Driving on slippery extreme condition poses an huge challenge for automated electric vehicles (AEVs) due to the significant degradation of tire–road friction and the strong coupling between longitudinal and lateral vehicle dynamics. The performance of traditional model predictive control (MPC) schemes relies heavily on accurate vehicle dynamics models and carefully tuned cost functions, both of which are difficult to achieve under slippery curved road conditions.To address these challenges, a hybrid vehicle motion model is first constructed by integrating a physics-based vehicle dynamics model with a 1-Lipschitz residual neural network, which improves prediction accuracy and adaptability under uncertain road conditions. Based on the hybrid model, an MPPI controller is developed in which actor–critic networks are employed to adaptively tune the stage cost weight factors, while a temporal-difference (TD) learning algorithm is used to learn the terminal cost from selected MPPI rollout trajectories. In this manner, short-horizon control performance and long-term cost optimization are jointly addressed within a unified MPPI framework.Compared with model-free reinforcement learning approaches, the proposed controller preserves high physical interpretability and enhanced safety awareness by embedding learning mechanisms into predictive control rollouts, rather than directly applying learned actions to the vehicle. Extensive simulation results demonstrate the effectiveness and superiority of the proposed RL-HMPPI controller under slippery extreme road conditions.

In order to comprehensively consider the influence of geometric error caused by manufacturing defects and elastic error caused by the gravity of structural components on the static accuracy of machine tools, as well as the coupling relationship between them, this paper proposes an identification method of static error of three-axis machine tools. Taking the three-axis machine tool as the research object, the static error model of the machine tool is established according to the multi-flexible body system theory and the homogeneous transformation matrix (HTM), and the geometric error component and the elastic error component in the static error are qualitatively analyzed. The Chebyshev polynomials are used to establish the parametric model of static error. Based on the three-axis linkage experiment of the Double ball bar (DBB), all the static errors are decoupled. Then, the finite element method is used to discretize the machine tool into three subsystems. Based on the space beam element, the stiffness model of each subsystem is established, and the elastic error component in the static error is quantitatively analyzed. The results show that the elastic error affected by gravity is mainly reflected in seven straightness errors and angle errors, and is generally greater than the corresponding static error. It shows that the machine tool offsets the influence of geometric errors from the perspective of elastomer compensation in the design stage, and proposes a simplified static error model of the machine tool.

Distributed drive vehicles provide enhanced actuation flexibility, making longitudinal-lateral coordinated stability control essential for improving vehicle handling and safety under complex driving conditions. Nevertheless, the existing coordinated control strategies commonly employ stability reference models with fixed tire-road friction coefficients, which restrict their adaptability to time-varying adhesion environments. In addition, conventional sliding mode-based lateral stability controllers may exhibit limited performance when confronted with strong nonlinear coupling and external disturbances. To address these issues, this paper proposes an integrated longitudinal-lateral coordinated stability control framework for distributed drive vehicles. A dual unscented Kalman filter-based estimator is developed to identify the tire-road friction coefficients and construct a friction-adaptive reference model for yaw rate and sideslip angle. An adaptive fractional power speed controller with resistance compensation is designed to generate the total longitudinal driving torque, while an adaptive neural sliding mode controller produces the corrective yaw moment for lateral stability enhancement. Furthermore, a pseudoinverse-based torque distribution strategy is employed to allocate the longitudinal torque and yaw moment to individual wheels. Simulation results demonstrate that the proposed framework significantly improves vehicle stability and tracking accuracy compared with conventional control methods under varying road conditions.

This paper presents a novel estimation and control framework for Quasi-Zero-Stiffness (QZS) air suspension systems based on Inertial Measurement Unit (IMU) data. A combined algorithm integrating Grey Wolf Optimisation (GWO) and Unscented Kalman Filtering (UKF) is proposed to address the challenges of noise and uncertainty inherent in IMU signals. First, the mathematical model of the QZS air suspension system is formulated, and an H-2 controller coupled with an IMU simulation model is developed. IMU measurements are incorporated into the state vector directly, while the remaining state variables are estimated through the GWO-UKF algorithm. To further improve estimation adaptability and accuracy, GWO is employed to optimise the UKF parameters. Simulation results demonstrate that the proposed method achieves high accuracy in estimating the unsprung mass velocity and dynamic displacement. Finally, Hardware-in-the-Loop (HiL) experiments confirm that the proposed controller significantly enhances vehicle ride comfort and operational stability.

Driving on icy roads poses significant challenges for automated electric vehicles (AEVs) motion planning and control due to uncertain dynamics, multiple constraints, and temporal rules satisfying problems.This paper proposes a hybrid data-driven Model Predictive Path Integral (MPPI) control framework with temporal logic constraints for real-time safe motion planning and trajectory tracking on slippery roads. To handle modeling uncertainties and mismatches in vehicle dynamics, a hybrid model is constructed by combining a nominal physics-based baseline with a 1-Lipschitz residual neural network pretrained via the collected vehicle data. This model captures both nominal dynamics and unmodeled residual effects, providing a reliable system representation of AEVs for controller design with robustness performance guaranteed. The pretrained model is embedded into a sampling-based predictive controller, where state constraints and task specifications expressed by temporal logic formulas are incorporated into the cost function. So that, our control strategy ensures that the generated trajectories adhere to both safety constraints and high-level behavioral objectives with real time solving guaranteed. Real electric vehicle experiments validate the effectiveness of the proposed method and demonstrate its superiority in achieving safe and reliable planning and tracking control on icy roads.

This study presents a robust event-triggered control protocol based on a discrete event-triggered communication scheme (DECS) to resolve vehicle platoon communication topological changes, external disturbances, and information delays. The random variation of the data transmission link among the platoons in real traffic was considered and modeled by the Markov chain combined with the directed graph method. The effects of delays and air resistance on the vehicle platoon were studied using the system parameters, such as external interference and equivalent information delays. To ensure the vehicle platoon's inner-vehicle stability, a variable-gain distributed controller is proposed based on Markovian jumping system stability theory and H control. Finally, the L2 stochastic string stability is defined to attenuate perturbations as they propagate through a platoon. Simulation studies were conducted on a vehicle platoon under four random-switching communication topologies with two different control methods to verify the theoretical results. Compared with traditional robust platoon control, the proposed control method achieves vehicle platoon stability with a lower computational burden.

This article proposes a fuzzy sliding mode fault-tolerant control method (FSM-FTC) to address the yaw instability of distributed drive electric vehicles (DDEV) under the demagnetization faults of a permanent magnet in-wheel motor (PM-IWM). Initially, the torque output variations caused by motor demagnetization faults are characterized using the Maxwell stress tensor method. Then, the impact of motor performance degradation caused by a demagnetization fault on the vehicle's yaw motion is analyzed in conjunction with the vehicle dynamic model. Based on this investigation, a fuzzy algorithm is employed to adaptively adjust the switching gain of the sliding mode controller (SMC), and the fault-tolerant control of both the yaw rate and the sideslip angle is carried out by using the fuzzy sliding mode control (FSMC). To validate the proposed control method, both simulation and experimental tests are conducted on a dSPACE-based platform. The results from these simulations and experiments demonstrate the effectiveness and practicality of the FSM-FTC control approach.

Most collision accidents are caused by drivers’ errors. To more effectively assist drivers in avoiding collisions, the human-machine shared driving system has become increasingly integrated into intelligent vehicles as consumer technologies and electronics. Furthermore, in collision avoidance scenarios, existing shared systems frequently exhibit excessive intervention when implementing corrective maneuvers for driver-induced errors, thereby inadvertently elevating the driver’s workload. To address these issues, this paper proposes a novel human-machine shared framework based on hybrid system theory. The shared framework contains a trajectory planning layer and a multi-state shared control layer. At the trajectory planning layer, the optimal collision-free trajectory is selected from the candidate trajectories based on natural driving data and collision constraints. The optimal trajectory is used as the reference trajectory for collision avoidance. At the shared control layer, a shared control strategy based on a hybrid automaton model performs multi-state shared control. The proposed humanmachine interaction criterion based on driver error governs the multi-state transitions. A model predictive controller is utilized to track the reference trajectory for collision avoidance. Simulation and experimental results show that the proposed method outperforms shared control methods based on steering angle deviation and control authority allocation. It reduces the drivers physical workload and automation intervention, enhancing cooperation satisfaction.

A critical research focus in shared driving is the dynamic switching of driving authority. Existing studies on driving authority switching predominantly address single driving tasks and often face efficiency challenges in resolving continuous multi-task driving issues. To address these limitations, this paper proposes a human-machine shared driving framework with three modules: risk assessment, driving authority switching, and human-autonomous driving. First, collision risk is assessed based on inter-vehicle distance and velocity. Then, if autonomous driving is inactive, the vehicle operates in human mode. When activated, lane-keeping is applied if the distance is safe; otherwise, obstacle avoidance takes over. The human driver is modeled using a preview driver model, while the model predictive control handles path tracking with different trajectory strategies. Finally, a hybrid automaton selects steering inputs for execution. The research results show that, compared to traditional human driver, the proposed shared control can effectively achieve collision avoidance and smoothly switch between multiple driving tasks.

Accurate and real-time acquisition of vehicular system dynamic states, road surface conditions, and motion states of surrounding participants is crucial for the safety, passenger comfort, and operational efficiency of autonomous vehicles (AVs) and connected automated vehicles (CAVs). In recent years, a significant amount of research has contributed to the field of state estimation for vehicles, roads, and pedestrians. From the systemwide perspective of intelligent transportation systems to a focused view on "vehicle-road-pedestrian", this survey aims to provide a comprehensive review and summary of recent state estimation techniques for vehicle motion, road surface, and pedestrian motion. A thorough analysis of the reviewed literature, relevant datasets, evaluation metrics, and experimental platforms in this field is also conducted. Finally, existing challenges and future research directions about methods and performance evaluation are further discussed. This survey is expected to contribute to the advancement of research in dynamic state estimation of vehicle-road-pedestrian, thereby facilitating the development of efficient and safe intelligent transportation systems.

In this paper, a hybrid platooning robust stability control method based on the Backward Predictive Multi-Vehicle Following Method (BLAMCFM) is proposed to address the problems that the following models of traditional human-driven vehicles (HDVs) do not take into account the personalized characteristics of real drivers and that it is difficult to achieve the stability of a hybrid vehicle platooning system with the vehicle platooning control method. Firstly, data from various vehicles in front and behind are used as inputs to the HDV. Subsequently, a hybrid platooning system consisting of a self-driving and connected vehicle (CAV) and an HDV is established, considering several unfavorable factors such as data dropout, communication delays, and external disturbances. Secondly, a string stability criterion for the hybrid platooning system is provided in the presence of disturbances and delays, and a stability controller is built based on the Lyapunov-Razumikhin stability theory. In conclusion, it is shown through simulation studies that drivers observing the behavior of multiple vehicles in front and behind them simultaneously can successfully stabilize the traffic flow, and the effectiveness of the controller is confirmed by illustrating the function of CAVs in reducing traffic oscillations.

In recent years, the frequency of moose-vehicle collisions (MVC) has constantly increased, becoming a serious traffic safety issue. Addressing the lack of research on collision response and driver injury in such scenarios, this study presents the following contributions: (1) A finite element (FE) model of MVC was developed and validated, analyzing the influence of impact velocity, offset, and impact angle on vehicle collision kinematics. The results show that collision speed and position are significant factors influencing the vehicle's response. (2) A driver-restraint system model was established and validated, examining the effects of impact velocity, offset, driver size, and posture on driver kinematics, dynamics and injuries. The findings indicate that the primary cause of driver injury is the head's collision with the deformed vehicle structure. The neck is the most vulnerable body part, with compression-bending or compression-extension injury modes observed. (3) Based on driver injury mechanisms, a top airbag model was proposed and designed. Using a multi-objective optimization algorithm, the airbag parameters (ignition time, gas flow rate, tether length, and vent size) were optimized for the highest risk scenario. The optimized top airbag successfully limited injury indexes across different driver sizes, improving protection and enhancing the safety of the vehicle restraint system. This study provides a comprehensive framework for driver injury and protection strategy research in MVC, contributing to improved vehicle passive safety.

Model Predictive Control (MPC) stands out as a prominent method for achieving optimal control in autonomous driving applications. However, the effectiveness of MPC approaches critically depends on the availability of accurate dynamic models and often necessitates substantial computational overhead for real-time optimization procedures at every iteration. Recently, the research community has been increasingly drawn to the concept of cloud-assisted MPC, which harnesses the capabilities of powerful cloud computing to provide users with on-demand computational resources and data storage services. Within these cloud-assisted MPC frameworks, control signals are merged with a cloud-based MPC, which leverages the substantial processing power of cloud infrastructure to determine optimal control actions using detailed nonlinear models for greater accuracy. Simultaneously, a local MPC runs on simplified linear models constrained by limited on-device computing resources, delivering prompt control responses at the cost of reduced model accuracy. To achieve an effective trade-off between rapid response and model fidelity, this work presents a new model-free deep reinforcement learning structure designed to merge cloud and local MPC outputs. Tests conducted on path-following scenarios show that the introduced method achieves superior control performance compared to existing reinforcement learning baselines and conventional rule-based fusion strategies.

Vehicle-to-vehicle (V2V) communication technology in connected automated vehicles (CAVs) substantially improves traffic capacity. During initial CAV deployment phases, mixed traffic flow combining CAVs and human-driven vehicles (HVs) will inevitably co-exist on highways. The absence of V2V capabilities in HVs prevents them from providing V2V services to CAVs, thereby constraining CAVs’ capacity improvement in mixed traffic environments. To address this limitation, we propose equipping partial HVs with V2V communication devices, enabling these retrofitted HVs to transmit V2V information and create essential communication environment for CAVs. This study develops a mixed traffic capacity analysis framework that simultaneously incorporates CAV penetration rate and V2V installation rate of HVs, which aims to improve mixed traffic capacity by adjusting the V2V installation rate of HVs. Firstly, we classified car-following patterns within mixed traffic flow and calculate their probabilities. Secondly, a mixed traffic capacity model was constructed using fundamental diagram theory. Using the established model, critical values for V2V installation rate of HVs were analytically derived to achieve capacity improvements under varying CAV penetration rates. Finally, numerical experiments validated both the model’s reliability and theoretical derivations. Results demonstrate that the proposed model effectively quantifies how CAV penetration rate and V2V installation rate of HVs jointly influence mixed traffic capacity. Strategic adjustment of V2V installation rate of HVs based on each level of CAV penetration rates significantly enhances mixed traffic capacity.

Sideslip angle, yaw rate, and vehicle velocity are essential for intelligent vehicle control. Since these vehicle states are not measured directly, some Kalman-based approaches have been developed to estimate these states using in-vehicle sensors. However, the existing studies seldom account for the influence of sensor data loss on estimation accuracy. In addition, the process and measurement noise change during the estimation process because of the various driving conditions. To address these problems, an expectation-maximization robust extended Kalman filter (EMREKF) is proposed. Firstly, a robust extended Kalman filter (REKF) is developed to deal with the impact of missing measurements. Then, an improved expectation maximization (EM) algorithm that considers data loss is presented to update the noise parameter of the REKF dynamically. Finally, the improved EM is fused with the REKF to form the EMREKF to estimate vehicle state. The experimental results demonstrate that the EMREKF outperforms EKF, REKF, and maximum correntropy criterion EKF for various degrees of data loss and the proposed algorithm has a strong adaptive ability to different driving conditions.

In recent years, deep learning-based image classification has made significant progress, especially in safety-critical perception fields such as intelligent vehicles. Factors such as vibrations caused by NVH (noise, vibration, and harshness), sensor noise, and road surface roughness pose challenges to robustness and real-time deployment. The Transformer architecture has become a fundamental component of high-performance models. However, in complex visual environments, shifted window attention mechanisms exhibit inherent limitations: although computationally efficient, local window constraints impede cross-region semantic integration, while deep feature processing obstructs robust representation learning. To address these challenges, we propose DAR-Swin (Dual-Attention Revamped Swin Transformer), enhancing the framework through two complementary attention mechanisms. First, Scalable Self-Attention universally substitutes the standard Window-based Multi-head Self-Attention via sub-quadratic complexity operators. These operators decouple spatial positions from feature associations, enabling position-adaptive receptive fields for comprehensive contextual modeling. Second, Latent Proxy Attention integrated before the classification head adopts a learnable spatial proxy to integrate global semantic information into a fixed-size representation, while preserving relational semantics and achieving linear computational complexity through efficient proxy interactions. Extensive experiments demonstrate significant improvements over Swin Transformer Base, achieving 87.3% top-1 accuracy on CIFAR-100 (+1.5% absolute improvement) and 57.0% mAP on COCO2017 (+1.3% absolute improvement). These characteristics are particularly important for the active and passive safety features of intelligent vehicles.

In an intelligent driving system, the rationality of driving decisions and the trajectory planning scheme directly determines the safety and stability of the system. Existing research mostly relies on high-definition maps and empirical parameters to estimate road adhesion conditions, ignoring the direct impact of real-time road status changes on the dynamic feasible domain of vehicles. This paper proposes an intelligent driving decision-making and trajectory planning method that comprehensively considers the influence factors of vehicle–road interaction. Firstly, real-time estimation of road adhesion coefficients was achieved based on the recursive least squares method, and a dynamic adhesion perception mechanism was constructed to guide the decision-making module to restrict lateral maneuvering behavior under low-adhesion conditions. A multi-objective lane evaluation function was designed for adaptive lane decision-making. Secondly, a longitudinal and lateral coupled trajectory planning framework was constructed based on the traditional lattice method to achieve smooth switching between lateral trajectory planning and longitudinal speed planning. The planned path is tracked based on a model predictive control algorithm and dual PID algorithm. Finally, the proposed method was verified on a co-simulation platform. The results show that this method has good safety, adaptability, and control stability in complex environments and dynamic adhesion conditions.

We propose a Stochastic MPC (SMPC) formulation for path planning with autonomous vehicles in scenarios involving multiple agents with multi-modal predictions. The multi-modal predictions capture the uncertainty of urban driving in distinct modes/maneuvers (e.g., yield, keep speed) and driving trajectories (e.g., speed, turning radius), which are incorporated for multi-modal collision avoidance chance constraints for path planning. In the presence of multi-modal uncertainties, it is challenging to reliably compute feasible path planning solutions at real-time frequencies ($\geq$ 10 Hz). Our main technological contribution is a convex SMPC formulation that simultaneously (1) optimizes over parameterized feedback policies and (2) allocates risk levels for each mode of the prediction. The use of feedback policies and risk allocation enhances the feasibility and performance of the SMPC formulation against multi-modal predictions with large uncertainty. We evaluate our approach via simulations and road experiments with a full-scale vehicle interacting in closed-loop with virtual vehicles. We consider distinct, multi-modal driving scenarios: 1) Negotiating a traffic light and a fast, tailgating agent, 2) Executing an unprotected left turn at a traffic intersection, and 3) Changing lanes in the presence of multiple agents. For all of these scenarios, our approach reliably computes multi-modal solutions to the path-planning problem at real-time frequencies.

The tire-road friction coefficient (TRFC) is essential for vehicle stability control and motion planning, particularly in four-wheel distributed drive electric vehicles. Estimating the TRFC typically requires obtaining the tire force first. However, onboard sensors usually do not directly measure tire force, making it common practice to use a tire model for calculation. The accuracy of tire force calculation is affected by time-varying sensor noise, which in turn impacts the TRFC estimation. To address this, we propose a method that combines the extended H-infinity Kalman filter (EHKF) with the adaptive Unscented Kalman filter (AUKF). The EHKF is used to obtain the tire force, and then the AUKF, along with the vehicle model, estimates the TRFC. Empirical data reveal that the Suggested algorithm surpasses the traditional UKF in terms of estimation accuracy and has lower volatility.