The existing research on intelligent driving vehicles mainly focuses on improving the performance of safety, economy, and control accuracy, ignoring the personalized manipulation pReferences of different driving groups. The differences in driving styles and preferences of different passengers require that the driving behavior of intelligent driving systems in different traffic situations should conform to the habits of self-vehicle passengers, that is, to achieve personalized driving considering human factors. This paper provides a comprehensive and systematic review of the research status in the field of personalized driving. Firstly, it clarifies the necessity of personalized driving. Secondly, the existing decision-making and planning methods for personalized driving of single-vehicle are summarized from two aspects: machine learning-based methods and driver characteristic characterization-based methods. On this basis, the interactive decision-making and planning method of multi-vehicle games considering personalized preference in intelligent networking and mixed driving environments is summarized. Finally, the problems faced by the research of personalized intelligent driving systems and the future development trend are analyzed and prospected.

Effective Traffic Signal Control (TSC) in large-scale, dynamic urban networks hinges on informative state representations, a key challenge for reinforcement learning (RL). Existing methods often struggle to capture complex long-range spatial dependencies and multi-scale traffic patterns efficiently. We introduce StarLight, a novel framework that learns enhanced global traffic state representations using a bespoke Variational Autoencoder (VAE). StarLight’s VAE encoder uniquely integrates spatial self-attention to model non-local interactions and multi-scale convolutions to capture heterogeneous traffic phenomena across diverse receptive fields. The resulting richer global embeddings significantly improve the value function estimation within a decentralized Proximal Policy Optimization (PPO) framework, leading to better context-aware local control decisions. Comprehensive experiments on benchmark simulations demonstrate that StarLight consistently outperforms state-of-the-art methods under both static and dynamic conditions, achieving substantial reductions in delay and queue lengths with improved convergence stability. StarLight offers a more effective representation learning paradigm for complex TSC problems.

The stability region is an important criterion in the active safety system of vehicle. Extensive literatures have developed various stability regions for the centralized driving vehicle (CDV). However, seldom of them make a thorough analysis of the stability for distributed driving electric vehicle (DDEV). Especially when the direct yaw moment control (DYC) intervenes, the stability region of DDEV shows a huge difference compared with CDV. So far, most researches on the stability control of DDEV are still based on the traditional CDV stability region, which leads to the conservation of controller design. To this end, a dynamic and analytical stability region of DDEV is firstly developed in this paper. By employing sum of square programming (SOSP) algorithm, we choose a high-order Lyapunov function to make a precise estimation of the stability region. A novel DC shape function is proposed to reduce the conservation of estimation when DYC involves. To ensure the real-time performance for control application, Long Short Term Memory (LSTM) neural network is employed to fit the coefficients of Lyapunov function, as well as enable the dynamic shifting with driving conditions. Based on the aforementioned stability region, we develop a MPC controller to ensure the stability and tracking performance during handling limit. Both simulations and road tests demonstrate that the developed stability region could effectively restraint the vehicle states from diverging, which enhances vehicle maneuverability while ensuring vehicle stability.Note to Practitioners—Handling stability is a crucial factor which concerns the safety of vehicle. Almost all vehicles should be equipped with active safety system, such as Electronic Stability Program (ESP) of Bosch and Electronic Stability Controller (ESC) of GM. They collect the real-time vehicle states by the Built-in sensors. Meanwhile, they calculate the current stability margin according to the driver’s control input and analyze the deviation of the vehicle states to decide whether the active control is needed to maintain the stability of vehicle. This system is established well in CDV. However, for DDEV, it has another input of DYC in addition to wheel steering angle, which changes the dynamic characteristic of vehicle. This means that the stability margin of traditional ESP is inaccurate when the DYC intervenes, which will lead to the misjudgment of instability or the unsafety of vehicle. This paper develops an analytic stability region of DDEV and describes the stability margin with different values of DYC, which could adapt to varying conditions. This technology fills the gap of the stability determination of DDEV and has a good application prospect in the active safety system of DDEV.

In this paper, a safety-oriented hierarchical personalized driving system is proposed, which aims to mitigate the preference conflict between the passengers and the intelligent vehicle control system. Firstly, experiments on driving simulator are designed to analyze both the general and individual characteristics of different drivers, and a driving risk field (DRF) model for various driving events, such as free-driving, car-following, and lane-changing, is constructed. Secondly, the HighD natural dataset is clustered to explore the real preferences of different driving styles, and the DRF is calibrated to describe the driver’s subjective risk feeling more realistically. Thirdly, a driving decision-making mechanism with consideration of safety, efficiency, and personalized tolerance on the current lane is designed to select optimal driving events. Then, multi-point visual preview longitudinal speed adjustment and lateral lane-changing trajectory planning methods based on the spatial-temporal DRF under different driving events are proposed. Finally, human-in-the-loop experiments show that the proposed real-time system can generate personalized trajectories for different passengers in changing environments.

The integration of look-ahead information into Model Predictive Control (MPC) frameworks has shown promise for intelligent transportation systems. However, transitioning Predictive Cruise Control (PCC) system research into practical application poses challenges due to numerous weighting parameters and increased computational demands in complex driving environments. Although the Weighted Sum Method is commonly used in PCC system research to balance fuel consumption and trip time objectives, it requires time-consuming weight tuning and often results in suboptimal performance due to fixed weighting parameters. To address this, this paper proposes a Utopia-tracking Model Predictive Control (UTM-MPC) controller, where the cost function is reformulated as the sum of the distances between the objectives and the average Utopia point over the prediction horizon. By analyzing the Pareto front of the PCC optimization problem under varying slope profiles extracted from digital map data, we demonstrate that the proposed UTM-MPC effectively leverages the geometric characteristics of the Pareto front to identify preferred trade-off solutions. The adaptive weighting mechanism—derived from the online-calculated Utopia point—enhances the robustness of the PCC system under complex and dynamic driving conditions. To mitigate the computational burden associated with integrating UTM-MPC into the MPC framework, we introduce a tailored neighboring extremal-based solving algorithm. Leveraging the receding horizon nature of MPC, this method requires only minimal updates to efficiently identify an optimal solution near the nominal trajectory from the previous sampling instance. Simulation results show that the UTM-MPC controller, with its adaptive weighting strategy, consistently outperforms the traditional Weighted Sum Method in terms of both fuel efficiency and trip time.

Urban intersections pose significant safety challenges due to the convergence of diverse traffic flows from various directions, resulting in a disturbingly high rate of annual road fatalities. Specifically, the presence of permissive left-turn signals introduces potential conflicts between vehicles making left turns and those proceeding straight from opposite directions. To address this issue, this article introduces a dynamic safety assessment model tailored for urban intersections. Leveraging drone videos, high-resolution vehicle trajectory data is extracted, enabling the conflicts identification of rear-end and angular. Through an ensemble learning approach utilizing artificial intelligence (AI) techniques, conflict frequency is estimated at a granular five-minute interval. Notably, the Random Forest model exhibits superior performance, yielding a mean squared error (MSE) of 5.35. Further analysis employing SHAP (SHapley Additive exPlanations) highlights the critical role of variables such as vehicle deceleration rate and speed. The insights garnered from this study can inform the development of proactive traffic management systems, facilitating real-time assessment of intersection safety conditions and the implementation of measures to mitigate potential risks.

In this study, a personalized adaptive cruise control system founded on driving risk field (DRF) is proposed, which aims to make the control system more consistent with the driver's driving habits and reduce discomfort. Firstly, founded on the collected driver's operation data, the common characteristics of different drivers' operation behavior under different conditions are analyzed, and the spatial-temporal coupling DRF model under the event of car-following is constructed. Secondly, the data processing and clustering analysis of the High D natural driving data set are carried out to obtain the individual driving preferences of aggressive, normal and conservative drivers, and the DRF is calibrated based on the clustering results. Finally, based on the calibrated DRF, an intelligent vehicle adaptive cruise controller with minimum driving risk is designed, and compared with the traditional optimal velocity model (OVM), the advantages of the constructed DRF in personalized cruise following are verified.

Lane-changing is a critical issue for autonomous vehicles (AVs), especially in complex environments. In addition, different drivers have different handling preferences. How to provide personalized maneuvers for individual drivers to increase their trust is another issue for AVs. Therefore, a framework of human-like path planning is proposed in this paper, considering driver characteristics of visual-preview, subjective risk perception, and degree of aggressiveness. In the decision making module, a model is built to select the most suitable merging spot, with respect to safety factors and the driver’s degree of aggressiveness. And a novel environmental potential field (PF) suitable for arbitrary road structures is designed to describe the driver’s individual risk perception. In the trajectory planning module, a model predictive control (MPC) based path planner is designed according to the decisions in coincidence with the driver’s individual intentions of collision avoidance. Simulation results have demonstrated that the proposed path planner can provide with personalized trajectories for different combinations of driver preferences and steering characteristics, in scenarios of curved roads with different risks of collision.

This study aims to develop an optimal cruise controller that can automatically adapt to individual car-following style. First, the adaptive cruise control (ACC) problem is formulated as a linear quadratic optimal control, and an optimal control law containing the longitudinal acceleration of the target vehicle is derived. Then, a certain number of individual car-following styles are predefined on the basis of the proposed optimal cruise controller. Thereafter, a car-following style learning algorithm is proposed to quantify the closeness of the predefined individual car-following style to the specific driver, and a proper style is thus determined for the specific driver by using this learning algorithm. On the basis of the learned car-following style, the proposed optimal cruise controller can adapt itself to individual car-following style. Finally, the proposed self-learning optimal cruise controller is evaluated through simulation and experimental tests. Results show that the control behavior of the proposed self-learning optimal controller is closer to that of the human driver than that of a factory-installed ACC.

A driver-vehicle-road (DVR) model based on kinematic vehicle model is proposed in this paper. In this DVR model, the kinematics vehicle-road model is adopted, and the driver model considering the human driver's characteristics is also included. Thus the behaviors of human driver's preview and neuromuscular delay can be considered in design of path planner and controller by using this DVR model. The repulsive force field based on the artificial potential field (APF) and the circle decomposition of vehicle shape are used to describe the constraints of obstacle avoidance and the road departure avoidance. Based on the proposed DVR model, a trajectory planer using model predictive control (MPC) is designed with consideration of collision and lane-departure avoidance, driver's intention, and vehicle occupant comfort. Simulation results show that with the proposed planner, the vehicle can successfully avoid static/moving obstacles and return to the original lane without lane departure. Simulation results indicate that the proposed kinematic vehicle model based DVR model can be used to design the path planner in normal driving and some typical driving scenarios. And the proposed path planner can provide the vehicle driven by different human drivers with individually safe trajectories in typical scenarios of obstacle avoidance.