Conducting a thorough driving risk assessment is important for the driving safety of autonomous vehicles. In this paper, the existing driving risk assessment methods are divided into three categories, namely, the single objectoriented methods, the reachability setbased methods, and the potential fieldbased methods. In order to conduct a comprehensive comparison of these methods and reveal their distinct characteristics and applicability, the paper proposes five evaluation dimensions, including realtime capability, the duration of the valid prediction horizon, application feasibility, the inclusion of various risk sources and adaptability in different scenarios. The research gaps and potential future research directions in driving risk assessment for autonomous vehicles are analyzed and prospected.

With the advancement of autonomous driving technology, the accuracy and reliability of object detection have become increasingly crucial. Deep learning, as a core component of autonomous driving systems, significantly influences the safety and stability of these systems by estimating the uncertainty in predictive results. The paper summarizes the application of deep learning uncertainty estimation in autonomous driving object detection and discusses the significance of an effective uncertainty evaluation system. Firstly, the paper introduces the fundamental theories of deep learning uncertainty estimation, including Bayesian neural networks, Monte Carlo methods, and ensemble learning. These methods quantify model prediction uncertainty in different ways, providing autonomous driving systems with richer information. Secondly, the paper delves into the application of uncertainty estimation in autonomous driving object detection. Through case studies, it demonstrates how uncertainty information can be used to improve detection accuracy, especially in complex environments and extreme conditions. In these scenarios, uncertainty estimation provides decision support, helping the system avoid potential risks. Lastly, the paper summarizes the evaluation metrics for uncertainty estimation in autonomous driving object detection, considering both the model's predictive performance and the accuracy of the uncertainty estimation.

In the visual perception task of autonomous driving, it is crucial to accurately and quickly extract the cognitive and accidental uncertainties to effectively resolve the Safety of the Intended Functionality (SOTIF) issues associated with autonomous driving. In traditional methods such as Monte Carlo dropout and deep ensembles, uncertainty is estimated by sampling the prediction results of different submodels, which slows down the estimation and tends to occupy a large amount of memory in the processor during the model inference stage. A fast Monte Carlo dropout method and a technique for correcting subsequent detection results are proposed to address the issues of slow estimation of uncertainty in Monte Carlo dropout and the selection of subsequent detection results. This method uses a multihead mechanism to replace the traditional multiple sampling mechanism in Monte Carlo dropout, thereby saving time in both sampling and inference throughout the uncertainty estimation process.

Aiming at acceptance criteria for automated driving, this paper reviews the best practices in relevant regulations, standards, and evaluation methods, identifying five safety concepts and their interrelationships. The paper focuses on the concept and research status of behavioral safety, centered around "reasonably foreseeable and preventable” behaviors. By combining scenario data statistics with the driver's emergency response mechanism, a quantitative research framework is proposed for reasonably foreseeable and preventable situations. Finally, combining traffic accident data and practical experience, the paper provides a method for using behavioral safety in autonomous driving evaluation, along with a closedloop certification and approval process based on this concept. The research in this paper serves as a reference for authorities, third parties, and R&D companies to establish relevant R&D, testing, and processes centered around behavioral safety.

To avoid unnecessary interventions by the driver assistance system, this paper combines collision risk and driving maneuverability to introduce the concept of a risk assessment zone in longitudinal following scenarios. The boundary of this zone is determined based on the normal distribution characteristics of the driving data. Subsequently, a new humanmachine codriving longitudinal driving rights allocation strategy is proposed, which takes the inverse time to collision (TTCi) as the basis for judgment. If the TTCi exceeds the threshold value, the upper boundary of the risk assessment zone represents the maximum deviation in driving maneuverability. The control rights of the assistance system are allocated according to the deviation in the driver's maneuverability. By combining Prescan, Matlab/Simulink and the Logitech G29 driving simulator, a driverintheloop simulation platform was constructed. The platform simulated the reduced driver maneuverability due to distracted driving, thereby verifying the effectiveness of the strategy. The results show that the proposed humanmachine codriving strategy can effectively prevent collisions caused by reduced driver maneuverability under highspeed road following conditions.

Aiming at the lack of effective methods for testing abnormal signals during the operation of unmanned vehicles, the paper focuses on signal anomalies caused by environmental disturbances in reliability driving tests. By using the correlation of signals from multiple sensors in both the time domain and spatial domain, a crossmathematical model is established based on the multisensor data. The signals collected from sensors are assigned as the row elements and the sensors as the column elements within the signal matrix. This numerical method transforms the original multisensor signals into a parameterized signal matrix model. A method combining matrix completion and deep matrix decomposition fusion (MC+DMF) is proposed to recover certain abnormal signals resulting from environmental disturbances. According to the forward propagation characteristics of the neural network, dimensionality reduction is applied to the row vectors (data collected by individual sensors at time i ) and column vectors (sensor arrays) in the original matrix. This process reduces the computational load during feature extraction from the distorted signal matrix. Additionally, the Hadamard product is used to regularize the MC+DMF loss function after feature extraction to avoid overfitting. The proposed method is applied on the SODA10M and KITTI public datasets, and comparing with traditional approaches, such as the single matrix factorization (MF), probability matrix factorization (PMF) and BiasSVD, the experiments using root mean square error (RMSE) show that the method can effectively detect abnormal sensor signals caused by vibration interference during driving. The results show that the MC+DMF method can greatly reduce the data recovery error and time. Compared with the probability matrix decomposition method, it achieves a 1% lower error rate and approximately 20.65% less recovery time.

Lane line detection is a key technology in the field of autonomous driving, and it currently faces many challenges. The sparsity of the lane line supervision signal, as well as factors such as occlusion and shadows in complex scenes, can affect detection accuracy and realtime performance. Based on this, this paper proposes a lane line detection model that integrates the CBAM attention mechanism and a line anchor feature aggregation module. The proposed algorithm achieves an accuracy of 96.19% and a comprehensive F1 score of 76.24% on the Tusimple and CULane datasets, respectively. Real vehicle tests show that the algorithm detects a frame rate of 67 fps, allowing for realtime detection in complex traffic scenarios and more effectively addressing the problem of lane line occlusion.

In existing visionbased intelligent wiper systems, the raindrop target detection model has a large number of parameters and excessive computational complexity, making it challenging to deploy in vehicle embedded devices. To address these issues, the paper proposes a lightweight raindrop target detection model, YOLOV5RGA. By integrating the RepVGG and GhostBottleneck modules to replace the convolution and C3 modules of the backbone network, we enhance the network's feature extraction capabilities while significantly reducing the parameters and computational load. Furthermore, adopting the Adam optimizer results in faster convergence and improves the average accuracy of the network model. Through experimental validation, compared with the YOLOv5s model, the YOLOv5RGA model achieves a 0.8% increase in average accuracy. Additionally, the number of model parameters is reduced by 48.5%, computation demand decreases by 35.2%, and the model size shrinks by 44.4%. The adoption of the lightweight raindrop target detection model effectively reduces hardware overhead and also facilitates model deployment.

In order to accelerate the gathering, sharing, development and utilization of ICV data resources, this paper proposes the establishment of a “public service platform for data interaction and comprehensive application of ICV” with a multicenter architecture comprising national, regional and enterprise levels. The platform is based on the standardized industry data collection and transmission protocols and extensively utilizes modern information technologies such as big data, cloud computing and blockchain. It can efficiently achieve the realtime collection, analysis and processing of data from tens of millions of vehicles, providing a basic support platform for promoting the mining and utilization of industry data. Based on the data resources collected and stored by the platform, we have explored comprehensive applications across multiple scenarios, including vehicle test and evaluation, safe operation monitoring, and data analysis and mining. These applications verified the platform's innovativeness and feasibility in actual use.

To fully utilize the energysaving and emissionreduction performance of the oilelectric hybrid system on mine truck, a dualmode energy management strategy (EMS) is proposed for a series hybrid electric mine truck. The back propagation neural network (BPNN) was used to construct the models of "optimal fuel consumption mode of engine" and "optimal efficiency mode of range extender" in this EMS. On this basis, a dualmode EMS was designed to adjust the power output of the range extender and battery pack, realizing the realtime adjustment of the energy consumption for the vehicle under complex working conditions. Finally, the proposed EMS was verified by hardware in the loop simulation with actual working condition data. The results show that compared with the rule strategy and equivalent consumption minimization strategy, the fuel saving rate of the dualmode EMS increases by 12.74% and 7.4% respectively, further improving the fuel saving performance of the realtime strategy.

Aiming at the problem of how to recover the waste heat of the motor to improve the thermal performance of the passenger cabin, a simulation model of the thermal management system of a battery electric passenger vehicle is constructed by using AMESim software. On this basis, the effects of refrigerant distribution ratio and thermal management system architecture on passenger cabin heating performance are analyzed under the motor waste heat recovery mode. The results show that at a vehicle speed of 60 km/h, the heat generation of the motor can be up to 1 402 W and the heat generation of the motor controller can be up to 427 W. Compared with the nomotor waste heat recovery mode, the total heat absorbed by the thermal management system from the electric drive system and the environment can be increased by 58.69%100.57% and the passenger cabin heating power can be increased by 71.36%100.37% by distributing the refrigerant rationally. In the motor waste heat recovery mode, the passenger cabin heating power with the parallel architecture was 23.42% to 27.23% higher than that with the series architecture.

A selfadaptive adjustment scheme is proposed to address the problem that traditional PI controllers cannot simultaneously achieve nonlinear gain transformation in both highspeed and lowspeed weak magnetic field voltage feedback loops. By analyzing the factors that lead to system nonlinearity in the decouplingvoltagefeedback currentleadangle control loop, an inverse function speed regulator and a fuzzy control current lead angle regulator have been designed. These regulators compensate for the nonlinearity of the voltage control loop under weak magnetic field conditions.Additionally, a clamping antisaturation module is developed to solve the issue of integral saturation in voltage feedback. On this basis, the particle swarm optimization algorithm is adopted to conduct offline optimization of the fuzzy rule weights and proportional factors in the fuzzy controller. Finally, simulation and experimental results show that the adaptive weak magnetic algorithm exhibits better response characteristics compared to traditional PI voltage feedback control algorithms.

Analyzing the extreme drifting conditions of vehicle tires can greatly improve the horizontal and vertical control capabilities and driving safety of autonomous vehicles. This paper first adopts the UniTire model to describe the friction characteristics in high slip regions, and then optimizes the vehicle drift control algorithm. Next, based on the vehicle stability control principle, the target pressure for the wheel cylinder was calculated to achieve a quick return of the vehicle to steady straightline driving after drifting. Finally, the rapid prototype verification was carried out on the CANoe's industrial computer platform by integrating DYNA4 and Simulink. The results show that the control algorithm proposed in this paper allows the vehicle to quickly achieve lateral and longitudinal stability during drifting and to promptly return to straightline driving after drifting, meeting the realtime control requirements.

Stress distribution at the tireground contact interface on soft terrain becomes increasingly complex under the influence of tire slip and sinkage, making it difficult to accurately model tire behavior. Using finite element analysis, the paper simulated tire longitudinal slip/skid under constant sinkage conditions. The variation in stress distribution at the tireground contact interface was investigated as the slip/skid degree changed. The results show three distinct stress distribution patterns corresponding to slip, small skid and large skid states, respectively. Soil characteristic parameters were obtained through simulating sinkage and shear tests, and the stress distribution model was established for the three slip/skid states. On this basis, the tiredeformable terrain interaction model for longitudinal slip was further developed, which effectively represents the inplane characteristics of tires on soft terrain.

Thermal oxygen aging is one of the primary thermal failure modes for nonmetallic components in the engine compartment. The traditional vehicle thermal management development process typically only focuses on the maximum working temperature of components, which is insufficient for effectively predicting the thermal degradation of these parts over their lifecycle. Based on China's climate conditions and extensive vehicle driving data, an equivalent thermal aging driving condition model is established to evaluate the thermal aging life of components. Using this method, the thermal aging life of an engine mount rubber bushing is evaluated. It is found that improving the rubber material formula increases its thermal aging life by approximately 3 times. However, if the operating temperature of the rubber bushing increases by 10 °C, its thermal aging life decreases by about 50.0%. In addition, an analysis of the heat transfer path of the rubber bushing shows that its actual working temperature can be lowered by optimizing the fan wake and reducing heat conduction between the engine and the rubber bushing, thereby improving its thermal aging life.

The paper aims to solve the problem of forecasting passenger travel demand in ehailing car operations, thereby reducing vehicle idle rates and minimizing passenger waiting times. Considering the dynamic spatiotemporal dependencies of passenger travel demand, this study proposes a method based on spatial data visualization and the Granger causality test for analyzing the spatial dependency. A spatiotemporal graph convolutional neural network model incorporating attention mechanisms is established to predict passenger travel demand. The case study shows that this model effectively captures the dynamic characteristics of the timespace dependencies of passenger travel demand, improves the prediction performance of the model, and achieves high accuracy and practicability.

Due to its low material costs and versatility in producing diverse products, 3D printing technology has attracted attention from researchers studying the crashworthiness of automotive energyabsorbing structures. This paper conducts quasistatic experimental research on automotive energyabsorbing structures, such as crash beams and honeycomb fillers, made from different base materials but with identical structural dimensions, using 3D printing technology. A comparative analysis of their mechanical responses and deformation modes is performed. Furthermore, finite element simulations are employed to study the influence of structural parameters on crashworthiness indicators. The results show that the loaddisplacement curves of 3Dprinted PLA crash beams and honeycomb filler structures exhibit similar trends to those of metal structures and reflect the deformation characteristics of automotive energyabsorbing structures. Increasing the wall thickness raises the relative density, which enhances the crashworthiness of both the crash beam and the honeycomb structure. Additionally, changes in the cell size also affect the crashworthiness of the honeycomb structure. This paper proposes an optimization scheme for automotive energyabsorbing structures based on 3D printing technology, systematically studying the effects of structural parameters on crashworthiness through experiments and simulations. This research offers valuable insights for designing educational tools in automotive engineering and analyzing automotive energyabsorbing structures.