strategy for connected and automated vehicles (CAVs) that considers the driving behavior of CAV platoons. Numerical simulations show that this strategy effectively reduces traffic oscillations and congestion, and performs better than the existing strategy in improving traffic efficiency.
EXPERT SYSTEMS WITH APPLICATIONS
(2024)
Article
Automation & Control Systems
Yang Shi, Zhenbo Wang, Chieh (Ross) Wang, Yunli Shao
Summary: Connected vehicle technologies can solve the challenges faced by drivers when merging onto highways and offer numerous benefits. However, real-time optimal control is still a challenge. To address this, a novel approach is proposed that balances computational efficiency and solution optimality.
JOURNAL OF THE FRANKLIN INSTITUTE-ENGINEERING AND APPLIED MATHEMATICS
(2023)
Article
Mathematics, Applied
Yicai Zhang, Min Zhao, Dihua Sun, Shi Hui Wang, Shuai Huang, Dong Chen
Summary: This study investigates the mixed traffic lattice hydrodynamic model to analyze the mixed traffic situation with connected and non-connected vehicles, and obtains the stability conditions of the traffic system and the modified Korteweg-de Vries equation through linear and nonlinear analysis. The numerical simulation results confirm the theoretical findings, showing that increasing the communication range and permeability of connected vehicles will enhance the stability of the traffic system.
COMMUNICATIONS IN NONLINEAR SCIENCE AND NUMERICAL SIMULATION
(2021)
Article
Engineering, Civil
Rebeka Yocum, Vikash V. Gayah
Summary: Recent studies have developed a coordinated traffic management scheme that implements perimeter flow control on an urban network and variable speed limits (VSL) on a freeway to reduce total travel time in a mixed network. VSL effectively meters traffic exiting the freeway into the urban network, improving overall system operations.
TRANSPORTATION RESEARCH RECORD
(2022)
Article
Transportation
Renato Guadamuz, Houjun Tang, Zhengyao Yu, S. Ilgin Guler, Vikash V. Gayah
Summary: The performance of traffic signal phasing and timing plans is influenced by fluctuations in traffic volumes. This study introduces new metrics and methods to evaluate the efficiency of green time allocation using high-resolution traffic data. An empirical application is conducted on a major arterial in Salt Lake City and provides insights for improving signal timing plans.
INTERNATIONAL JOURNAL OF TRANSPORTATION SCIENCE AND TECHNOLOGY
(2022)
Article
Transportation
Xiao (Joyce) Liang, S. Ilgin Guler, Vikash V. Gayah
Summary: This paper proposes a decentralized signal control algorithm that leverages connected vehicle information to improve traffic operations. The algorithm optimizes signal timing based on real-time vehicle locations, speeds, and pedestrian waiting information, and facilitates coordination between adjacent intersections through sharing vehicle platoons information. Compared to the centralized algorithm and traditional strategy, the proposed algorithm is more computationally efficient and provides better operational performance, while being robust to different demand patterns.
JOURNAL OF INTELLIGENT TRANSPORTATION SYSTEMS
(2023)
Article
Transportation
Zhengyao Yu, Vikash V. Gayah
Summary: This study examines the performance of three street network configurations under disruptive events using aggregated network-level operation metrics. The results show that a two-way network without left turns is the most efficient configuration, able to handle the most challenging disruptions. Additionally, providing advance information to drivers about disruptions may have negative effects on overall network performance.
JOURNAL OF INTELLIGENT TRANSPORTATION SYSTEMS
(2023)
Article
Transportation
Jonathan Wood, Zhengyao Yu, Vikash V. Gayah
Summary: Seating availability and boarding space on buses have a significant impact on riders' attitudes. However, little research has been done on short-term passenger occupancy predictions on individual buses. This study investigates the use of linear regression models and machine learning models to predict passenger occupancies on buses in real-time, based on data from bus operations and weather information. The results show that both models provide accurate estimates.
INTERNATIONAL JOURNAL OF TRANSPORTATION SCIENCE AND TECHNOLOGY
(2023)
Article
Transportation
Murat Bayrak, Zhengyao Yu, Vikash V. Gayah
Summary: This paper proposes a population-based incremental learning (PBIL) algorithm to determine left-turn restrictions at intersections in order to maximize the network's operational performance. The algorithm is effective at identifying near-optimal configurations, suggesting that left turns should generally be restricted at intersections with the highest flow. This approach provides additional intersection capacity and reduces additional travel distance.
TRANSPORTMETRICA B-TRANSPORT DYNAMICS
(2023)
Article
Engineering, Civil
Hao Liu, Vikash V. Gayah
Summary: This paper proposes a novel decentralized signal control algorithm that improves traffic delay equity without significantly increasing average delay. The algorithm uses the sum of cumulative delay as the weight calculation metric, ensuring that less congested movements have a higher chance of being served. Microscopic simulations comparing the proposed algorithm with three baseline models demonstrate its effectiveness, especially for highly unbalanced traffic flows. Additionally, the algorithm outperforms other models in reducing traffic delay and increasing delay equity in a connected vehicle environment with a penetration rate less than or equal to 60%.
TRANSPORTATION RESEARCH RECORD
(2023)
Article
Transportation Science & Technology
Dongqin Zhou, Vikash V. Gayah
Summary: Perimeter metering control based on macroscopic fundamental diagrams has gained attention in traffic management. Existing methods require accurate knowledge of traffic dynamics, but this paper proposes a scalable model-free scheme based on multi-agent deep reinforcement learning that overcomes this limitation. Experimental results show the scheme's effectiveness, resilience, and transferability in managing traffic in urban networks.
TRANSPORTATION RESEARCH PART C-EMERGING TECHNOLOGIES
(2023)
Article
Engineering, Civil
Guanhao Xu, Pengxiang Zhang, Vikash V. Gayah, Xianbiao Hu
Summary: The relationship between average network flow and density (flow-MFD) and the relationship between trip completion and density (o-MFD) are two key aggregated traffic models. Recent studies have shown that these two relationships might have different patterns when traffic conditions vary. This paper presents an alternative explanation for these findings by showing that a vehicle's entire trip contributes to a network's average flow, while only its end contributes to the trip completion rate. This lag can lead to different patterns in the o-MFD. The paper provides examples and simulations to support these explanations.
TRANSPORTATION RESEARCH RECORD
(2023)
Article
Engineering, Civil
Dongqin Zhou, Vikash V. V. Gayah
Summary: This paper proposes integrating domain control knowledge (DCK) into agent designs to improve learning and control performances. Two types of DCK are introduced to provide knowledge-guided exploration strategies for agents to explore the most rewarding part of the action spaces. Experimental results show that integrating DCK can effectively enhance learning and control performances, improve agents' resilience against environmental uncertainties, and mitigate scalability issues.
TRANSPORTATION RESEARCH RECORD
(2023)
Article
Ergonomics
Asif Mahmud, Vikash V. Gayah, Rajesh Paleti
Summary: This study introduces a novel approach to address the issue of crash misclassification and incorporates it into two commonly used crash frequency prediction models. The proposed models demonstrate their capability to estimate true parameters and provide more reliable results compared to models that ignore misclassification errors.
ACCIDENT ANALYSIS AND PREVENTION
(2023)
Article
Economics
Guanhao Xu, Vikash V. Gayah
Summary: Recent research has shown that there are unimodal, concave relationships between average network productivity and accumulation or density in urban networks. These relationships, known as network Macroscopic Fundamental Diagrams (MFDs), have implications for the modeling of traffic congestion and the development of regional traffic control strategies. However, real street networks are not homogeneous and have hierarchical structures, which may result in non-unimodal patterns in MFDs. This paper examines how the presence of hierarchical roadway structures can affect a network's MFD using analytical models, simulations, and empirical data. The findings suggest that the presence of roadway hierarchies can lead to non-unimodal or non-concave MFD patterns, contrary to traditional assumptions.
TRANSPORTATION RESEARCH PART B-METHODOLOGICAL
(2023)
Article
Engineering, Civil
David Taglieri, Hao Liu, Vikash V. Gayah
Summary: This paper examines the impact of implementing roundabouts at intersections in a dense urban network on operational performance. Three intersection strategies are compared: signalized intersections allowing left turns, signalized intersections prohibiting left turns, and modern roundabouts. The results show that roundabouts perform better than signalized intersections in networks with a single travel lane in each direction, but signalized intersections with two travel lanes outperform roundabouts in terms of flow-moving and trip-serving capacities. The higher fuel consumption rate in roundabouts is attributed to more frequent acceleration and deceleration.
TRANSPORTATION RESEARCH RECORD
(2023)
Article
Ergonomics
Tanveer Ahmed, Asif Mahmud, Vikash V. Gayah
Summary: This study uses the propensity score potential outcome framework to investigate the impact of rumble strips on crashes on horizontal curves. The findings suggest that centerline rumble strips reduce sideswipe and head-on crashes but increase run off the road and hit fixed object crashes. Shoulder rumble strips, either alone or in combination with centerline rumble strips, decrease crash frequencies for most types except sideswipe and head-on crashes.
ACCIDENT ANALYSIS AND PREVENTION
(2024)
Article
Engineering, Civil
Muyang Lu, Vikash V. Gayah, S. Ilgin Guler
Summary: Crashes involving vulnerable roadway users have been on the rise recently. This study incorporates exposure metrics related to nonmotorized and public transportation use to develop a crash-prediction model. The results show a positive correlation between shared-bike trips and POI visits with increases in pedestrian and cyclist crash frequencies.
TRANSPORTATION RESEARCH RECORD
(2023)
Article
Transportation Science & Technology
Yue Zhao, Liujiang Kang, Huijun Sun, Jianjun Wu, Nsabimana Buhigiro
Summary: This study proposes a 2-population 3-strategy evolutionary game model to address the issue of subway network operation extension. The analysis reveals that the rule of maximum total fitness ensures the priority of evolutionary equilibrium strategies, and proper adjustment minutes can enhance the effectiveness of operation extension.
TRANSPORTATION RESEARCH PART C-EMERGING TECHNOLOGIES
(2024)
Article
Transportation Science & Technology
Hongtao Hu, Jiao Mob, Lu Zhen
Summary: This study investigates the challenges of daily storage yard management in marine container terminals considering delayed transshipment of containers. A mixed-integer linear programming model is proposed to minimize various costs associated with transportation and yard management. The improved Benders decomposition algorithm is applied to solve the problem effectively and efficiently.
TRANSPORTATION RESEARCH PART C-EMERGING TECHNOLOGIES
(2024)
Article
Transportation Science & Technology
Zhandong Xu, Yiyang Peng, Guoyuan Li, Anthony Chen, Xiaobo Liu
Summary: This paper studied the impact of range anxiety among electric vehicle drivers on traffic assignment. Two types of range-constrained traffic assignment problems were defined based on discrete or continuous distributed range anxiety. Models and algorithms were proposed to solve the two types of problems. Experimental results showed the superiority of the proposed algorithm and revealed that drivers with heightened range anxiety may cause severe congestion.
TRANSPORTATION RESEARCH PART C-EMERGING TECHNOLOGIES
(2024)
Article
Transportation Science & Technology
Chuanjia Li, Maosi Geng, Yong Chen, Zeen Cai, Zheng Zhu, Xiqun (Michael) Chen
Summary: Understanding spatial-temporal stochasticity in shared mobility is crucial, and this study introduces the Bi-STTNP prediction model that provides probabilistic predictions and uncertainty estimations for ride-sourcing demand, outperforming conventional deep learning methods. The model captures the multivariate spatial-temporal Gaussian distribution of demand and offers comprehensive uncertainty representations.
TRANSPORTATION RESEARCH PART C-EMERGING TECHNOLOGIES
(2024)
Article
Transportation Science & Technology
Benjamin Coifman, Lizhe Li
Summary: This paper develops a partial trajectory method for aligning views from successive fixed cameras in order to ensure high fidelity with the actual vehicle movements. The method operates on the output of vehicle tracking to provide direct feedback and improve alignment quality. Experimental results show that this method can enhance accuracy and increase the number of vehicles in the dataset.
TRANSPORTATION RESEARCH PART C-EMERGING TECHNOLOGIES
(2024)
Article
Transportation Science & Technology
Mohsen Dastpak, Fausto Errico, Ola Jabali, Federico Malucelli
Summary: This article discusses the problem of an Electric Vehicle (EV) finding the shortest route from an origin to a destination and proposes a problem model that considers the occupancy indicator information of charging stations. A Markov Decision Process formulation is presented to optimize the EV routing and charging policy. A reoptimization algorithm is developed to establish the sequence of charging station visits and charging amounts based on system updates. Results from a comprehensive computational study show that the proposed method significantly reduces waiting times and total trip duration.
TRANSPORTATION RESEARCH PART C-EMERGING TECHNOLOGIES
(2024)