Search

This paper focuses on the cooperative driving challenges of connected and automated vehicles (CAVs) at single-lane roundabouts. First, a geometric path planning method is proposed for CAVs navigating a single-lane roundabout. Based on this method, a vehicle roundabout model is established. Four potential traffic scenarios for CAVs are established, and the optimal arrival times at conflict points are analyzed. By correlating the optimal arrival times at conflict points with the optimal entry times into the roundabout, the multi-vehicle coordination problem in complex intersections is simplified to a speed control issue during entry. Utilizing the principles of optimal control and Pontryagin minimization, two speed optimization strategies are proposed. Finally, MATLAB is employed for simulation analysis. The results indicate that the control strategy proposed in this paper enables the system to clearly identify potential conflicts between vehicles and implement an optimal control strategy, ensuring that vehicles can navigate the roundabout efficiently in terms of time and fuel without collisions. Additionally, the minimum time interval is established at 0.2 seconds to completely prevent vehicle collisions. In this study, the fusion problem involving two vehicles at a single conflict point is further expanded to encompass multiple vehicles at multiple conflict points. Thus, the efficient scheduling of multiple vehicles in single-lane roundabouts is realized. [ABSTRACT FROM AUTHOR]

In response to the issues of low merging success rates and poor safety in the on-ramp merging scenario within autonomous driving, we propose an on-ramp merging model for unmanned vehicles based on the Multi-Agent Proximal Policy Optimization (MAPPO) algorithm. Firstly, we introduce an Action-Mask (AM) to prevent the sampling of invalid actions during merging, thus enhancing safety by ensuring only valid actions are considered. Secondly, we incorporate noise advantage values to encourage unmanned vehicles to thoroughly explore the environment and avoid being trapped in local optimal solutions. Experimental results demonstrate that the AM-MAPPO algorithm model improves both safety and traffic efficiency. [ABSTRACT FROM AUTHOR]

Nowadays, control is pervasive in vehicles, and a full and accurate knowledge of vehicle states is crucial to guarantee safety levels and support the development of Advanced Driver-Assistance Systems (ADASs). In this scenario, real-time monitoring of the vehicle sideslip angle becomes fundamental, and various virtual sensing techniques based on both vehicle dynamics models and data-driven methods are widely presented in the literature. Given the need for on-board embedded device solutions in autonomous vehicles, it is mandatory to find the correct balance between estimation accuracy and the computational burden required. This work mainly presents different physical KF-based methodologies and proposes both mathematical and graphical analysis to explore the effectiveness of these solutions, all employing equal tire and vehicle simplified models. For this purpose, results are compared with accurate sensor acquisition provided by the on-track campaign on passenger vehicles; moreover, to truthfully represent the possibility of using such virtual sensing techniques in real-world scenarios, the vehicle is also equipped with low-end sensors that provide information to all the employed observers. [ABSTRACT FROM AUTHOR]

Providing safe, smooth, and efficient trajectories for autonomous vehicles has long been a question of great interest in the field of autopiloting. In dynamic and ever-changing urban environments, safe and efficient trajectory planning is fundamental to achieving autonomous driving. Nevertheless, the complexity of environments with multiple constraints poses challenges for trajectory planning. It is possible that behavior planners may not successfully obtain collision-free trajectories in complex urban environments. Herein, this paper introduces spatio–temporal joint optimization-based trajectory planning (SJOTP) with multi-constraints for complex urban environments. The behavior planner generates initial trajectory clusters based on the current state of the vehicle, and a topology-guided hybrid A* algorithm applied to an inflated map is utilized to address the risk of collisions between the initial trajectories and static obstacles. Taking into consideration obstacles, road surface adhesion coefficients, and vehicle dynamics constraints, multi-constraint multi-objective coordinated trajectory planning is conducted, using both differential-flatness vehicle models and point-mass vehicle models. Taking into consideration longitudinal and lateral coupling in trajectory optimization, a spatio–temporal joint optimization solver is used to obtain the optimal trajectory. The simulation verification was conducted on a multi-agent simulation platform. The results demonstrate that this methodology can obtain optimal trajectories safely and efficiently in complex urban environments. [ABSTRACT FROM AUTHOR]

Autonomous vehicles (AVs) present a paradigm shift in addressing conventional parking challenges. Unlike human‐driven vehicles, AVs can strategically park or cruise until summoned by users. Utilizing utility theory, the parking decision‐making processes of AVs users are explored, taking into account constraints related to both cost and time. An agent‐based simulation approach is adopted to construct an AV parking model, reflecting the complex dynamics of the parking decision process in the real world, where each user's choice has a ripple effect on traffic conditions, consequently affecting the feasible options for other users. The simulation experiments indicate that 11.50% of AVs gravitate towards parking lots near their destinations, while over 50% of AVs avoid public parking amenities altogether. This trend towards minimizing individual parking costs prompts AVs to undertake extended empty cruising, resulting in a significant increase of 48.18% in total vehicle mileage. Moreover, the pricing structure across various parking facilities and management dictates the parking preferences of AVs, establishing a nuanced trade‐off between parking expenses and proximity for these vehicles. [ABSTRACT FROM AUTHOR]

Existing vehicle-road models used for road tracking do not take into account the side slip angle, which leads to a reduction in road tracking accuracy in scenarios where the vehicle is at a large side slip angle, such as an emergency lane change. Consequently, this study presents a path-tracking control technique based on the T-S fuzzy model of heading angle vehicle autonomy. In this paper, based on the yaw angle-based vehicle tracking model, a heading angle-based tracking model considering the side slip angle is constructed. Second, since the vehicle speed varies with time, this paper selects the membership function of the vehicle speed to establish the T-S fuzzy model of autonomous vehicle based on the yaw angle and heading angle, respectively, and ensures the robustness and stability over the whole parameter space by the linear parameter variation robust H ∞ controller. Then, cost functions based on the yaw angle and heading angle augmented error systems are created separately to optimize the system's overall performance. Ultimately, simulation and experimentation confirm that the algorithm for control, which is based on the fuzzy model of the heading angle vehicle, has superior autonomous trajectory performance. [ABSTRACT FROM AUTHOR]

Many advanced driver assistance schemes or autonomous vehicle controllers are based on a motion model of the vehicle behavior, i.e., a function predicting how the vehicle will react to a given control input. Data-driven models, based on experimental or simulated data, are very useful, especially for vehicles difficult to model analytically, for instance, ground vehicles for which the ground-tire interaction is hard to model from first principles. However, learning schemes are limited by the difficulty of collecting large amounts of experimental data or having to rely on high-fidelity simulations. This paper explores the potential of an approach that uses dimensionless numbers based on Buckingham's π theorem to improve the efficiency of data for learning models, with the goal of facilitating knowledge sharing between similar systems. A case study using car-like vehicles compares traditional and dimensionless models on simulated and experimental data to validate the benefits of the new dimensionless learning approach. Preliminary results from the case study presented show that this new dimensionless approach could accelerate the learning rate and improve the accuracy of the model prediction when transferring the learned model between various similar vehicles. Prediction accuracy improvements with the dimensionless scheme when using a shared database, that is, predicting the motion of a vehicle based on data from various different vehicles was found to be 480% more accurate for predicting a simple no-slip maneuver based on simulated data and 11% more accurate to predict a highly dynamic braking maneuver based on experimental data. A modified physics-informed learning scheme with hand-crafted dimensionless features was also shown to increase the improvement to precision gains of 917% and 28% respectively. A comparative study also shows that using Buckingham's π theorem is a much more effective preprocessing step for this task than principal component analysis (PCA) or simply normalizing the data. These results show that the use of dimensionless variables is a promising tool to help in the task of learning a more generalizable motion model for vehicles, and hence potentially taking advantage of the data generated by fleets of vehicles on the road even though they are not identical. [ABSTRACT FROM AUTHOR]

Trajectory tracking on a low-speed vehicle using the model predictive control (MPC) algorithm usually assumes a simple road terrain. This assumption does not correspond to the actual road situation, leading to low tracking accuracy. Therefore, a trajectory tracking method considering road curvature based on MPC is proposed in this paper. In this method, the controller can automatically switch between MPC types. Linear model predictive control (LMPC) is selected for small road curvatures, while nonlinear model predictive control (NMPC) is employed for large road curvatures. In addition, the NMPC algorithm in this work considers the effect of road curvature on tracking accuracy, making it suitable for tracking time-varying curvature roads. To verify the feasibility of the algorithm, simulation comparisons with the basic MPC model were carried out at different testing roads and vehicle longitudinal speeds. The results indicate that the method significantly improves trajectory tracking accuracy, all while ensuring real-time calculations. The intelligent switching capability of control models based on road curvature allows its application to track trajectories on arbitrarily complex roads. [ABSTRACT FROM AUTHOR]

The systems that are currently installed in autonomous vehicles are not designed to avoid obstacles on the road by manoeuvring at the limits of the vehicle and the road surface – the goal of the research presented was to develop such system. For these purposes, a universal test track based on ISO 3888-1 and ISO 3888-2 standards was adopted, which can be used to represent any situation in which there is an obstacle on the road in front of the vehicle that needs to be avoided. An analysis of the curves for generating the paths through the test track was carried out, on the basis of which the Bézier curves were chosen. In addition to them, the results of simulations in Adams Car software were used to generate the paths, which can be considered equivalent to real-world trials with a professional driver behind the wheel. A control model was developed for longitudinal and transverse control of the vehicle based on PID controllers, with the selection of optimal parameters – the ones that define PID controllers, and the others that define other characteristics of the model. The model proved to be successful in guiding the vehicle through the test track at all speeds at which manoeuvres are possible. Bézier curves are shown to be a better choice at lower speeds, while paths based on Adams Car simulations are a better choice at higher speeds. [ABSTRACT FROM AUTHOR]

This paper proposes a learning-based control approach for autonomous vehicles. An explicit Takagi–Sugeno (TS) controller is learned using input and output data from a preexisting controller, employing the Adaptive Neuro-Fuzzy Inference System (ANFIS) algorithm. At the same time, the vehicle model is identified in the TS model form for closed-loop stability assessment using Lyapunov theory and LMIs. The proposed approach is applied to learn the control law from an MPC controller, thus avoiding the use of online optimization. This reduces the computational burden of the control loop and facilitates real-time implementation. Finally, the proposed approach is assessed through simulation using a small-scale autonomous racing car. [ABSTRACT FROM AUTHOR]

Energy and environmental concerns have fostered the era of electric vehicles (EVs) to take over and be welcomed more than ever. Fuel-powered vehicles are still predominant; however, this trend appears to be changing sooner than we might expect. Countries in Europe, Asia, and many states in America have already made the decision to transition to a fully EV industry in the next few years. This looks promising; however, drivers still have concerns about the battery mileage of such vehicles and the anxiety that such driving experiences! Indeed, driving with the probability of having insufficient battery charge that may be involved in guaranteeing the delivery to the trip destination imposes a level of anxiety on the vehicle drivers. Therefore, for an alternative to traditional fuel-powered vehicles to be convincing, there needs to be sufficient coverage of charging stations to serve cities in the same way that fuel stations serve traditional vehicles. The current navigation models select routes based solely on distance and traffic metrics, without taking into account the coverage of fuel service stations that these routes may offer. This assumption is made under the belief that all routes are adequately covered. This might be true for fuel-powered vehicles, but not for EVs. Hence, in this work, we are presenting AFARM, a routing model that enables a smart navigation system specifically designed for EVs. This model routes the EVs via paths that are lined with charging stations that align with the EV's current charge requirements. Different from the other models proposed in the literature, AFARM is autonomous in the sense that it determines navigation paths for each vehicle based on its make, model, and current battery status. Moreover, it employs Dijkstra's algorithm to accommodate varying least-cost navigation preferences, ranging from shortest-distance routes to routes with the shortest trip time and routes with maximum residual battery capacities as well. According to the EV driver's preference, AFARM checks the set of candidate paths at the source point and selects the appropriate path for the vehicle to drive based on its current status. Consequently, AFARM provides an anxiety-free navigation model that allows for a reliable and environmentally friendly driving experience, promoting this alternative mode of transportation. [ABSTRACT FROM AUTHOR]

To promote the application of automated vehicles in large airports, in this study, we present an integrated optimization method for scheduling Unmanned follow-me cars. The scheduling process is divided into three phases: Dispatch, Guidance, and Recycle. For the Dispatch phase, we establish a vehicle assignment model, to allocate the vehicle resource equitably. For the Guidance phase, we offer an quantitative way, to measure the spacing between Unmanned follow-me car and aircraft. To optimize the efficiency of airport operation in the three phases and ensure safety, the collaborative planning model, and the conflict prediction model are established. An improved grey wolf optimization algorithm is adopted to enhance the convergence speed and generalization performance. A case study at Ezhou Huahu Airport in China demonstrates the effectiveness of the methods. The results show that the model of collaborative planning can make the balance of path selection, Unmanned follow-me car's working time, and departure sequence. The convergence speed of the improved algorithm has been increased by 18.75%. The inequity index of vehicle assignment is only 0.015731, and the spatiotemporal distribution of conflicts is influenced by the airport's surface layout. [ABSTRACT FROM AUTHOR]

The development of intelligent transportation technology has provided a significant impetus for autonomous driving technology. Currently, autonomous vehicles based on Model Predictive Control (MPC) employ motion control strategies based on sampling time, which fail to fully utilize the spatial information of obstacles. To address this issue, this paper proposes a dual-layer MPC vehicle collision-free trajectory tracking control strategy that integrates spatial kinematics and vehicle dynamics. To fully utilize the spatial information of obstacles, we designed a vehicle model based on spatial kinematics, enabling the upper-layer MPC to plan collision avoidance trajectories based on distance sampling. To improve the accuracy and safety of trajectory tracking, we designed an 8-degree-of-freedom vehicle dynamic model. This allows the lower-layer MPC to consider lateral stability and roll stability during trajectory tracking. In collision avoidance trajectory tracking experiments using three scenarios, compared to two advanced time-based algorithms, the trajectories planned by the proposed algorithm in this paper exhibited predictability. The proposed algorithm can initiate collision avoidance at predetermined positions and can avoid collisions in predetermined directions, with all state variables within safe ranges. In terms of time efficiency, it also outperformed the comparative algorithms. [ABSTRACT FROM AUTHOR]

Precise trajectory prediction is pivotal for autonomous vehicles operating in real-world traffic conditions, and can help them make the right decisions to ensure safety on the road. However, state-of-the-art approaches consider limited information about the historical movements of vehicles. On highways, drivers make their next judgments according to the behavior of the ambient vehicles. Thus, vehicles need to consider temporal and spatial interactions to reduce the risk of future collisions. In the current work, a trajectory prediction method is put forward in accordance with a graph attention mechanism. We add the absolute and relative motion information of vehicles to the input of the model to describe the vehicles' past motion states more accurately. LSTM models are employed to process the historical motion information of vehicles, as well as the temporal correlations in interactions. The graph attention mechanism is applied to capture the spatial correlations between vehicles. Utilizing a decoder rooted in an LSTM framework, the future trajectory distribution is generated. Evaluation on the NGSIM US-101 and I-80 datasets substantiates the superiority of our approach over existing state-of-the-art algorithms. Moreover, the predictions of our model are analyzed. [ABSTRACT FROM AUTHOR]

Despite its excellent performance in path tracking control, the model predictive control (MPC) is limited by computational complexity in practical applications. The neural network control (NNC) is another attractive solution by learning the historical driving data to approximate optimal control law, but a concern is that the NNC lacks security guarantees when encountering new scenarios that it has never been trained on. Inspired by the prediction process of MPC, the deviation sequence neural network control (DS-NNC) separates the vehicle dynamic model from the approximation process and rebuilds the input of the neural network (NN). Taking full use of the deviation sequence architecture and the real-time vehicle dynamic model, the DS-NNC is expected to enhance the adaptability and the training efficiency of NN. Finally, the effectiveness of the proposed controller is verified through simulations in Matlab/Simulink. The simulation results indicate that the proposed path tracking NN controller possesses adaptability and learning capabilities, enabling it to generate optimal control variables within a shorter computation time and handle variations in vehicle models and driving scenarios. [ABSTRACT FROM AUTHOR]

The perception system is essential for autonomous vehicle safety and stability. However, on‐board sensors are vulnerable to external attacks, compromising driving strategies and security. Traditional attack detection methods, relying on static anomaly thresholds from data distributions, falter in complex driving scenarios. Recent studies have sought more nuanced detection techniques, including deep learning and inter‐vehicle communication, but these approaches face limitations related to data security and environmental dependency. This letter introduces an innovative, adaptive method for sensor attack detection in autonomous vehicles. By modelling the perception system's functions and employing the Gaussian process for probabilistic modelling, we generate dynamic uncertainty estimates that serve as adaptable anomaly boundaries. Our method's efficacy and resilience are validated through quantitative analysis of the real‐world KITTI dataset, demonstrating superior adaptive detection capabilities. [ABSTRACT FROM AUTHOR]

At work, three tasks were presented: road lane detection and trajectory estimation, environment mapping, and the application of a neural network. All these tasks are based on the results of the lane detection method. The presented lane detection method stands out due to the execution of an interpolation transformation for all previously detected edge points. This transformation transfers these points to a "bird's-eye" coordinate system and distributes them on a grid. Road lanes are identified by a lane feature filter based on the analysis of the distances between unique points. This allows lane views to be obtained in a coordinate system while preserving the distance condition. The road environment map is constructed from the obtained images using a probabilistic algorithm called Distributed Particle-SLAM (DP-SLAM). Based on the map result, a method for representing characteristic points describing the path of road lanes in each incoming camera image has been developed. These points are then used for training the neural network. The neural network solves a regression task for the coordinates of the points on the road lanes, enabling the identification of coefficients for parabolic fitting. Validation has been performed. [ABSTRACT FROM AUTHOR]

The autonomous driving simulation field lacks evaluation and forecasting systems for simulation results. The data obtained from the simulation of target algorithms and vehicle models cannot be reasonably estimated. This problem affects subsequent vehicle improvement and parameter calibration. The authors relied on the simulation results of the AEB algorithm. We selected the BP Neural Network as the basis and improved it with a genetic algorithm optimized via a roulette algorithm. The regression evaluation indicators of the prediction results show that the GA-BP neural network has better prediction accuracy and generalization ability than the original BP neural network and other optimized BP neural networks. This GA-BP neural network also fills the Gap in Evaluation and Prediction Systems. [ABSTRACT FROM AUTHOR]

A pre-emptive braking control method is proposed to improve the stability of autonomous vehicles during emergency collision avoidance, aiming to imitate the realistic human driving experience. A linear model predictive control is used to derive the front wheel steering angle to track a predefined fifth-degree polynomial trajectory. Based on a two-degrees-of-freedom (DOF) vehicle dynamics model, the maximum stable vehicle speed during collision avoidance can be determined. If the actual vehicle speed exceeds the maximum stable vehicle speed, braking action will be applied to the vehicle. Furthermore, four-wheel steering (4WS) control and direct yaw moment control (DYC) are employed to further improve the stability of the vehicle during collision avoidance. Simulation results under a double lane change scenario demonstrate that the control system incorporating pre-emptive braking, 4WS, and DYC can enhance the vehicle stability effectively during collision avoidance. Compared to the 2WS system without pre-emptive braking control, the maximum stable vehicle speed of the integrated control system can be increased by at least 56.9%. The proposed integrated control strategy has a positive impact on the safety of autonomous vehicles, and it can also provide reference for the research and development of autonomous driving systems. [ABSTRACT FROM AUTHOR]

Task offloading in vehicular networks is hot topic in the development of autonomous driving. In these scenarios, due to the role of vehicles and pedestrians, task characteristics are changing constantly. The classical deep learning algorithm always uses a pre-trained neural network to optimize task offloading, which leads to system performance degradation. Therefore, this paper proposes a neural network fine-tuning task offloading algorithm, combining with location prediction for pedestrians and vehicles by the Payne model of fluid dynamics and the car-following model, respectively. After the locations are predicted, characteristics of tasks can be obtained and the neural network will be fine-tuned. Finally, the proposed algorithm continuously predicts task characteristics and fine-tunes a neural network to maintain high system performance and meet low delay requirements. From the simulation results, compared with other algorithms, the proposed algorithm still guarantees a lower task offloading delay, especially when congestion occurs. [ABSTRACT FROM AUTHOR]

This article addresses a common issue in the design of battery electric vehicles (BEVs) by introducing a comprehensive methodology for the modeling and simulation of BEVs, referred to as the "PerfECT Design Tool". The primary objective of this study is to provide engineers and researchers with a robust and streamlined approach for the early stages of electric vehicle (EV) design, offering valuable insights into the performance, energy consumption, current flow, and thermal behavior of these advanced automotive systems. Recognizing the complex nature of contemporary EVs, the study highlights the need for efficient design tools that facilitate decision-making during the conceptual phases of development. The PerfECT Design Tool is presented as a multi-level framework, divided into four logically sequential modules: Performance, Energy, Currents, and Temperature. These modules are underpinned by sound theoretical foundations and are implemented using a combination of MATLAB/Simulink and the vehicle dynamics software VI-CRT. The research culminates in the validation of the model through a series of experimental maneuvers conducted with a Tesla Model 3, establishing its accuracy in representing the mechanical, electrical, and thermal behavior of BEVs. The study's main findings underscore the viability of the design tool as an asset in the initial phases of BEV design. Beyond its primary application, the tool holds promise for broader utilization, including the development of active control systems, advanced driver assistance systems (ADAS), and solutions for autonomous driving within the domain of electric vehicles. [ABSTRACT FROM AUTHOR]

An effective path-following controller is a guarantee for stable sailing of underactuated unmanned surface vehicles (USVs). This paper proposes an event-triggered robust control approach considering an unknown model nonlinearity, external disturbance, and event-triggered mechanism. The proposed method consists of guidance and dynamic control subsystems. Based on the tracking error dynamics equations, the guidance subsystem is designed to achieve the guidance law. For the dynamic control subsystem, the radial basis function neural networks (RBFNNs) are designed to approximate the unknown model nonlinearity and external disturbances to improve the robustness of the proposed method. In addition, an event-triggered mechanism is constructed to reduce the triggering times. The closed-loop system is proven to be stable, and the effectiveness of the proposed method is illustrated through simulation results. [ABSTRACT FROM AUTHOR]

In this paper, the authors investigate the issue of constructing and incorporating an accurate vehicle dynamic model for model predictive control (MPC) with an application to autonomous vehicle path following. To achieve the desired performance, MPC employs a precise dynamic model. However, the uncertainty of complex systems and their operating environments presents a challenge to the development of an adequately accurate vehicle dynamic model. This paper proposes a Deep Gaussian Process Regression (DGPR) method to improve model precision. Meanwhile, the learning model is incorporated into a novel MPC framework to enhance closed‐loop performance. High‐fidelity simulations using CarSim‐MATLAB demonstrate the validity of the proposed approach in terms of enhancing the path following performance and lateral stability under the condition of large curvature at medium to high speeds on roads with different friction coefficients when compared to the nominal MPC approach. [ABSTRACT FROM AUTHOR]

Model-predictive control (MPC) offers significant advantages in addressing constraint-related challenges and plays a pivotal role in self-driving car technology. Its primary goal is to achieve precise trajectory tracking while prioritizing vehicle stability and safety. However, real-time operations often face challenges related to computational demands and low computational efficiency. To address these challenges, this paper introduces a novel lateral control algorithm for self-driving vehicles, which utilizes the linear complementarity problem (LCP) instead of the conventional quadratic programming (QP) method as the MPC optimization solution. This innovative approach incorporates the electric steering system into the vehicle dynamics model, allowing for precise torque regulation of the steering motor and enhancing control accuracy. The MPC algorithm adopts the LCP solution method to calculate control signals based on the vehicle's state, ensuring both rapid and stable vehicle control. Simulation results demonstrate that the proposed MPC algorithm, utilizing the LCP solution method, effectively addresses efficiency issues in the lateral motion of self-driving cars. This leads to improvements in both driving stability and real-time performance. Overall, this innovative approach lays a solid foundation for the practical implementation of self-driving cars. [ABSTRACT FROM AUTHOR]

Accurate prediction of vehicle acceleration has significant practical applications. Deep learning, as one of the methods for acceleration prediction, has shown promising applications in acceleration prediction. However, due to the influence of multiple factors on acceleration, a single data model may not be suitable for various driving scenarios. Therefore, this paper proposes a hybrid approach for vehicle acceleration prediction by combining clustering and deep learning techniques. Based on historical data of vehicle speed, acceleration, and distance to the preceding vehicle, the proposed method first clusters the acceleration patterns of vehicles. Subsequently, different prediction models and parameters are applied to each cluster, aiming to improve the prediction accuracy. By considering the unique characteristics of each cluster, the proposed method can effectively capture the diverse acceleration patterns. Experimental results demonstrate the superiority of the proposed approach in terms of prediction accuracy compared to benchmarks. This paper contributes to the advancement of sensor data processing and artificial intelligence techniques in the field of vehicle acceleration prediction. The proposed hybrid method has the potential to enhance the accuracy and reliability of acceleration prediction, enabling applications in various domains, such as autonomous driving, traffic management, and vehicle control. [ABSTRACT FROM AUTHOR]

In this paper, a model predictive control (MPC) approach for controlling automated vehicle steering during path tracking is presented. A (linear parameter-varying) LPV vehicle plant model including steering dynamics is proposed to determine the system evolution matrices. The steering dynamics are modeled in two different ways by using first-order lag and a second-order lag; the application of the first-order system resulted in a slightly more accurate path-following. Additionally, a cascade MPC structure is applied in which two MPCs are used; the second-order steering dynamics are separated from the path-following controller in a second MPC. Both steering system models and the cascade MPC are evaluated in simulation and on a test vehicle. The reference trajectory is calculated based on a fixed predefined path by transforming the necessary path segment to the vehicle ego coordinate system, thereby describing the reference for the path-following task in a novel way. The MPC method computes the optimal steering angle vector at each time step for following the path. The longitudinal dynamics is controlled separately by a PI controller. After simulation evaluation, experimental tests were conducted on a test vehicle on an asphalt surface. Both simulation and experimental results prove the effectiveness of the proposed reference definition method. The effect of the applied steering system models is evaluated. The inclusion of the steering dynamics in the prediction model resulted in a significant increase in controller performance. Finally, the computational requirements of the proposed control and modeling methods are also discussed. [ABSTRACT FROM AUTHOR]

This paper investigates the impact of tyre dynamics on autonomous vehicle dynamic control. The commonly used 2 degrees of freedom bicycle model and a detailed vehicle model considering tyre dynamics are built, respectively, to describe the vehicle dynamics. The two models are firstly compared with the response to front wheel steering input and differential motor torque input. The transient vehicle body vibrations are clearly demonstrated by the detailed model but overlooked by the bicycle model. The influence of tyre nonlinearity on path offset is also revealed. Then, the path following control strategy is designed based on the linear quadratic regulator control to compare the two models from the path following performance perspective. The double lane change simulation is conducted. The results show that at low vehicle speed, the path following errors of two models are very close, which proves the rationality of using the bicycle model to represent the vehicle dynamics in mild and moderate driving conditions. However, when the path following is conducted with high vehicle speed, the required lateral tyre force is large, so the tyres work with large slip angles and the tyre nonlinearity generates significant deviation on the path following errors between the two models. [ABSTRACT FROM AUTHOR]

Planning for autonomous vehicles to merge into high‐density traffic flows within limited mileage is quite challenging. Specifically, the driving trajectory will inevitably have intersections with other vehicles whose driving intentions can't be directly observed. Herein, a two‐stage algorithm framework that is decomposed into the longitudinal and lateral planning processes for online merging planning is proposed. An improved particle filter is used to estimate the driving models of surrounding vehicles for predicting their future driving intentions. Based on Monte Carlo tree search (MCTS), different action spaces are evaluated for longitudinal merging gap selection and lateral interactive merging operation, while heuristic pruning is used to reduce the computation cost. Moreover, the coefficients related to the driving styles are introduced, and their influences on merging performance are analyzed. Finally, the proposed algorithm is implemented in a two‐lane simulation environment. The results show that the proposal has outperformed other baseline methods. [ABSTRACT FROM AUTHOR]

The motion planning and control method of automated vehicles, as the key technology of automated vehicles, directly affects the safety, comfort, and other technical indicators of vehicles. The planning module is responsible for generating a vehicle driving path. The control module is responsible for driving the vehicle. In this study, we review the main methods and achievements in motion planning and motion control for automated vehicles. The advantages and disadvantages of various planning and control methods are comparatively analyzed. Finally, some predictions and summaries based on the existing research results and trends are proposed. Through this analysis, it is believed that various types of algorithms will be further integrated in the future to complement each other's strengths and weaknesses. The next area of research will be to establish more accurate vehicle models to describe vehicle motion, improve the generalization-solving ability of algorithms, and enhance the planning and control of integrated 'human-vehicle-road' traffic systems. [ABSTRACT FROM AUTHOR]

In the future, considering the expansion of the autonomous driving society, autonomous driving systems that can drive safely and quickly will be required for the purpose of saving lives and transporting goods even on rough road such as snowy, icy, and unpaved roads. In such unknown environments, technologies that combine model-based control and artificial intelligence (AI) are attracting attention for the purpose of ensuring operational stability and reliability. The second author has proposed a vehicle driving model that is robust to road geometry and ever-changing environmental disturbances. This model is based on a two-wheel model, and expresses the error in the position of the center of gravity of the vehicle by the front wheel steering angle deviation, and adaptively estimates this deviation. However, this model has large modeling errors when driving at high velocity on slippery roads. In this study, we extend this model proposed in previous study, and propose a new vehicle driving model that can handle situations such as driving with large acceleration changes and steering on bad roads such as snowy and wet roads. Then, we demonstrate the usefulness of the proposed method in a simulation using vehicle motion analysis software. [ABSTRACT FROM AUTHOR]

In this paper, parallel navigation is proposed to track the target in three-dimensional space. Firstly, the polar kinematics models for the vehicle and the target are established. Secondly, parallel navigation is derived by using polar kinematics models. Thirdly, cell decomposition method is applied to implement obstacle avoidance. Fourthly, a brief study is given on the inuence of uncertainties. Finally, simulations are conducted by MATLAB. Simulation results demonstrate the effectiveness of the parallel navigation. [ABSTRACT FROM AUTHOR]

This paper studies how autonomous vehicles (AVs) influence future traffic and energy consumption when adopting various route guidance strategies, which can be divided into global information strategies and local information strategies according to the scope of information collection. A mixed traffic flow model is established. Then, an autonomous vehicle model is improved to investigate the impact of six route guidance strategies. The selected strategies are specifically evaluated in a double-route scenario, considering both single-exit and dual-exit configurations. Three indicators are chosen to evaluate traffic efficiency, including traffic flow, average speed and quantity of vehicles. Consumption per unit flux is the indicator of energy consumption level. Simulation results show that autonomous vehicles can improve traffic efficiency and reduce energy consumption. [ABSTRACT FROM AUTHOR]

Road accidents are one of the major cause of human deaths around the globe. In order to accelerate autonomous driving, a problem of designing suitable lateral and longitudinal drive control scheme, with an obstacle avoidance mechanism has been considered. For this purpose, a two-wheel equivalent model of a vehicle has been adopted and steering angle velocity is treated as a control input. A cascaded architecture for Obstacle Avoidance and Drive Control has been presented. Impact point algorithm has been developed for Obstacle Avoidance System that receives data from various onboard sensors, and computes potential impact probability based on position and velocity of own vehicle and potential static and moving obstacles. The reference heading and speed signals are continuously updated by the Obstacle Avoidance System. Feedback linearization based lateral and longitudinal drive control laws have been proposed to control the required heading angle and longitudinal speed, respectively. Performance of the proposed control scheme for various operational scenarios has been evaluated through simulations. [ABSTRACT FROM AUTHOR]

This study proposes a two-level optimization model system for vehicle control and signal timing at isolated signal intersections under the mixed traffic flow environment composed of intelligent connected autonomous vehicles (CAVs) and connected human-driven vehicles (CHVs), to minimize the energy consumption and vehicle delay at intersections. The proposed two-layer optimization model is composed of a two-layer vehicle trajectory control model and a fuzzy control signal timing optimization model. The two-layer vehicle trajectory control model includes a signal-oriented vehicle trajectory control model and a car-following oriented vehicle trajectory control model. The former calculates expected acceleration and speed commands at each time step according to the coming signal information, to help vehicle pass the closest signal intersection without stopping during the green light interval; the latter uses the variable headway (VTH) strategy to follow the preceding vehicle by maintaining a safe distance. A microscopic simulator based on SUMO is developed to test the performance of the proposed optimization algorithm. In the simulation experiment, with the driving characteristics of CHV drivers considered, the results show that our model performs well under a CAV penetration rate of 30%–60% and under small or moderate levels of traffic flow. The average waiting time of vehicles is reduced by about 25% compared with the uncontrolled scheme. Under the condition of penetration rate of 60%, the average energy consumption of vehicles in the proposed model is 17.56% lower than that of the uncontrolled scheme. In addition, the proposed model reduces by 21.94% compared with the scheme of only controlling vehicles. When the traffic flow is at a low or medium level, the average energy consumption and waiting time of vehicles are reduced by nearly 35% with the proposed model. [ABSTRACT FROM AUTHOR]

Autonomous driving is an important branch of artificial intelligence, and real-time and accurate object detection is key to ensuring the safe and stable operation of autonomous vehicles. To this end, this paper proposes a fast and accurate object detector for autonomous driving based on improved YOLOv5. First, the YOLOv5 algorithm is improved by using structural re-parameterization (Rep), enhancing the accuracy and speed of the model through training-inference decoupling. Additionally, the neural architecture search method is introduced to cut redundant branches in the multi-branch re-parameterization module during the training phase, which ameliorates the training efficiency and accuracy. Finally, a small object detection layer is added to the network and the coordinate attention mechanism is added to all detection layers to improve the recognition rate of the model for small vehicles and pedestrians. The experimental results show that the detection accuracy of the proposed method on the KITTI dataset reaches 96.1%, and the FPS reaches 202, which is superior to many current mainstream algorithms and effectively improves the accuracy and real-time performance of unmanned driving object detection. [ABSTRACT FROM AUTHOR]

Advanced active safety systems play a crucial role in ensuring the safe driving of vehicles in critical conditions such as an obstacle avoidance manoeuvre. However, conventional techniques relying mainly on braking interventions may not result in the desired vehicle response in such situations. Over-actuation through the control of individual motion actuators could potentially improve the safety performance of vehicles. This study evaluates various configurations of motion actuators for path following and yaw stability control of vehicles in critical driving scenarios. The configurations include active front steering (S), active front steering + torque vectoring (ST), active front steering + active camber (SC) and active front steering + torque vectoring + active camber (STC). The evaluation is achieved based on a nonlinear model predictive control formulation, which considers yaw stability and the physical limits of motion actuators. This problem formulation uses a double-track vehicle model, combined with the Dugoff tyre model and its variant with the camber effect, to model the vehicle dynamics. The actuator configurations are evaluated regarding the passing velocity, tracking accuracy, safety distance and robustness to reference trajectory variation. The results indicate that the integrated control of STC performs the best among all the four configurations while S performs the worst. Furthermore, SC is generally superior to ST. [ABSTRACT FROM AUTHOR]

This paper provides a review of path-tracking strategies used in autonomous agricultural vehicles, mainly from two aspects: vehicle model construction and the development and improvement of path-tracking algorithms. Vehicle models are grouped into numerous types based on the structural characteristics and working conditions, including wheeled tractors, tracked tractors, rice transplanters, high clearance sprays, agricultural robots, agricultural tractor–trailers, etc. The application and improvement of path-tracking control methods are summarized based on the different working scenes and types of agricultural machinery. This study explores each of these methods in terms of accuracy, stability, robustness, and disadvantages/advantages. The main challenges in the field of agricultural vehicle path tracking control are defined, and future research directions are offered based on critical reviews. This review aims to provide a reference for determining which controllers to use in path-tracking control development for an autonomous agricultural vehicle. [ABSTRACT FROM AUTHOR]

In this paper, we propose an adaptive path tracking algorithm based on the BP (back propagation) neural network to increase the performance of vehicle path tracking in different paths. Specifically, based on the kinematic model of the vehicle, the front wheel steering angle of the vehicle was derived with the PP (Pure Pursuit) algorithm, and related parameters affecting path tracking accuracy were analyzed. In the next step, BP neural networks were introduced and vehicle speed, radius of path curvature, and lateral error were used as inputs to train models. The output of the model was used as the control coefficient of the PP algorithm to improve the accuracy of the calculation of the front wheel steering angle, which is referred to as the BP–PP algorithm in this paper. As a final step, simulation experiments and real vehicle experiments are performed to verify the algorithm's performance. Simulation experiments show that compared with the traditional path tracking algorithm, the average tracking error of BP–PP algorithm is reduced by 0.025 m when traveling at a speed of 3 m/s on a straight path, and the average tracking error is reduced by 0.27 m, 0.42 m, and 0.67 m, respectively, at a speed of 1.5 m/s with a curvature radius of 6.8 m, 5.5 m, and 4.5 m, respectively. In the real vehicle experiment, an electric patrol vehicle with an autonomous tracking function was used as the experimental platform. The average tracking error was reduced by 0.1 m and 0.086 m on a rectangular road and a large curvature road, respectively. Experimental results show that the proposed algorithm performs well in both simulation and actual scenarios, improves the accuracy of path tracking, and enhances the robustness of the system. Moreover, facing paths with changes in road curvature, the BP–PP algorithm achieved significant improvement and demonstrated great robustness. In conclusion, the proposed BP–PP algorithm reduced the interference of nonlinear factors on the system and did not require complex calculations. Furthermore, the proposed algorithm has been applied to the autonomous driving patrol vehicle in the park and achieved good results. [ABSTRACT FROM AUTHOR]

With the gradual maturity of autonomous driving and automatic parking technology, electric vehicle charging is moving towards automation. The charging port (CP) location is an important basis for realizing automatic charging. Existing CP identification algorithms are only suitable for a single vehicle model with poor universality. Therefore, this paper proposes a set of methods that can identify the CPs of various vehicle types. The recognition process is divided into a rough positioning stage (RPS) and a precise positioning stage (PPS). In this study, the data sets corresponding to four types of vehicle CPs under different environments are established. In the RPS, the characteristic information of the CP is obtained based on the combination of convolutional block attention module (CBAM) and YOLOV7-tinp, and its position information is calculated using the similar projection relationship. For the PPS, this paper proposes a data enhancement method based on similar feature location to determine the label category (SFLDLC). The CBAM-YOLOV7-tinp is used to identify the feature location information, and the cluster template matching algorithm (CTMA) is used to obtain the accurate feature location and tag type, and the EPnP algorithm is used to calculate the location and posture (LP) information. The results of the LP solution are used to provide the position coordinates of the CP relative to the robot base. Finally, the AUBO-i10 robot is used to complete the experimental test. The corresponding results show that the average positioning errors (x, y, z, rx, ry, and rz) of the CP are 0.64 mm, 0.88 mm, 1.24 mm, 1.19 degrees, 1.00 degrees, and 0.57 degrees, respectively, and the integrated insertion success rate is 94.25%. Therefore, the algorithm proposed in this paper can efficiently and accurately identify and locate various types of CP and meet the actual plugging requirements. [ABSTRACT FROM AUTHOR]

To explore the impact of autonomous vehicles (AVs) on human-driven vehicles (HDVs), a solution for AV to coexist harmoniously with HDV during the car following period when AVs are in low market penetration rate (MPR) was provided. An extension car following framework with two possible soft optimization targets was proposed in this article to improve the experience of HDV followers with different following strategies by deep deterministic policy gradient (DDPG) algorithm. The pretreated Next Generation Simulation (NGSIM) dataset was used for the experiments. 1027 car following events with being redefined were extracted from it, in which 600 of the events were used for training and 427 of the events were used for testing. The different driving strategies obtained from the classical car following models were embedded into virtual environment built by OpenAI gym. The reward function combined safety, efficiency, jerk, and stability was used to encourage the agent with DDPG algorithm to maximize it. The final result reveals that disturbance of HDV followers decreases by 2.362% (strategy a), 8.184% (strategy b), and 13.904% (strategy c), respectively. The disturbance of HDV follower decreases by 14.961% (strategy a), 12.020% (strategy b), and 13.425% (strategy c), respectively. HDV followers with different strategies get less jerk in both soft optimizations. AV passengers get a loss on jerk and efficiency, but safety is enhanced. Also, AV car following performs better than HDV car following in both soft and brutal optimizations. Moreover, two possible solutions for harmonious coexistence of HDVs and AVs when AVs are in low MPR are proposed. [ABSTRACT FROM AUTHOR]

This article presents a procedure algorithm and vehicle dynamics models that can be applied to planning and controlling the motion of an autonomous car. The simulation results obtained using a simplified bicycle model with three degrees of freedom and a spatial model with 10 degrees of freedom were compared. The numerical efficiency of both models was evaluated. The task of dynamic optimization was formulated, the solution to which enables the implementation of lane change and overtaking maneuvers. The task was solved using the bicycle model, and the results (implementation of the intended maneuver) were validated using the spatial model. [ABSTRACT FROM AUTHOR]

Lane-level route planning is a critical issue for a lane-level navigation system for autonomous vehicles. Current route-planning methods mainly focus on the road level and applying them directly to search for lane-level routes results in a reduction in search efficiency. In addition, previously developed lane-level methods lack consideration for vehicle characteristics and adaptability to multiple road network structures. To solve this issue, this study proposes an accelerated and refined lane-level route-planning algorithm based on a new lane-level road network model. First, five sub-layers are designed to refine the internal structure of the divided road and intersection areas so that the model can express multiple variations in road network structures. Then, a multi-level route-planning algorithm is designed for sequential planning at the road level, lane group level, lane section level, and lane level to reduce the search space and significantly improve routing efficiency. Last, an optimal lane determination algorithm considering traffic rules, vehicle characteristics, and optimization objectives is developed at the lane level to find the optimal lanes on roads with different configurations, including those with a constant or variable number of lanes while satisfying traffic rules and vehicle characteristics. Tests were performed on simulated road networks and a real road network. The results demonstrate the algorithm's better adaptability to changing road network structures and vehicle characteristics compared with past hierarchical route planning, and its higher efficiency compared with direct route planning, past hierarchical route planning, and the Apollo route-planning method, which can better support autonomous vehicle navigation. [ABSTRACT FROM AUTHOR]

This paper proposes a double-layer model predictive control (MPC) algorithm for the integrated path planning and trajectory tracking of autonomous vehicles on roads. The upper module is responsible for generating collision-free lane trajectories, while the lower module is responsible for tracking this trajectory. A simplified vehicle model based on the friction cone is proposed to reduce the computation time for trajectory planning in the upper layer module. To achieve dynamic and accurate collision avoidance, a polygonal distance-based dynamic obstacle avoidance method is proposed. A vertical load calculation method for the tires is introduced to design the anti-rollover constraint in the lower layer module. Numerical simulations, with static and dynamic obstacle scenarios, are conducted on the MATLAB platform and compared with two state-of-the-art MPC algorithms. The results demonstrate that the proposed algorithm outperforms the other two algorithms regarding computation time and collision avoidance efficiency. [ABSTRACT FROM AUTHOR]

Reinforcement learning-based controllers for safety-critical applications, such as autonomous driving, are typically trained in simulation, where a vehicle model is provided during the learning process. However, an inaccurate parameterization of the vehicle model used for training heavily influences the performance of the reinforcement learning agent during execution. This inaccuracy is either caused by changes due to environmental influences or by falsely estimated vehicle parameters. In this work, we present our approach of combining dynamics randomization with reinforcement learning to overcome this issue for a path-following control task of an autonomous and over-actuated robotic vehicle. We train three independent agents, where each agent experiences randomization for a different vehicle dynamics parameter, i.e., the mass, the yaw inertia, and the road-tire friction. We randomize the parameters uniformly within predefined ranges to enable the agents to learn an equally robust control behavior for all possible parameter values. Finally, in a simulation study, we compare the performance of the agents trained with dynamics randomization to the performance of an agent trained with the nominal parameter values. Simulation results demonstrate that the former agents obtain a higher level of robustness against model uncertainties and varying environmental conditions than the latter agent trained with nominal vehicle parameter values. [ABSTRACT FROM AUTHOR]

The road friction coefficient and the forces between the tire and the road have a significant impact on the stability and precise control of the vehicle. For four-wheel independent drive electric vehicles, an adaptive tire force calculation method based on the improved Levenberg–Marquarelt multi-module and self-organizing feedforward neural networks (LM-MMSOFNN) was proposed to estimate the three-directional tire forces of four wheels. The input data was provided by common sensors amounted on the autonomous vehicle, including the inertial measurement unit (IMU) and the wheel speed/rotation angle sensors (WSS, WAS). The road type was recognized through the road friction coefficient based on the vehicle dynamics model and Dugoff tire model, and then the tire force was calculated by the neural network. The computational complexity and storage space of the system were also reduced by the improved LM learning algorithm and self-organizing neurons. The estimation accuracy was further improved by using the Extended Kalman Filter (EKF) and Moving Average (MA). The performance of the proposed LM-MMSOFNN was verified through simulations and experiments. The results confirmed that the proposed method was capable of extracting important information from the sensors to estimate three-directional tire forces and accurately adapt to different road surfaces. [ABSTRACT FROM AUTHOR]

An antenna's radiation pattern is dependent on its geometrical characteristics and its antenna's surroundings, materials, and geometries. As such, to predict the antenna's performance in complex environments, such as that of small antennas on large vehicles, it is necessary to obtain a model that represents such a full scenario, so that the simulation may be accomplished in the process of antenna design and placement. Due to the complex and electrically large nature of some electromagnetic problems, the detailed representation, even for a simplified model, may imply a large computational effort, both in terms of time and memory, is needed to perform the simulation. This paper evaluates how machine learning models can be used to mitigate the computational effort required to predict the behavior of antennas requiring complex modeling. It is proposed to start from a more simplified model of the electromagnetic structure to obtain a prediction for the correct solution, without needing to simulate the full structure in every iteration, and to combine this with prediction algorithms to obtain the solution of the full problem. The proposed solution uses convolutional neural networks (U-Net) of a certain accuracy to help with the correct placement of small antennas on autonomous vehicles. The standard approach requires the simulation of a full model at each test position, requiring high computational time and memory. With this new proposal, it is possible to analyze more positions and radiation patterns in a much shorter time, and with less memory, when compared with the solution from the full model. Along with this methodology for each simulation, a Bayesian optimizer is proposed to improve the search process for the best location, leading to a reduction in the required steps. This methodology was applied to support the correct positioning of a GNSS antenna with reference to a set of performance indicators required for autonomous vehicles, but it can be also applied to larger and more complex structures, allowing one to reduce the simulation time of a large electromagnetic structure and the search time for the optimum location. [ABSTRACT FROM AUTHOR]

To investigate and compare the lane changing behavior of passenger cars and heavy vehicles during the implementation period (defined as the interval from the start time to the end time of a lane change maneuver), this study applies the gradient boosting decision tree (GBDT) method to model the lane changing behavior of heavy vehicles and passenger cars, respectively. Results show that the lane change models vary with the vehicle types and lane change directions. Different factors are considered by the drivers of passenger cars and heavy vehicles when implementing lane changes to different directions. Partial dependence plots of GBDT models reveal that the influence of independent variables on lane changing behavior is nonlinear and complicated, which means that the same variable leads to various effects on the lane change decision across different vehicle types and lane change directions. In contrast with other state-of-the-art methods, the proposed method can obtain more accurate results. The findings indicate that it is necessary to build specific lane change models based on vehicle types and lane change directions for microscopic traffic simulators and autonomous vehicles. [ABSTRACT FROM AUTHOR]

The differential steering can be used not only as the backup system of steer-by-wire, but also as the only steering system. Because the differential steering is realized through the differential moment between the coaxial left and right driving wheels, the sharp reduction of the load on the inner driving wheel will directly lead to the failure of the differential steering when the four-wheel independent drive electric vehicle approaches the rollover. Therefore, this paper not only realizes the trajectory tracking of autonomous ground vehicle through the differential steering, but also puts forward the body attitude control to improve the handling stability. Firstly, the dynamic and kinematic models of differential steering autonomous ground vehicle (DSAGV) and its roll model are established, and the linear three-degree of freedom vehicle model is selected as the reference model to generate the ideal body roll angle. Secondly, a model predictive controller (MPC) is designed to control the DSAGV to track the given reference trajectory, and obtain the required differential moment and the resulting front-wheel steering angle. Then, a sliding mode controller (SMC) is adopted to control the DSAGV to track the ideal body roll angle, and obtain the required roll moment. The simulation results show that the proposed MPC and SMC can not only make the DSAGV realize the trajectory tracking, but also achieve the body attitude control. [ABSTRACT FROM AUTHOR]

There is a need for in-depth studies of autonomous vehicle safety that evaluate the effectiveness of safety functions and different "atomic" technology combinations for vehicles and roads. In this paper, we provide a crash avoidance effectiveness evaluation model for autonomous vehicles enabled with different sensor combinations based on multiple variables of 14 different "atomic" sensing technologies on the vehicle side and road side, 52 safety functions, and 14 accident types. Meanwhile, a cost-sharing model is developed based on the traveled distance during the life cycle of vehicles and based on the traffic flow over the life cycle of roads to evaluate the unit cost per km of different "atomic" technology combinations. The results clearly show that the cost increases with the addition of "atomic" sensing technologies on the vehicle side, while an increase in crash avoidance effectiveness decreases. It is necessary to switch to V2X and to introduce roadside "atomic" technology combinations to realize better safety effectiveness at a lower cost for vehicles. In addition, a map that covers the safety effectiveness and cost per kilometer of all "atomic" technology combinations is calculated for decision-makers to select combinations under the preconditions of cost and safety. [ABSTRACT FROM AUTHOR]

The rapid development of autonomous vehicle technology has brought a new experience to people's daily travel. However, if a traffic accident involving autonomous vehicles occurs, it will face difficulties in vehicle accident forensic‐preservation, leakage of vehicle owner's privacy, and identifying legal liabilities. This article proposes an accident responsibility identification model for the Internet of Vehicles based on lightweight blockchain to solve the above problems. This model uses Car Forensics Master to collect evidence from the accident vehicle, and at the same time collects evidence from maintenance service providers, automobile manufacturers, transportation management departments, insurance companies, and other vehicle accident related parties and stores them in the preservation chain. We also use VPKI to protect the autonomous vehicle identity privacy. In order to improve the efficiency of the model and set up authorized access to related entities, the identification of accident liability is jointly completed by the preservation chain and the accident identification chain. In addition, we prove that the protocol proposed in the model has ideal security properties. Finally, we implement the smart contracts in the model through the Solidity language, and evaluate its performance. [ABSTRACT FROM AUTHOR]