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.

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.

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.

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.

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.

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.

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.

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.

As the core product of the hydrogen energy industry, proton exchange membrane fuel cells are characterized by high energy conversion efficiency, zero emissions and no pollution. They are one of the most promising power sources in the automotive field. However, the high cost limits the largescale application and promotion of PEMFCs for vehicles. The development of lowplatinum PEMFCs for vehicles is an important technical route to improve cost competitiveness. However, the serious mass transfer and lifespan issues faced in the lowplatinum process urgently need to be solved. This paper summarizes the research progress of lowplatinum membrane electrode assembly technology and the shortcomings of existing technologies. It also looks forward to the future development trends, providing reference value for the advancement of lowplatinum membrane electrode technology for vehicle PEMFCs.

The threedimensional form of the metal foam flow field is established. Through threedimensional numerical simulation, the results show that the metal foam flow field can effectively reduce the concentration polarization loss, thereby improving the performance of the fuel cell at high current densities. The increase in output power density is significant, while the corresponding pumping power loss is negligible. Furthermore, under the influence of the metal foam flow field, the oxygen concentration distribution inside the PEMFC is more uniform than that in the traditional straightchannel fuel cells. Bench experiments were conducted to observe the flow state of liquid water in the foam flow field and similar flow phenomenon was obtained through threedimensional numerical simulations. Compared with the traditional straightchannel designs,