Kinematic Equation-Based Vehicle Queue Location Estimation Method for Signalized Intersections Using Mobile Sensor Data

The paper presents an algorithm for matching individual vehicles measured at a freeway detector with the vehicles' corresponding measurements taken earlier at another detector located upstream. Although this algorithm is potentially compatible with many vehicle detector technologies, the paper illustrates the method using existing dual-loop-detectors to measure vehicle lengths. This detector technology has seen widespread deployment for velocity measurement. Since the detectors were not developed to measure vehicle length, these measurements can include significant errors. To overcome this problem, the algorithm exploits drivers' tendencies to retain their positions within dense platoons. The otherwise complicated task of vehicle reidentification is carried-out by matching these platoons rather than individual vehicles. Of course once a vehicle has been matched across neighboring detector stations, the difference in its arrival time at each station defines the vehicle's travel time on the intervening segment. Findings from an application of the algorithm over a 1/3 mile long segment are presented herein and they indicate that a sufficient number of vehicles can be matched for the purpose of traffic surveillance. As such, the algorithm extracts travel time data without requiring the deployment of new detector technologies. In addition to the immediate impacts on traffic monitoring, the work provides a means to quantify the potential benefits of emerging detector technologies that promise to extract more detailed information from individual vehicles.

Real time queue length estimation for signalized intersections using travel times from mobile sensors

Vehicle travel time on arterial roads is a crucial parameter for traffic management and traveler information systems. A travel time distribution is an effective way to represent the essential properties of this parameter. This paper proposes a modified Gaussian Mixture Model for representing travel time distributions on arterial roads with signalized intersections. The proposed model is applicable to travel time data from both fixed and mobile sensors. The performance of the model was evaluated using real travel time measurements from fixed sensors in the field and virtual mobile sensor data generated from those real-world measurements. The evaluation results show very good performance of the model in representing the traffic state on arterial roads. The model can be applied to historical datasets to estimate the amount of stop time and non-stop time for vehicles on arterial links during a specific time period, which is useful information for a variety of traffic applications, such as arterial travel time prediction and arterial traffic energy/emission estimation.

In major cities of Vietnam, serious road congestions are partially caused by rainfalls and road flooding. To help mitigate negative impacts of the adverse weather conditions on transport and traffic system, it is important to implement weather-responsive traffic management strategies for those cities. However, weather-responsive traffic management measures are often formulated based on practitioners’ experience and not tested prior to application. Taking Ho Chi Minh City as a case study, this paper aims to develop a methodological framework to help formulate and test such strategies. It consists of literature review of good practices, expert consultation process, road user interview survey, and strategic travel demand model-based scenario test. Active traffic management strategies are suggested for the city of study and a number of selected measures are tested by a VISUM model. It shows that vehicle speeds and travel times could be improved significantly if weather-responsive traffic management strategies are applied. This research could serve as a toolkit to assist the design of smart urban traffic management system.

This paper presents a cell transmission model with a lane-changing and vehicle-tracking (CTM-LV) framework for simulation of international land ports of entry (POEs). The development of the modeling framework is motivated by the need to simulate lane-specific queuing yet permit lane changing of vehicles between queues–-a behavior that was not accounted for or tested by the earlier cell transmission models and that cannot be easily replicated in microscopic traffic simulation models. The CTM-LV's network representation, traffic flow logic, and lane-changing rules are discussed. A simulation experiment is then presented to illustrate the importance of modeling the lane changing between queues that will affect the estimation of average queue length. The concept of CTM-LV has been applied to simulate the northbound traffic at the Bridge of the Americas POE, for passenger cars entering El Paso, Texas, from Ciudad Juarez, Mexico. Finally, a method is proposed to track selected vehicles within the CTM-LV framework so that an individual vehicle's travel time can be calculated and vehicle trajectories compared against data collected by probe vehicles with Global Positioning System receivers.

This paper introduces an AI-based strategy for the deployment of adaptive communication protocols in resource-limited IoT networks, with a focus on smart city intelligent traffic management. As the complexity of urban transport increases and the number of IoT devices being deployed grows, there is an urgent need for intelligent models that can maximize the flow of traffic, minimize congestion, and enable scalable energy-efficient operation. In the research, a dataset of 14,000 traffic records was created with the SUMO simulator, recording real-time values like vehicle numbers, waiting time, queue lengths, signal phases, and travel times. Four machine learning algorithms Long Short-Term Memory (LSTM), Random Forest (RF), XGBoost, and Deep Q-Network (DQN) were applied and analyzed against different performance metrics such as accuracy, latency, energy efficiency, throughput, and scalability. Severe preprocessing was carried out to pre-clean, normalize, and enrich the dataset with time-features. Out of the models, DQN performed the best, yielding the highest accuracy (95.6%) and lowest latency (60 ms), and having a correct prediction of major traffic indicators with minimal margin of error. The DQN model also exhibited high flexibility and scalability, making it perfect for real-time deployment in dynamic traffic conditions. Real and estimated values of indicators like mean car waiting time and travel time closely matched, confirming the credibility of the model. Furthermore, comparative analysis indicated that DQN optimizes real-time responsiveness while employing reasonable energy consumption compared to conventional models. The results validate that DQN is the best model to use for adaptive traffic control in IoT-based smart cities, which provides a scalable, robust, and intelligent solution for enhancing urban mobility and facilitating sustainable infrastructure development.

Traffic congestion has been aggravated in many cities, which not only negatively affects the traffic efficiency, but also exacerbates the related social problems. Accurate prediction of urban road travel times plays a crucial role in assisting traffic management and alleviating the derived problems caused by traffic congestion. This study aims to propose an innovative Gated Recurrent Unit (GRU)‐based model for vehicle travel time prediction on urban road networks using the Internet vehicle travel time data. The Internet data used in the paper represents the real‐world average vehicle travel times on urban road networks, avoiding the privacy issue and the computational challenge in individual trajectory data. Before presenting the model, a data imputation method based on time series to reconstruct the missing data, and a time‐series data similarity evaluation method for road link classification are developed. The road‐category‐based model helps balance the computational efficiency and the prediction accuracy. Finally, the modelling framework is tested on a road network in Xuhui District, Shanghai. By comparing its performance with different models, it is concluded that the GRU‐based model considering road link categories is more efficient and more accurate in urban road travel time prediction.

Predicting truck (heavy vehicle) travel time is a principal component of freight project prioritization and planning. However, most existing travel time prediction models are designed for passenger vehicles and fail to make truck specific forecasts or use truck specific data. Little is known about the impact of this limitation, or how truck travel time prediction could be improved in response to freight investments with an improved methodology. In light of this, this paper proposes a pragmatic multi-regime speed-density relationship based approach to predict freeway truck travel time using empirical truck probe GPS data (which is increasingly available in North American and Europe) and loop detector data. Traffic regimes are segmented using a cluster analysis approach. Two case studies are presented to illustrate the approach. The travel time estimates are compared with the Bureau of Public Roads (BPR) model and the Akçelik model outputs. It is found that the proposed method is able to estimate more accurate travel times than traditional methods. The predicted travel time can support freight prioritization and planning.

Traffic congestion is increasingly becoming a severe problem in many large cities around the world. The problem is more complex in developing countries where cities are growing at a much faster rate than those in the developed world. Advanced Traffic Management Systems (ATMS) are one of the Intelligent Transport Systems (ITS) technologies that have been recommended and used as a tool to ease congestion problems in many large cities in the developing world. However, it is unknown how specific local conditions commonly observed in these cities, such as poor lane discipline and complex road user interactions, affect the performance of these systems. GETRAM (Generic Environment for Traffic Analysis and Modeling) was used in this research as a tool to develop microscopic traffic simulation models for the city of Bandung in Indonesia. The field data in this research, comprising throughputs, queue lengths and travel times, were collected during peak and off peak periods from all 90 signalised intersections connected to SCATS (Sydney Co-ordinated Adaptive Traffic System). This field data is believed to comprise one of the largest sets of “real world” data available for the development and validation of microscopic traffic simulation models. Two data sets were collected for this research: the first was used to develop and calibrate the simulation model and the second was used for validation. A number of statistical tests were used to determine the adequacy of the model in replicating traffic conditions. The results of statistical tests clearly showed that all of the calibrated and validated models reproduced field conditions with an acceptable degree of confidence. Therefore, the models were accepted as accurate and valid replications of the “real world”. The validated models were then used to evaluate the performance of SCATS which was implemented in Bandung in June 1997 as a pilot project. The results of comparative evaluation of the models under SCATS and under the Fixed Time control (without SCATS) demonstrated that SCATS did not necessarily always produce better results than the Fixed Time control. Furthermore, the performance of SCATS was strongly influenced by specific local conditions in the city. The multiple regression method was used to investigate the relationship between the traffic performance measures and significant basic variables. Based on this analysis, the main findings were: first, throughput was found to increase at intersections with higher v/c (volume to capacity) ratios. Second, throughput was found to decrease at intersections with higher numbers of phases and movements, longer widths of leg intersections, and farther distances to adjacent intersections. Third, queue length was found to increase at intersections with higher numbers of phases and movements. Based on the above findings, a number of improvements were recommended to enhance the performance of SCATS. This research also used traffic simulation to evaluate the impacts of these recommended improvements in increasing the performance of SCATS. The main findings from this evaluation were: first, restricted number of phases and movements at selected intersections substantially increased the traffic flow (78%) and decreased the queue length (by 55 to 67%) at the intersection. Second, making leg intersections wider—without physically building additional road capacity but by changing the stream with higher road hierarchy and higher v/c ratio from a two-way road into a one-way road—has a great impact on enhancing the performance of SCATS. Traffic flows were found to increase between 7 and 106%, and queue lengths were found to markedly decrease between 77 and 100% at all the suggested intersections. Third, the application of SCATS at intersections which are not closely spaced was not effective. Therefore, it is recommended that intersections which are not closely spaced remain under the Fixed Time control. The results and findings from this study provide road authorities in developing countries with an appreciation and enhanced understanding of the factors that influence the performance of traffic management systems in cities with similar characteristics to those in Bandung. These findings will also assist traffic engineers determine the best practices for the implementation of advanced traffic control systems in their cities.

Traffic congestion and delays at signalized intersections remain a challenge in urban mobility. To minimize congestion, adaptive traffic signal control systems have been adopted across the United States. However, for these systems to function at their best, systems require an accurate estimation of traffic states, such as traffic density and queue length. This paper implements a relatively novel method, Physics-Informed Neural Networks (PINNs), for real-time traffic density estimation to enhance adaptive intersection signal control. The methodology leverages PINNs, which integrate both data-driven learning and physical constraints imposed by the Lighthill-Whitham-Richards (LWR) macroscopic traffic flow model. A simulation of a four-way intersection was used to generate realistic spatio-temporal traffic data to evaluate the performance of the model. Separate PINNs models, one trained for each incoming approach using simulation-based spatio-temporal density data, provide segment-level density predictions. These real-time density estimates are then employed within an adaptive traffic signal control algorithm designed to adjust green light phasing based on detected demand. The proposed PINNs control strategy was evaluated through simulation, comparing its performance against the Webster traffic timing method using key metrics such as average vehicle delay at the intersection and average vehicle travel time. The findings show an approximate 18% decrease in average vehicle delay and more than a 6% reduction in average travel time when utilizing adaptive traffic control based on the PINNs method for determining density values. These findings highlight the potential of leveraging PINNs for accurate, real-time traffic state estimation, which can effectively inform and improve the performance of adaptive traffic signal control systems, leading to reduced congestion and enhanced mobility at intersections.

With the rapid development of the economy, urban road congestion has become more serious. The travel times for vehicles are becoming more uncontrollable, making it challenging to reach destinations on time. In order to find an optimal route and arrive at the destination with the shortest travel time, this paper proposes a dynamic shortest travel time path planning algorithm with an overtaking function (DSTTPP-OF) based on a vehicular ad hoc network (VANET) environment. Considering the uncertainty of driving vehicles, the target vehicle (vehicle for special tasks) is influenced by surrounding vehicles, leading to possible deadlock or congestion situations that extend travel time. Therefore, overtaking planning should be conducted through V2V communication, enabling surrounding vehicles to coordinate with the target vehicle to avoid deadlock and congestion through lane changing and overtaking. In the proposed DSTTPP-OF, vehicles may queue up at intersections, so we take into account the impact of traffic signals. We classify road segments into congested and non-congested sections, calculating travel times for each section separately. Subsequently, in front of each intersection, the improved Dijkstra algorithm is employed to find the shortest travel time path to the destination, and the overtaking function is used to prevent the target vehicle from entering a deadlocked state. The real-time traffic data essential for dynamic path planning were collected through a VANET of symmetrically deployed roadside units (RSUs) along the roadway. Finally, simulations were conducted using the SUMO simulator. Under different traffic flows, the proposed DSTTPP-OF demonstrates good performance; the target vehicle can travel smoothly without significant interruptions and experiences the fewest stops, thanks to the proposed algorithm. Compared to the shortest distance path planning (SDPP) algorithm, the travel time is reduced by approximately 36.9%, and the waiting time is reduced by about 83.2%. Compared to the dynamic minimum time path planning (DMTPP) algorithm, the travel time is reduced by around 18.2%, and the waiting time is reduced by approximately 65.6%.

With increasing urbanization, problems such as traffic congestion and environmental pollution have become more pronounced. Alternative modes of transportation such as micromobility (bicycles, e-scooters, e-bikes, segways) have the potential to reduce these problems. This study analyzes the effects of micromobility on the performance of an intersection using a simulation-based approach. A four-arm signalized intersection in Nilüfer, Bursa, is taken as a model, and the impact of micromobility on intersection performance is evaluated in terms of "average vehicle speed", "queue delay", and "vehicle travel time" performance indicators. In the study, the inclusion of micromobility at low levels (2.5% and 5%) improves intersection performance, while at higher levels (7.5% and 10%) this improvement is reversed, resulting in longer travel times and lower speeds. Signal modification has shown an improvement in the performance of the intersection. However, these results suggest the need for special signaling studies for micromobility vehicles at intersections. The study provides important findings for transportation management and policy makers in micromobility planning.

In densely populated cities, severe vehicle congestion is an obstacle due to the massive increase of vehicles and bottleneck of roads. Traffic congestion brings severe economic and environmental hazards. Although it is hard to eliminate, it can be mitigated by finding the occurrence of the congestion well in advance to initiate appropriate control measures. Accurately estimating traffic speed, travel time, and other external factors is mandatory for forecasting congestion levels in a dynamic road network. In recent years, sensor-based traffic detection technologies have evolved to achieve accuracy and safety in intelligent transportation systems (ITS). However, some of them need more reliability, have weak usage in different visibility conditions, are hard to set, and have a high cost. Alternatively, modern navigation systems are developed to find the fastest, alternative routes, travel times, and congestion levels for a given source to destination. These systems use Global Positioning Systems (GPS) data to provide the routing information. Due to inaccurate/ inadequate GPS data samples, sometimes these systems may give misleading information. This work presents Long-Range Wide Area Network (LoRaWAN) architecture to overcome the abovementioned limitations. In our proposed case study, we have used the Dragino LoRaWAn Gps sensor (IN865), air quality sensor (MQ135), temperature and humidity sensor (SHT31), and other sensors to extract direct and indirect factors that influence traffic congestion. Haversine formula and hyper-heuristic-based Encoder-Decoder using Gated Recurrent Units with attention mechanism (ED-GRUAT) are used to estimate the segment-based distance, speed, vehicle travel times, and congestion levels. Our case study helps to calculate accurate traffic speed, travel times, and congestion levels.

Traffic data collection and traffic state estimation are essential for traffic congestion management within smart cities framework. To overcome the inherent shortcomings of single-source data collection techniques, this paper investigates a data fusion method, employing fix and floating (or probe) data types, to estimate traffic states on both freeway and signalized arterial links. The proposed method explores the relationships among the number of probe data, sampling interval of probe vehicles, probe vehicles penetration rate, estimation interval, and traffic density. This paper introduces the definition of generalized penetration rate based on the quotient of travel time of probe vehicles and total travel time. Furthermore, traffic generalized density is estimated with probe data and observed long-term average of actual penetration rate of probe vehicles. Furthermore, real-time penetration rate of probe vehicles is estimated with probe data and density measurements collected by fixed loop detectors. The validity of the proposed method is investigated by extensive tests on NGSIM field data and microsimulation data that reveal accurate performance for real-time traffic state estimation. The proposed methods demonstrate promising extensions for network-wide traffic state estimation.

U.S. transportation agencies have invested more than $300 million in dynamic message sign (DMS) systems for communicating important messages to travelers, including weather conditions, incidents, construction, and homeland security and AMBER alerts. Recent FHWA policy encourages states to use their DMS infrastructure more effectively by displaying reliable travel-time information along freeway corridors. The Oregon Department of Transportation (ODOT), which maintains a freeway surveillance system in the Portland metropolitan area, calculates and reports travel-time estimates derived from inductive loop detector data. These estimates can be reported via 18 DMS and other traveler information systems but are displayed on a limited basis at key junction points during peak periods. Results are presented of an evaluation of ODOT's travel-time reporting capabilities by comparing the ODOT travel-time estimates with probe vehicle (ground truth) travel times. The freeway network was divided into 17 key corridors, and 87 probe vehicle runs were collected under various traffic conditions with handheld Global Positioning System devices. This evaluation used the regional transportation data archive, Portland Regional Transportation Archive Listing, to generate the ODOT travel-time estimates. Probe estimates were compared to travel estimates on the corridors with a paired t-test. The evaluation found that travel times on a majority of links were reasonably accurate under most traffic conditions but were affected by the presence of an incident or by poor detector placement.