Heterogeneous Traffic Flow Research Articles

Road traffic accident prediction for mixed traffic flow using artificial neural network

Transport scenariosin developingcountries arefundamentally different fromthose indevelopedcountries. The latterconsists primarilyof passenger cars and can beadequately describedas“homogeneous” traffic,butthe formerconsistsof vehicle types withdifferentstatic and dynamiccharacteristics thatoccupy the same right ofway. Vehiclemovementis asynchronous. Fewstudies have attempted tounderstand the characteristics of mixed traffic. Thisarticleexplores the sharing attributes and influencing causes of traffic accidents inamixed trafficarea. A predictability model isemployed todescribethe connection between highwaydisastersand appropriate constraints such astraffic capacity, road provisions,and atmosphereissues. In this paper,the comparison has been done between the Multiple Linear Regression (MLR) and Artificial Neural Network (ANN) predictive models. The study has been conducted at Pimpri Chinchwad Muncipal Corporation (PCMC) region of Pune, Maharashtra, India. For this work, nine years data has been used ranging from the year 2011 to 2019. Results revels that, maximum numbers of accidents were occurred in clear weather condition. Distinctive accidents were occurred due to overloaded vehicle conditions. Also it has been found that the less number of female drivers are responsible for accident. Forecasting model using ANN presents outstanding precision. In this study, additional prominence has been givento the real constraints which are accountable for accident cause in heterogeneous traffic flow.

Controller design for heterogeneous traffic with bottleneck and disturbances

This paper studies an optimal tuning of the boundary controller for a heterogeneous traffic flow model with disturbances in order to alleviate congested traffic. The macroscopic first-order N-class Aw–Rascle traffic model consists of 2N hyperbolic partial differential equations. The vehicle size and the driver’s behavior characterize the type of vehicle. There are m positive characteristic velocities and 2N−m negative characteristic velocities in the congested traffic after linearizing the model equations around the steady state depending on the spatial variable. By using the backstepping method, a controller implemented by a ramp metering at the inlet boundary is designed for rejecting the disturbances to stabilize the 2N×2N heterogeneous traffic system. The developed controller in terms of proportional integral control is derived from mapping the original system to a target system with a proportional integral boundary control rejecting the disturbances. The integral input-to-state stability of the target system is proved by using the Lyapunov method. Finally, an optimization problem is established and solved for seeking the optimal tuning of the controller.

Effects of electronic throttle dynamics in non-equilibrium heterogeneous traffic flow without lane discipline

Urban transportation systems are quickly developing more intelligent and networked systems. To further enhance the intelligent networked traffic environment, this study undertakes a thorough investigation and analysis of the features of heterogeneous traffic flow in a linked environment without lane discipline. A new non-equilibrium mixed traffic flow macroscopic model is proposed in connection with electronic throttle dynamics in light of the significance of electronic throttle angle information for vehicle-to-vehicle communication technologies. This paper investigates the stability of mixed traffic systems using a small disturbance method, as well as the nonlinearity of the systems is analyzed near the neutral stability curve. The effects of electronic throttle opening angle, lateral gap, and CAV penetration rate on the evolution of the traffic flow density wave are numerically investigated. The numerical experiment also compares and evaluates how the new model and three other scene models fares in terms of tiny perturbation evolution, energy consumption, and extra emission. The experiment's finding demonstrated that this macro model had a larger stable domain and less energy consumption and extra emissions when compared to other scenarios.

Modeling of Driver Cut-in Behavior Towards a Platoon

A vehicle platoon is a group of vehicles driving together with a harmonized speed and a short inter-vehicle gap by using vehicle automation and vehicle-to-vehicle communication. Platoons have to share road with human-driven vehicles (HDVs) and can only be applied in heterogeneous traffic flow for a long period. Driver cut-in behavior (DCB) towards a platoon can be frequently expected in such driving context. In this paper, to understand and simulate such behavior, we propose a platoon-oriented cut-in behavior (POCB) model by fusing a lateral and a longitudinal control model into the queuing network (QN) cognitive architecture. Platoon-oriented cut-in experiments are conducted to collect driver data under cut-in from back and front scenarios, which both include six sub-scenarios with different platoon gaps or initial velocities. We demonstrate the effectiveness of the proposed model in simulating the DCB towards platoons by comparing experimental and simulation results under various driving scenarios across different subjects.

Exploring the Impact of the Takeover Time for Conditionally Automated Driving Vehicles on Traffic Flow in Highway Merging Area

Human-machine handover of conditionally automated driving vehicles (CADVs) significantly affects traffic safety. Therefore, a simulation modeling was conducted for the traffic flow mixed with manual driving vehicles, fully automated driving vehicles (FADVs), and CADVs under different takeover times to unravel the impact of CADVs on traffic flow. The results showed that different takeover times significantly affected traffic flow stability. A moderate takeover time allows the driver to complete the takeover quickly with sufficient observation of the surrounding traffic conditions and mitigate the adverse effects of CADVs takeover transition on traffic flow and improve traffic flow safety. Taking moderate takeover time (7s) as the given takeover time, we developed a traffic flow model, and it is found that increasing the total penetration rates of CADVs and FADVs or that of CADVs alone will expand the traffic flow stability area. Moreover, the improving effects of traffic flow stability increase with the value of both penetration rates. This research can be a reference for the safety analysis of heterogeneous traffic flow mixed with CADVs.

The Scanner of Heterogeneous Traffic Flow in Smart Cities by an Updating Model of Connected and Automated Vehicles

The problems of traditional traffic flow detection and calculation methods include limited traffic scenes, high system costs, and lower efficiency over detecting and calculating. Therefore, in this paper, we presented the updating Connected and Automated Vehicles (CAVs) model as the scanner of heterogeneous traffic flow, which uses various sensors to detect the characteristics of traffic flow in several traffic scenes on the roads. The model contains the hardware platform, software algorithm of CAV, and the analysis of traffic flow detection and simulation by Flow Project, where the driving of vehicles is mainly controlled by Reinforcement Learning (RL). Finally, the effectiveness of the proposed model and the corresponding swarm intelligence strategy is evaluated through simulation experiments. The results showed that the traffic flow scanning, tracking, and data recording performed continuously by CAVs are effective. The increase in the penetration rate of CAVs in the overall traffic flow has a significant effect on vehicle detection and identification. In addition, the vehicle occlusion rate is independent of the CAV lane position in all cases. The complete street scanner is a new technology that realizes the perception of the human settlement environment with the help of the Internet of Vehicles based on 5G communications and sensors. Although there are some shortcomings in the experiment, it still provides an experimental reference for the development of smart vehicles.

Congestion and energy consumption of heterogeneous traffic flow mixed with intelligent connected vehicles and platoons

In the future, there will inevitably be a mixed driving situation of intelligent connected vehicles and traditional manual driving vehicles. How intelligent connected vehicles affect traditional traffic flow has attracted increasing attention. Based on the different characteristics of these two types of vehicles a two-lane heterogeneous traffic flow cellular automata model of expressway is proposed, and the effects of whether intelligent connected vehicles form platoons and the size of platoons on traffic flow congestion and energy consumption are simulated. The results show that: as the proportion of intelligent connected vehicles and the size of platoons increase, the maximum traffic capacity can be effectively improved. Besides, with the increase of the mixed ratio, the larger the platoon size, the higher the average speed of traffic flow. The platoon can alleviate even eliminate the congestion faster and more thoroughly. However, in the high-density fully intelligent connected vehicles environment, the larger platoon size leads a negative impact on the traffic flow in the form of “moving bottleneck”. When the platoon size is 4, it can maximize the positive effect of the platoon on the traffic flow. Besides, increasing the proportion and shortening the reaction time of intelligent connected vehicles can effectively reduce the average energy consumption. And platoon mode is more conducive to reduce the average energy consumption than the discrete mode, but the platoon size should be controlled within a reasonable range, otherwise too larger platoon size will aggravate the energy consumption in traffic flow.

Modeling the heterogeneous traffic flow considering mean expected velocity field and effect of two-lane communication under connected environment

With the increasing popularity of the autonomous vehicles, heterogeneous traffic flow of autonomous vehicles (AVs) and human-driving vehicles (HDVs) will exist for long time. Based on single-lane mean expected velocity field model (MEV model), an improved two-lane heterogeneous car-following model (MEVTC model) is proposed which considers the mean expected velocity field of main lane and mean velocity field of adjacent lane in a connected environment. The strength factor of two fields are key parameters. Linear and nonlinear methods are used to reveal the basic characteristics of traffic flow under the new model. Theoretical results show that greater parameters mean larger stability regions. The MEVTC model is verified by numerical simulation, the results show that comparing with MEV model, MEVTC model can reduce the headway fluctuation by 11.2% and increase the traffic flow by 4.2%. With increased strength factor of two fields, the traffic flow becomes more stable However, the influence of the adjacent lane field on vehicle driving is dramatically smaller than main lane field. In addition, the higher penetration rate of the AVs is also good for the stability of traffic flow.

Stability and capacity for heterogeneous traffic flow mixed with vehicles in multiple controls

Cooperative adaptive cruise control (CACC) is regarded as a promising approach to improve traffic stability and capacity by operating vehicle-to-vehicle (V2V) communication. However, the beneficial effect of CACC vehicles is greatly reduced due to the influence of manually driven vehicles (MDVs) in the heterogeneous traffic flow, in which the degradation of CACC vehicles is a considerable problem. One proposed solution is to install communication devices for MDVs, called IMDVs, to propagate information to CACC vehicles and prevent the degradation. This study analyzed the traffic flow configuration by introducing IMDVs and considering multiple traffic flow operations, e.g. vehicle degradation and platoon formation. Then, multiple factors, including market penetration rate, platoon length, and information flow topology, were taken into consideration in the theoretical modelling of linear stability and fundamental diagram. Finally, we verified the high accuracy of theoretical analysis by numerical experiments and gave some reasonable recommendations for traffic management.

Vehicular Traffic Flow Characterization: An Edge Computing Perspective

With rapid urbanization, road network inefficiencies have become a primary impediment for developing sustainable smart cities. Associated challenges range from traffic congestion, ambient pollution, accidents, and lost productivity. In this regard, intelligent transportation system (ITS) based solutions are being proposed to design and develop smart urban mobility. However, real-world traffic flow parameters (such as vehicular count, flow, classification, speed, road capacity, time/distance headway, temporal/spatial densities, heatmaps, and trajectories) are fundamental building blocks for designing and developing ITS solutions. In existing literature, varying solutions have been proposed for traffic flow characterization. These can be categorized as either intrusive or non-intrusive sensors. However, these solutions have serious limitations, especially under heterogeneous traffic flow behavior. To overcome these limitations, compute vision-based solutions have emerged as optimum traffic flow characterization solutions. In this work, all compute vision-based edge computing solutions in existing literature have been reported and analyzed. Through comparative analysis, it is concluded that edge computing solutions are the optimum choice as compared to Internet-of-Video-Things based solutions. However, edge computing solutions are seriously constrained because of the compute resources of single board computers. To overcome this limitation, mathematical traffic flow characterization equations have been reported for calculating eight additional traffic flow parameters. These mathematical equations can optimize the already proposed edge computing solution’s performance by 400%.

A Proof of Concept on Digital Twin-Controlled WiFi Core Network Selection for In-Flight Connectivity

The in-flight connectivity (IFC) turns to a crucial need from luxury with technological advances. The WiFi-enabled IFC (W-IFC) meets most of this need by deploying access points within the aircraft. These access points can allow Internet connectivity through various core network links air-to-ground (A2G), air-to-satellite (A2S), and air-to-air (A2A) at different times during the flight. More specifically, the core network of W-IFC should be selected from these links according to their availabilities throughout the aircraft's flight. However, the ultra-dynamic characteristic of aeronautical networks caused by aircraft's high speed reduces W-IFC's core network selection efficiency. The problems on the core network selection of W-IFC increase the core network selection delay with higher packet losses. Additionally, the core network selection of W-IFC becomes more complex when user traffic heterogeneity is added to this connection availability. These complexities necessitate the continuous monitoring of the aircraft environment while dealing with multiple data entries. At that point, the digital twin (DT) technology enables us a continuous monitoring and management opportunity in a virtual manner for the ultra-dynamic aeronautical environment. By considering this, in this article, we aim to introduce a proof-of-concept (PoC) about the utilization of digital twin technology in WiFi core network selection for IFC. Our proposed DT module executes the hybrid combination by utilizing the connectivity and traffic-based core network selection models simultaneously. Here, the connectivity-based core network selection focuses on determining aircraft's possible core network links, while the traffic-based selection considers heterogeneous traffic flows of passengers. Results reveal that the proposed DT-controlled model reduces the WiFi core network selection delay 36 percent with 25 percent packet delivery improvement. Also, we prove the feasibility of the PoC W-IFC model through twinning rate with near-real-time measurements. And we show the decision performance of DT with false positive and false negative rates.

MANTA: Multi-Lane Capsule Network Assisted Traffic Classification for 5G Network Slicing

As network slicing is an enabling technology for the fifth-generation (5G) networks, it comes with complex challenges to ensure that resource management is consistent with slice tenant activities to provide better performance and cost-effective services to different tenants tailored to their needs. To this end, traffic classification is fundamental for the provisioning of the resources in a network by analyzing the network traffic to anticipate future requests. However, the massive increase of heterogeneous traffic features challenges dynamic network slices traffic classification. Previous literature have explored statistical and machine learning techniques but are constrained by feature engineering and computational costs. In this letter, we propose the multi-lane CapsNet assisted network traffic classification (MANTA), a framework based on multi-lane Capsule Networks (CapsNet) deep learning technique, to identify and classify heterogeneous traffic flows in 5G network slicing. Furthermore, we conduct a comparative analysis of the model with previous literature using deep learning techniques. The experimental results exhibit improved performance with high accuracy of 97.3975%, compared with other classifiers from previous literature.

Overall Influence of Dedicated Lanes for Connected and Autonomous Vehicles on Freeway Heterogeneous Traffic Flow

With the development of autonomous driving and communication technology, the heterogeneous traffic flow by combining connected and autonomous vehicles (CAVs) and manually driven vehicles (MVs) will appear on the freeway in the near future. It is expected that CAVs can improve the freeway capacity and reduce vehicle exhaust emissions, but sharing the same road by CAVs and MVs will cause certain interference to CAVs. In order to reduce the negative influence of the heterogeneous traffic flow, setting up CAV dedicated lanes to separate CAVs from MVs to a certain extent is regarded as a reasonable solution. Based on the characteristics that MVs should be decelerated by a realistic amplitude and that the connected and autonomous vehicle can accurately predict the speed of its preceding and rear CAVs at the next time step, a heterogeneous traffic flow model was established. Based on this model, we studied the overall influence of different lane strategies on the operating efficiency of freeway traffic flow and vehicle exhaust emissions under different densities with different CAV penetration rates. The results show that setting up CAV dedicated lanes with low CAV penetration rates will have a negative impact on the freeway traffic flow. When the CAV penetration rate is 40%–60% and the density is not less than 30 veh/km/lane, setting up one CAV dedicated lane is the best choice. When the CAV penetration rate exceeds 60% and the density is not less than 40 veh/km/lane, setting up two CAV dedicated lanes is the best choice. The research finding will assist in understanding the overall influence of CAV dedicated lanes on freeway traffic flow and help determine the optimal number of CAV dedicated lanes under different traffic conditions.

Stability Analysis of Heterogeneous Traffic Flow with Connected and Automated Vehicles: Joint Consideration of Communication Failures and Driver Takeover

As a primary stage of connected and automated vehicles (CAVs), the cooperative adaptive cruise control (CACC) system takes some outstanding advantages such as accurate perception and timely reaction, which benefit from vehicular communication, over human-driven vehicles (HDVs). However, these advantages will turn into stability risks in case of communication failures caused by malicious attacks. Thus, this study aims at analyzing the stability of heterogeneous traffic flow with communication failures. We model two types of communication failures: bogus messages and transmission delay, and introduce drivers’ takeovers to react to communication failures. As a result, heterogeneous traffic flow consists of normal CACC vehicles, CACC vehicles with communication failures, and HDVs. Then, a series of numerical analyses, including startup and braking analysis, incidents analysis, and density wave, are proposed to verify the theoretical models and demonstrate their major properties. Besides, a discussion on traffic capacity is presented to analyze the overall impact of communication failures on traffic flow characteristics. The findings can help to investigate the stability evolution of heterogeneous traffic flow and determine the appropriate traffic flow configuration under communication failures.

Modeling and stability analysis of cyberattack effects on heterogeneous intelligent traffic flow

The platooning of connected automated vehicles (CAVs) will have a dramatic impact on the future market. The open-access environment is available to share travel information among CAVs to format vehicular platooning, but makes cooperative vehicle platoons vulnerable to suffer cyberattacks. Cyberattacks are classified as bogus messages, replay/delay, and collusion attacks and affect the transmission of information on CAVs. Besides, heterogeneous traffic composed of different vehicles will be an extremely common form of traffic, including mixed operations of different models such as cars and trucks. Meanwhile, different car-following combinations influence the overall stability of heterogeneous traffic flow dynamics. This paper proposes a novel intelligent driving model considering cyberattacks and heterogeneous vehicles. In addition, this model integrates dynamic communication topology, which is a time-varying function determined by the communication range and the distance between vehicles. Through linear stability analysis, the stability conditions of the model are derived. On the other hand, numerical simulation was performed, and the results validated that under cyberattacks high proportion of cars and the information accepted from cooperative vehicles ahead can efficaciously enhance traffic stability and safety. Inversely, the proportion of car-following pairs and response/delay time will destabilize mixed traffic. From the perspective of platoon operation, the perniciousness of cyberattacks on CAV platoon is demonstrated, which lead to different levels of dangerous traffic behavior: unnecessary delay, congestions and potential collisions. The numerical results verified the feasibility and effectiveness of the model.

Research on the Deployment of Joint Dedicated Lanes for CAVs and Buses

CAVs (Connected Autonomous Vehicles) can be effective in improving the efficiency of transportation, but heterogeneous multi-modal traffic flows may hinder this efficiency. This paper addresses the issue of heterogeneous traffic flows affecting the efficiency of transportation when CAVs enter the market and proposes a joint dedicated lane for CAVs and buses. In the bi-level program model for the joint dedicated lane, the lower-level is aimed at the multi-modal traffic assignment problem, while the upper-level is aimed at system optimality. For the lower-level, the paper examines the characteristics of various traffic flows in a mixed traffic flow, investigates the impact of CAV mixing on the road link’s capacity, calculates the travel time of various traffic modes accordingly, and generates a generalized travel cost function for each mode, which is solved using the diagonalized weighted successive averaging method (MSWA) algorithm. The upper-level issue considers the continuity of dedicated and non-dedicated road segments, and the goal is to reduce the overall cost for all travelers by utilizing the dedicated road deployment scheme as the decision variable, which is addressed using a genetic algorithm. Finally, numerical examples and sensitivity analyses are designed accordingly. The numerical example demonstrates that the joint dedicated lane not only lowers the overall cost of the system, but also enhances the efficiency of CAV and bus travel, optimizing the road network and promoting bus and CAV travel modes. The sensitivity analysis shows that in order to set up a joint dedicated lane, the frequency of bus departures and the penetration of CAVs are conditions that must be considered, and that the benefits of a joint dedicated lane can only be fully realized if the frequency of bus departures and the penetration of CAVs are appropriate.

Impact of Cooperative Adaptive Cruise Control on Traffic Stability

Cooperative adaptive cruise control (CACC) is one of the popular connected and automated vehicle (CAV) applications for cooperative driving automation with combined connectivity and automation technologies to improve string stability. This study aimed to derive the string stability conditions of a CACC controller and analyze the impacts of CACC on string stability for both a fleet of homogeneous CAVs and for heterogeneous traffic with human-driven vehicles (HDVs), connected vehicles (CVs) with connectivity technologies only, and autonomous vehicles (AVs) with automation technologies only. We mathematically analyzed the impact of CACC on string stability for both homogeneous and heterogeneous traffic flow. We adopted parameters from literature for HDVs, CVs, and AVs for the heterogeneous traffic case. We found there was a minimum constant time headway required for each parameter design to ensure stability in homogeneous CACC traffic. In addition, the constant time headway and the length of control time interval had positive correlation with stability, but the control parameter had a negative correlation with stability. The numerical analysis also showed that CACC vehicles could maintain string stability better than CVs and AVs under low HDV market penetration rates for the mixed traffic case.

R‐CTM: A data‐driven macroscopic simulation model for heterogeneous traffic

AbstractThere is a well‐known trade‐off between computational efficiency and computational accuracy in the field of traffic simulation. In this article, we propose a novel recurrent neural network based model with an integrated attention mechanism, called R‐CTM, to simulate heterogeneous traffic flow with multiple types of vehicles. It can effectively extract the traffic flow patterns of spatial and temporal changes from training traffic data, which can be real‐world traffic data or synthetic traffic data via microscopic simulation models. Through experiments and comparisons, we show that it can significantly outperform the state of the art methods in terms of simulation accuracy. Besides accuracy, we also demonstrate its scalability: its runtime consumption does not linearly increase with respect to the spatial extent.

Stability analysis of heterogeneous traffic flow influenced by memory feedback control signal

Urban traffic is developing rapidly in the direction of intelligence and networking. In order to further enhance the role of connected vehicles in improving the traffic characteristic of the heterogeneous traffic flow, this paper designs a memory feedback control signal based on the historical traffic information of the vehicle itself, so as to improve the intelligent driver model. Furthermore, the improved homogeneous intelligent driver model is extended to heterogeneous intelligent driver model of heterogeneous traffic flow composed of connected vehicles and regular vehicles, and the stability of heterogeneous traffic flow is discussed. The stability condition of the heterogeneous traffic flow is derived by linear stability analysis method, which shows that the proportion and distribution of connected vehicles and the strength of memory feedback control signal affect the stability of traffic flow to a certain extent. In addition, the results of numerical simulation reveal that the stability of heterogeneous traffic flow is enhanced after considering the memory feedback control signal, no matter in low or high proportion of connected vehicles.

Analysis of Chinese Typical Lane Change Behavior in Car–Truck Heterogeneous Traffic Flow from UAV View

Chinese driver behavior in heterogeneous traffic is commonly available, but it is difficult to acquire due to view limitations and sensor limitations. In this study, Chinese typical lane change behavior in car-truck heterogeneous traffic flow was collected and analyzed using an Unmanned Aerial Vehicle (UAV). The velocity of ego vehicle, relative velocity and distance of ego and surrounding vehicles, time to collision (TTC), time headway (THW) at the lane change moment, and brake and accelerate reaction time during lane changes were investigated. Results showed that large differences existed in various car follow types and lane change types. Cars drove more aggressively than trucks with shorter reaction times, and cars would change lanes at a longer distance when facing trucks. Smaller TTC and THW were found for trucks when facing cars. Chinese drivers showed more frequent lane-change maneuvers and shorter reaction times compared to other countries. The driver characteristic in China provided data support for the training of artificial intelligence-based decision algorithms, the development of a localized system, and the design of roads.