Achieving safe and efficient cooperative maneuvering in mixed highway traffic constitutes a significant engineering challenge, primarily due to the complex spatiotemporal coupling of multi-vehicle interactions and the inherent conflict between risk suppression and operational efficiency. This paper proposes a hierarchical cooperative control framework that formulates the overtaking task as a team-level constrained multi-agent Markov game with explicit safety budgets. Departing from heuristic penalty tuning or traditional safety layers, we introduce a Lagrangian-based policy optimization mechanism that models safety as a decoupled cost constraint and employs adaptive dual updates to regulate the safety–efficiency trade-off dynamically. A coordination-oriented reward and cost scheme is constructed to guide multiple agents in learning reciprocal yielding and efficient passing behaviors during complex interactions. Structurally, the framework integrates a hierarchical execution interface that maps high-level semantic maneuvers to low-level kinematic references. Under stochastic mixed traffic in highway-env, the proposed method limits the collision rate to 0.28% in the Extended traffic suite while maintaining improved TTC-based safety margins and robust time-gap performance. In addition, zero-shot transfer to the CARLA simulator achieves a 100% success rate with zero collisions under continuous vehicle dynamics and closed-loop control, demonstrating that the learned cooperative behavior remains executable beyond the original training environment. This work provides a scalable and reproducible solution for autonomous vehicle coordination under mixed traffic.

The modular chassis architecture of distributed drive electric vehicles (DDEVs) provides flexibility for integrating more electrical control units. To address the challenge of enhancing longitudinal dynamics while guaranteeing ride comfort, especially under frequent urban acceleration and deceleration conditions, this paper proposes a multi-agent system (MAS)-based framework to integrate the torque vectoring system (TVS) and the active suspension system (ASS), aiming to achieve better vehicle dynamics performance. First, a half-vehicle dynamics model is constructed to describe the coupling between longitudinal and vertical motions. The polytope technique is employed to address tire nonlinearity and time-varying system states. Then, cooperative control between the TVS and ASS is developed using the MAS system, where interaction behavior is modeled based on distributed model predictive control (DMPC) optimization results, and game theory is applied to find the optimal solution. This design effectively addresses the need for modularity and scalability in integrated chassis control systems. Furthermore, terminal constraints are introduced to ensure system stability performance. Finally, the experimental tests are performed to verify the performance of the proposed MAS framework. The results demonstrate the effectiveness in enhancing vehicle longitudinal driving performance while ensuring driving comfort.

This paper proposes an event-triggered control method for the CAN-network delayed human-machine shared steering system. The uncertain model parameter of vehicle speed is handled by the polytypic technology, and then represented by a new state with fewer vertices. Thus, a driver-vehicle path-tracking model is built. After that, the communication model of the shared control scheme considering the CAN network delays is redefined by the event-triggered system (ETS). Instead of employing the periodic communication from the sensor to the controller, it only occurs when the triggered condition of ETS is satisfied. Such a design can reduce the communication load and improve the usage of network resources. Finally, a robust state-feedback controller with the parallel distribution method is adopted to guarantee vehicle path-tracking accuracy, while reducing driver steering efforts. Through constructing a Lyapunov-Krasovskii function, the asymptotic stability of the system is proved. Some essential conditions are derived to obtain the controller and triggered parameters. The hardware-in-the-loop (HIL) tests by Carsim/ Matlab joint platform are further used to validate the proposed shared assistance control strategy. The results illustrate the effectiveness to ensure the prescribed system performance while using fewer CAN network resources.Note to Practitioners—The driver assistance steering system plays an important role to enhance driving performance. Almost all road vehicles have been equipped with the Electrical Power Steering (EPS) function. Based on the information feedback from the onboard sensors, it can generate an extra steering input to assist the driver in real time. The advanced steering control technology, such as Servolectric of ZF and ESTEERTM of Delphi, can significantly reduce traffic accidents and improve the driving experience. Recently, the Original Equipment Manufacturers (OEMs) bring various advanced driver assistance systems to further guarantee the vehicle safety. This is usually accompanied by the communication load of the in-vehicle network CAN (Controller Area Network). Meanwhile, the x-by-wire technique can also induce the possibility of CAN delays. It would deteriorate the control performance. Hence, this paper introduces the event-triggered system to develop the steering assistance controller. The CAN network delays are also integrated into the human-machine shared steering model. The communication only occurs when the triggered condition of ETS is satisfied. A robust control method is further presented to ensure the system prescribed performance. This technology aims to be a paradigm to design active safety control units. Note that some poor driver states, such as fatigued driving and distracted driving have not been considered in this study for the design of the assistance controller. Future research will focus on developing a shared controller to accommodate time-varying driver characteristics.

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.

Accurate gradient and heavy vehicle mass estimation are crucial to improve vehicle control effects. However, significant obstacles remain in the way of accurately estimating gradient and mass in real-time, mainly reflected in the connection between vehicle mass and gradient. to instantly calculate the vehicle's mass and the gradient, this paper proposes a double variable forgetting factor recursive least squares(VFFRLS) algorithm based on vehicle longitudinal dynamics. Firstly, considering the deep coupling of mass and gradient, a multivariate VFFRLS algorithm is designed to obtain a joint mass-slope estimation, to determine the precise, steady vehicle mass and the uneven gradient. Secondly, because the slope of the road changes more frequently than the vehicle's mass, the upper layer estimation mass is used as input to design the lower layer VFFRLS algorithm to realize the fine estimation of road slope. The influence of cumulative error and coupling relationship on slope estimation accuracy is effectively reduced. Finally, To get an exact estimate of the slope of the road, the rough and fine estimates of the slope are distributed according to a specific proportion. The Trucksim and Matlab/Simulink simulations confirm the efficacy of this algorithm. The findings indicate that the real-time estimation algorithm designed can achieve a mass estimation error is less than 4%, and a slope estimation error is less than 3%.

The intelligent electric vehicle with wheel corner module not only exhibits exceptional mobility and stability, but also encounters the challenge of controlling excessive degrees of freedom. In order to enhance yaw stability, the yaw control method grounded in the concept of dynamic stability region is introduced. And the corresponding controllers are built based on the hierarchical control theory. The upper layer control uses the multi-constrained sideslip angle-yaw rate (β–w) phase curve to construct vehicle's dynamic stability region, the vehicle status is categorized into zones of absolute stability, transition and instability range. The stability margin which determines intervention time of the yaw control is designed according to the stability region. The middle layer control generates generalized force to sustain vehicle stability utilizing sliding mode algorithm. The bottom layer control is configured to allocate driving force of each wheel based on the wheel load. The proposed approach's effectiveness has been confirmed through a collaborative simulation involving MATLAB/Simulink and Carsim. The findings indicate that employing the yaw stability control method rooted in the dynamic stability region achieves a 55% reduction in sideslip angle error, thereby significantly enhancing yaw stability.

In order to improve the obstacle avoidance effect of smart car under communication delay, a local obstacle avoidance control strategy of smart car based on remote control considering communication delay is proposed. This paper first classifies the foreseeable risks in the process of driving, and then designs obstacle avoidance strategies and tracking control methods corresponding to different risk levels according to the results of risk classification. Finally, an experiment is designed to verify the effectiveness of the obstacle avoidance strategy proposed in this paper. The results show that the local obstacle avoidance control strategy proposed in this paper can improve the accuracy and real-time performance of the smart car control system in the case of communication delay in remote control.

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.

In this paper, we propose a new RGB-thermal image segmentation method based on parameter sharing and attention fusion for safe autonomous driving. An encoder-decoder network structure is adopted. The encoder, which has shared convolution layer parameters and private batch normalization layer parameters (parameter sharing scheme), is used to extract features from RGB and thermal images. The extracted features are then fused by spatial and channel attention. The output of each residual block is fused, and the self-learning weight is used to integrate the fusion information of all residual blocks of the same levels. Subsequently, the fused features are integrated through a feature integration (FI) module in the decoder. Cross-entropy supervision of segmentation and edge is performed on the outputs of the decoders. Our proposed method is evaluated and compared with 17 state-of-the-art image segmentation methods, both qualitatively and quantitatively on the MFNet dataset which includes various objects in urban scenes. The results show that the proposed method outperforms previous methods by at least 0.3% and 1.8% in MRecall and MIoU, respectively, providing foundations for the development of autonomous driving technologies for safety enhancement.

Heterogeneous vehicle platoons, consisting of a human-driven vehicle (HDV) as the leader and connected automated vehicles (CAVs) as followers, present a promising solution to address various challenges arising from fully autonomous driving. In this paper, we propose a novel LSTM-based distributed model predictive control (DMPC) platooning method. Initially, we develop and train a vehicle acceleration prediction model based on a long short-term memory (LSTM) network using real-world driving data. Subsequently, the predicted acceleration sequence of the leading HDV is integrated into the DMPC-based platoon control model for the following CAVs. To validate the effectiveness of our method, we conduct simulation experiments using real-world driving data. The results demonstrate that, with a time headway of 1 s, the maximum speed error and maximum spacing error of the heterogeneous vehicle platoon using the proposed LSTM-based DMPC are reduced by at least 5.8% and 5.9%, respectively, compared to the traditional DMPC method. Furthermore, the LSTM-based DMPC outperforms the Transformer-based DMPC method, resulting in a 1.0% reduction in maximum speed error and a 0.7% reduction in maximum spacing error. The proposed method effectively dampens oscillation caused by the leading HDV and enhances tracking accuracy.