Traffic Breakdown Research Articles

Modeling curves and derivatives as predictors for traffic breakdown probabilities

Modeling curves and derivatives as predictors for traffic breakdown probabilities

Hidden Markov Model-Based Dynamic Hard Shoulders Running Strategy in Hybrid Network Environments

With the development of vehicle-road network technologies, the future traffic flow will appear in the form of hybrid network traffic flow for a long time. Due to the change in traffic characteristics, the current hard shoulder running strategy based on traditional traffic characteristics cannot effectively serve the hybrid network traffic flow scenario, and will even lead to the further deterioration of traffic congestion. In order to propose a hard shoulder running strategy suitable for a hybrid network environment, a traffic breakdown prediction method based on a hidden Markov model was established. Secondly, the characteristics of traffic breakdown in a hybrid network environment were analyzed. Finally, based on the traffic breakdown characteristics in a hybrid network environment, a dynamic hard shoulder running method based on the hidden Markov model was proposed. The effectiveness of HMMD-HSR was verified by simulation and comparison with HMM-HSR, LMD-HSR, and N-HSR. The simulation results show that the HMMD-HSR proposed in this paper can improve operation efficiency and reduce travel time in a congested expressway.

Exploring traffic breakdown with vehicle-level data

Traffic breakdown involves complicated vehicle behavior, and is regarded as a probabilistic event with macroscopic traffic data from fixed detectors. However, with the advent of connected vehicle technologies, traffic data will develop to the vehicle-level, such as trajectory data, and provide unprecedented opportunities to better understand various traffic phenomena. Using novel vehicle-level data from drone videos, this research explores the traffic breakdown by interactions between vehicles. Specifically, this paper categorizes the typical behavior of individual vehicles that causes or resolves traffic congestion. Based on the behavior that occurred in the extensive time–space domain, this research develops a novel measurement method to quantify the behavior as temporal delay or spatial residual. With real-world data, this research verifies the vehicle-level congestion can be estimated from specific vehicle behavior, and their aggregation could describe the change in flow speed or traffic breakdown. The proposed framework can address the traffic phenomenon better when more extensive data is available.

Model of driver overacceleration causing breakdown in vehicular traffic.

We introduce a mathematical approach for the description of driver overacceleration in a microscopic traffic flow model. The model, in which no driver overreaction occurs, explains the empirical nucleation nature of traffic breakdown.

Physics of automated-driving vehicular traffic.

We have found that phase transitions occurring between three traffic phases [free flow (F), synchronized flow (S), and wide moving jam (J)] determine the spatiotemporal dynamics of traffic consisting of 100% automated-driving vehicles moving on a two-lane road with an on-ramp bottleneck. This means that three-phase traffic theory is a common framework for the description of traffic states independent of whether human-driving or automated-driving vehicles move in vehicular traffic. To prove this, we have studied automated-driving vehicular traffic with the use of classical Helly's model [Proceedings of the Symposium on Theory of Traffic Flow (Elsevier, Amsterdam, 1959), pp. 207-238] widely applied for automated vehicle motion. Although dynamic rules of the motion of automated-driving vehicles in a road lane are qualitatively different from those of human-driving vehicles, we have revealed that traffic breakdown (F→S transition) at the bottleneck exhibits the nucleation nature, which was observed in empirical field data measured in traffic consisting of 100% human-driving vehicles. The physics of the nucleation nature of the F→S transition in automated-driving traffic is associated with a discontinuity in the rate of lane-changing that causes the discontinuity in the rate of over-acceleration. This discontinuous character of over-acceleration leads to both the existence and self-maintaining of synchronized flow at the bottleneck in automated-driving vehicular traffic as well as to the existence at any time instant of a range of highway capacities between some minimum and maximum capacities. Within the capacity range, an F→S transition can be induced; however, when the maximum capacity is exceeded, then after some time-delay a spontaneous F→S transition occurs at the bottleneck. The phases F, S, and J can coexist each other in space and time.

Prediction of Freeway Traffic Breakdown Using Artificial Neural Networks

Traffic breakdown is the transition of traffic flow from an uncongested state to a congested state. During peak hours, when a large number of on-ramp vehicles merge with mainline traffic, it can cause a significant drop in speed and subsequently lead to traffic breakdown. Therefore, ramp meters have been used to regulate the traffic flow from the ramps to maintain stable traffic flow on the mainline. However, existing traffic breakdown prediction models do not consider on-ramp traffic flow. In this paper, an algorithm based on artificial neural networks (ANN) is developed to predict the probability of a traffic breakdown occurrence on freeway segments with merging traffic, considering temporal and spatial correlations of the traffic conditions from the location of interest, the ramp, and the upstream and downstream segments. The feature selection analysis reveals that the traffic condition of the ramps has a significant impact on the occurrence of traffic breakdown on the mainline. Therefore, the traffic flow characteristics of the on-ramp, along with other significant features, are used to build the ANN model. The proposed ANN algorithm can predict the occurrence of traffic breakdowns on freeway segments with merging traffic with an accuracy of 96%. Furthermore, the model has been deployed at a different location, which yields a predictive accuracy of 97%. In traffic operations, the high probability of the occurrence of a traffic breakdown can be used as a trigger for the ramp meters.

Traffic Breakdown Probability Estimation for Mixed Flow of Autonomous Vehicles and Human Driven Vehicles.

Automated vehicles are expected to greatly boost traffic efficiency. However, how to estimate traffic breakdown probability for the mixed flow of autonomous vehicles and human driven vehicles around ramping areas remains to be answered. In this paper, we propose a stochastic temporal queueing model to reliably depict the queue dynamics of mixed traffic flow at ramping bottlenecks. The new model is a specified Newell's car-following model that allows two kinds of vehicle velocities and first-in-first-out (FIFO) queueing behaviors. The jam queue join time is supposed to be a random variable for human driven vehicles but a constant for automated vehicles. Different from many known models, we check the occurrence of significant velocity drop along the road instead of examining the duration of the simulated jam queue so as to avoid drawing the wrong conclusions of traffic breakdown. Monte Carlo simulation results show that the generated breakdown probability curves for pure human driven vehicles agree well with empirical observations. Having noticed that various driving strategy of automated vehicles exist, we carry out further analysis to show that the chosen car-following strategy of automated vehicles characterizes the breakdown probabilities. Further tests indicate that when the penetration rate of automated vehicles is larger than 20%, the traffic breakdown probability curve of the mixed traffic will be noticeably shifted rightward, if an appropriate car-following strategy is applied. This indicates the potential benefit of automated vehicles in improving traffic efficiency.

An Automated Process for Identification of Bottlenecks in the Traffic System Using Large Data Sets

Traffic breakdowns are frequently observed phenomena on roads in larger cities, especially during peak hours. Locations along a road stretch with frequently observed breakdowns are known as recurrent bottlenecks. Knowledge about bottleneck locations are important for improvement of traffic conditions at these locations. Bottleneck locations can be identified through manual inspection of data. However, due to the comprehensive amount of data that are available today, it becomes impractical to manually identify breakdowns and instead, an automated process can be used. We propose such an automated method. The proposed method is applied to a use case south of Stockholm in Sweden. One month of data collected at densely spaced detectors is used to investigate the sensitivity of the parameter settings. After calibration of the threshold values, 100% of the larger breakdowns and 40% of the medium size breakdowns are identified. Smaller breakdowns, not giving significant impact on the traffic conditions, are only detected in 10%–20% of the cases. Thereafter, the method is applied to 1 year of data to illustrate the applicability of the method on a larger data set. The results show that the method is promising to use for identification of recurrent bottleneck locations.

Freeway Congestion Management With Reinforcement Learning Headway Control of Connected and Autonomous Vehicles

Adaptive cruise control (ACC) systems are increasingly offered in new vehicles in the market today, and they form a core building block for future full autonomous driving. ACC systems allow vehicles to maintain a desired headway to a leading vehicle automatically. Recent research demonstrates that (1) shorter headways lead to higher throughput, and (2) the effective use of ACC can improve traffic flow by adapting the desired time headway in response to changing traffic conditions. In this paper we show that, although shorter headways result in higher capacity, flow breakdown still occurs if traffic densities at bottlenecks are allowed to exceed the critical density. Therefore, dynamic traffic control near bottlenecks is still necessary to avoid bottleneck activation and capacity loss. We propose an adaptive reinforcement learning (RL) headway controller that uses ACC headways to optimize traffic flow and minimize delay. Based on state measurements, the controller dynamically assigns an optimal headway value for each freeway section within a control cycle. In a freeway simulation example, we first demonstrate that different nondynamic headway assignment strategies failed to avoid congestion and traffic breakdown. We then present a dynamic headway control strategy based on deep reinforcement learning (DRL) that adapts the desired headway according to the changing traffic conditions on both the freeway and the ramp to effectively maximize traffic flow and minimize system delay. We quantitatively demonstrate that our DRL dynamic headway control strategy improved traffic and reduced system delay by up to 57% compared with the examined nondynamic headways.

Probabilistic traffic breakdown forecasting through Bayesian approximation using variational LSTMs

This paper proposes a framework for short-term traffic breakdown probability calculation using a Variational LSTM neural network model. Considering that traffic breakdown is a stochastic event, this forecast framework was devised to produce distributions as outputs, which cannot be achieved using standard deterministic recurrent neural networks. Therefore, the model counts on the robustness of neural networks but also includes the stochastic characteristics of highway capacity. The framework consists of three main steps: (i) build and train a probabilistic speed forecasting neural network, (ii) forecast speed distributions with the trained model using Monte Carlo (MC) dropout, and therefore perform Bayesian approximation, and (iii) establish a speed threshold that characterizes breakdown occurrence and calculate breakdown probabilities based on the speed distributions. The proposed framework produced an efficient control over traffic breakdown occurrence, can deal with many independent variables or features, and can be combined with traffic management strategies.

Predicting traffic breakdown on expressways using linear combination of vehicle detector data

Traffic congestion is closely associated with various social issues that must be solved urgently. With the recent advancement of machine learning technologies, diverse methods for predicting traffic congestion have been developed. Specifically, traffic prediction using deep learning can provide highly accurate performance. Nevertheless, several difficulties remain because of the complexity of deep learning models: particularly, they require large amounts of data and computational power. For this study, we strive to achieve traffic prediction precision using a simple linear model. Instead of improving complex models, we select training data appropriately with a linear model and then verify the feasibility of prediction by exploring “data complexity”. The prediction results imply that the linear model is as precise as deep learning even with fewer number of data and parameters. We use actual data from expressways collected using detectors.

Statistical physics of the development of Kerner's synchronized-to-free-flow instability at a moving bottleneck in vehicular traffic.

With the use of simulations of a stochastic microscopic traffic model in the framework of the three-phase traffic theory, we have revealed the statistical physics of a traffic flow instability with respect to a transition from synchronized flow (S) to free flow (F) (Kerner's S→F instability) at a moving bottleneck (MB) occurring through a slow-moving vehicle in vehicular traffic. We have found that the S→F instability can occur at the MB more frequently than at an on-ramp bottleneck. From a comparison of the occurrence of the S→F instability at the MB and on-ramp bottleneck at the same probability of traffic breakdown and the same flow rate it has been found that, whereas the frequency of the S→F instability at the on-ramp bottleneck barely changes, the larger the velocity of the MB, the more frequently the S→F instability occurs at the MB. Contrarily, when the MB velocity decreases considerably, then rather than the S→F instability, in synchronized flow at the MB the classical traffic flow instability leading to the emergence of wide-moving jams (S→J instability) occurs. It has been found that the physics of the intensification of the S→F instability at the MB with the increase in the MB velocity is associated with the increase in the mean space gap (mean time headway) between vehicles in synchronized flow. For this reason, when the MB velocity increases, there is an MB velocity at which the S→F instability dominates the S→J instability: The MB velocity influences considerably on the competition between the S→F and classical traffic flow instabilities in synchronized flow.

Hierarchical Optimal Maneuver Planning and Trajectory Control at On-Ramps With Multiple Mainstream Lanes

Connected Automated Vehicles (CAVs) have the potential to improve traffic operations when they cooperatively maneuver in merging sections. State-of-the-art approaches in cooperative merging either build on heuristics solutions or prohibit mainline CAVs to change lane on multilane highways. This paper proposes a hierarchical cooperative merging control approach that ensures collision-free and traffic-efficient merging through the interaction of a maneuver planner and an operational trajectory controller. The planner predicts future vehicular trajectories, including acceleration trajectories and time instants when lane changes start, in a long horizon up to 50 seconds with a linear prediction model. It establishes the optimal dynamic vehicle sequence in each lane by minimizing predicted traffic disturbances that can propagate upstream and lead to traffic breakdown. During the process, mainline vehicles may change lane to facilitate the on-ramp merging, albeit with a higher ego cost. The operational controller follows the established instructions from the planner and regulates vehicular trajectories with model predictive control in a shorter horizon of 6 seconds. The performance of the designed hierarchical cooperative merging control approach was compared to a cooperative merging method utilizing widely used first-in-first-out rule to establish merging sequences and the same operational controller to generate vehicular trajectories. Systematic comparison shows that the proposed approach consistently results in less disturbances during merging under 528 different scenarios with different traffic states, initial vehicular states, and desired time gap settings. On average, a decrease of 39.18% in disturbances was observed.

Chain reaction of traffic breakdowns in coupled-cycle networks

We present a dynamic model for major traffic jams in urban-scale networks. We investigate the traffic breakdown in the directed network consisted of cycle graphs when an intersection is closed to vehicles. We show how the traffic breakdown propagates from cycle graph to cycle graph. The deadlock (jam) of vehicles is induced by the closed intersection, a local breakdown occurs at an early stage, and the breakdown propagates toward the whole network. The macroscopic dynamic equations of vehicular densities are derived by using the speed-matching model. The densities and currents (flows) on all roads are obtained numerically. We show that the chain reaction of traffic breakdowns occurs when a density is higher than a critical value, while it does not propagate over the network at lower density than the critical value. The chain reaction of traffic breakdowns induces the major traffic jam. The jamming transition between free traffic and major traffic jam is found in the traffic network.

Heterogeneous traffic flow characteristics on the highway with a climbing lane under different truck percentages: The framework of Kerner’s three-phase traffic theory

Nowadays, in order to improve the traffic conditions in mountainous areas, the demand of climbing lanes is increasing. In this paper, car–truck heterogeneous traffic flow characteristics on the highway with a climbing lane are studied up based on an improved Kerner–Klenov–Schreckenberg–Wolf (KKSW) cellular automation (CA) model. To depict the speed characteristics of vehicle’s climbing and lane-changing behaviors, additional evolution rules for trucks are introduced into the KKSW model. Specifically, the motion of trucks climbing on the slope is described as a deceleration process and an equilibrium process. Furthermore, we define the probability of a truck driver using the climbing lane as a function of the observed real-time occupancy on it. We have found that in accordance with Kerner’s theory, traffic breakdown is an F→S transition that occurs in metastable free flow with respect to the F→S transition. When the traffic demand increases, the bottleneck appears due to the merging of trucks from the climbing lane to the inner lane. Localized synchronized flow patterns (LSP) emerge on both the inner and outer lanes. When traffic demand increases further, wide moving jams emerge in synchronized flow and general pattern (GP) appears on the inner lane, whereas synchronized flow patterns remain on the outer lane only. In addition, the macroscopic traffic flow characteristics under varying truck percentages are analyzed. We have found that the improving effect of climbing lane on traffic efficiency is closely related to the truck percentage.

Influence of tidal lane on traffic breakdown and spatiotemporal congested patterns at moving bottleneck in the framework of Kerner’s three-phase traffic theory

With tidal traffic becoming an important feature of urban traffic, tidal lane is becoming more and more important. The influence of tidal lane on traffic flow is studied by many scholars. Existing tidal lane control methods generally select flow of lane or density of vehicles as the determining factors for decide the opening time and direction of the tidal lane, which is not predictive actually. In this article, a bilateral six-lanes motorway model with tidal lane model is established to study the positive influence of tidal lane on relieving upstream congestion induced by moving bottleneck and the negative effect of moving bottleneck on tidal lane. This model is based on the well-known KKSW (Kerner–Klenov–Schreckeneberg–Wolf) CA (cellular automaton) model, proposed to simulate the effect of tidal lane on adjacent lanes. Through numerical simulation, the characteristics of traffic flow are studied in the framework of Kerner’s three-phase traffic theory. By comparing density and speed of vehicles and flow without tidal lane to these indicators with tidal lane opening, we discover moving bottleneck having a significantly negative impact on the road service level in the direction of lane reduced. And tidal lane has the positive effect on dissipating the upstream moving bottleneck in the direction of lane increased. Based on the simulation results, a qualitatively tidal lane opening strategy that considers the upstream moving bottleneck is proposed.

Optimal observer‐based output feedback controller for traffic congestion with bottleneck

AbstractThis article designs an optimal observer‐based output feedback control for traffic breakdown to dissolve traffic congestion using the backstepping method and optimization. The linearized Aw–Rascle–Zhang model is used to represent the congested traffic dynamics resulting from traffic breakdown. Based on the factors leading to traffic breakdown, we take into account the boundary conditions consisting of a boundary with a constant density and a speed drop at the upstream inlet of a bottleneck, and a boundary with a disturbance of inflow (high traffic demand) at the inlet of the road segment under consideration. To dissolve traffic congestion, a dynamic feedback controller is designed at the upstream boundary. By using the backstepping approach, an observer‐based output feedback controller is computed to guarantee the integral input‐to‐state stability of the closed‐loop system. By establishing an optimization problem and solving it, the optimal value of the considered class controller is obtained. The performance of the output feedback controller is also validated by numerical simulations.

Using Traffic Disturbance Metrics to Estimate and Predict Freeway Traffic Breakdown and Safety Events

The introduction of connected vehicles, connected and automated vehicles, and advanced infrastructure sensors will allow the collection of microscopic metrics that can be used for better estimation and prediction of traffic performance. This study examines the use of disturbance metrics in combination with the macroscopic metrics usually used for the estimation of traffic safety and mobility. The disturbance metrics used are the number of oscillations and a measure of disturbance durations in the time exposed time to collision. The study investigates using the disturbance metrics in data clustering for better off-line categorization of traffic states. In addition, the study uses machine-learning based classifiers for the recognition and prediction of the traffic state and safety in real-time operations. The study also demonstrates that the disturbance metrics investigated are significantly related to crashes. Thus, this study recommends the use of these metrics as part of decision tools that support the activation of transportation management strategies to reduce the probability of traffic breakdown, ease traffic disturbances, and reduce the probability of crashes.

Optimizing sensitivity parameters of automated driving vehicles in an open heterogeneous traffic flow system

In this paper, we attempt to address the issue of controlling the sensitivity parameters (or control gains) of automated driving vehicles in an open heterogeneous traffic flow system. The automated driving vehicles are supposedly equipped with adaptive cruise control and connectivity while the conventional vehicles are characterized by a stochastic safe time headway. To optimize the sensitivity parameters, the natural policy gradient reinforcement learning algorithm has been used for the best policy search. In this context, two performance indices were considered: the traffic breakdown probability and fuel consumption. After extensive simulations, it is found that the sensitivity parameters should depend on both the flow and the penetration rate for maximum performance. In particular, a low-penetration rate of 5% can improve traffic performance. A comparison with other algorithms suggests that natural policy gradient and Q-learning yield a good approximation and reduce significantly the computational cost.

A formulation of the relaxation phenomenon for lane changing dynamics in an arbitrary car following model

Lane changing dynamics are an important part of traffic microsimulation and are vital for modeling weaving sections and merge bottlenecks. However, there is often much more emphasis placed on car following and gap acceptance models, whereas lane changing dynamics such as tactical, cooperation, and relaxation models receive comparatively little attention. This paper develops a general relaxation model which can be applied to an arbitrary parametric or nonparametric microsimulation model. The relaxation model modifies car following dynamics after a lane change, when vehicles can be far from equilibrium. Relaxation prevents car following models from reacting too strongly to the changes in space headway caused by lane changing, leading to more accurate and realistic simulated trajectories. We also show that relaxation is necessary for correctly simulating traffic breakdown with realistic values of capacity drop.