Vehicle Lane Research Articles

Multi-lane traffic flow model based on cellular automaton fine-scale under cooperative vehicle infrastructure system

Microscopic traffic flow modeling is crucial for predicting future traffic demand and optimizing the design of transportation systems. At the microscopic level, a well-crafted model is capable of describing the interactions and dynamic variations among vehicles with greater accuracy. The cell scale in the classical cellular automaton (CA) multi-lane traffic flow model is a critical parameter to accurately express the location relationship of vehicles. In this paper, a new method based on Symmetric Two-lane Cellular Automaton (STCA), entitled STCA-X, is proposed for the cell scale selection. Firstly, the position, velocity, acceleration, and interaction of vehicle operation in the urban multi-lane environment are analyzed, and a feature model is built based on CA. One important drawback of the existing models is that they do not match the vehicle movement in the actual lane. To handle this problem, a fine-scale CA multi-lane model is developed. Secondly, a new traffic flow model is created by redefining several key behaviors such as road following, lane changing, and blocking in the STCA model. The experimental results are analyzed and compared with several of the state-of-the-art methods. Analysis of the simulation results proves that STCA-X improves vehicle lane change frequency and lane utilization efficiency. However, the enhancements in the model have resulted in increased computational complexity. Consequently, future research will delve into novel approaches to boost computational efficiency, thereby propelling the progress of traffic flow modeling technology.

A simulation‐based approach for optimizing the placement of dedicated lanes for autonomous vehicles in large‐scale networks

AbstractThis study introduces a framework to maximize societal benefits associated with the autonomous vehicle (AV)‐dedicated lane implementation at large‐scale transportation networks, considering the travel time savings and the required investments to prepare the infrastructure for their deployment. To this end, a bi‐level optimization problem is formulated. The upper level determines the links for dedicated lane deployment, while at the lower level, a mesoscopic traffic simulation tool is employed to enable a realistic representation of these vehicles in a mixed traffic. The problem is solved using the genetic algorithm. To further reduce the computational burden, this study adopts a clustering method based on the snake algorithm to group the candidate links and reduce the size of the solution space. The proposed framework is successfully applied to the case study of Chicago downtown network, considering various demand levels, AV market penetration rates, and implementation approaches. The results highlight the need for optimizing the placement of AV‐dedicated lanes (AVDLs) to ensure the economically beneficial adoption of this strategy across different scenarios. This study provides transportation planners with key operational insights to facilitate the effective adoption of AVDLs during the transitional phase from human‐driven vehicles to a fully AV environment.

Research on a work zone model with metering zone under mixed traffic flow environment

In the upstream of the highway work zone, vehicles will change lanes automatically or forcibly, which has complexity and randomness. Most studies fail to consider the impact of actual mixed traffic characteristics on traffic flow. For example, the dependence of the lane-changing behaviors of Connected and Automated Vehicles (CAVs) on the length of the zone is ignored in upstream of work zone. In addition, it is assumed that vehicles in the merge lane of the work zone would “yield” or not consider an impact on vehicles in the through lane. This simplifies the complex dynamics of the interaction between the two streams of traffic, which leads to the results of the study and the actual situation inconsistency. Based on the Gipps model, the adaptive cruise control (ACC) and the collaborative adaptive cruise control (CACC) vehicle-following models, this paper proposes a continuous cellular automata model under Vehicle-Road Collaboration and studies the mixed traffic flow characteristics in the work zone. By setting a metering zone before the lane reduction sign, ACC/CACC can adjust headway by obtaining road information in advance. The simulation results indicate that ACC/CACC vehicles have better following response compared to human-driven vehicles. In other words, the platoon composed of ACC/CACC vehicles has stability and can improve the traffic capacity of the work zone. The results of the study also found that the insertion of vehicles from adjacent lane into the ACC/CACC vehicles platoon is detrimental, especially when the penetration rate [Formula: see text] is high. Furthermore, when the length of the metering zone [Formula: see text] is set at 120–150[Formula: see text]m, it can significantly improve the road congestion in the work zone.

Vehicle Lane Assist System

This research paper presents the development of a fast and reliable lane detection device designed to detect and alert the user for efficient and safe journey .Our lane detection device makes it easier to see lane markings on the road and warns the user when he switches to wrong side of road. This budget friendly device will provide the real time data with the help of sensors and used it for google maps integration. Our device is even flexible foe extreme weather conditions.

Assessment of maximum and minimum hanger forces in a triple-cable suspension bridge under live load: Analytical algorithm with manta ray foraging optimization

Triple-cable suspension bridges (TCSBs) are widely used in sea-crossing, island-linking projects with extra-long spans and ultra-wide decks. Their safe operation requires sufficient resistance of all bridge components (towers, cables, girders, and hangers) to static/dead and cyclic/live loads. Therefore, reliable assessment of maximum and minimum axial forces acting on each hanger is topical. This study proposes an analytical algorithm for assessing the internal forces and deformations of a TCSB. Specific steps and formulae for solving the coefficients are described by taking the estimation of girder response under random eccentric line loading as an example. Parameters of the suspension bridge under dead load are treated as known quantities. Actual engineering scenarios, including girder displacements along the bridge, are analyzed and discussed in detail. Basic unknown quantities are determined via governing equations under conditions of elevation differences’ closure and conservation of main cables’ unstressed lengths, yielding direct solutions for deformations of the main cables, girder, towers, and hangers. The proposed analytical model’s feasibility is verified via the finite element method. Optimal solutions to the above equations are derived by the manta ray foraging optimization (MRFO) algorithm to find the most unfavorable load distributions for all vehicle lanes of the bridge and the maximum and minimum axial forces of random hangers. Finally, the proposed method is successfully applied to a TCSB with a 1600 m main span under two operating conditions. The most unfavorable load distributions and the maximum and minimum axial forces of hangers at the mid-span and at the quarter-span point are estimated. The calculation results are compared against those obtained by the influence surface method, showing their good correlation and superiority of the proposed method in computation workload.

A platoon formation algorithm for intersections with blue phase control in mixed traffic

Increasing attention is being paid to intersection signal control with cooperative platoons. Assuming platoons being formed, such platoons cannot only improve the intersection capacity but also minimize the number of control units, especially when dedicated connected and automated vehicle (CAV) lanes are considered. However, the platoon formation process is often neglected, especially for lane-changing and overtaking maneuvers in mixed traffic. This may jeopardize the potential of signal control with platoons. This article proposes a platoon formation algorithm that computes the optimal lane, platoon sequence, and speed profiles of CAVs under the requirement of the central traffic controller. The algorithm is designed for mixed traffic conditions and hence the performance of human-driven vehicles is also considered. A mixed integer linear program model is formulated to minimize the deviation from the desired platoon configuration and the disturbance to overall traffic under any arbitrary initial condition. Numerical experiments are designed to test the effectiveness and the computational performance of the proposed algorithm. Results show that CAVs with signal control can form platoons with rational motion. Besides, the platoon penetration significantly affects platooning feasibility, while the platoon length does not. This suggests that CAVs can form long platoons at intersections to improve traffic throughput.

Comparison of human injury differences in vehicle-riding/pushing bicycle accidents

To support regulations related to cyclists dismounting and pushing across motor vehicle lanes, this study first extracted posture parameters for riding/pushing through physical experiments, then simplified the posture parameters and extracted typical postures with distinguishability. Finally, simulated experiments were designed to compare the differences in human injury between riding and pushing in collision accidents. The physical experiment found that the bicycle controller’s (individuals who ride or push bicycles) forward leaning angle of the back (referred to as the ‘back angle’) when riding can be estimated by the ratio of saddle height to bicycle handlebar height, but the back angle when pushing is not affected by other parameters. Eight typical postures containing only lower limb posture parameters were then identified, and statistical analysis showed significant differences in over 80% of parameters among the postures. Through simulated experiments, the rider’s tolerable saddle height was identified. Even at this saddle height, the injury in riding state was still significantly higher than that in the pushing state, indicating that pushing the bicycle across the motor vehicle lane can reduce the injury to the bicycle controller. The research results not only support relevant regulations, but also provide typical postures for the bicycle controller in vehicle-bicycle collision experiments in the future, and have certain theoretical and practical value.

A hybrid connectionist/LCS for hidden-state problems

This paper describes and evaluates the performance of a learning classifier system (lcs) inspired algorithm called Temporal Reinforcement And Classification Architecture (traca) on maze navigation tasks which contain hidden state. The evaluation of traca includes comparisons with other learning algorithms on selected difficult maze navigation tasks. Not all lcss are capable of learning all types of hidden-state mazes so traca is specifically compared against selected other lcs-based approaches that are most capable on these tasks, including xcsmh, AgentP (G), and AgentP (SA). Each algorithm is evaluated using a maze navigation task that has been identified as among the most difficult due to recurring aliased regions. The comparisons between algorithms include training time, test performance, and the size of the learned rule sets. The results indicate that each algorithm has its own advantages and drawbacks. For example, on the most difficult maze traca’s average steps to the goal are 10.1 while AgentP (G) are 7.87; however, traca requires an average of only 354 training trials compared with 537 for AgentP (G). Following the maze tasks, traca is also tested on two variations in a truck driving task where it must learn to navigate four lanes of slower vehicles while avoiding collisions. The results show that traca can achieve a low number of collisions with relatively few trials (as low as 24 collisions over 5000 time steps after 10,000 training time steps) but may require multiple network construction attempts to achieve high performance.

Analysis of road traffic accidents and casualties associated with electric bikes and bicycles in Guangzhou, China: A retrospective descriptive analysis

IntroductionElectric bicycles (e-bikes) and bicycles in large Chinese cities have recently witnessed substantial growth in ridership. According to related accident trends, this study analyzed characteristics and spatial distribution in the period when e-bike-related accidents rapidly increased to propose priority measures to reduce accident casualties. MethodsFor e-bike- and bicycle-related accident data from the Guangzhou Public Security Traffic Management Integrated System, linear regression was used to examine the trends in the number of accidents and age-adjusted road traffic casualties from 2011 to 2021. Then, for the period when e-bike-related accidents rapidly increased, descriptive statistics were computed regarding rider characteristics, illegal behaviors, road types, collision objects and their accident liability. One-way analysis of variance (ANOVA) followed by Bonferroni's multiple comparison test. P < 0.05 was considered statistically significant. Finally, the density distribution of accidents was presented, and Moran's I (MI) was used for assessing spatial autocorrelation. Hotspots were identified based on an optimized hotspot analysis tool. ResultsBetween 2011 and 2021, the number of accidents and casualty rate (per 100,000 population) increased for e-bikes but decreased for bicycles. After 2018, e-bike-related accidents increased rapidly, and bicycle-related accidents plateaued. Accident hotspots were concentrated in central city areas and suburban areas close to the former. Three-quarters of accidents occurred in motorized vehicle lanes. Most occurred on roads without physically segregated nonmotorized vehicle lanes. More than three-fifths of the accidents involved motor vehicles with at least four wheels. The prevalence (per 100 people) of casualties among e-bike rider victims and cyclist victims accounted for 92.0 % and 96.5 %, respectively. A total of 71.6 % of e-bike-related accidents involved migrant workers. Riding in motorized vehicle lanes was the most common illegal behavior. ConclusionsAlthough e-bike-related and bicycle-related accidents presented similar characteristics, the sharp increase in e-bike-related accidents requires attention. To improve e-bike safety, governments should develop appropriate countermeasures to prevent riders from riding on motorways, such as improving road infrastructure, adjusting the driver's license system and addressing priority control areas.

Enunciating outrage: Sidewalk mobility injustice and activism

This article focuses on winter pedestrian conditions and sidewalk clearing activism in the Canadian city of St. John’s where most sidewalks are left uncleared over its long winters. The study employs ethnographic methods, with a focus on participants’ autoethnographic accounts of navigating the city in winter and advocating for changes in snow clearing – accounts that also form the core of a documentary film directed by the authors. The findings demonstrate how uncleared sidewalks lead to an urban winter environment that is disabling, furthering existing mobility injustices produced by intersections between various forms of inequality and limited public or active transportation options. City residents enunciate their outrage about this situation through physical mobility practices such as walking in the middle of vehicle lanes and self-conscious critiques of everyday idioms about the ‘hardiness’ of residents. This study highlights the importance of taking seasonality into account when examining conditions for pedestrian mobilities.

IOT BASED MOVABLE ROAD DIVIDING SYSTEM

Road dividers conventionally serve the purpose of segregating traffic on roads into lanes for ongoing and incoming vehicles, facilitating smooth traffic flow. Typically, an equal number of lanes are designated for each direction of traffic. However, static road dividers present a limitation as they do not adapt to varying traffic demands. Our objective is to devise an automated road divider system capable of dynamically adjusting lane allocation, thereby accommodating the prevailing traffic patterns. The potential benefits of such a system include significant savings in time and fuel consumption, particularly by reallocating lanes to the direction experiencing higher traffic volume. This innovation promises to alleviate traffic congestion effectively and enhance traffic management strategies.

Multi-head attention-based intelligent vehicle lane change decision and trajectory prediction model in highways

With the aim to improve the interaction between intelligent vehicles and human drivers, this article proposes the MCLG (multi-head attention + convolutional social pooling + long short-term memory + Gaussian mixture model) lane change decision and trajectory prediction model, which includes a lane-changing intention decision module. The model comprises a lane change decision module responsible for determining three lane change intentions: left lane change, right lane change, and car-following. Subsequently, a multi-head attention mechanism processes complex vehicle interaction information to enhance modeling accuracy and intelligence. In addition, uncertainty in trajectory prediction is considered by using multimodal trajectory prediction and Gaussian mixture model, and diversity and uncertainty are combined by combining trajectory prediction from several different modalities through probabilistic combinatorial sampling patterns. Test results indicate that the MCLG model, based on the multi-head attention module, outperforms existing methods in trajectory prediction. The decision module, which takes interactive information into account, exhibits higher predictability and accuracy. Furthermore, the MCLG model, considering the lane-changing decision module, significantly enhances trajectory prediction accuracy, providing robust decision-making support for autonomous driving systems.

Traffic Management using Real-time Density-Based Traffic Light Control System

Abstract: In modern times, cities commonly encounter a big challenge dealing with traffic issues. It's hard to find empty roads nowadays, and waiting at red lights takes forever. The traffic lights are set based on average traffic, but this causes issues at certain spots where traffic suddenly gets heavy. That's why we need a smart system that can handle traffic jams better by looking at how much traffic there is. This system would change the traffic lights in real-time, making things smoother and reducing wait times. In simple terms, we need a clever system to fix the traffic mess in our cities. One of the solution is to manage traffic on signal, traffic signal timing (TST) optimization is one of the fastest and most economical ways to curtail congestion at the intersections and improve traffic flow in the urban network. In this paper we are going to discuss some of the existing traffic light control systems, their drawbacks as well as our proposed system where we are trying to avoid the drawbacks of existing systems. The main objective of our project is to provide a smooth flow of traffic and to reduce the time duration for which one has to stand at the traffic signal. The cameras will monitor the density of vehicles standing at the signal using image processing.This camera takes pictures, and those pictures are analyzed to figure out the density of vehicles in particular lanes. The camera can also recognize sirens and, when it does, it changes the traffic light to green so that emergency vehicles like ambulances and fire trucks can pass through.

Proactive Braking Control System for Collision Avoidance during Right Turns with Occluded Vision at an Intersection

This paper describes the development of an Advanced Driver Assistance System (ADAS) which will allow drivers to avoid collisions with an oncoming vehicle from an occluded area when turning right at intersections in left-hand traffic. Connected vehicles, in coordination with infrastructure, represent one of the commercialized ADAS technologies for collision avoidance. However, the coverage of the ADAS will be limited to designated intersections only, as communication equipment needs to be installed in both the vehicle and infrastructure to enable the assistance. This paper proposes an ADAS using on-board sensors, independent of infrastructure facilities, to control the vehicle velocity to avoid collisions. Most current intersection assistance, by using an Autonomous Emergency Braking System (AEBS), allows the driver to avoid a collision with oncoming vehicles when there is clear vision without occlusion. However, many accidents occur when the vehicle detects the oncoming vehicle too late because of occlusion in the intersection, such as a vehicle in the opposite lane. This system calculates the hazardous speed criteria of the ego vehicle, which might result in a high risk of collision when darting out occurs, and provides speed control assistance to allow the driver to escape from the hazardous speed region. The simulation results reveal that the proposed system effectively reduces the possibility of collisions compared to conventional AEBS.

Enhancing lane changing trajectory prediction on highways: A heuristic attention-based encoder-decoder model

Accurate prediction of lane changing (LC) trajectories plays a vital role in ensuring safe and efficient traffic flow on highways. This paper proposes a LC trajectory prediction model based on encoder-decoder architecture to address low long-term prediction accuracy problem and to gain insight into the underlying motivations of LC behavior. Three specific enhancements were proposed to improve the performance of encoder-decoder. The first enhancement involves the utilization of Neighborhood Component Analysis (NCA) to identify the most relevant input features from driving environment. The second enhancement involves the introduction of heuristic attention to capture intricate time-dependent and environment-dependent patterns of input data. Finally, a trajectory check module was proposed to supervise and adjust the prediction outputs based on vehicle dynamics constraints. The proposed model was trained and evaluated using the HighD dataset. Experimental results demonstrated that the proposed model outperforms improved encoder-decoder architectures designed by previous studies in terms of prediction accuracy in long-term prediction, which the lateral and longitude MAE were 0.041 m and 1.842 m in 5 s prediction duration, respectively. Additionally, it was observed that preceding vehicles in the current and target lane, and following vehicle in the target lane, exert a significantly influential effect on LC maneuvers, which represents the underlying motivations behind LC behavior. The findings of this study contribute to the advancement of intelligent transportation systems (ITS) and autonomous vehicles (AVs) by providing an effective LC trajectory prediction.

Assessing the impact of ride-sourcing vehicles on HOV-lane efficacy and management strategies

High-occupancy vehicle (HOV) lanes, which exclusively allow vehicles with two or more travelers on board to enter, has been recognized as a promising and practical way to motivate travelers to carpool. However, in the presence of ride-sourcing services, ride-sourcing vehicles with one driver and one (or more) passenger on board also meet the vehicle requirements of HOV lanes. So instead of encouraging travelers to carpool, HOV lanes may benefit ride-sourcing users and stimulate ride-sourcing demand. In this paper, in a single-corridor network with both HOV lanes and general purpose (GP) lanes, we model travelers’ mode choices among transit, driving alone, ride-sourcing, and carpool, and delineate travelers’ lane choices at user equilibrium, with the travel time of GP/HOV lanes and the carpool price being endogenously determined. With numerical examples, we show that the occupation of HOV lanes by ride-sourcing vehicles will greatly reduce the time saving on HOV lanes, thus lower the attractiveness of carpool, and increase the total travel time cost on the corridor. To solve this problem, we propose to implement an additional tolling scheme on HOV lanes, so that carpool users can split the toll evenly, while ride-sourcing riders have to pay the toll alone. As shown by numerical examples, the optimal tolling scheme can effectively reduce the occupancy of ride-sourcing vehicles on the HOV lane and encourage users to carpool. And the impacts of the ride-sourcing price, driving car cost and the HOV lane capacity ratio on the effectiveness of the proposed hybrid toll and HOV strategies are examined through sensitivity analysis.

Safe-by-construction autonomous vehicle overtaking using control barrier functions and model predictive control

Ensuring safety for vehicle overtaking systems is one of the most fundamental and challenging tasks in autonomous driving. This task is particularly intricate when the vehicle must not only overtake its front vehicle safely but also consider the presence of potential opposing vehicles in the opposite lane that it will temporarily occupy. In order to tackle the overtaking task in such challenging scenarios, we introduce a novel integrated framework tailored for vehicle overtaking manoeuvres. Our approach integrates the theories of varying-level control barrier functions (CBF) and time-optimal model predictive control (MPC). The main feature of our proposed overtaking strategy is that it is safe-by-construction, which enables rigorous mathematical proof and validation of the safety guarantees. We show that the proposed framework is applicable when the opposing vehicle is either fully autonomous or driven by human drivers. To demonstrate our framework, we perform a set of simulations for overtaking scenarios under different settings. The simulation results show the superiority of our framework in the sense that it ensures collision-free and achieves better safety performance compared with the standard MPC-based approach without safety guarantees.

Machine Learning and Signal Processing for Bridge Traffic Classification with Radar Displacement Time-Series Data

This paper introduces a novel nothing-on-road (NOR) bridge weigh-in-motion (BWIM) approach with deep learning (DL) and non-invasive ground-based radar (GBR) time-series data. BWIMs allow site-specific structural health monitoring (SHM) but are usually difficult to attach and maintain. GBR measures the bridge deflection contactless. In this study, GBR and an unmanned aerial vehicle (UAV) monitor a two-span bridge in Germany to gather ground-truth data. Based on the UAV data, we determine vehicle type, lane, locus, speed, axle count, and axle spacing for single-presence vehicle crossings. Since displacement is a global response, using peak detection like conventional strain-based BWIMs is challenging. Therefore, we investigate data-driven machine learning approaches to extract the vehicle configurations directly from the displacement data. Despite a small and imbalanced real-world dataset, the proposed approaches classify, e.g., the axle count for trucks with a balanced accuracy of 76.7% satisfyingly. Additionally, we demonstrate that, for the selected bridge, high-frequency vibrations can coincide with axles crossing the junction between the street and the bridge. We evaluate whether filtering approaches via bandpass filtering or wavelet transform can be exploited for axle count and axle spacing identification. Overall, we can show that GBR is a serious contender for BWIM systems.

Analyzing the relationship between the efficiency and safety of a turbo roundabout by the factor analysis method

The construction of cities and economic development lead to more and more serious environmental pollution, and the concept of green and low-carbon city has been proposed. Therefore, a series of requirements have been put forward for transportation. CO and other pollutants will be produced in the exhaust of conventional fuel vehicles, which will seriously affect the urban environment, especially at intersections with large passenger and vehicle flows. When multiple roads, especially more than 4 roads, intersect on urban roads, traffic organization can usually be achieved by using a roundabout. However, due to the limited capacity of the conventional roundabout, with the rapid increase of the traffic volume, and there are many vehicles in the circle lane change and interweaving behavior. This has caused serious congestion at the roundabout, the significantly increase in pollutants emissions and the decline in air quality. As an unconventional design, the turbo roundabouts use canalized traffic to allowed drivers to select the appropriate lanes in advance depending on their destinations so that different lanes within the circle do not interfere with one another, which improves the safety of the intersection while ensuring capacity. The main purpose of this paper is to analyze the traffic efficiency and safety of the conventional roundabout scheme and turbo roundabout scheme for five-way intersections. Using VISSIM to simulate different forms of roundabout and analyzing the six selected evaluation indicators. The number of vehicles in different entrance lanes and the diameter of the circle are selected as sensitivity factors for sensitivity analysis. Finally, the factor analysis method (FAM) is used to classify the six indicators into two categories: traffic efficiency and traffic safety, so as to comprehensively evaluate the different schemes. The results show that the difference in performance between the two schemes was not significant at low traffic volumes. At high traffic volumes, the turbo roundabout was better than the conventional roundabout in terms of emissions, safety and throughput efficiency. CO emissions from vehicles on conventional roundabout are generally higher than those on turbo roundabout, up to 53.62%. Therefore, the turbo roundabout is more appropriate for heavy traffic conditions.

Research on lane-changing decision and control of autonomous vehicles based on game theory

Designing a secure and reliable decision-planning model for vehicle lane changing is of utmost practical significance because it is one of the most frequent driving behaviors and has a substantial impact on the safety of drivers’ lives and property. First, a Gaussian mixed Hidden Markov model (GMHMM) is trained for lane change intention recognition (LCIR), and the results reveal that the model has a great performance. This will simplify the game process and provide drivers and passengers with warnings. Second, the safety, efficiency, and comfort payoffs of vehicle lane changes are taken into account when building the game model. When building the safety payoff function, temporal collision risk and spatial collision risk of vehicles are two of them that are carefully taken into account. After that, the vehicle’s trajectory tracking control is decoupled into lateral LQR + feedforward control and longitudinal dual proportional integral derivative (PID) control based on the Frenet coordinate system. Finally, a vehicle lane change scenario is built for simulation analysis, and the effects of driving comfort factor and driving efficiency factor on lane change results are considered. The results show that the proposed game theory lane change model ensures lane change safety while satisfying human drivers’ requirements for lane change efficiency and comfort.