Lane Change Research Articles

Behavioral Modeling of Drivers near Speed Control Cameras: A Dual Perspective from Micro and Macro Data

The present study investigates the efficacy of speed cameras in managing vehicle speeds and their influence on various driver demographics within the operational context of the cameras. The research, conducted as a case study in Iran, comprises both macroscopic and detailed analyses, quantifying vehicle speeds at different spatial points relative to the speed camera location—upstream, adjacent to, and downstream of the camera—using a manual laser speedometer. Furthermore, the study examines diverse driver behavior metrics, including vehicle type, speeds at different locations, lane changes, braking actions, and measures such as obscuring license plates. Statistical analyses show that speed cameras effectively reduce speeds across different user groups and lead to increased braking and lane-changing behaviors, particularly among light vehicle categories. Moreover, the study reveals distinct behavioral patterns between indigenous and non-indigenous drivers. In addition, a multi-layer perceptron neural network model successfully approximates user speed selection behaviors within the operational range of speed cameras. Overall, this research provides valuable insights into the effectiveness of speed cameras and their impact on diverse driver demographics, contributing to a deeper understanding of advanced speed control mechanisms.

Real-Time Run-Off-Road Risk Prediction Based on Deep Learning Sequence Forecasting Approach

Driving risk prediction is crucial for advanced driving technologies, with deep learning approaches leading the way in driving safety analysis. Current driving risk prediction methods typically establish a mapping between driving features and risk statuses. However, status prediction fails to provide detailed risk sequence information, and existing driving safety analyses seldom focus on run-off-road (ROR) risk. This study extracted 660 near-roadside lane-changing samples from the high-D natural driving dataset. The performance of sequence and status prediction for ROR risk was compared across five mainstream deep learning models: LSTM, CNN, LSTM-CNN, CNN-LSTM-MA, and Transformer. The results indicate the following: (1) The deep learning approach effectively predicts ROR risk. The Macro F1 Score of sequence prediction significantly surpasses that of status prediction, with no notable difference in efficiency; (2) Sequence prediction captures risk evolution trends, such as increases, turns, and declines, providing more comprehensive safety information; (3) The presence of surrounding vehicles significantly impacts lane change duration and ROR risk. This study offers new insights into the quantitative research of ROR risk, demonstrating that risk sequence prediction is superior to status prediction in multiple aspects and can provide theoretical support for the development of roadside safety.

Vehicle Lane Changing Game Model Based on Improved SVM Algorithm

In order to improve the autonomous lane-changing performance of unmanned vehicles, this paper aims to solve the problem of inaccurate decision classification in traditional support vector machine (SVM) algorithms applied to the lane-changing decision-making stage of intelligent driving vehicles. By using game theory-related theories and combining the improved support vector machine (SSA-SVM) method, a vehicle autonomous lane-changing strategy based on game theory is established. The optimized SVM method has certain advantages for vehicle lane-changing decision-making with a small sample size in actual production processes. The lane-changing decision judgment accuracy rate of the SSA-SVM algorithm model can reach 93.6% compared with the SVM algorithm model without algorithm optimization; the SSA-SVM algorithm model has obvious advantages in decision performance and running speed. Therefore, the proposed new algorithm can effectively solve the problem of the objective consideration of the payoff function in conventional decision game theory.

Lane Change Behavior Patterns and Risk Analysis in Expressway Weaving Areas: Unsupervised Data-Mining Method

Lane Change Behavior Patterns and Risk Analysis in Expressway Weaving Areas: Unsupervised Data-Mining Method

Human-like Decision Making for autonomous lane change driving: a hybrid inverse reinforcement learning with game-theoretical vehicle interaction model

The development of automated driving vehicles aims to provide safer, comfortable, and more efficient mobility options. However, the decision-making control of autonomous vehicles still embraces limitations on human performance mimicry. These limitations become particularly evident in complex and unfamiliar driving scenarios, where weak decisionmaking abilities and poor adaptation of vehicle behaviour are prominent issues. This paper proposes a game-theoretic decisionmaking algorithm for human-like driving in the vehicle lane change scenario. Firstly, an inverse reinforcement learning (IRL) model is used to quantitatively analyse the lane change trajectories of the natural driving dataset, establishing the human-like human cost function. Subsequently, joint safety, comfort to build the comprehensive decision cost function. Use the combined decision cost function to conduct a non-cooperative game of vehicle lane changing decision to solve the optimal decision of host vehicle lane changing. The host vehicle lane-changing decision problem is formulated as a Stackelberg game optimization problem. To verify the feasibility and effectiveness of the algorithm proposed in this study, a lane change test scenario has been established. Firstly, we analyse the human-like decision-making model derived by the maximum entropy inverse reinforcement learning algorithm to verify the effectiveness and robustness of the IRL algorithm. Secondly, the human-like game decisionmaking algorithm in this paper is validated by conducting an interactive lane-changing experiment with obstacle vehicles of different driving styles. The experimental results prove that the human-like driving decision-making model proposed in this study can make lane-changing behaviours in line with human driving patterns in lane-changing scenarios of expressway.

Towards Sustainable Transportation: Adaptive Trajectory Tracking Control Strategies of a Four-Wheel-Steering Autonomous Vehicle for Improved Stability and Efficacy

The objective of continuous increase in the evolution of autonomous and intelligent vehicles is to attain a trustworthy, economical, and safe transportation system. Four-wheel steering (4WS) vehicles are favored over traditional front-wheel steering (FWS) vehicles because they have excellent dynamic characteristics. This paper exhibits the trajectory tracking task of a two degree of freedom (2DOF) underactuated 4WS Autonomous Vehicle (AV). Because the system is underactuated, MIMO, and has a nontriangular form, the traditional adaptive backstepping control scheme cannot be utilized to control it. For the purpose of rectifying this issue, two-state feedback-based methods grounded on the hierarchical steps of the block backstepping controller are proposed and compared in this paper. In the first strategy, a modified block backstepping is applied for the entire dynamic system. Global stability of the overall system is manifested by Lyapunov theory and Barbalat’s Lemma. In the second strategy, a block backstepping controller has been applied after a reduction of the high-order model into various first-order subsystems, consisting of Lyapunov-based design and stability warranty. A trajectory tracking controller that can follow a double lane change path with high accuracy is designed, and then simulation experiments of the CarSim/Simulink connection are carried out against various vehicle longitudinal speeds and road surface roughness to demonstrate the effectiveness of the presented controllers. Furthermore, a PID driver model is introduced for comparison with the two proposed controllers. Simulation outcomes show that the proposed controllers can attain good response implementation and enhance the 4WS AV performance and stability. Indeed, enhancement of the stability and efficacy of 4WS autonomous vehicles would afford a sustainable transportation system by lessening fuel consumption and gas emissions.

Drone Vision-based Lane Change Prediction in Urban Vehicle Driving with Transformer

Drone Vision-based Lane Change Prediction in Urban Vehicle Driving with Transformer

Efficient Vehicle Detection and Optimization in Multi-Graph Mode Considering Multi-Section Tracking Based on Geographic Similarity

Vehicle detection is an important part of modern intelligent transportation systems. At present, complex deep learning algorithms are often used for vehicle detection and tracking, but high-precision detection results are often obtained at the cost of time, and the existing research rarely considers optimization algorithms for vehicle information. Based on this, we propose an efficient method for vehicle detection in multi-graph mode and optimization method considering multi-section tracking based on geographic similarity. In this framework, we design a vehicle extraction method based on multi-graph mode and a vehicle detection technology based on traffic flow characteristics, which can cope with the challenge of vehicle detection under an unstable environment. Further, a multi-section tracking optimization technology based on geographic similarity at a high video frame rate is proposed, which can efficiently identify lane change behavior and match, track, and optimize vehicles. Experiments are carried out on several road sections, and the model performance and optimization effect are analyzed. The experimental results show that the vehicle detection and optimization algorithm proposed in this paper has the best effect and high detection accuracy and robustness. The average results of Recall, Precision, and F1 are 0.9715, 0.979, and 0.9752, respectively, all of which are above 0.97, showing certain competitiveness in the field of vehicle detection.

Risk-Aware Lane Change and Trajectory Planning for Connected Autonomous Vehicles Based on a Potential Field Model

To enhance the safety of lane changes for connected autonomous vehicles in an intelligent transportation environment, this study draws from potential field theory to analyze variations in the risks that vehicles face under different traffic conditions. The safe minimum vehicle distance is dynamically adjusted, and a comprehensive vehicle risk potential field model is developed. This model systematically quantifies the risks encountered by connected autonomous vehicles during the driving process, providing a more accurate assessment of safety conditions. Subsequently, vehicle motion is decoupled into lateral and longitudinal components within the Frenet coordinate system, with quintic polynomials employed to generate clusters of potential trajectories. To improve computational efficiency, trajectory evaluation metrics are developed based on vehicle dynamics, incorporating factors such as acceleration, jerk, and curvature. An initial filtering process is applied to these trajectories, yielding a refined set of candidates. These candidate trajectories are further assessed using a minimum safety distance model derived from potential field theory, with optimization focusing on safety, comfort, and efficiency. The algorithm is tested in a three-lane curved simulation environment that includes both constant-speed and variable-speed lane change scenarios. Results show that the collision risk between the target vehicle and surrounding vehicles remains below the minimum safety distance threshold throughout the lane change process, ensuring a high level of safety. Furthermore, across various driving conditions, the target vehicle’s acceleration, jerk, and trajectory curvature remained well within acceptable limits, demonstrating that the proposed lane change trajectory planning algorithm successfully balances safety, comfort, and smoothness, even in complex traffic environments.

An Improved Vehicle Path-Tracking Model Based on Adaptive Nonlinear Model Predictive Control via Online Big Bang—Big Crunch Algorithm and Artificial Neural Network

<div>In this article, a novel tuning approach is proposed to obtain the best weights of the discrete-time adaptive nonlinear model predictive controller (AN-MPC) with consideration of improved path-following performance of a vehicle at different speeds in the NATO double lane change (DLC) maneuvers. The proposed approach combines artificial neural network (ANN) and Big Bang–Big Crunch (BB–BC) algorithm in two stages. Initially, ANN is used to tune all AN-MPC weights online. Vehicle speed, lateral position, and yaw angle outputs from many simulations, performed with different AN-MPC weights, are used to train the ANN structure. In addition, set-point signals are used as inputs to the ANN. Later, the BB–BC algorithm is implemented to enhance the path-tracking performance. ANN outputs are selected as the initial center of mass in the first iteration of the BB–BC algorithm. To prevent control signal fluctuations, control and prediction horizons are kept constant during the simulations. The results showed that all AN-MPC weights are successfully tuned online and updated during the maneuvers, and the path-following performance of the ego vehicle is improved at different NATO DLC speeds using the proposed ANN + BB–BC, compared to the method where ANN is used only.</div>

An Improved RRT Path-Planning Algorithm Based on Vehicle Lane-Change Trajectory Data

The Rapidly-exploring Random Tree (RRT) algorithm faces issues in path planning, including low search efficiency, high randomness, and suboptimal path quality. To overcome these issues, this paper proposes an improved RRT planning algorithm based on vehicle lane change trajectory data. This algorithm dynamically adjusts the sampling area based on road environment and trajectory change laws, allowing the random tree to sample within an effective area, thereby improving the algorithm’s sampling efficiency. After determining the sampling area, a sampling point optimization strategy is used to enhance sampling quality, resulting in a smoother and more executable path. Finally, the vehicle is processed in a standardized manner to further improve path safety. Simulation results indicate that, compared to the original RRT algorithm, the improved version reduces nodes, planning time, and path length by 12.77%, 64.79%, and 12.87%, respectively. It also improves path smoothness and more closely aligns with actual lane-change trajectories, demonstrating the effectiveness and executability of the improved algorithm.

A Lane Change Model Considering the Stability of Cooperative Adaptive Cruise Control Platoon Fleet

In this article, lane change models for mixed traffic flow under cooperative adaptive cruise control (CACC) platoon formation are established. The analysis begins by examining the impact of lane changes on traffic flow stability. The influences of various factors such as lane change locations, timing, and the current traffic state on stability are discussed. In this analysis, it is assumed that the lane change location and the entry position in the adjacent lane have already been selected, without considering the specific intention behind the lane change. The speeds of the involved vehicles are adjusted based on an existing lane change model, and various conditions are analyzed for traffic flow disturbances, including duration, shock amplitude, and driving delays. Numerical calculations are provided to illustrate these effects. Additionally, traffic flow stability is factored into the lane change decision-making process. By incorporating disturbances to the fleet into the lane change income model, both a lane change intention model and a lane change execution model are constructed. These models are then compared with a model that does not account for stability, leading to the corresponding conclusions.

Comparative Analysis of AR-HUDs Crash Warning Icon Designs: An Eye-Tracking Study Using 360° Panoramic Driving Simulation

Augmented Reality Head-Up Displays (AR-HUDs) enhance driver perception and safety, yet optimal hazard warning design remains unclear. This study examines three AR-HUD crash warning icon types (BD, BR, BW) across various turning scenarios. Using a 360-degree video-based driving simulation with 36 participants, eye-tracking metrics were collected. Results show BW icons, dynamically linked to hazards, significantly improve drivers’ pedestrian risk awareness and visual attention allocation compared to BD and BR systems. BW consistently demonstrated longer gaze duration, higher fixation counts, and shorter time to first fixation across all turns. BD and BR icons were more susceptible to lane changes, potentially diverting attention from hazards. Findings suggest prioritizing dynamic tracking warning icons over fixed-position alternatives to minimize visual competition and distraction, providing crucial insights for AR-HUD optimization in automated vehicles.

Evolution of the “4-D Approach” to Dynamic Vision for Vehicles

Spatiotemporal models for the 3-D shape and motion of objects allowed large progress in the 1980s in visual perception of moving objects observed from a moving platform. Despite the successes demonstrated with several vehicles, the “4-D approach” has not been accepted generally. Its advantage is that only the last image of the sequence needs to be analyzed in detail to allow the full state vectors of moving objects, including their velocity components, to be reconstructed by the feedback of prediction errors. The vehicle carrying the cameras can, thus, together with conventional measurements, directly create a visualization of the situation encountered. In 1994, at the final demonstration of the project PROMETHEUS, two sedan vehicles using this approach were the only ones worldwide capable of driving autonomously in standard heavy traffic on three-lane Autoroutes near Paris at speeds up to 130 km/h (convoy driving, lane changes, passing). Up to ten vehicles nearby could be perceived. In this paper, the three-layer architecture of the perception system is reviewed. At the end of the 1990s, the system evolved from mere recognition of objects in motion, to understanding complex dynamic scenes by developing behavioral capabilities, like fast saccadic changes in the gaze direction for flexible concentration on objects of interest. By analyzing motion of objects over time, the situation for decision making was assessed. In the third-generation system “EMS-vision” behavioral capabilities of agents were represented on an abstract level for characterizing their potential behaviors. These maneuvers form an additional knowledge base. The system has proven capable of driving in networks of minor roads, including off-road sections, with avoidance of negative obstacles (ditches). Results are shown for road vehicle guidance. Potential transitions to a robot mind and to the now-favored CNN are touched on.

Predictive Models of Brake Reaction and Steering of Police Officers in Critical Driving Situations

Motor vehicle crashes involving police vehicles significantly impact law enforcement officer (LEO) safety, often occurring during high-risk maneuvers like pursuit driving and sudden lane changes. These incidents are exacerbated by LEOs’ interaction with in-vehicle technologies, including Mobile Computer Terminals. Advanced Driver-Assistance Systems (ADAS) could mitigate these risks, though existing ADAS algorithms are not tailored to the unique work demands. To address these challenges, our study develops predictive models for LEO braking and steering in critical situations, based on a driving simulator experiment with police officers. Both braking and steering models were constructed and identified as effective in predicting police officer braking response and steering. The models can be practically applied as part of ADAS systems to deliver warnings at appropriate times, adapting to police officer demands in critical driving situations. Study implications contribute to the wider body of knowledge on surface transportation, occupational safety, and the use of adaptive models.

Autonomous driving decision-making control algorithm based on hierarchical reinforcement learning

In the decision-making model of autonomous driving based on learning, the reinforcement learning model has the problems of slow convergence and single application scenario, while the imitation learning model has the problem of poor generalization. In order to solve this problem, a two-layer reinforcement learning framework is proposed to replace the decision layer and control layer in the autonomous driving task. The decision layer divides the driving behavior into lane keeping, left lane change and right lane change. After the decision layer selects the corresponding behavior, it completes the behavior by changing the input of the control layer. Then, a new method for training the control layer, RL_COE (Reinforcement learning combined with online experts), is proposed by combining reinforcement learning and online experts. Finally, a highway simulation environment is built in Carla to verify the proposed algorithm and compare it with the reinforcement learning baseline algorithm. The results show that this method greatly improves the convergence speed and stability of the algorithm and can better complete the driving task.

Adaptive MPC path-tracking controller based on reinforcement learning and preview-based PID controller

Path-tracking control is a crucial process for autonomous vehicles, ensuring that the vehicle drives safely along the reference path, and the suitable controller parameters ensure the accuracy and stability of this process. To enhance the adaptability of traditional path-tracking controller parameters, this paper proposes an adaptive model predictive control (MPC) controller based on a preview-based PID controller and deep deterministic policy gradient (DDPG) algorithm to achieve adaptive tuning of the controller parameters. Starting with the design of the dynamics tracking error model of the vehicle and the MPC controller. Based on the actor-critic reinforcement learning architecture, the DDPG agent is designed to tune the prediction horizon and weight matrix of the MPC controller. A preview-based PID controller is proposed to improve the efficiency and stability of reinforcement learning and compensate for the error in vehicle modeling. The improved algorithm performance is verified through the simulation scenarios of high-speed lane changing and accelerated overtaking scenarios constructed by MATLAB/Simulink. The results show that the improved algorithm significantly improves the adaptive ability of the traditional MPC controller to time-varying conditions and achieves higher tracking accuracy and stability.

Integrated Control of Intelligent Vehicle Driving Stability Using Three-Dimensional Phase Space

<div>To enhance vehicle dynamic stability during driving, we developed a three-dimensional phase space model that incorporates the sideslip angle of center of mass, yaw rate, and lateral load transfer rate. This model enabled real-time evaluation and active control of vehicle stability. First, longitudinal and lateral controllers were implemented to ensure precise vehicle trajectory. Second, a hierarchical control strategy was designed to actively manage the desired sideslip angle, yaw rate, and roll angle based on the vehicle’s destabilizing conditions, thereby maintaining the vehicle within a stable state space. We simulated and tested the stability analysis methods and integrated control strategies for both cars and trucks under DLC (double lane change) and CDC (circular driving condition) scenarios using joint simulations with CarSim/TruckSim and Simulink. The proposed integrated stability control strategy, which combined MPC-based trajectory tracking with direct yaw moment control and active suspension control, enhanced the vehicle’s directional and roll stability. This approach effectively mitigated vehicle instability under extreme conditions. Compared to the MPC lateral tracking control system, the performance of the integrated control system was significantly improved. In the DLC scenario, the maximum values of the sedan’s lateral deviation, sideslip angle, yaw rate, and vehicle roll angle decreased by 22.6%, 33.9%, 5.5%, and 1.2%, respectively. In the CDC scenario, the truck’s lateral acceleration, sideslip angle, yaw rate, and vehicle roll angle decreased by 7.5%, 46.8%, 8.2%, and 80%, respectively. Additionally, open-loop simulation tests were conducted under fishhook steering conditions for both passenger cars and trucks. The results further validated the effectiveness of the integrated control strategy, demonstrating its ability to significantly improve yaw rate and roll response, thereby enhancing overall vehicle stability under challenging driving conditions.</div>

Zero-cost upgrade to a multi-fiber network with partial lane-change capabilities

Growing capacity requirements are leading to the deployment of multiple fibers in each optical network link. Even though deploying state-of-the-art multi-fiber network architectures with stacked and independent fiber layers simplifies network design and control, spectrum can be used more efficiently if the optical-network nodes allow fiber layers to be interconnected, i.e., if the so-called lane change is enabled. Unfortunately, lane change in high-degree optical nodes requires wavelength selective switches (WSSs) with a high number of ports, which is prohibitively costly or even unfeasible with current WSS technology. Instead, lane change in low-degree optical nodes can be enabled at no extra cost, using WSS ports that are otherwise left empty. In this study, we describe our proposal for a multi-fiber network with partial lane-change capabilities and perform a simulative study to identify the advantages of this architecture, as well as discuss the emerging resource allocation challenges associated with it. We demonstrate that, by enabling lane change in degree-2 nodes, we can increase network throughput by 3% and restore 5%–8% more traffic in the case of single- and double-link failures at no additional equipment cost.

Multi-lane cellular automata model considering bus-HOV lane

To quantify the impacts of high occupancy vehicles (HOV) entering the exclusive bus lane on road traffic efficiency, the car following and lane changing characteristics of bus, HOV and non-HOV were analyzed when setting the bus-HOV lane. Using the theory of cellular automata (CA) and combining the control rules of the bus-HOV lane, the lane occupied by a vehicle and the type of a vehicle regarded as constraints were introduced into the asymmetric lane changing rules, and then a multi-lane CA model was established for the car following and lane changing of multi-type vehicles considering the bus-HOV lane. MATLAB software was used to accomplish numerical simulation to analyze the specific effects of the proportion of HOV, bus departure frequency and bus stop spacing on the traffic flow parameters and their relationships. The results show that: when the proportion of HOV is less than 0.5 on a three-lane road segment, setting the bus-HOV lane can not only improve road traffic efficiency but also ensure the speed of bus operation under the condition of high initial space occupancy; when the proportion of HOV exceeds 0.5 , it is difficult to improve road traffic efficiency by restricting non-HOV from entering the bus-HOV lane; when the initial space occupancy is greater than 0.2 , the higher the bus departure frequency is, the greater the decline of traffic volume of the bus-HOV lane is; when there are 5 bus routes to dispatch a bus every 3 minutes, compared with the low initial space occupancy, the traffic volume of the bus-HOV lane under the condition of the high initial space occupancy reduces by about 30%; the bus stop spacing more significantly affects the traffic efficiency of the bus-HOV lane, the longer the bus stop spacing is, the higher the frequency of HOV lane changing is, the more the increase of the congestion segments on the bus-HOV lane and the adjacent normal lane is, thus the traffic efficiency of the whole road is influenced.