A major obstacle to the rapid maturation and real-world deployment of cooperative connected and automated vehicles (CAVs) is the prohibitive cost and extensive on-road testing mileage required to validate safety in natural traffic, where genuinely high-risk scenarios are exceedingly rare. Although existing scenario-generation methods can generate high-risk scenarios at scale, such scenarios frequently violate real-world physics or driver-behavior patterns, making them implausible and unsuitable for rigorous evaluation. To bridge this critical gap, we propose a plausible high-risk scenario generation method utilizing a bidirectional and autoregressive transformer (BART). Continuous vehicle trajectories from extensive naturalistic datasets are tokenized into a concise behavioral vocabulary, enabling the model to capture latent plausibility structures and realistically reproduce vehicle maneuvers. An iterative risk-feedback mechanism further steers scenario generation toward aggressive yet physically plausible driving conditions, effectively escalating cumulative risk within each simulation and thus yielding more plausible high-risk scenarios. Across cooperative lane-change and merging verification, the proposed BART-driven plausible high-risk generator yields markedly more high-risk and informative test scenarios than the Markov Decision Process (MDP) baseline, an Adaptive Stress Testing with a Deep Q-Network (AST-DQN), and a BART variant without risk-guided decoding, while maintaining a practical balance between scenario plausibility and risk elevation.

Highway interchanges are critical nodes in transportation networks but frequently experience congestion due to complex interactions between ramp diverging and merging flows. While Connected and Automated Vehicles (CAVs) are expected to improve traffic efficiency, the coexistence of Human-Driven Vehicles (HDVs) introduces disturbances that undermine performance. Prior studies have addressed certain cooperative strategies of CAVs in mixed traffic, but they often overlook the interactions between adjacent bottlenecks in interchange scenarios and the heterogeneity of HDV driving styles. To address this gap, this study proposes an Idealization-Oriented Planning (IOP) scheme that enhances interchange traffic efficiency in mixed traffic with high CAV penetration. Enabled by Cloud Control Systems (CCS), an idealized optimum for the overall travel efficiency under the assumption of full CAV penetration is firstly derived as a reference, based on which short-horizon strategies are computed to mitigate disturbances caused by HDV behaviors. Specifically, a DeePC-based Lane-Change Hesitation Guidance mechanism identifies conservative HDVs in advance and adjusts lane-change gaps to prevent excessive deceleration. In parallel, an Aggressive Merging Avoidance mechanism formulates a potential game in which adjacent CAVs cooperate to constrain inefficient HDV cut-ins, yielding safe and system-efficient strategies. A Python-based simulation platform validates the proposed approach, showing that IOP outperforms benchmark methods across various traffic conditions and HDV penetration rates (5%–30%); as an illustrative case, under high-flow conditions with 15% HDV penetration, IOP achieves a delay reduction of up to 53%.

End-to-end autonomous driving offers a stream-lined alternative to the traditional modular pipeline, integrating perception, prediction, and planning within a single framework. While Deep Reinforcement Learning (DRL) has recently gained traction in this domain, existing approaches often overlook the critical connection between feature extraction of DRL and perception. In this paper, we bridge this gap by mapping the DRL feature extraction network directly to the perception phase, en-abling clearer interpretation through semantic segmentation. By leveraging Bird's-Eye- View (BEV) representations, we propose a novel DRL-based end-to-end driving framework that utilizes multi-sensor inputs to construct a unified three-dimensional understanding of the environment. This BEV-based system extracts and translates critical environmental features into high-level abstract states for DRL, facilitating more informed control. Extensive experimental evaluations demonstrate that our approach not only enhances interpretability but also significantly outperforms state-of-the-art methods in autonomous driving control tasks, reducing the collision rate by 20 %.

Autonomous Intersection Management (AIM) has attracted increasing research attention with the rapid advancement of Connected and Automated Vehicles (CAVs), Vehicle-to-Infrastructure (V2I) communication, and Internet of Things (IoT) technologies. Existing research demonstrates the potential for jointly optimizing signal schemes and vehicle trajectories to improve traffic efficiency at isolated urban intersections, while coordination of signal schemes and CAV trajectories among multiple intersections remains underexplored. Building upon our previous work on joint optimization at an isolated intersection, this paper proposes a bi-level optimization framework for urban corridors under mixed traffic conditions. At the upper level, a corridor arrival-departure model is developed to capture the dynamic relationships between consecutive intersections and to estimate total delay. The lower-level model, adapted from our previous work, takes the cycle lengths, phase orders, and reference green time durations from the upper level as input, and optimizes the final signal schemes and CAV trajectories at each intersection. A heuristic solution algorithm based on block coordinate descent is proposed to solve the upper-level problem. Simulations under varying traffic demands and CAV penetration rates are conducted, and the results demonstrate that the proposed method significantly enhances the traffic efficiency of urban corridors.

The development of connected and automated vehicles (CAVs), vehicle-to-infrastructure (V2I) communication technologies, and Internet of Things (IoT) provides new opportunities for intelligent intersection management. Existing research primarily focuses on optimizing the signal scheme of the intersection based on CAV trajectory data, while overlooking the influence of human-driven vehicles (HDVs) and the interactive relationship between the signal scheme and vehicle trajectories. This article proposes a joint optimization framework for both signal schemes and CAV trajectories at an isolated intersection. A vehicular delay estimation model is developed to predict the travel delay of each vehicle based on its trajectory under a given signal scheme. The estimation model consists of analytical trajectory generation models for both CAVs and HDVs. A heuristic search algorithm is designed to efficiently solve for the optimal signal scheme and CAV trajectories. Simulations are conducted under varying traffic demands and penetration rates, and the results indicate that the proposed method can significantly improve the traffic efficiency of a typical intersection. A sensitivity analysis is performed to investigate the impact of control zone length on the performance of the method.

Cooperative lane-change is a pivotal application of connected and automated vehicles (CAVs), enhancing traffic safety and efficiency, especially in congested urban areas and highway on-ramps. However, the widespread implementation of multi-CAV cooperative lane-change is hindered by the lack of efficient verification strategies. This issue is exacerbated by the “curse of dimensionality”, stemming from numerous scenario variables and complex algorithms. To overcome this, we propose an efficient verification strategy that accelerates the process through optimal feature selection. By eliminating variables that have minimal impact on evaluation outcomes yet significantly increase testing complexity, our approach streamlines the verification process, minimizing information loss while maintaining high efficiency. We validated this strategy in various urban and highway scenarios involving multiple CAVs. During the verification process, the dimensionality of scenario variables was reduced, resulting in an exponential decrease in the number of testing scenarios, with information loss limited to no more than 6%. The results demonstrate that our proposed strategy significantly improves the efficiency of verifying cooperative lane-change algorithms in high-dimensional scenario variables, with minimal loss of essential information.

With the development of intelligent vehicle and platoon technology, multi-platoon system will become a new solution to further improve traffic efficiency on highways. However, the existing research seldom consider the interference of human-driven vehicles on multi-platoon stability and the following strategy of multi-platoon leader in mixed traffic. In this paper, a robust distributed model predictive control method for multi-platoon leader in mixed traffic is proposed to reduce the impact of human-driven vehicles on multi-platoon control performance. The following control strategy of multi-platoon leader is proposed firstly, which flexibly determines the following control targets according to the states of leader and HDV to avoid unnecessary frequent acceleration and deceleration. Then, the robust model prediction controller of multi-platoon leader is designed, where the states of sub-platoon leader are added to the objective function in the nominal system optimization problem to reduce the states change of the following vehicles under the influence of HDV from both forward and backward traffic. Furthermore, the auxiliary control law is designed to eliminate the error between the actual states and the nominal states to achieve the suppression of HDV interference. The simulation results show that the multi-platoon leader following control strategy can effectively reduce the speed variation of the multi-platoon to suppress the impact of HDV motion uncertainty on multi-platoon. Moreover, compared with the robust model prediction method of single-platoon leader without considering the state of the rear vehicle, the proposed method can reduce the control errors and improve the stability of multi-platoon.

This study focuses on the anti-rollover control problem for autonomous semi-trailer tank trucks and proposes an anti-rollover path tracking control algorithm suitable for autonomous driving scenarios. A simplified semi-trailer tank truck model is established in the controller, modeling liquid as a single pendulum considering both lateral and roll inputs, and an anti-rollover path tracking algorithm that utilizes it is developed based on multi-constraint model predictive control (MPC). The equivalent lateral load transfer rate (LTR), liquid sloshing angle, and angular velocity are used as constraints to achieve multi-objective optimization for path tracking, sloshing suppression, and rollover prevention. A vehicle-fluid coupling co-simulation platform based on computational fluid dynamics (CFD) is built to verify the control performance under extreme scenarios of left turning, high-speed single-lane change (SLC), and short-distance double-lane change (DLC). Additionally, the similarity principle for experimental validation using a down-scale model tank truck is derived, and experiments are conducted on the model semi-trailer tank truck under the DLC scenario. Through simulation and experimental verification, the proposed anti-rollover path tracking algorithm demonstrates acceptable tracking performance while ensuring that no rollover is carried out under extreme conditions, limiting the angle of$|LTR|<0.75$and sloshing within -20∘-20∘, reducing the angle of sloshing by a maximum of 42% in the experiment. Moreover, the real-time capability of the proposed algorithm meets the requirements for practical applications with a peak time consumption of one control step less than 20msin the controller tested.

Intelligent intersection management has been a research hotspot in recent years within the domain of intelligent transportation systems (ITS). Existing studies exhibit a deficiency in explicitly addressing the trajectories of human driven vehicles (HDVs) under mixed traffic environment, and they fall short of harnessing the full potential of connected and automated vehicles (CAVs) and Vehicle-to-Infrastructure (V2I) technologies for the joint optimization of signal timing and phasing and vehicle trajectories. In this study, we propose a cooperative intersection management method designed for mixed traffic environment. Our approach jointly optimizes the green time durations, phase order of traffic signals, and vehicle trajectories. To account for the impact of traffic signals on HDVs, we incorporate it as a virtual leading vehicle within the optimal velocity model (OVM). The comprehensive model is formulated as a nonlinear programming problem and then converted into a mixed integer programming problem using the big-M method. We conduct simulations of the proposed method in various scenarios at different MPRs. The results reveal a significant reduction in average travel time compared to the actuated signal control, highlighting the enhanced efficiency of the intersection achieved through our proposed method.

The multi-vehicle coordinated lane change is one typical application of intelligent connected vehicle(ICV), which must be systematically and thoroughly verified before across-the-board commercial application. Existing evaluation frameworks face challenges in effectively verifying multi-vehicle coordinated lane change algorithm, whose decision-making process is more complex and needs to consider more complex surrounding environments. This complexity introduces the "curse of dimensionality" into the verification process, adversely impacting verification efficiency. To address the aforementioned challenge, an efficient verification strategy with optimal feature subset selection is proposed in this study. Initially, the subset feature is defined by the integrals of position probability density function between host vehicle and surrounding vehicles across various decision-making phases of coordinated lane change algorithm. Following this, the optimal feature subset selection method is presented for verification in different decision-making phases of coordinated lane change algorithm. Subsequently, the verification strategy is delineated. Finally, the optimal feature subset selection verification strategy is implemented within a coordinated lane change scenario. A multi-start search algorithm is employed to explore the feasible domain of the multi-vehicle coordinated lane change algorithm. Verification through simulation is then executed, and its efficiency is compared with a widely used evaluation framework based on Test Matrix. Notably, the proposed strategy demonstrates a minimum efficiency improvement of 85%. The verification results underscore the effectiveness the proposed method in verification of phased multi-vehicle coordinated lane change decision-making algorithm, particularly within high-dimensional and complex environments.

The on-ramp merging is one of the typical bottlenecks on highways, and it’s expected to improve vehicle safety and traffic efficiency in this area through multi-vehicle collaboration. Existing research rarely coordinates on-ramp merging utilizing global information in a cyber-physical system, and most of them assume that vehicles in the mainline wouldn’t change lanes for simplification. However, scheduling methods dealing with multi-lane merging areas have been less explored. To address the problem, an optimized scheduling method with dynamic conflict graph is proposed in this study. First, the dynamic conflict graph is established, where vertices define the attributes of vehicle groups and edges describe the relationship among them; the optimization problem is then reconstructed as a graph search problem. Subsequently, a graph decomposition method is presented for the dynamic conflict graph. The feasible domain of vertices’ final states and costs of edges are determined based on optimal control theory, after which the heuristic depth-first search strategy is adopted to find a near-optimal solution. Finally, the dynamic conflict graph is applied in a continuous traffic flow. Simulations are conducted, and the performance is compared with the default algorithm in SUMO. The simulation results reveal that the proposed method reduces the overall travel delay while guaranteeing safety.

In real life, due to the influence of environment and physical equipments, C-V2X wireless communication network connection is prone to be intermittent. When intermittent communication occurs, the vehicle cannot make correct control decisions because it cannot receive the required information from neighboring vehicles, which will lead to the deterioration of the performance of the vehicle platoon. Considering the intermittent information connection of the leading vehicle through C-V2X communication network, a robust control method is proposed to realize vehicle platoon control. The platoon control strategy of a connected vehicle system is designed based on the mode-dependent average dwell time (MDADT) method. The designed strategy has better performance in reducing conservatism and improving flexibility, by comparison with the average dwell time (ADT) method. Moreover, based on the designed switching strategy, the sufficient conditions for the platoon control system to meet the exponential stability and exponential$L_{2}$performance are analyzed, and then, the linear matrix inequalities for solving the controller gain are given. Furthermore, the designed method has an advantage in applying to a variety of communication topologies. Finally, the effectiveness of the proposed robust control method in the case of intermittent communication in leading vehicle’s information transmission is verified by simulation.

The cooperation between connected and automated vehicles (CAVs) has emerged as a promising way to improve traffic efficiency and safety for ramp merging on highways. Existing research mostly focused on the collaboration of individual CAVs, while the cooperative merging strategy in mixed traffic considering vehicle platoons has been less explored. To address the above problem, this study aims to build connections between sequence scheduling and motion planning in mixed traffic, where individual CAVs, CAVs platoons, and mixed platoons coexist. First, optimal control strategies are presented for vehicles with flexible merging points based on Pontryagin’s minimum principle (PMP), and the final vehicle states in variable conditions are summarized in a phase diagram. Subsequently, the optimal final-state phase diagram is introduced into the passing sequence tree search process, which is designed for different vehicle groups in mixed traffic. Heuristic pruning rules are added to the depth-first search strategy to facilitate finding the optimal solution. Finally, an event-triggered receding horizon optimization algorithm is developed for continuous implementation. The numerical simulations are conducted in multiple traffic volumes, and the simulation results reveal that our proposed algorithm significantly improves the overall traffic efficiency and reduces vehicle-passing delays compared with the traditional FIFO-based cooperation method.

Intelligent electric vehicles (IEVs) have attracted more and more attention benefitting from the characteristics of high degree of safety and energy efficiency. This paper proposes an adaptive cruise control framework considering regenerative braking to improve safety and energy efficiency of IEVs during the car-following process. At first, a coupled and nonlinear dynamic model of IEVs system is constructed, which is mainly composed of a powerful battery, an electric motor, a single-speed transmission, and a hydraulic braking system. Then, an adaptive fuzzy sliding mode high-level controller is designed to accurately obtain the desired longitudinal acceleration of IEVs, in which the fuzzy logic is utilized to approximate the switching control item of the sliding mode control for chattering free. And the stability of high-level controller is proven by the Lyapunov theory. In the lower-level controller, traction control and brake control are designed to track the desired acceleration produced by the high-level controller, in addition, a novel regenerative braking strategy is presented to maximize the braking energy recovery. Finally, the simulation results indicate that the proposed control scheme has the excellent performance of longitudinal tracking and braking energy recovery with no loss of safety.

On a highway, the frequency of occurrence of irrelevant features, such as trees, varies a lot in different scenes. A limitation of the deep conventional neural networks used in end-to-end self-driving systems is that if the incoming images contain too much information, it makes it difficult for the network to extract only the subset of features required for decision making. Consequently, while existing end-to-end approaches may perform well in training scenes, they may not work correctly in other scenes. In this study, we developed a novel training method for an auto-encoder that equips it to ignore irrelevant features in input images while simultaneously retaining relevant features. Compared with feature extraction methods in existing end-to-end approaches, the proposed method reduces the labeling costs by only requiring image-level tags. The method was validated by training a convolutional neural network model to process the output of the encoder and produce a steering angle to control the vehicle. The entire end-to-end self-driving approach can ignore the influence of irrelevant features even though there are no such features when training the convolutional neural network.

Cooperative adaptive cruise control (CACC) has the potential to significantly improve road safety, highway throughput and reduce fuel consumption. However, the safety of the intended functionality (SOTIF) of CACC that focuses on unreasonable risks related to performance limitations has not been addressed. Moreover, various unknown uncertainties, disturbances, and controller perturbations present in the road environment make the guarantee of SOTIF for CACC a more challenging problem. This study presents a robust non-fragile fault tolerant control (RNFTC) strategy as a quantitative risk reduction method for ensuring SOTIF of CACC with system uncertainty, multisource disturbances, and controller perturbations. First, an intermediate based robust estimation method is proposed to estimate the performance limitations of perception and actuation, system states, and matched disturbances, simultaneously. Second, a robust non-fragile$\text{H}_{\infty }$FTC method is proposed to accommodate the simultaneous presence of performance limitations and disturbances. Third, theorems for solving optimal estimator and controller gains of the proposed RNFTC are derived in terms of linear matrix inequalities (LMIs). The requirements for CACC system stability, robustness, non-fragile and$\text{H}_{\infty }$performances under the proposed RNFTC are analyzed using Lyapunov theory. Finally, a series of comparative simulations with the CACC system are conducted to demonstrate the effectiveness and superiority of the proposed RNFTC method on ensuring SOTIF of CACC under unknown uncertainties, disturbances, and perturbations.

Wireless communication plays a significant role in the control of connected and automated vehicles (CAVs). In particular, poor communication would cause worse vehicle performances, and may even cause safety issues. This paper aims to establish a communication model for vehicular environments and deeply analyze the impact of communication characteristics on CAVs control. Firstly, the three-parameter Burr distribution delay model and the Nakagami distribution packet delivery rate (PDR) model are proposed to describe vehicular wireless networks' characteristics. Then, the platooning control is selected for a case study, and a vehicle platoon control system incorporating the proposed communication model is established. Furthermore, a simulation platform is built based on SUMO and Python, and the impact of communication characteristics on the platoon's performance is studied. The simulation results show that the characteristics presented by the communication model are consistent with those in field tests, and the quantized relationships between communication model parameters and vehicle control performance are also provided.

Making long-term trajectory prediction accurately for surrounding vehicles is the crucial prerequisite for intelligent vehicles to accomplish superb decision making and motion planning. In this paper, to achieve high-quality prediction accuracy both in the short and long term, we propose an integrated probabilistic framework with the combination of driver awareness model and Gaussian process model. The former model can obtain high-level semantic information using low-level two-dimensional motion elements. And the latter incorporates the vehicle physical model to reach good prediction performance with strengthened historical input sequence. Furthermore, experiments on the public naturalistic driving dataset in lane-changing scenarios are conducted to verify our novel approach. Compared with another advanced method, the superiorities of our proposed approach are demonstrated with higher estimation and prediction accuracy, as well as more reasonable uncertainty description in terms of the whole prediction process.

Research on collision avoidance has received significant attention in academia, but few attempts have been made regarding the impact of the real driver. Focusing on the hybrid vehicle controlled by a real driver, this paper proposes a combined yaw moment and steering torque control method based on driving behaviors during the emergency steering evasion (ESE). First, a CarSim vehicle model and a vision-based driving simulator are built to acquire and analyze ESE driving behaviors, and the trigger condition of the assistance is defined. Second, a preview distance adaptive driver steering model is created and followed by the calculation of the desired value of the steering angle and yaw rate from the planned collision avoidance path. Third, an ESE assistance controller is designed on the basis of the electric power steering (EPS) torque assistance law during normal driving and driving behaviors for the steering evasion lane change. Controllers used for this paper include a yaw rate tracking controller and a steering torque assistance fuzzy controller. The actuators are EPS, an electric stability program, and two hub motors in the rear axle. The preview distance is optimized by the particle swarm optimization method and the driving behavior-based ESE controller is tested with the driving simulator. The result shows that the optimized preview distance is credible, and the path tracking accuracy and the vehicle stability are improved with the help of the proposed ESE assistance controller by giving full consideration to driving behaviors in ESE.

This paper deals with the trajectory following control problem of a class of autonomous vehicles with parametric uncertainties, external disturbances, and over-actuated features. A novel adaptive hierarchical control framework is proposed to supervise the lateral motion of autonomous four-wheel independent drive electric vehicles. First, an adaptive sliding mode high-level control law with the linear matrix inequality-based switching surface is designed to produce a vector of front steering angle and external yaw moment, in which the uncertain term and the switching control gain are adaptively regulated by the fuzzy logic technique, to further moderate the chattering phenomenon, an adaptive boundary layer is introduced. Second, a pseudo-inverse low-level control allocation algorithm is presented to optimally allocate the external yaw moment via coordinating and reconstructing the tire longitudinal forces. Finally, numerical simulation and experimental results demonstrate that the proposed adaptive control approach has outstanding tracking performance.

This paper presents an energy-efficient and terrain-information-and-preceding-vehicle-information-incorporated energy management strategy for fully electric vehicles (FEVs) equipped with in-wheel motors. Saving driving energy with terrain preview and preceding vehicle movement prediction are crucial to prolong the driving distance for an FEV. Unlike conducting energy optimization under the assumption that the preceding vehicle movements are already known in most studies, the front vehicle movements are predicted during each control cycle based on the vehicle-to-vehicle communication, and the FEV vehicle velocity and motor torque distribution are optimized by a nonlinear model predictive controller to reduce energy consumption. The energy-saving objective is achieved by including, in the cost function, the motor energy consumption in each control cycle, while the safety objective is accomplished by keeping a suitable relative distance from the preceding vehicle. Since the nonlinear vehicle longitudinal model is applied, the gridding initial torque plane is utilized in each time step to search for the global minimum. Simulation results show that this method has a better energy-saving performance than the control method without using the preceding vehicle movement information, and the algorithm proposed here has a wide applicability under various driving conditions.

Adaptive cruise control (ACC) of hybrid electric vehicles (HEVs) has been traditionally developed without an efficient integration with active safety and energy management systems of hybrid power-trains, mainly for facilitating its implementation. This, however, leads to a compromise in the fuel economy of HEVs, since the predictive driving information provided by ACC is not exploited by the energy management system. In order to enhance the energy efficiency and control system integration, a novel ACC system for intelligent HEVs (i-HEV ACC) is developed in this study. The controller is proposed within the framework of nonlinear model predictive control, and a position-based nonlinear longitudinal intervehicle dynamics model is developed. A coordinated optimal control problem for both the tracking safety and the fuel consumption is formulated subject to the constraints on stable tracking. A multistep offline dynamic programming optimization and an online lookup table are used to implement the real-time control algorithm. Experiments are further conducted, which demonstrate that the proposed i-HEV ACC achieves enhanced performance and cooperation in traffic safety, fuel efficiency, and ride comfort.

The concept of an intelligent environment-friendly vehicle (i-EFV) is proposed in this paper. It integrates three components, i.e., clean-energy powertrain, electrified chassis, and intelligent information interaction devices. By employing such technologies as structure sharing, data fusion, and control coordination, more comprehensive performances are achievable, in terms of traffic safety, fuel efficiency, and environmental protection. Based on its definition and configuration, some key technologies, including design for resource effectiveness, driving environment identification, and coordinated control, are studied. As a basic application, a platform of an intelligent hybrid electric vehicle (i-HEV), which incorporates a hybrid powertrain with adaptive cruise control, has been designed and implemented. Both simulation and experimental results demonstrated that the i-EFV performed better than a conventional vehicle.