Traffic State Estimation Research Articles

Learning Traffic Flow Dynamics Using Random Fields

This paper presents a mesoscopic traffic flow model that explicitly describes the spatio-temporal evolution of the probability distributions of vehicle trajectories. The dynamics are represented by a sequence of factor graphs, which enable learning of traffic dynamics from limited Lagrangian measurements using an efficient message passing technique. The approach ensures that estimated speeds and traffic densities are non-negative with probability one. The estimation technique is tested using vehicle trajectory datasets generated using an independent microscopic traffic simulator and is shown to efficiently reproduce traffic conditions with probe vehicle penetration levels as little as 10\%. The proposed algorithm is also compared with state-of-the-art traffic state estimation techniques developed for the same purpose and it is shown that the proposed approach can outperform the state-of-the-art techniques in terms reconstruction accuracy.

A Real-Time Queue Length Estimation Method Based on Probe Vehicles in CV Environment

The real-time traffic status estimation in urban signalized intersections is highly valuable for modern traffic control and management. This paper presents a real-time queue length estimation method based on probe vehicles' data in the connected vehicle (CV) environment. The probe data are used to identify the stopping states of CVs. Based on this, a queue length time series referring to the stopping time and the positions of CVs is built for describing the queuing process at an intersection. Considering the statistical average traffic rate, queue length time series in historical cycles, and the stopping states for real-time CV arrival features in the current cycle, the critical queuing time is forecasted based on the linear fitting method and the real-time queue length is estimated based on the Markov model. The overall scheme is thoroughly tested and demonstrated in a realistic scenario at different penetration rates. Under different conditions, the stationarity of the queue length series is tested by the augmented Dickey-Fuller. Two Markov models based on the transition matrices of the current cycle and both the current and historical cycles are verified, respectively. The results demonstrate the high accuracy in the real-time queue length estimation, and the proposed method shows good performance in handling the randomness, especially when the CV penetration rate is low.

An Infrastructure-Assisted Crowdsensing Approach for On-Demand Traffic Condition Estimation

With the widespread use of smartphones and the continuous increase of their capabilities, a new sensing paradigm has emerged: mobile crowdsensing. The concept of crowdsensing implies the reliance on the crowd to perform sensing tasks and collect data about a phenomena of interest. Due to the benefits it offers in terms of time and cost savings in terms of sensors' deployment and maintenance, the concept of mobile crowdsensing is now being adopted in the area of intelligent transportation. In this context, drivers or pedestrians equipped with sensor enabled smartphones collaborate to collect information about roads and traffic. However, the current solutions proposed for the use of crowdsensing for the collection of traffic related data adopt an opportunistic continuous sensing approach, which entails high resource consumption on the server and mobile device side, a high communication overhead, while offering little control of the users over the sensing activity. In this paper, we address these limitations by proposing an infrastructure-assisted on-demand crowdsensing approach for the real time detection and prediction of traffic conditions in an area of interest. Our approach combines the strengths of mobile crowdsensing, with the support of the mobile infrastructure, a multi-criteria algorithm for the participants' selection, and a deductive rule-based model for traffic condition estimation. The proposed solution was validated through a combination of prototyping and simulated traffic traces, and the results show a significant reduction in terms of resources' consumption and network overhead, while reaching high accuracy for the traffic condition estimation.

Freeway traffic state estimation: A Lagrangian-space Kalman filter approach

Recent researches have shown the potential benefits of using Lagrangian coordinates in modeling mobile sensor data such as GPS, Bluetooth, Wi-Fi, and cellphone probe data. Research shows the numerical accuracy and convenience of Lagrangian traffic flow models in traffic state estimation. In this paper, a new traffic state estimation model by using Lagrangian-space Kalman filter is proposed based on the travel time transition model (TTM). The proposed methodology reformulates the TTM model into a state-space form to fit the Kalman filter framework. The corresponding state-updating matrices for various traffic conditions are also provided. A numerical experiment is conducted based on a simulation model calibrated with the field loop detector data on IH-894 in Milwaukee, Wisconsin for model evaluation. The proposed TTM-based method is compared with a CTM-based Kalman filter estimator on Eulerian coordinate under different penetration rates of the input Bluetooth, Wi-Fi, or Cellular probe vehicle data in which vehicles are re-identified between two consecutive physical or virtual readers. The evaluation results indicate that TTM-based estimation model performs well especially during congestion and can track traffic breakdowns and recovery effectively. The TTM-based estimator outperforms CTM-based methods at all penetration rates levels. Furthermore, the 4% penetration rate is found to be a threshold beyond which TTM-based estimation results improve significantly. With increased penetration rates, the TTM-based model can achieve a mean absolute percentage error around 10%; while CTM-based model remains higher than 13%.

A constrained filtering algorithm for freeway traffic state estimation

ABSTRACTA real-time traffic state estimation algorithm is developed and applied to a freeway. The evolution of the traffic is defined by a second-order macroscopic model which computes, for each section of the freeway, the density, and the mean speed according to several nonlinear equations. Different extensions of the Kalman method were already applied to this model, though none of them considers the natural constraints in the state variables. In this work, a new method that incorporates those natural constraints is applied to the macroscopic model obtaining better results. To validate the proposed method, a simulation over a freeway section was made using two different tools: the macroscopic simulator called METANET and the microscopic simulator called SUMO. Promising results were obtained using both approaches.

Estimation of Urban Traffic State With Probe Vehicles

We present in this paper a method to estimate urban traffic state with communicating vehicles. Vehicles moving on the links of the urban road network form queues at the traffic lights. We assume that a proportion of vehicles are equipped with localization and communication capabilities, and name them probe vehicles. First, we propose a method for the estimation of the penetration ratio of probe vehicles, as well as the vehicles arrival rate on a link. Moreover, we show that turn ratios at each junction can be estimated. Second, assuming that the turn ratios at each junction are given, we propose an estimation of the queue lengths on a 2-lanes link, by extending a 1-lane existing method. Our extension introduces vehicles assignment onto the lanes. Third, based on this approach, we propose control laws for the traffic light and for the assignment of the arriving vehicles onto the lane queues. Finally, numerical simulations are conducted with Veins framework that bi-directionally couples microscopic road traffic and communication simulators. We illustrate and discuss our propositions with the simulation results.

A Deep Generative Adversarial Architecture for Network-Wide Spatial-Temporal Traffic-State Estimation

This study proposes a deep generative adversarial architecture (GAA) for network-wide spatial-temporal traffic-state estimation. The GAA is able to combine traffic-flow theory with neural networks and thus improve the accuracy of traffic-state estimation. It consists of two Long Short-Term Memory Neural Networks (LSTM NNs) which capture correlation in time and space among traffic flow and traffic density. One of the LSTM NNs, called a discriminative network, aims to maximize the probability of assigning correct labels to both true traffic-state matrices (i.e., traffic flow and traffic density within a given spatial-temporal area) and the traffic-state matrices generated from the other neural network. The other LSTM NN, called a generative network, aims to generate traffic-state matrices which maximize the probability that the discriminative network assigns true labels to them. The two LSTM NNs are trained simultaneously such that the trained generative network can generate traffic matrices similar to those in the training data set. Given a traffic-state matrix with missing values, we use back-propagation on three defined loss functions to map the corrupted matrix to a latent space. The mapping vector is then passed through the pre-trained generative network to estimate the missing values of the corrupted matrix. The proposed GAA is compared with the existing Bayesian network approach on loop detector data collected from Seattle, Washington and that collected from San Diego, California. Experimental results indicate that the GAA can achieve higher accuracy in traffic-state estimation than the Bayesian network approach.

Traffic state estimation using stochastic Lagrangian dynamics

This paper proposes a new stochastic model of traffic dynamics in Lagrangian coordinates. The source of uncertainty is heterogeneity in driving behavior, captured using driver-specific speed-spacing relations, i.e., parametric uncertainty. It also results in smooth vehicle trajectories in a stochastic context, which is in agreement with real-world traffic dynamics and, thereby, overcoming issues with aggressive oscillation typically observed in sample paths of stochastic traffic flow models. We utilize ensemble filtering techniques for data assimilation (traffic state estimation), but derive the mean and covariance dynamics as the ensemble sizes go to infinity, thereby bypassing the need to sample from the parameter distributions while estimating the traffic states. As a result, the estimation algorithm is just a standard Kalman–Bucy algorithm, which renders the proposed approach amenable to real-time applications using recursive data. Data assimilation examples are performed and our results indicate good agreement with out-of-sample data.

Macroscopic traffic state estimation using relative flows from stationary and moving observers

This article presents a procedure to estimate the macroscopic traffic state in a pre-defined space-time mesh using relative flow data collected by stationary and moving observers. The procedure consist of two consecutive and independent processes: (1) estimate point observations of the cumulative vehicle number in space-time, i.e., N(x, t), based on relative flow data from the observers and (2) estimate flow and density in a pre-define space-time mesh based on the point observations of N. In this paper, the principles behind the first process are explained and a methodology (the Point-Observations N (PON) estimation methodology) is introduced for the second process. This methodology does not incorporate information in the form of a traffic flow model or historical data. To evaluate this performance and improve our understanding of the methodology, a microscopic simulation study is conducted. The estimation performance is effected by the homogeneity and stationarity of traffic in estimation area and in the sample area. In case of large changes in traffic conditions, e.g., from free-flow to congestion or stop-and-go waves, a better sampling resolution will improve localizing these changes in space and time and hence improve the estimation performance. In the simulation study, the proposed methodology is also compared with estimates based on loop-detector data. This indicates that the combination of the proposed methodology and data yields an alternative for existing combinations of methodology and data. Especially, in terms of density estimation the introduced methodology shows promising results.

A data fusion approach for real-time traffic state estimation in urban signalized links

Real-time estimation of the traffic state in urban signalized links is valuable information for modern traffic control and management. In recent years, with the development of in-vehicle and communication technologies, connected vehicle data has been increasingly used in literature and practice. In this work, a novel data fusion approach is proposed for the high-resolution (second-by-second) estimation of queue length, vehicle accumulation, and outflow in urban signalized links. Required data includes input flow from a fixed detector at the upstream end of the link as well as location and speed of the connected vehicles. A probability-based approach is derived to compensate the error associated with low penetration rates while estimating the queue tail location, which renders the proposed methodology more robust to varying penetration rates of connected vehicles. A well-defined nonlinear function based on traffic flow theory is developed to attain the number of vehicles inside the queue based on queue tail location and average speed of connected vehicles. The overall scheme is thoroughly tested and demonstrated in a realistic microscopic simulation environment for three types of links with different penetration rates of connected vehicles. In order to test the efficiency of the proposed methodology in case that data are available at higher sampling times, the estimation procedure is also demonstrated for different time resolutions. The results demonstrate the efficiency and accuracy of the approach for high-resolution estimation, even in the presence of measurement noise.

State-Space Model for Traffic State Estimation of a Two-Dimensional Network

This study proposes a real-time monitoring method for two-dimensional (2D) networks via the fusion of probe data and a traffic flow model. In the Great East Japan Earthquake occurring on March 11, 2011, there was major traffic congestion as evacuees concentrated in cities on the Sanriku Coast. A tragedy occurred when a tsunami overtook the stuck vehicles. To evacuate safely and efficiently, the state of traffic must be monitored in real time on a 2D network, where all networks are linked. Generally, the traffic state is monitored only at observation points. However, observation data presents the risk of errors. Additionally, in the estimated traffic state of the 2D network, unlike non-intersecting road sections (i.e., one-dimensional), it is necessary to model user route choice behavior and origin/destination (OD) demand to input in the model. Therefore, in this study, we develop a state-space model that assimilates vehicle density and divergence ratio data obtained from probe vehicles in a traffic flow model that considers route choice. Our state-space model considers observational errors in the probe data and can simultaneously estimate traffic state and destination component ratio of OD demand. The result of simulated traffic model verification shows that the proposed model has good congestion estimation precision in a small-scale test network.

Traffic State Estimation of Signalized Intersections Based on Stacked Denoising Auto-Encoder Model

To solve the problem of fuzziness and uncertainty of traffic states in signalized intersection, a method was proposed for estimating traffic condition based on stacked de-noising auto-encoder model. The simulation data and empirical data were used to train the model, and the K-means clustering method was used to determine the traffic state thresholds and the data were divided into three categories based on the threshold values. Relevant features based on the reconstruction theory of de-noising auto-encoder were automatically extracted, and unsupervised greedy layer-wise pre-training and supervised fine-tuning were utilized to train the deep auto-encoder network, so that it had good robust performance on obtaining the traffic state characters with low quality in the complex environment. From the experimental results, the proposed method obtains an accuracy of 91.5% in simulation data and 88% in empirical data, which is better by 7.1% than using decision tree model.

A Low-Cost GPS-Data-Enhanced Approach for Traffic Network Evaluations

Evaluating traffic networks is crucial for administration of roadway systems, to better address congestion, safety, and air quality issues around the globe. However, challenges in implementation abound, including major investment costs, large and dynamic data streams and a need for real-time response. Recently developed Global Positioning System (GPS) data loggers are a promising tool for traffic monitoring, thanks to their low cost, ready availability on smartphones, and ability to simultaneously track many travelers and vehicles, relative to expensive, built-in traffic GPS. GPS data from many travelers provides real-time details of traffic conditions and can improve active traffic management using various big-data analytics. We demonstrate how to couple such GPS data to estimate relative roadway speeds in order to improve system management. By analyzing real-time traffic surveillance software with high data coupling and concurrent processing, a new coupling method for real-time traffic evaluation is proposed. Experimental results show efficient coupling of all available GPS data with road condition can improve traffic state estimation accuracy. This new method may increase matching accuracy by more than 1 m in vehicle position. Over 98% of GPS data can be successfully matched to service routes when the low-cost GPS devices are used to detect real-time traffic conditions. The results of traffic network evaluation could well serve as a driving assistant for connected and autonomous vehicles (C/AVs) and other traffic operations.

Location‐dependent sensing data collection and processing mechanism in vehicular network

AbstractWith the promotion of the Internet of Things, in which a growing number of objects in everyday life are able to communicate with each other, crowdsensing has attracted public attention. Among different devices, vehicles with various sensors can perform the traffic data collection tasks released by the traffic center, which is helpful for monitoring road conditions. Thus, we use crowdsensing between vehicles to improve the precision of traffic state estimation. We also propose a location‐dependent sensing task assignment mechanism for traffic data collection and a multisource data fusion model for traffic data processing in a vehicular network. First, we establish a mathematical model for the sensing task assignment considering the vehicle's time budget constraint, location, and collection task requirements. We then propose a task assignment algorithm consisting of determining the order for vehicle allocation and scheduling the optimal collection path for each vehicle, which aims to achieve maximum platform utility. Furthermore, we put forward a fusion model, including spatial fusion and temporal fusion, to better process the collected data. We use a power average operator for the spatial fusion and a temporal correlation–based data compression algorithm for the temporal fusion. The obtained simulation results validate the accuracy and correctness of our approach.

Traffic State Estimation Using Connected Vehicles and Stationary Detectors

Real-time traffic state estimation is of importance for efficient traffic management. This is especially the case for traffic management systems that require fast detection of changes in the traffic conditions in order to apply an effective control measure. In this paper, we propose a method for estimating the traffic state and speed and density, by using connected vehicles combined with stationary detectors. The aim is to allow fast and accurate estimation of changes in the traffic conditions. The proposed method does only require information about the speed and the position of connected vehicles and can make use of sparsely located stationary detectors to limit the dependence on the infrastructure equipment. An evaluation of the proposed method is carried out by microscopic traffic simulation. The traffic state estimated using the proposed method is compared to the true simulated traffic state. Further, the density estimates are compared to density estimates from one detector-based method, one combined method, and one connected-vehicle-based method. The results of the study show that the proposed method is a promising alternative for estimating the traffic state in traffic management applications.

Traffic state estimation using small imaging satellites and connected vehicles

Abstract Small imaging satellites (SISs), which has attracted attention in remote sensing field recently, would provide a novel type of data for traffic state estimation (TSE): that is, spatial distribution of every cars in anywhere on our planet with relatively short time interval. This nature is particularly useful to complement connected vehicle (CV) data, which is sampled but time-continuous data. This paper proposes an ensemble Kalman filter-based TSE method using SIS and CV data. The proposed method endogenously estimates the fundamental diagram of traffic flow and penetration rate of CVs based only on SIS and CV data, making the method completely free from roadside detectors. The accuracy of the proposed method is verified by numerical simulation.

Stochastic Link Flow Model for Signalized Traffic Networks with Uncertainty in Demand

In order to investigate the stochastic features in urban traffic dynamics, we propose a Stochastic Link Flow Model (SLFM) for signalized traffic networks with demand uncertainties. In the proposed model, the link traffic state is described using four different link state modes, and the probability for each link state mode is determined based on the stochastic link states. The SLFM model is expressed as a finite mixture approximation of the link state probabilities and the dynamic link flow models for all the four link state modes. Using data from microscopic traffic simulator SUMO, we illustrate that the proposed model can provide a reliable estimation of the link traffic states, and as well as good estimations on the link state uncertainties propagating within a signalized traffic network.

A Novel Approach to Estimate Freeway Traffic State: Parallel Computing and Improved Kalman Filter

This paper presents a novel approach for freeway traffic state estimation. Although there is currently a wide variety of estimation methods, new designs and technologies can still be created and implemented to improve the accuracy and time efficiency. In this study, a parallel computing framework is developed. The parallel computing framework uses a genetic algorithm process to calibrate the parameters of the traffic model based on the freeway traffic data once an hour. Meanwhile, the framework uses a Kalman filter algorithm process to optimize the traffic model results with the real-time freeway traffic data. Under the framework, the operations of the two processes will not interfere with each other, thus reducing the time it takes to estimate, increasing the efficiency. Furthermore, an improved Kalman filter algorithm is proposed. The algorithm optimizes the traffic model results by balancing the ratio of detector measurements to model results based on their variances, instead of using the Taylor series expansion. Therefore, time efficiency and accuracy of the Kalman filter algorithm are improved. The effectiveness of the approach is evaluated using real field data. Experiments have shown that this approach has high real-time tracking accuracy, and is faster and more accurate than the extended Kalman filter. Results also indicated that the estimation accuracy can be enhanced by accessing additional data sources.

Analysis on Sag Bottleneck Phenomena Based on Multiclass Traffic State Estimation

Abstract This study proposes a novel technique for analyzing traffic dynamics based on multiclass traffic state estimation. One of the most common causes of bottlenecks on Japan’s roads are sags. Considerable scientific attention has been paid to the bottleneck phenomena at sags in terms of both their microscopic and macroscopic aspects. However, the mechanisms of traffic breakdown at sags are not understood in detail yet. This paper presents a data assimilation system using a particle filter in which online observations from fixed detectors and probe vehicles are combined with multiclass traffic flow simulations to analyze the traffic dynamics that contribute to congestion at sags. The application of a particle filter enables the monitoring of the hidden traffic state described by the unobservable parameters of traffic flow models. On the application of this method to an existing sag bottleneck section, we found that i) the estimation results are a good fit to observation data from both fixed detectors and probes, ii) the integrated use of multiple data source enables estimation accuracy to be improved, iii) the traffic capacity of the upgrade section is lower than that of the other sections and this tendency is more marked for heavy vehicles than for regular vehicles.

Cooperative Driving and Lane Changing Modeling for Connected Vehicles in the Vicinity of Traffic Signals: A Cyber-Physical Perspective

The vicinity of traffic signals is one of the most critical areas in road systems. New information technology paradigms like vehicle-to-vehicle and vehicle-to-infrastructure communication are applied to improve traffic operations at intersections; for example, a typical cyber-physical system enables efficient traffic state estimation and traffic modeling. A new model of vehicle cooperative driving under a typical scenario vicinity of traffic signals and Vehicle to X environment was proposed in this paper. Based on the intelligent driver model, the model planned trajectories for vehicles in the vicinity of traffic signals in advance to reduce stopping frequency and travel time and improve the throughput of the road according to traffic conditions, such as signal cycle state, the distance to traffic signals, and the situation regarding adjacent vehicles. In accordance with the relationship between the host vehicle and the surrounding vehicles, the model also planed the cooperative lane changing strategy in this scenario to improve safety and comfort in the process of lane changing. A simulation experiment compared the proposed model with the traditional intelligent driver model, and analyzed its performance in different traffic conditions. The feasibility and superiority of the model were confirmed.