Lane-changing Model Research Articles

Modeling Lane-Changing Behaviors in Merging Areas of Urban Expressways in Nanjing, China

Merging bottlenecks in urban expressways have attracted much attention in recent years. In this paper, vehicular mandatory lane-changing (MLC) data are collected from Yingtian Avenue in Nanjing, China using cameras. Based on a series of video processing algorithms, 656 MLC behaviors of 1,560 vehicles are extracted from videos. A logistic regression model is proposed to depict MLC at the merging bottleneck and estimate the possibility of accepting gaps for merging, which is validated by precision testing and simulation. During the simulation, a discretionary lane-changing (DLC) model is utilized and calibrated to describe vehicular DLC behaviors for the sake of consistency and completeness. Finally, by simulating different arrival rates of mainline and ramp, a linear regression model is built to predict breakdown at merging bottlenecks. According to data analysis, the MLC model represents high precision during the decision-making process. Besides, the breakdown prediction model implies strong correlation between traffic demand and breakdown occurrence.

A novel evaluation method for vehicle and traffic performance of different decision control of automatic lane change based on miniature model

Research on automatic lane-change decision is mainly limited to simulation validation and lacks real vehicle validation methods because it is limited by experimental site and automatic driving technology on real vehicles. This paper puts forward a miniature traffic model to simulate the actual traffic scene and achieves to verify the decision control of automatic lane-change scene. The miniature intelligent traffic scene contains miniature vehicles, simplified miniature road traffic environment, and wireless network communication. After testing the basic functions of the miniature traffic scene model, such as automatic lane change, lane keeping, and automatic following, a semi-physical simulation test of the traffic flow composed of the model vehicle and the virtual vehicle is carried out. The semi-physical simulation test includes vehicle-following test of hybrid-condition intelligent driver model, lane-change test of lane-change decision two-vehicle gaming model, and minimizing overall braking induced by lane changes. The results show that the feasibility of the method and of the lane-change decision two-vehicle gaming model of automatic lane change is better in terms of traffic safety, traffic efficiency, and homogeneity. Compared to the minimizing overall braking induced by lane-change model test, the test of lane-change decision two-vehicle gaming model improves 2.26% and 1.5% in the average speed and total driving distance, respectively. The standard deviation of the traffic speed of the lane-change decision two-vehicle gaming model was 28.57% lower than the minimizing overall braking induced by lane changes. Compared to pure simulation verification, the method considers the effects of actual sensor signals and actuator control, which is closer to the actual application.

Safe and optimal lane-change path planning for automated driving

This paper proposes an integrated lane-change trajectory planning method for advanced driver assistance system of connected and automated vehicles. First, the time-based quintic polynomial automated lane-change model is presented, which could adjust longitudinal and lateral velocity simultaneously. By tuning the lane-change duration and longitudinal displacement in the lane-change model, the lane-change reference trajectories satisfying the demands of safety, lane-change duration, travel distance, and comfort were derived under traffic-free condition. All feasible reference trajectories compose a trajectory map, which includes different driving situations, such as quick and comfortable or sudden and safe lane change. Second, the lane-change constraints induced by surrounding vehicles are introduced. The effects of surrounding vehicles on the lane-change performance are investigated by adjusting the speeds and initial gaps of preceding and rear vehicles. In addition, the initial velocity of the host vehicle is optimized to maximize the area of the trajectory map to enable a safer lane change. Finally, within the derived trajectory map, an optimal lane-change trajectory eliminating potential collisions is calculated by minimizing the lane-change duration, travel distance, driving comfort, and fuel consumption.

Modeling Lane-Change Risk in Urban Expressway Off-Ramp Area Based on Naturalistic Driving Data

Abstract Off-ramp areas are considered the critical sections of urban expressways where the exiting vehicles and straight-through vehicles merge. Therefore, lane-change behaviors frequently occur at the upstream of the urban expressway off-ramp, which lead to high chance of traffic crashes. This study looks at the risk of lane-change behaviors in the multilane urban expressway off-ramp areas. First, lane-change process information of exit vehicles in urban expressway off-ramp area was extracted from the Shanghai Naturalistic Driving Study (SH-NDS) database. Second, for each lane-change movements of exit vehicles, a risk evaluation indicator (risk perception, RP) was adopted to quantify the lane-change risk. Based on the RP, the study proposed a four-rank risk classification criterion using K-means clustering to define the risk rank of each lane-change movement. Finally, a lane-change risk rank classification model was developed for traffic in the off-ramp areas of multilane expressways using four distinctive influencing factors. Four influencing factors, namely, traffic congestion level, demand lane change times, lane-change direction, and relative distance between vehicle and exit, were used to describe the traffic flow characteristics and exiting lane-change route for the modeling purpose. The risk model was developed using two support vector machine models, which were based on the partial binary tree structure and the directed acyclic graph structure, respectively. The results showed that the overall accuracy of the partial binary tree structure classifier was 65.71 % and the average AUC value was 0.9004, both of which shows a better performance of the partial binary tree structure classifier, compared with the directed acyclic graph structure classifier.

Application of machine learning algorithms in lane-changing model for intelligent vehicles exiting to off-ramp

ABSTRACT The primary objective of this study is to evaluate how intelligent vehicles equipped with cooperative adaptive cruise control (CACC) improve freeway efficiency and safety at an off-ramp bottleneck. Applying randomized forest and back-propagation neural network (BPNN) algorithms, lane-changing characteristics are obtained based on ground-truth vehicle trajectory data extracted from the NGSIM dataset. The results show that both CACC penetration rate and length of diverge influence areas exert considerable influence on road capacity and traffic safety. Overall, the capacity will peak after an initial decrease as the CACC penetration rate increases. The maximum capacity obtained in 100% of CACC vehicle scenarios improved by over 60%, compared with 50% CACC penetration rate scenario. The proposed integration system with 100% CACC penetration rate significantly reduced the rear-end collision risks, decreasing time exposed time-to-collision and time integrated time-to-collision by 70.8%–97.5%.

A Repeated Game Freeway Lane Changing Model.

Lane changes are complex safety- and throughput-critical driver actions. Most lane-changing models deal with lane-changing maneuvers solely from the merging driver’s standpoint and thus ignore driver interaction. To overcome this shortcoming, we develop a game-theoretical decision-making model and validate the model using empirical merging maneuver data at a freeway on-ramp. Specifically, this paper advances our repeated game model by using updated payoff functions. Validation results using the Next Generation SIMulation (NGSIM) empirical data show that the developed game-theoretical model provides better prediction accuracy compared to previous work, giving correct predictions approximately 86% of the time. In addition, a sensitivity analysis demonstrates the rationality of the model and its sensitivity to variations in various factors. To provide evidence of the benefits of the repeated game approach, which takes into account previous decision-making results, a case study is conducted using an agent-based simulation model. The proposed repeated game model produces superior performance to a one-shot game model when simulating actual freeway merging behaviors. Finally, this lane change model, which captures the collective decision-making between human drivers, can be used to develop automated vehicle driving strategies.

Microscopic modelling of area-based heterogeneous traffic flow: Area selection and vehicle movement

The area-based (i.e., non-lane based) heterogeneous traffic (as in developing countries) has significant differences from the lane-based homogeneous traffic (as in developed countries). In area-based traffic, drivers generally ignore the lane markings and perceive the entire road space while progressing longitudinally. The traditional car-following and lane changing models are not directly applicable to model such driving behaviour.This research aims to microscopically model the dynamics of the subject vehicle in area-based traffic flow. The modelling is conducted in two steps: area selection, and vehicle movement. In step-1, a multinomial logit (MNL) model is considered for selecting the area-based movement direction of the subject vehicle. The choice space of the subject vehicle is divided into numbers of realistic radial cones considering the possible moving directions of the subject vehicle in the next simulation time step. These radial cones form the alternatives for the decision of the subject vehicle. The attributes of the alternatives are defined in terms of angular deviation from the direction of the flow, spacing and relative speed. This model is calibrated and validated for both cars and motorcycles using real trajectory data, and the results demonstrate the good performance of the model. In step-2, a modified intelligent driving model (MIDM) is proposed to simulate the next position of the subject vehicle (along the selected direction as the outcome of the model in step-1). The parameters of the MIDM model are calibrated using real data for cars and motorcycles.The deterministic parameters for MNL model and the empirical distribution of the MIDM model parameters are utilized to stochastically simulate vehicle trajectories with the initial and boundary conditions determined by the real dataset. The comparison of the macroscopic properties between the simulated and real datasets provides promising results for the simulation applicability of the proposed modelling framework.

Development of a binary logistic lane change model and its validation using empirical freeway data

An effective macroscopic lane change (LC) model is required to facilitate active and dynamic lane management to develop cell-based multilane macroscopic traffic models. Existing logistic regression LC models do not undertake model classification of lane change; do not consider performance measures in the validation of field data and ignore movement between lanes during time-varying traffic. Models that consider the direction of LC are, however, biased in their prediction of left LC (LLC) and right LC (RLC) direction. This study proposed a simplified macroscopic cell-based binary logistic LC (BLLC) model describing the LC probability using fewer explanatory variables; in this model, the direction of LC is considered as a new variable. Considering the model performance measures, the results show that there exists substantial difference in LC behaviour in both directions. The present model also achieved a smaller difference in the percentage of accurate prediction (0.9%) between the LLC and RLC.

A probability lane-changing model considering memory effect and driver heterogeneity

Lane changing is one of the basic driving behaviours, which may induce traffic oscillations and incidents. However, it is difficult to well model the lane-changing decision process due to the complex traffic status. To promote the prediction accuracy of lane-changing decisions, this paper presents a probability lane-changing model by taking into account the memory effect. That is, the lane-changing decision model considers a series of trajectory data rather than the data of a specific time utilized in most existing models. Furthermore, the drivers are classified in terms of lane-changing trajectories, which is expected to further promote the prediction accuracy of the lane-changing decision model. Calibrations and validations are carried out based on the NGSIM data, which indicate that the proposed model can significantly promote the prediction accuracy of lane-changing decisions.

Modelling and Analysis of Mutually Adaptive Vehicle Maneuvers During the Inserting Process of Lane Changing Vehicle in Urban Driving Context

This study developed a pair of lane changing (LC) model and car following (CF) model. They are used to investigate mutually adaptive maneuver of LC vehicle (LCV) and its immediate CF vehicle during the LCV's inserting process. The two models are developed based on a multianticipative CF model to simulate both of the LC and LC-adaptive CF maneuvers. A group of pairwise parameters are applied in the models to reflect the stimuli perceived by the two vehicle drivers simultaneously. Based on the united model framework, the features of the two vehicle maneuvers which are mutually and intensively influenced can be compared and analyzed. Vehicle trajectories collected on the urban arterial are applied to calibrating and validating the two models. Results show that the developed models can fit the trajectories in a higher accuracy than the previous models. The estimates of the model parameters revealed that dynamics of lateral moving vehicle influence the LC and CV maneuvers in different ways. It is found that the lateral influence has the heaviest influence on the vehicle maneuvers than other stimuli. The vehicles also adjust their maneuvers along with the change of traffic signal or LC target.

A Cooperative Lane Change Model for Connected and Automated Vehicles

The emerging technology of vehicle-to-vehicle (V2V) communication, vehicle-to-infrastructure (V2I) communication makes it possible for vehicles to sense the environment information, which can be exploited to assist the vehicle in cooperative motion planning. In this paper, we focus on the cooperative trajectory planning of lane changes for connected and automated vehicles (CAVs). The proposed model considers the traffic scene with multiple mandatory lane change demands and completes the trajectory planning for vehicles by taking the safety and efficiency into consideration. The model solves two critical issues: the vehicle grouping and the motion planning. In the first issue, CAVs in the cooperative zone are divided into different groups. Then the problem is simplified and divided into several subproblems. In the second issue, the trajectory planning is conducted in each group. Trajectories are generated for vehicles with and without lane change demands. Besides, these two steps are iterated and updated in the fixed time interval, which makes full use of the dynamic cooperation ability of vehicles. Extensive simulation tests are conducted to validate the performance of the model. Results show that the cooperation of vehicles realizes safe and effective lane changes.

A two-lane mixed traffic flow model with drivers' intention to change lane based on cellular automata

Aiming at the shortcomings of the classic NaSch model and the two-lane lane change model (STCA), the viaduct was used as the simulation object on the basis of improving the rules and lane changing rules. Under the open boundary condition, a two-lane mixed traffic flow model considering the intention to enter the lane is established. Aim at the willingness of driver to enter lane research, this model puts forward the vehicle enter rules, which take into account the relevant factors that affect driver's intention to enter the road and quantify the influencing factors through the method of average input rate in queuing theory. Computer numerical simulation shows that the average input rate λ is determined by input rate λ and output rate μ, and is affected by the sensitivity parameter β, and is not greater than μ. The passing state of a road vehicle is determined by the output rate μ and is affected by β. At the same time, compared with the model that ignores the driver's intention to enter the road, the model proposed in this paper is closer to the actual traffic situation.

A review of game theory models of lane changing

Driver lane-changing behaviors have a significant impact on the safety and the capacity of the vehicle-based traffic system. Therefore, modeling lane-changing maneuvers has become an essential component of driving behavior analysis. Among microscopic LC models, game theory-based lane-changing models highlight the interaction of drivers, which reveal a more realistic image of driving behaviors compared to other classic models. However, the potential of game theory to describe the human driver's lane-changing strategies is currently under-estimated. This paper aims to review the recent development of game-theoretic models that are classified according to their different methodologies and features. They are designed for both human-driven and autonomous vehicles, and we hope they can find applications in future AV industries.

Analysis of vehicle lane-changing behaviour at signalised intersection

In order to analyse the characteristics of the lane-changing behaviour at the signalised intersection, the desired speed of vehicle and the lane-changing benefits were studied based on the theory of traffic flow. A vehicle lane-changing model is established, and the adjacent vehicle relative speed, the adjacent vehicle relative distance and the space for the vehicle lane changing are considered. The feasibility of the model is discussed in the fifth part of the paper. Finally we analyse the influence of lane changing behaviour through the actual data. The main content of the analysis is the impact of vehicle lane-changing behaviour on traffic capacity, the results show that traffic flow in the current lane and the traffic flow in the target lane are reduced due to vehicle lane changing at the intersection.

A Personalized Lane-Changing Model for Advanced Driver Assistance System Based on Deep Learning and Spatial-Temporal Modeling

A Personalized Lane-Changing Model for Advanced Driver Assistance System Based on Deep Learning and Spatial-Temporal Modeling

A Pragmatic Dynamic Lane-changing Trajectory Planning Model for Autonomous Vehicles

Automatic lane change is a complex and essential part of autonomous vehicle control. Existing researches on autonomous vehicle technology mainly focused on avoiding obstacles, but few studies have focused on the issue of dynamic lane change. Moreover, existing dynamic lane-changing models were based on some certain assumptions. Considering that the actual road is not a complete straight line and the function of the road cannot be accurately established, this paper establishes a cubic polynomial path planning model based on discrete global trajectory points. Then, in order to ensure the trajectory’s safety, comfort and efficiency, an all-sided trajectory optimization function is proposed. At last, simulation verifications are carried out. Results show that the proposed method can generate a splendid lanechanging trajectory.

An Automatic Calibration Procedure of Driving Behaviour Parameters in the Presence of High Bus Volume

Most of the microscopic traffic simulation programs used today incorporate car-following and lane-change models to simulate driving behaviour across a given area. The main goal of this study has been to develop an automatic calibration process for the parameters of driving behaviour models using metaheuristic algorithms. Genetic Algorithm (GA), Particle Swarm Optimization (PSO), and a combination of GA and PSO (i.e. hybrid GAPSO and hybrid PSOGA) were used during the optimization stage. In order to verify our proposed methodology, a suitable study area with high bus volume on-ramp from the O-1 Highway in Istanbul has been modelled in VISSIM. Traffic data have been gathered through detectors. The calibration procedure has been coded using MATLAB and implemented via the VISSIM-MATLAB COM interface. Using the proposed methodology, the results of the calibrated model showed that hybrid GAPSO and hybrid PSOGA techniques outperformed the GA-only and PSO-only techniques during the calibration process. Thus, both are recommended for use in the calibration of microsimulation traffic models, rather than GA-only and PSO-only techniques.

Review of Lane-Changing Maneuvers of Connected and Automated Vehicles: Models, Algorithms and Traffic Impact Analyses

Connected and automated vehicle (CAV) technologies have been developed to improve traffic safety, mobility, and environmental impacts throughout the years. One of the enabling CAV technologies is the lane-changing function, which has attracted much attention from both industry and academia in recent years. This paper provides an overview of representative studies on CAV lane-changing models, algorithms, traffic impact analyses as well as testing experiments. Several crucial concepts, such as vehicle-to-vehicle (V2V) communication, lane-changing decision and planning, and vehicle control algorithms are focus of this review. Overall, despite existing successful studies on CAV lane changing, research gaps between state-of-the-art technologies and real-world CAV applications are identified in the hope of facilitating future research in this direction.

Optimal location of lane-changing warning point in a two-lane road considering different traffic flows

The timely lane-changing (LC) warning information should be informed to vehicles upstream when some things (such as accident or vehicle breakdown) happen. To avoid secondary accidents or reduce traffic congestion, this paper investigates the optimal LC warning point in a two-lane road considering the different traffic condition. The Intelligent Driver car-following Model and MOBIL LC model are used to describe the vehicle’s longitudinal and lateral motion rules, and methods based on probability theory and numerical simulations are proposed to investigate the optimal warning point under different traffic scenarios. The numerical results show that: i) the successful LC probability is not monotone changing with velocity. ii) providing LC warning information can reduce the average travel time, especially in moderate or congested traffic conditions. iii) the appropriate LC warning point location range becomes smaller with the increase of flow rate. iv) the effective LC warning​ point is about 30–300 meters far from the event point under different traffic flows.

Active lane-changing model of vehicle in B-type weaving region based on potential energy field theory

To define lane-changing time accurately and quantitatively, the influence of vehicle spacing on lane-changing time was studied using cars. Taking into account the influence of surrounding vehicles’ spacing on lane-changing, a vehicle lane-changing time model on an urban road B-type weaving section based on a potential energy field theory was proposed. The model quantitatively illustrated the influence of surrounding vehicles’ spacing on lane-changing lateral acceleration and then deduced the relationship between the lateral displacement, longitudinal displacement and time of the lane-changing vehicle. By using the aerial data of passenger cars lane-changing in the weaving area of an urban trunk road, the parameters in the model were calibrated and the lane-changing trajectory of vehicles simulated by the model was tested. It is found that the accuracy of the lane-changing model to quantitatively define the transverse acceleration while changing lanes and the spacing between constrained regions reaches 90%, and the fitting degree between simulated lane change trajectory and actual lane change trajectory is over 90%. The results show that the vehicle lane-change model based on the potential energy field theory can effectively simulate the relationship between vehicle lane-change time and lateral and longitudinal displacement and can provide theoretical and technical support for traffic simulation and multi-vehicle interaction.