Lane Change Trajectory Research Articles

Modeling decentralized mandatory lane change for connected and autonomous vehicles: An analytical method

Mandatory lane change (MLC) is the core of lane-specific motion planning for connected and autonomous vehicles (CAVs). To model the MLC for CAVs, this paper presented a decentralized cooperative MLC (DC-MLC) framework. The framework aimed to achieve a safe MLC maneuver with multiple-CAV cooperation, including the lane change times, positions, and trajectories for the CAVs, while minimizing the impacts of the MLC maneuver on overall traffic. This problem was rigorously formulated and solved by an analytical method that significantly decreases computational time and renders the methodology suitable for practical implementations. To evaluate the performance of the proposed DC-MLC framework, we built a CAV testing environment by referring to the next generation simulation program (NGSIM) US 101 dataset. A series of numerical experiments were conducted under the built CAV testing environment. The results showed that the proposed DC-MLC framework could achieve safe, traffic-efficient, and comfortable MLC maneuvers. Moreover, the trajectories generated by the proposed DC-MLC framework outperformed those of human drivers in terms of speed standard deviation, maximum acceleration/deceleration, and maximum acceleration jerk.

Dynamic lane changing trajectory planning for CAV: A multi-agent model with path preplanning

This paper presents a multi-agent dynamic lane-changing (LC) trajectory planning method for CAV. In this method, a decision module is constructed by means of a potential field to determine the LC starting point. Then a series of trajectories is generated in the trajectory generation module. A cost function is constructed for searching for the corresponding optimal trajectory for both the subject vehicle and the participants. The simulation results indicate that the proposed model improves the LC success rate and reduces duration. Differing from the traditional model, we consider the cooperation feature of CAV’s LC and satisfy the subject vehicle’s demand as well as minimizing its impact on the other participants. Moreover, the driving environment including mesoscale information is considered to improve the LC success rate, which provides a new strategy for optimizing LC decision. Additionally, the method can also be applied to simulate CAVs’ LC behaviour.

A cooperative lane change approach for heterogeneous platoons under different communication topologies

To improve the platoon's passability and traffic efficiency, a cooperative lane change approach is proposed when the platoon encounters a slow obstacle vehicle ahead in this paper. The algorithm is designed for the heterogeneous platoon, that is, the vehicles are dynamically decoupled and have different parameters. The vehicles in the platoon can have different communication topologies. To complete the lane change process quickly, all vehicles in the platoon perform simultaneously. The approach is mainly divided into two parts: trajectory planning and cooperative control. In the trajectory planning part, combined with the polynomial method and the optimization method, the leading vehicle plans an optimal lane change trajectory according to its own states and the obstacle vehicle's states. A distributed model predictive control algorithm is designed in the cooperative control part to meet the requirement that all vehicles should change lanes simultaneously. Besides, the sufficient conditions to achieve the asymptotic stability are also given, and the simulation results can show the effectiveness of the algorithm.

Influence of the median opening length on driving behaviors in the crossover work zone—A driving simulation study

Work zone safety has been a major concern for drivers and transportation agencies. Considering the severe consequences of crossover work zone crashes coupled with the limited literature on the median opening length, this paper aims to investigate the influence of the median opening length on driving behaviors from a behavioral perspective in crossover work zones. A driving simulation study with 32 participants was carried out to investigate the driving performance by metrics (speed, acceleration, maximum steering wheel speed, and lane-changing trajectory) with respect to five median opening lengths. The significant differences of each driving performance metric among various median opening lengths were found in the process of crossing through the median opening on the entrance by-pass and exit by-pass. The results indicated that drivers’ speeds were always higher than the speed limits for all median opening lengths. A narrower median opening may induce risky driving behaviors such as sharp deceleration and decelerating while lane-changing, which may increase speed variance. When crossing through the median opening with a larger length, high speed variance, sluggish lane-changing operations, and improper lane-using behaviors were observed because the excessive lane-changing space provided by the larger median opening length would decrease the situation awareness and increase the speed preference heterogeneity among drivers. Finally, some traffic management strategies were proposed, which can improve the safety and mobility of crossover work zones and further provide a basis for the formulation of related standards.

Long-term prediction for high-resolution lane-changing data using temporal convolution network

Lane-changing is an important driving behaviour and unreasonable lane changes can potentially result in traffic accidents. Currently, the lane-changing data are often recorded with high resolution, which are not appropriate for some common deep learning approaches. To capture the stochastic time series of high-resolution lane-changing behaviour, this study introduces a temporal convolutional network (TCN) to predict the long-term lane-changing trajectory and behaviour. The lane-changing dataset was collected by the driving simulator at the frequency of 60 Hz. Prediction results show that the TCN can accurately predict the long-term lane-changing trajectory and driving behaviour with shorter computational time compared with two benchmark models including the convolutional neural network (CNN) and long short-term memory neural network (LSTM). The advantages of the TCN are rapid response and accurate long-term prediction, which are important for lane-changing assistance in the advanced driver assistance system.

Dynamic Lane-changing Trajectory Planning Model for Intelligent Vehicle Based on Quadratic Programming

Dynamic Lane-changing Trajectory Planning Model for Intelligent Vehicle Based on Quadratic Programming

A Personalized Human-Like Lane-Changing Trajectory Planning Method for Automated Driving System

This article describes a human-like automated lane-changing system to mimic the lane-changing maneuver of human drivers in order to make automated vehicles more realistic. In this system, both the personalized factors of human drivers and the traffic environmental factors are considered to derive a personalized human-like lane-changing trajectory planning model, which includes a longitudinal driving behavior model and a lateral lane-changing trajectory planning model. The longitudinal model is derived based on the traffic environment information to predict the longitudinal speed of human-driven vehicles in the lane-changing processes, and also to analyze the longitudinal driving habits of drivers in different driving scenarios. The lateral model plans a suitable lateral lane-changing trajectory preferred by the driver. The personalized parameters of the longitudinal and lateral models are calibrated by the driving data with multi-dimensional time series regression method. The simulation results show that the proposed method can well realize the human-like and personalized lane-changing trajectory planning.

Research on Unmanned Static Trajectory

With the development of science and technology, the intelligence of society is getting higher and higher. The development of safe and reliable intelligent driving has become one of the important topics in today’s era. As a high-tech complex integrating environmental awareness, planning decision-making, control execution and information interaction, driverless cars are increasingly becoming the needs of the times.[1] How to accurately extract effective information to provide safe and reliable control instructions for the next decision-making of vehicles in complex multi-source and heterogeneous environment is the technical basis of intelligent driving.In this paper, a certain amount of research has been done on lane change trajectory planning in different environments. In the aspect of static driving environment, a lane-changing trajectory planning method based on the fifth-order Bessel curve is planned. The physical problems are transformed into optimization problems of coordinate points of Bessel curve expression by planning the left and right boundaries of feasible region through lane-changing trajectory. [2]In the aspect of dynamic driving, based on the model predictive control theory, a lane-changing trajectory optimization method for multi-lane and multi-surrounding vehicles is proposed.

A self-learning lane change motion planning system considering the driver’s personality

Nowadays, with more and more attention being paid to the characteristics and experience of drivers, a large number of driver classification algorithms have emerged. However, these methods basically cannot be adjusted independently to each driver. Therefore, this paper proposes a self-learning lane change motion planning system considering the driver’s personality. Firstly, the method of driver data acquisition and processing is determined to obtain and extract the lane change data. Then, the planning system built in this paper is explained from two aspects: lane change trigger and lane change trajectory. According to the artificial potential field theory, an obstacle driving risk field is established to evaluate the acceptance of environmental risks of different drivers, and to achieve personalized lane change triggers through online statistics. At the same time, the safety of lane change is ensured by establishing the safety distance model of the target lane. On the other hand, the driver characteristic coefficient Jc and the driver reaction and operation time td are introduced into the traditional Gaussian-distributed model to establish a personalized lane change trajectory planning model, in which the parameters are obtained from offline and online learning. Offline learning is based on DTW for trajectory matching, and uses AP clustering to obtain the generalized parameters; Online learning uses LSTM to achieve personalized updates. Finally, this paper selected 15 drivers for verification, and the results show that the motion planning system can well reproduce the lane change behavior of the driver.

Comparison of Machine Learning Algorithms for Predicting Lane Changing Intent

The ability to predict the intent of drivers from surrounding vehicles to change lanes is key to risk assessment and early danger warning systems. Since lane change trajectories are highly nonlinear, many studies have been performed on various machine learning algorithms using different features to predict a driver’s intent to change lanes. However, these algorithms use various features that cannot be obtained from the ego vehicle’s view point. In this paper, we define features that can be detected from the ego vehicle via on-board sensors and vehicle-to-vehicle communication (V2V). Gini Impurity is used to select the most appropriate features. Additionally, we compare several machine learning algorithms, including random forest (RF), support vector machine (SVM), long short term memory (LSTM), and gated recurrent unit (GRU), to find the best algorithm to predict lane changes. We evaluate the performance of these four algorithms on the Next Generation Simulation (NGSIM) dataset, which was collected by the Federal Highway Administration of the U.S. Department of Transportation. We use the I-80 dataset to train a lane changing prediction model and the US-101 dataset to test it. The test results indicate that RF had the best accuracy of the tested algorithms with an accuracy of 82 % in predicting lane changing intent.

A Dynamic Lane-changing Trajectory Planning Methodology in Weaving Areas of Dedicated Connected-and Automated-Vehicle Lanes

A Dynamic Lane-changing Trajectory Planning Methodology in Weaving Areas of Dedicated Connected-and Automated-Vehicle Lanes

Time‐dependent lane change trajectory optimisation considering comfort and efficiency for lateral collision avoidance

Lateral collision is one of the top two accidents in the world and often occurs in the lane change. Trajectory optimisation is an effective method to solve traffic conflicts in the lane-changing process. However, current trajectory optimisation methods are not friendly to human-computer-based driving assistance. This study proposes a time-dependent lanechange trajectory optimisation considering comfort and efficiency. First, spacing constraints between the lane-changing vehicle and surrounding vehicles are determined and quantified. Second, lane-changing trajectory data are obtained by driving simulation experiments and extracted by data features. Third, a quintic multinomial model of lane-changing trajectory is proposed. The results reveal that the predicted trajectory is close to the observed value. Then, the obtained trajectory is optimised by the objective function considering lane-changing efficiency and comfort. Finally, a case study is used to demonstrate the application of the model. When a lane-changing vehicle changes a lane at an initial speed of 90 km/h to the faster lane at the terminal speed of 110 km/h, the optimal lane-changing time is 3.4 s, with the lateral acceleration 1.79 m/s2 and the maximum yaw angle 0.081 rad.

Intelligent vehicle lane change trajectory control algorithm based on weight coefficient adaptive adjustment

In order to improve the trajectory smoothness and the accuracy of lane change control, an adaptive control algorithm based on weight coefficient was proposed. According to lane change trajectory constraint conditions, the sixth-order polynomial lane change trajectory applied to intelligent vehicles was constructed. Based on the vehicle model and the model predictive control theory, the time-varying linear variable path vehicle predictive model was derived by combining soft constraint of the side slip angle. Combined with fuzzy control algorithm, the weight coefficient of the deviation of the lateral displacement was dynamically adjusted. Finally, the FMPC (model predictive controller based on fuzzy control) and MPC controller were compared and analyzed by co-simulation of CarSim and Simulink under different speeds. The simulation results show that the designed FMPC controller can track the lane change trajectory better, and the controller has better robustness when the vehicle changes lanes at different speeds.

A dynamic trajectory planning method for lane-changing maneuver of connected and automated vehicles

This paper describes a dynamic trajectory planning method for lane-changing maneuver of connected and automated vehicles (CAVs). The proposed dynamic lane-changing trajectory planning (DLTP) model adopts vehicle-to-vehicle (V2V) communication to generate an automated lane-changing maneuver with avoiding potential collisions and rollovers during the lane-changing process. The novelty of this method is that the DLTP model combines a detailed velocity planning strategy and considers more complete driving environment information. Besides, a lane-changing safety monitoring algorithm and a lane-changing starting-point determination algorithm are presented to guarantee the lane-changing safety, efficiency and stability of automated vehicles. Moreover, a trajectory-tracking controller based on model predictive control (MPC) is introduced to make the automated vehicle travel along the reference trajectory. The field traffic data from NGSIM are selected as the target dataset to simulate a real-world lane-changing driving environment. The simulations are performed in CarSim-Simulink platform and the experimental results show that the proposed method is effective for lane-changing maneuver.

A New Parametric Function-Based Dynamic Lane Changing Trajectory Planning and Simulation Model

Lane-changing (LC) problem may cause serious accidents or create a painful traffic jam at multi-lane roads. Existing LC simulation model was created with some limitations (less fitted, without velocity and acceleration profiles, high curvature) by using well known trajectory curve such as Hyperbolic Tangent Curve (HTC), Sine-Based Curve (SC), Polynomial Curve (PC). In this study, a new parametric curve had been proposed by using curvilinear coordinate system and fitted against Next Generation Simulation (NGSIM) real dataset. Further, new profiles of velocity and acceleration were designed using the proposed LC trajectory curve. The curvature of proposed model was zero-based curvature both at LC starting and ending points. This proposed curvature was compared with two models such as HTC and SC. The average root-mean-square-error of proposed model decreased with 1.84% for left LC and 15.48% for right LC compared to HTC model and 1.74% for left LC and 15.60% for right LC compared to SC model. Similarly, the proposed model for velocity and acceleration profiles improved significantly from PC model. The proposed parametric curve solves the gap and collision points of LC vehicle with a front vehicle and rear vehicle at target lane and can be used in real LC path planning.

Tracking Control of Intelligent Vehicle Lane Change Based on RLMPC

Autonomous lane changing, as a key module to realize high-level automatic driving, has important practical significance for improving the driving safety, comfort and commuting efficiency of vehicles. Traditional controllers have disadvantages such as weak scene adaptability and difficulty in balancing multi-objective optimization. In this paper, combined with the excellent self-learning ability of reinforcement learning, an interactive model predictive control algorithm is designed to realize the tracking control of the lane change trajectory. At the same time, two typical scenarios are verified by PreScan and Simulink, and the results show that the control algorithm can significantly improve the tracking accuracy and stability of the lane change trajectory.

Robust Tube-Based Model Predictive Control for Lane Change Maneuver of Tractor-Trailer Vehicles Based on a Polynomial Trajectory

This paper reports an effective quintic polynomial-based trajectory planning approach and a robust tube-based model predictive control (RTMPC) method for an underactuated tractor-trailer vehicle system during lane change maneuver. To begin with, a time-based quintic polynomial function is introduced for implementation of trajectory planning, which takes vehicle system safety, comfort, and traffic efficiency into account. After that, an RTMPC scheme, consisting of a nominal system-oriented model predictive controller and an ancillary feedback control law, is proposed to construct posture controller, such that favorable transient performances can be achieved for the trajectory tracking process. Lastly, the simulation results confirm that the proposed lane change trajectory planning and tracking control methods can effectively perform the lane change behaviors for tractor-trailer vehicles.

Research on Vehicle Trajectory Tracking Control in Expressway Maintenance Work Area Based on Coordinate Calibration

In the highway maintenance work area, how to reduce traffic congestion and traffic accidents caused by vehicle changing lanes has become a continuing research issue. This research focuses on the lane-changing behavior of vehicles in the highway maintenance work area. By changing the lane-changing trajectory of vehicles under different lane numbers, it can intuitively understand the influence of different lane numbers on lane-changing characteristics. Studies have shown that when the number of highway lanes increases, the distance between the starting point of the vehicle lane change and the highway maintenance work area will increase. At the same time, the probability of changing lanes in front lanes that are barrier-free and does not need to change lanes decreases as the number of overlapping lanes increases. Under the condition of the same number of lanes, the closer the distance between the vehicle and the obstacle lane, the more convergent the lane-changing trajectory of the vehicle, and the probability of lane-changing greatly increases.

Lane-Change Model and Tracking Control for Autonomous Vehicles on Curved Highway Sections in Rainy Weather

In this study, we propose an adaptive path planning model and tracking control method for collision avoidance and lane-changing manoeuvres on highways in rainy weather. Considering the human-vehicle-road interaction, we developed an adaptive lane change system that consists of an intelligent trajectory planning and tracking controller. Gaussian distribution was introduced to evaluate the impact of rain on the pavement characteristics and deduce adaptive lane-change trajectories. Subsequently, a score-based decision mechanism and multilevel autonomous driving mode that considers safety, comfort, and efficiency were proposed. A tracking controller was designed using a linearised model predictive control method. Finally, using simulated scenarios, the feasibility and effectiveness of the proposed method were demonstrated. The results obtained herein are a valuable resource that can be used to develop an intelligent lane change system for autonomous vehicles and can help improve highway traffic safety and efficiency in adverse weather conditions.

Investigating model and impacts of lane-changing execution process based on CA model

Lane changing is one of the basic driving behaviors and consists of lane-changing decision-making process and lane-changing execution process. However, most existing traffic simulation models focus on lane-changing decision-making process and assume that drivers complete their lane-changing behaviors instantaneously. Then these models may not reproduce the actual traffic phenomenon. Furthermore, there are several failed lane-changing behaviors, referring to that drivers may go back to the original lane during lane-changing process. And the impacts of these behaviors have not been investigated up to now. In order to characterize the lateral movement process and to investigate its impacts on traffic flow, this study puts forward a symmetric two-lane cellular automaton model with lane-changing execution (STCA-LE model). In this model, the lateral movement rules of lane changing vehicles are formulated and introduced. The results of numerical simulation indicate that there is a positive relationship between the lane-changing duration and traffic density that is consistent with observation data analysis. Based on this model, the lane-changing trajectories and impacts of lane-changing process are investigated by introducing the critical lane-changing duration. The results of this study could be taken as an important reference to the development of traffic measures and the designation of intelligent vehicles.