Traffic Status Evaluations on an Urban Street Section

The purposes of this study were to investigate accuracy and reliability of travel time information and to assess the effectiveness of probe vehicle in providing traffic information (travel time) under various traffic conditions. A widely used traffic microsimulation model, Paramics V5, was used to generate travel time data on a hypothetical network that was vuilt according to geometrics of corridor, traffic flow parameters and configuration of signalized intersection. Average travel time on links and routes were analyzed for various percentage of probe vehicles (market penetration) and traffic flow conditions (level of congestion) and compared to the ‘true’ average travel time. Moreover, the variation of travel time data obtained from probe vehicles was examined from ‘bootstrapping’ technique where this method of resampling represents the varying condition for probe vehicles. It was found that the plots of probe vehicle average travel time versus ‘tree’ average travel time for link and route case agreed well which imply the obtainment of travel time accuracy by probe vehicles in wide range of traffic volumes (situations). However, the probe vehicle performed less accurately when traffic congestion was forming. A case study of network and traffic condition similar to a real world condition was carried out to demonstrate the quality of travel time data from probe vehicles in selected routes (OD). It was clear that when having all vehicles in the link to be probes, the OD estimates are rather rlilable.

The road traffic state is usually analyzed from a temporal and macroscopic perspective; however, traffic flow parameters, such as density and spacing, can explain the evolution of traffic states from the microscopic perspective and the spatial distribution of vehicles in lanes. In this paper, we attempt to take both temporal and spatial characteristics into consideration simultaneously, and a parameter is defined as the traffic spatiotemporal state of urban road sections to represent the operational status of road traffic, using advanced prediction techniques to estimate its short-term trends. An estimation method is constructed for the traffic spatiotemporal state considering travel times, speeds, and queuing situations from temporal and spatial perspectives. Then, based on Takens’ theorem and the single variable phase space, the phase space of multiple traffic parameters is reconstructed and the chaotic characteristics are analyzed. Next, an LSTM prediction model is constructed based on the phase space reconstruction of multiple variables, and the traffic parameters are predicted by empirical analysis. The results show the proposed estimation method has a significantly improved accuracy. Finally, combined with RFID data, the traffic spatiotemporal state of the case section is calculated, which provides a theoretical basis and practical reference for road traffic state evaluations.

Travel time estimation (TTE) is widely applied for ride dispatching, ride-hailing, and route navigation. There are many factors affecting the travel time of a driver on a given trajectory, including the distance, road type, driving habits, traffic congestion, etc. Existing works fail to model the complex relationships of these factors for TTE. To fill this gap, in this paper, we first analyze how these factors work together in determining the travel time. In particular, the travel time depends on the distance and driving speed on each road segment of the trajectory, where the driving speed depends on the driving habits and the environment, including the static factors like the road type (highway or byway) and speed limit and the dynamic factor like the time of the day and congestion. Among these factors, driving habits and traffic conditions (e.g., jam) are the most difficult ones to model. Second, we propose to learn the driving habits of each driver via meta-learning and estimate the conditions based on the current and historical traffic conditions (via recurrent neural networks) of this road and its connected road segments (via graph convolutional neural network). The experimental results on two real taxi trajectory datasets show that our approach outperforms three state-of-the-art methods significantly.

Driving behavior of L3 autonomous vehicle drivers in fog zones under different traffic flow conditions

People tend to know whether the traffic flow state in their desired route is smooth or the unblocked degree of traffic flow state in real life. To quantitatively measure the unblocked degree of traffic flow states for urban freeway, traffic flow states identification was firstly studied with fuzzy mathematics using speed data of urban freeway in Beijing, which were obtained from video capture technique. In this paper, fuzzy c-means clustering algorithm was used for developing membership functions. Traffic flow states were divided into four types, free flow, coherent moving flow, synchronized flow and jam. And then a computational method of unblocked index of traffic flow states was proposed from the viewpoint of similarity using max-min similarity statistical parameter and weighted summation. Free flow was chosen as the reference traffic flow state for the computational of similarity. Moreover, an entropy function was further developed for describing how the unblocked index change during traffic flow states transformation. Finally empirical analyses were discovered and studied based on field data.

Traffic flow state is a vague concept. It can not be measured off in different traffic flow states by using a specific index, which is in line with the fuzzy clustering characteristics. The Fuzzy C-Means (FCM) algorithm is used to analyze the traffic flow state in fog and non-fog periods in terms of a large amount of data of speed, density, and volume. The traffic flow state is classified into three, four, and six categories, respectively. By comparing and analyzing the traffic flow state in the two periods, results show that the regularity in fog is more obvious than that in non-fog. The traffic flow state in the fog period can be well described by four categories.

Travel time is an important parameter in evaluating the operating efficiency of traffic networks, in assessing the performance of traffic management strategies, and as input to many intelligent transportation systems applications such as advanced traveler information systems. Travel time can be obtained directly from instrumented test vehicles, license plate matching, probe vehicles etc., or from indirect methods such as inductance loop detectors. Because of the widespread deployment of loop detectors, they are one of the most widely used inputs to travel time estimation techniques. There are different methods available to calculate the travel time from loop detector data, such as extrapolation of the point speed values, statistical methods, and models based on traffic flow theory. However, most of these methods fail during the transition period between the normal and congested flow conditions. The present study proposes several modifications to an existing traffic flow theory based model for travel time estimation on freeways, such that the model can estimate travel time for varying traffic flow conditions, including transition period, directly from the loop detector data. Field data collected from the I-35 freeway in San Antonio, Tex., USA, are used for illustrating the results. Automatic vehicle identification data collected from the same location are used for validating the results. Simulated data using CORSIM simulation software are also used for the validation of the model.

The vehicles normally move at their free speeds when it is least impeded due to traffic flow under lean traffic (free flow) conditions. As traffic flow increases, the vehicles cannot sustain their free speeds due to interactions from other vehicles in the traffic stream. In addition to that the vehicles that are operating in the congested traffic conditions will consume more fuel than those operating in steady state traffic conditions for the same average speed. This leads to increase in travel time and fuel consumption of the vehicles and thereby adding to total road user cost (RUC). On the contrary, fuel consumption is also high at very high speeds under free flow traffic flow conditions leading to increase RUC. Considering these scenarios, the travel time and fuel cost of the vehicle due to the congestion and free flow conditions (uncongested) has to be necessarily modelled in order to estimate realistic assessment of RUC on Indian highways. In the present study, the congestion cost relationships have been developed between Congestion Factor, a ratio of cost under congestion and steady state conditions and Volume-Capacity Ratio by considering various vehicle types plying on varying widths of multi-lane highways (four, six and eight lane divided carriageways) through the collection of exhaustive time related and fuel related data. Time related data was collected through questionnaire survey method whereas fuel consumption data was collected using advanced sophisticated fuel flow measuring equipment (V-Box). The developed equations have been successfully applied to demonstrate their applicability in terms of estimating realistic effect of congestion on time and fuel cost by considering a section on NH-2 in Delhi. The analysis shows that the congestion effect is more significant on fuel cost for heavy commercial vehicles whereas it is more prominent on time cost for passenger vehicles. However, the congestion effect on combined fuel and time cost is more significant on multi-axle trucks followed by cars, two wheelers and buses.

Traffic flow state identification is an important foundation for intelligent traffic management and traveler information service systems. By analyzing traffic flow data of expressways and arterial roads in Beijing through following models, such as single quadratic parabola model, segmented traffic flow model and so on, this paper studied the thresholds to identify the traffic state of expressways and arterial roads in Beijing. The results show that it is feasible to use travel speeds for identifying the traffic flow state.

According to the poor adaptive ability of traditional filter algorithm in the estimatio n for traffic state and travel time with Kalman filter, an improved fuzzy adaptive Kalman filtering method was pro posed. The new interest of observation noise was defined, and the fuzzy logic was used to adjust the importance weights of system noise and observation noise through on-line monitoring the interest changes, which changed the trust and utilization degree of the model for the observation information, and this made the filter eventually tend to be stable. To guarantee the real-time performance of system, a direct input - output fuzzy membership function matching method was put forward to take the place of fuzzy reasoning. The method was tested on the urban expressway in Guangzhou by using real-time detection data, and the result show that the traffic state es timation model had better tracking ability than conventional Kalman filter, and results of travel time prediction show that there was a sligh t difference between the prediction value and that of actual observation in free traffic flow state, and the relative error was under 1 5% in traffic congested state. The precision and applicability of this method were acceptable, and it can be used to provide a basis for travel time of urban expressway in traffic control and guidance system.

Real-time traffic status information provides good references for urban traffic control and management. Travel time is easy to understand and widely employed in representing traffic status. With significantly improved positioning accuracy and coverage, trajectory data collected from GPS-equipped probe vehicles have great potential for traffic state recognition. This paper presents a machine learning enabled travel time estimation method based on the GPS-equipped probe vehicles data. This research considers the spatial-temporal relevancy while solving the travel time allocation problem: the travel time of target segment might be associated with its previous travel times and/or the traffic states of nearby relevant segments. After data normalization and network clustering, an artificial neural network (ANN) algorithm considering such spatial-temporal relevancy was conducted to infer the travel time distribution among the traveled segments within one path. Furthermore, a weighted summation of the travel time estimation result from various trajectories was calculated to better represent the segment travel time in one time step. The proposed method was evaluated by evaluating the estimation results with automatic vehicle identification obtained ground truth. The experimental results illustrated that by utilizing the ANN to consider the spatial-temporal relevancy, the proposed method is effective and efficient in estimating the travel time.

Traffic congestion and travel time prediction based on historical congestion maps and identification of consensual days

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.

Travel time is considered more useful to users than other travel-related information such as speed. It is mainly estimated by point or interval detection systems. In this study, the authors investigate the deficiency of these systems in estimating travel times when they are used in isolation, and proposed a fusion algorithm that simultaneously utilises data from both point and interval detection systems. The fusion algorithm is based on the traffic flow and k-nearest neighbourhood (k-NN) models. Specifically, the authors precisely define the so-called the time lag issue in interval detection systems. To overcome this problem, they analysed the travel time variation because of variation in traffic states using fused data from point and interval detection systems. The authors show that the travel time obtained from interval detection systems is renewed by considering the travel time variation and their results show that the proposed algorithm satisfactorily predicts the travel time with the mean absolute percentage errors (MAPE).

Travel time is an important characteristic of traffic conditions in a road network. Up-to-date travel time information is important in dynamic traffic management. Presented are the findings of a recently completed research and evaluation program called DACCORD, regarding the evaluation of tools for online estimation and prediction of travel times by using induction loop detector data. Many methods exist with which to estimate and predict travel time by using induction loop data. Several of these methods were implemented and evaluated in three test sites in France, Italy, and the Netherlands. Both cross-tool and cross-site evaluations have been carried out. Travel time estimators based on induction loop detectors were evaluated against observed travel times and were seen to be reasonably accurate (10 percent to 15 percent root mean square error proportional) across different sites for uncongested to lightly congested traffic conditions. The evaluation period varied by site from 4 to 30 days. Results were seen to diverge at higher congestion levels: at one test site, congestion levels were seen to have a strong negative impact on estimation accuracy; at another test site, accuracy was maintained even in congested conditions.