Vehicle Lane Change Research Articles

Lane change maneuver detection considering real-time vehicle dynamic features via V2X communication

More than 90% of traffic accidents are caused by driver behavior, with lane change behavior being a major contributor. Recently, driving assistance systems are being introduced on vehicles to reduce traffic accidents, and a reliable vehicle lane change collision detection system is a key component of these systems. Besides, the foundation of the vehicle lane change detection system is the effective vehicle lane change detection model. In this paper, based on the support vector machine, we propose a model for detecting driver lane change maneuvers and take into account the real-time vehicle dynamic features transmitted via Vehicle to X (V2X) Communication. The accuracy is ideal for lane keep and lane change situations, and it is also robust for zigzag driving situations, according to tests conducted using the NGSIM real traffic dataset. The detection accuracy for left and right lane change maneuvers is 97.5% and 99.09%, respectively, while the false alarm rate is 8.56%. Additionally, the average advance detection time is 1.7 s, which is suitable for actual driving application scenarios.

Analysis of Lane-Changing Decision-Making Behavior and Molecular Interaction Potential Modeling for Connected and Automated Vehicles

With the technical support of an intelligent networking environment, autonomous driving technology is facing a new stage of development, and the decision-making behavior of autonomous vehicles is changing fundamentally, so it is urgent to explore the lane-changing decision-making behavior mechanism of autonomous driving. Firstly, through the analysis of system similarity, the similarity between autonomous vehicles and moving molecules is sought, and the attraction and repulsion between molecules are applied to the lane-changing process of vehicles to effectively recognize the traffic scene of lane-changing vehicles. Secondly, the molecular interaction potential is introduced to unify the attraction and repulsion, and explore the dynamic influencing factors of lane-changing behavior for vehicles. Moreover, we systematically analyze the interaction relationship in the lane-changing process of Connected and Automated Vehicles, and establish the molecular interaction potential lane-changing model to explore the lane-changing decision-making behavior mechanism. Furthermore, we study the impact of micro lane-changing behavior on macro traffic flow. Finally, the SL2015 lane-changing model and the molecular interaction potential lane-changing model are compared and analyzed by using the SUMO platform. The results show that the speed fluctuation of Connected and Automated Vehicles based on the molecular interaction potential lane-changing model is reduced by 15.5%, and the number of passed vehicles is increased by 3.26% on average, which has better safety, stability, and efficiency. The molecular interaction potential modeling of lane-changing decision-making behavior for Connected and Automated Vehicles comprehensively considers the interaction relationship of dynamic factors in the traffic environment, and scientifically shows the lane-changing decision-making mechanism of Connected and Automated Vehicles.

Modeling bounded rationality in discretionary lane change with the quantal response equilibrium of game theory

The primary purpose of discretionary lane change is to provide a speed advantage or a better driving environment. Game theory is one way to find each driver's most reasonable behavior plan by studying their competitive lane-changing behavior. Nash equilibrium provides an effective strategy to ensure the lane-changing vehicle can reach the maximum value of its expected returns. Other vehicles in the game also follow this strategy. However, due to the inadequate understanding of the driving environment and drivers’ physiological and psychological factors, it is difficult to have the entirely rational conditions required by Nash equilibrium, whose solution is usually quite different from the actual result. To quantify drivers’ rationality in lane-changing decisions, we established a model of bounded rationality based on the quantal response equilibrium (QRE), in which drivers are not perfect optimizers and face uncertainty in other drivers’ actions. The maximum likelihood estimation and data analysis from NGSIM confirm that drivers in discretionary lane-changing games exhibit bounded rationality. As the lane-changing decision continues, drivers become more aware of their surroundings to be more rational. More than 91.5% of our model predictions are in line, which means our QRE model can effectively describe discretionary lane-changing decision behavior. Compared to Talebpour's game model, our model has a stronger predictive ability and can more accurately describe discretionary lane-changing behavior.

Video Action Recognition for Lane-Change Classification and Prediction of Surrounding Vehicles

In highway scenarios, an alert human driver will typically anticipate early cut-in/cut-out maneuvers of surrounding vehicles using visual cues mainly. Autonomous vehicles must anticipate these situations at an early stage too, to increase their safety and efficiency. In this work, lane-change recognition and prediction tasks are posed as video action recognition problems. Up to four different two-stream-based approaches, that have been successfully applied to address human action recognition, are adapted here by stacking visual cues from forward-looking video cameras to recognize and anticipate lane-changes of target vehicles. We study the influence of context and observation horizons on performance, and different prediction horizons are analyzed. The different models are trained and evaluated using the PREVENTION dataset. The obtained results clearly demonstrate the potential of these methodologies to serve as robust predictors of future lane-changes of surrounding vehicles proving an accuracy higher than 90% in time horizons of between 1-2 seconds.

Sentinel: An Onboard Lane Change Advisory System for Intelligent Vehicles to Reduce Traffic Delay During Freeway Incidents

This paper introduces Sentinel, an onboard system for intelligent vehicles that guides their lane changing behavior during a freeway incident with the goal of reducing traffic congestion, capacity drop, and delay. When an incident blocking the lanes ahead is detected, Sentinel calculates the probability of leaving the blocked lane(s) before reaching the incident point at each time step. It advises the vehicle to leave the blocked lane(s) when that probability drops below a certain threshold, as the vehicle nears the congestion boundary. By doing this, Sentinel reduces the number of late-stage lane changes of vehicles in the blocked lane(s) trying to move to other lanes, and distributes those maneuvers upstream of the incident point. A simulation case study is conducted in which one lane of a four-lane section of the I-66 interstate highway in the U.S. is temporarily blocked due to an incident, to understand how Sentinel impacts traffic flow and how different parameters - traffic flow, system penetration rate, and incident duration - affect Sentinel’s performance. The results show that Sentinel has a positive impact on traffic flow, reducing average delay by up to 37%, particularly when it has a considerable penetration rate. Working alongside Traffic Incident Management Systems (TIMS), Sentinel can be a valuable asset for reducing traffic delay and potentially saving billions of dollars annually in costs associated with congestion caused by freeway incidents.

Congestion Identification for Multilane Highway by Vehicle Lane Change as Driver Behavior


 
 
 
 This work introduces a new way to assess the condition of highways and classify them as congested or uncongested highways. This was done by recording a video and sorting the number of lane change orders instead of finding the traffic density, delay, and flow rate. Then extracting data from the video and performing a microscopic simulation for it to study the driver's behavior and create the statistical model. Thus, obtaining the mathematical relationships and coefficients that illustrate that process, after verifying the reliability and calibration of these variables.
 This research aims to facilitate the highway assessment process, as an alternative or supplementary method of highway evaluation by the Highway Capacity Manual 2010. It is adequate to record a video and count the number of vehicles that change their lanes and then compare them with the results that have been determined in the search to judge the highway is congested or not.
 The study area was achieved by choosing five segments of multilane arterial roads (six lanes divided) on the left coast of Mosul city. These segments were selected to be as similar as possible in the geometric configuration as well as like traffic flow. After that, cameras were installed according to criteria to record traffic movement and for a time not less than ten hours for each segment, and on the workdays for traffic movement. Then, the videos were uploaded using the Goodvision traffic data recognition program. These outputs were converted to be entered into the PTV-VISSIM traffic simulation program in addition to the other geometric information needed by the program to complete the analysis process and find traffic flow parameters. In the extraction process, the normal distribution and the uniform nature of the data representation of the observed event on the segments were examined using the Z-test and the K-S test, the results were normal and significant. Then the results were verified and the traffic parameters such as density and flow rate were checked to ensure the nature of the traffic flow. The process was also verified using the vehicle motion graphic representation method (Vehicle Trajectory), which is the initial examination to estimate the new variable.
 A new variable has been extracted, which is one of the traffic movement variables, which depends on the percentage of complete and proper lane change completion within the parameters imposed by the simulation program, it’s the Lane Change Occupancy factor (LnChOc.). Then the statistical model was derived using SPSS for the new variable. It describes traffic conditions on highways and the results are verified and calibrated in more than one way. It’s a simple statistical model was obtained to estimate the traffic movement from this variable and vice versa from the following equation:, Which gave results for critical traffic on multi-lane roads in the Mosul city as follows: -
 Ø 
 Ø 
 Ø 
 
 
 

Evaluating the Sustainable Traffic Flow Operational Features of U-turn Design with Advance Left Turn

Median U-turn intersection treatment (MUIT) has been considered as an alternative measure to reduce congestion and traffic conflict at intersection areas, but the required spacing between the U-turn opening and the intersection limits its applicability. In this paper, a U-turn design with Advance Left Turn (UALT) is proposed with the aim of addressing the disadvantages of insufficient intersection spacing and difficulty in the continuous vehicle lane change. UALT provides a dedicated lane to advance the turning vehicle out of the intersection and directly to the U-turn opening without interacting with through traffic. The effectiveness and traffic volume applicability of UALT was demonstrated through field data investigation, simulation and analysis with VISSIM software. The proposed design was evaluated in terms of three parameters: delay, queue length and the number of stops. The results show that when the traffic volume range of the main road is (1900, 2200) pcu/h and the traffic volume of the secondary road is more than 900 pcu/h, the optimization effect of UALT on both conventional intersections and MUIT is very significant. Taking a signal-controlled intersection in Zhengzhou City, China, as an example to build a simulation model, compared with the conventional intersection and MUIT, the delay drop is reduced by 73.48% and 41.48%, the queue length is reduced by 84.85% and 41.66%, and the operation efficiency is significantly improved.

Research on human-like lane-changing control of intelligent vehicles based on extension goodness evaluation

In order to improve the trajectory tracking accuracy and passenger comfort for intelligent vehicle lane-changing at medium and high speed, this paper proposes a new control algorithm based on extension evaluation system for intelligent vehicle lane-changing. In this research, firstly, a vehicle-road dynamics model has been developed. In addition, the actual driving trajectory data of skilled drivers are collected by driving simulator, and the lane-changing path planning model is established based on generalized regression neural network (GRNN). Last, in order to improve the tracking ability to the planning path, the trajectory tracking controller is established. A two-layer structure of lateral trajectory tracking control system is designed, in which the upper layer includes two algorithms: (1) PID feedback control based on preview deviation; (2) PID feedforward-feedback control based on the curvature of the path planning by skilled drivers. While the extension goodness evaluation is introduced in the lower layer which is used to evaluate two controllers in upper layer. According to the real-time state of vehicle-road system, the controller output with higher goodness is selected. Finally, the simulation results verify that comparing with the conventional single PID feedback control, the extension goodness evaluation control can effectively improve the passenger comfort while ensuring tracking accuracy.

Influencing Factors of the Length of Lane-Changing Buffer Zone for Autonomous Driving Dedicated Lanes

With the development of intelligent transportation, dedicated highway lanes for autonomous vehicles (AVs), necessary for ensuring their right of way, have emerged as critical issues in intelligent transportation research, which makes it necessary to set up specialized lane-changing buffer zones in the lane adjacent to the dedicated one. Restricted by the current situation of intelligent transportation systems, based on NGSIM data, this study filters out typical lane-changing description data featuring lane-changing behaviors and constructs a principal component analysis (PCA) model containing factors affecting the longitudinal driving distance during the whole lane-changing procedure. The validity of the model is evaluated with a significance test. Comparing the PCA model to a general linear regression model, suggestions on setting the length of lane-changing buffer zones are put forward. The length of the buffer zone mainly considers speed, acceleration, and the flow in the dedicated lane. In general, a shorter buffer zone length can be achieved by increasing the design speed of the buffer zone, raising the headway of AVs in the dedicated lane, reducing the acceleration rate of lane-changing vehicles, and reducing the time proportion of the lane change preparation stage, which occurs earlier in the procedure.

Support Vector Machine Based Lane-Changing Behavior Recognition and Lateral Trajectory Prediction.

With the development of technology, vehicle trajectory prediction and safety decision technology has become an important part of active safety technology. Among them, the vehicle trajectory prediction technology can predict the vehicle position, speed, and other motion states in the predicted period according to the current and historical vehicle running state, and the prediction results can provide support for judging the vehicle safety in the predicted period. In order to analyze the above problems, this study fully extracted the main feature information from the vehicle lane change track data with the help of the powerful nonlinear learning and high pattern recognition ability of support vector machine, and conducted identification modeling for the actual lane change process of the vehicle and predictive analysis of the vehicle lateral movement track. First, the lane-changing behavior of vehicles was analyzed, and the vehicle lane-changing execution stage and 10 influencing factors that could characterize lane-changing behavior were determined based on NGSIM to extract the data of lane-change-related variables. Then, a lane-changing recognition model based on gridsearch-PSO is proposed. In the Matlab environment, the model has a test accuracy of 97.68%, while the SVM model without optimization parameters has a recognition accuracy of only 80.87%. The results show that the model has strong classification ability and robustness. Finally, by using the polynomial model for lateral movement trajectory fitting, K-fold cross-validation method is used for fitting polynomial model fitting test.

Research on Vehicle Lane Change Warning Method Based on Deep Learning Image Processing.

In order to improve vehicle driving safety in a low-cost manner, we used a monocular camera to study a lane-changing warning algorithm for highway vehicles based on deep learning image processing technology. We improved the mask region-based convolutional neural network for vehicle target detection. Suitable anchor frame ratios were obtained by means of K-means++ method clustering for 66,389 vehicle targets with the width/height ratio, which is one more set of anchor frames than the original setting, so as to ensure that the generation accuracy of candidate frames can be improved without sacrificing more network performance. Using the vehicle target annotation set, we trained the vehicle targets. Through the analysis of indicators for mean average precision, a new set of anchor frames was added to improve the accuracy of vehicle target detection. Based on the improved vehicle detection network and an end-to-end lane detection network in series, we proposed an algorithm for the detection of highway vehicle lane-changing behavior with the first-person perspective by summing the inter-frame change rates in the vehicle lane-changing data pool. After the identification and verification of the marked lane-changing picture sequences, a lane-changing detection accuracy rate of 94.5% was achieved.

Characterizing lane changing behavior and identifying extreme lane changing traits

ABSTRACT This study characterizes lane changing behavior of drivers under differing congestion levels and identifies extreme lane changing traits using high-resolution trajectory data. Total lane change frequency exhibited a reciprocal relationship with congestion level, but the distribution of lane change per vehicle remained unchanged as congestion increased. On average, the speed of trajectories increased by 5.4 ft/s after changing a lane. However, this gain significantly diminished as congestion worsened. Further, the average speed of lane changing vehicles was 3.9 ft/s higher than those that executed no lane changes. Two metrics were employed to identify extreme lane changing behavior: critical time-to-line-crossing (TLCc) and lane changes per unit distance. The lowest 1% TLCc varied between 0.71–1.57 seconds. The highest 1% of lane change rates for all lane changing vehicles was 2.5 lane changes per 1,000 ft traveled. Interestingly, no drivers in thisdataset had both excessive lane changes and lane changes with low TLCc.

An integrated car-following and lane changing vehicle trajectory prediction algorithm based on a deep neural network

Vehicle trajectory prediction is essential for the operation safety and control efficiency of automated driving. Prevailing studies predict car following and lane change processes in a separate manner, ignoring the dependencies of these two behaviors. To remedy this issue, this paper proposes an integrated deep learning-based two-dimension trajectory prediction model that can predict combined behaviors. Specifically, we designed a switch neural network structure based on the attention mechanism, bi-directional long-short term memory (BiLSTM) and Temporal convolution neural network (TCN) to mimic and predict the joint behaviors. Experiments are conducted based on the Next Generation Simulation (NGSIM) dataset to validate the effectiveness of our proposed model. As results indicate, our proposed model outperforms the state-of-art trajectory prediction models and can provide accurate short-term and long-term predictions.

A variable weight adaptive cruise control strategy based on lane change recognition of leading vehicle

The traditional adaptive cruise system is responsible for delay in recognizing the cut-in/cut-out behaviour of front vehicle, and there is significant longitudinal acceleration of the vehicle fluctuation leading to reduced driver’s comfort level and even dangerous situation. In this paper, the next generation simulation data set and back propagation (BP) neural network are used to train the vehicle lane change recognition model to recognize the lane change behaviour of the preceding vehicle. The higher controller adopts variable weight linear quadratic optimal control to adjust the weight parameters according to the recognition results of front vehicle to reduce the fluctuation of vehicle acceleration. The lower layer adopts fuzzy proportional-integral-derivative (PID) control to follow the expected acceleration and builds the vehicle inverse dynamic model. Through CarSim/Simulink co-simulation, the results show that, under the cut-in or cut-out and working conditions, the behaviour of the leading vehicle can be recognized, following target can be switched in advance, weight parameters can be adjusted and the large fluctuation of longitudinal acceleration can be reduced.

Two-lane mixed traffic flow model considering lane changing

Based on the analysis of the advantages and disadvantages of the existing car-following model and combined with the actual road conditions, an improvement scheme is proposed for the selected model. The improvement plan adds the consideration of the speed difference between the front and rear vehicles, and introduces the safe distance parameter of the most dangerous situation when the vehicle is braking. The comparison with the actual measurement results after simulation and conversion shows that the improved car following model is effective and the vehicle lane change rules are improved. The improvement of lane changing rules allows different lane changing rules to be obtained in different situations. The lane-changing rules are coupled with the improved car-following model to obtain a two-lane model based on different rules. The corresponding programming simulation is compared with the measured road results to verify the practicability of the model. The simulation result shows that the new model can still reproduce the road traffic flow under different lane changing rules. After the introduction of mixed traffic, the model can reproduce the maximum flow of the road within the error tolerance.

Research on collaborative lane changing control method of unmanned vehicle based on internet of vehicles cooperation

In this paper, a new method of coordinated lane change control for unmanned vehicles based on the cooperation of vehicle network is proposed. The paper analyses the vehicle lane change strategy, calculates the distance between the self-vehicle and the front vehicle without collision and tail, and preliminarily plans the track of lane change according to the environmental information obtained from the visual environment perception part. With the support of the collaborative model control of the vehicle network, the Kalman predictor and SIFT feature extraction method are used to obtain the information of the motion and position of the unmanned vehicles, and realise the coordinated lane change control. The experimental results show that the error range of the operation failure rate is 1.00-2.31, the response time is 0.878 min, the vehicle lane change efficiency is high, and the practical application effect is good.

Environment-aware vehicle lane change prediction using a cumulative probability mapping model

Environment-aware vehicle lane change prediction using a cumulative probability mapping model

Environment-aware vehicle lane change prediction using a cumulative probability mapping model

Environment-aware vehicle lane change prediction using a cumulative probability mapping model

Deep Learning Model for Vehicle Lane-Change Detection in Phantom Traffic Jam Using CCTV Images

Traffic jams are a threat to safety and can result in economic losses. Traffic jams that occur for no specific reason are called phantom traffic jams. If there are many cars on the road, all the cars try to choose a faster route. In this case, the following cars have no choice but to slow down to avoid an accident, resulting in congestion. In this paper, an artificial intelligence model based on image deep learning for vehicle lane-change detection in phantom traffic jams is proposed. Pictures were captured every 0.2 s from a real-time CCTV video of one position in Seoul. The precision of the proposed model for determining and detecting vehicle lane change was found to be 0.842. The proposed model is expected to help analyze the impact of phantom traffic jams on traffic flow.

Multimodal Feature-Assisted Continuous Driver Behavior Analysis and Solving for Edge-Enabled Internet of Connected Vehicles Using Deep Learning

The emerging technology of internet of connected vehicles (IoCV) introduced many new solutions for accident prevention and traffic safety by monitoring the behavior of drivers. In addition, monitoring drivers’ behavior to reduce accidents has attracted considerable attention from industry and academic researchers in recent years. However, there are still many issues that have not been addressed due to the lack of feature extraction. To this end, in this paper, we propose the multimodal driver analysis internet of connected vehicles (MODAL-IoCV) approach for analyzing drivers’ behavior using a deep learning method. This approach includes three consecutive phases. In the first phase, the hidden Markov model (HMM) is proposed to predict vehicle motion and lane changes. In the second phase, SqueezeNet is proposed to perform feature extraction from these classes. Lastly, in the final phase, tri-agent-based soft actor critic (TA-SAC) is proposed for recommendation and route planning, in which each driver is precisely handled by an edge node for personalized assistance. Finally, detailed experimental results prove that our proposed MODAL-IoCV method can achieve high performance in terms of latency, accuracy, false alarm rate, and motion prediction error compared to existing works.