The driving environment of intelligent vehicles often has high uncertainty and complexity, which can lead to accidents and injuries to passengers. In order to improve the safety of intelligent vehicles, three major research methods are currently used to evaluate driving risks, including deterministic methods, probabilistic methods, and machine learning methods. Deterministic methods are traditional binary prediction methods, probabilistic methods can model various uncertainty, and machine learning methods can automatically learn driving behavior, making more accurate assessments of the risk of driving. Future research should combine the advantages of the three approaches to develop safer and more reliable autonomous driving systems.

In order to reduce the influence of driving fatigue on drivers in man-machine co-driving environment, this paper elaborates the mechanism of driving fatigue in man-machine co-driving environment, then analyzes the detection methods of driving fatigue from subjective and objective aspects, and introduces the alleviation methods of driving fatigue from active fatigue and passive fatigue. Finally, the deficiency of current research on driving fatigue detection and alleviation in man-machine co-driving environment is pointed out, and the prospect of research on driving fatigue detection and alleviation in man-machine co-driving environment is presented from the perspective of multi-feature and multi-mode fusion.

Safety analysis is an integral part of the automotive development process, as the complexity of automated driving systems increases, traditional safety analysis methods are facing challenges. Firstly, the advantages and disadvantages of traditional analysis methods, such as Fault Tree Analysis (FTA), Failure Modes and Effect Analysis (FMEA), and Hazard and Operability (HAZOP), are compared with the System Theoretic Process Analysis (STPA), especially the advantages of STPA for the safety analysis of automated driving systems. Secondly, the current status of STPA applications in essential areas, such as Functional Safety, Safety of the Intended Functionality (SOTIF), Cyber Security, and Human Machine Interface (HMI), are discussed in detail. Finally, the application of STPA in automated driving is prospected from the perspectives of expanding the STPA analysis, integration of analysis and verification, and extending application areas.

This paper analyzes the support policies of the fuel cell vehicle industry in the United States, Japan, South Korea, European Union and other regions, and summarizes the support policies represented by the fuel cell vehicle demonstration policy in China. By analyzing and learning from the global fuel cell vehicle policy, combined with the development status of China's fuel cell vehicle industry, this paper provides a reference for further optimizing the top-level policy design and efficiently supporting and guiding the development of fuel cell vehicle related industries in the future.

In order to improve user satisfaction, design quality and development efficiency of intelligent cockpit products, and ensure the attractiveness and user stickiness of intelligent cokpit products, this paper elaborates on the automobile HMI system from 3 perspectives: innovation, quality and iteration. An innovative and user-centered automotive HMI design system has been established, which includes a collaborative innovation design system, quality management system such as design self-inspection, consistency testing, and problem management, as well as an HMI self-evolution system. This enables symbiotic and co-growing relationships with users.

Through the comparative analysis of cell base materials, various cell integration technologies, and lightweight battery housing solutions, the technical paths for battery density enhancement are elaborated. The improvement in energy density of individual battery cells heavily relies on significant breakthroughs in basic material science. In the post-lithium-ion era, cell densities are expected to reach 1200 W·h/kg, while in the short term, semi-solid battery technology with a cell density of 360 W·h/kg is anticipated to be the first to achieve mass production, enabling electric vehicles with longer driving ranges and higher energy efficiency. Another key technology is to improve cell integration efficiency. Innovative solutions such as Cell-to-Pack (CTP), Cell-to-Chassis (CTC), and Cell-to-Body (CTB) are anticipated to increase cell integration rates to 90% and space utilization to 70%, breaking traditional design limitations and significantly enhancing battery pack energy density. The lightweight design of battery housings is also essential. Lightweight housing design like aluminum alloy extruded profiles, aluminum alloy integrated die-casting, ultra-high-strength steel rolling, and carbon fiber composite materials molding can effectively reduce the overall weight of battery while ensuring performance, thus improving energy density.

Using the patent analysis method, this paper constructs the technical decomposition system of high definition map and localization technology. On the basis of full patent data processing, this paper analyzes the patent technology development status and competition pattern of high definition map and localization technology from the aspects of patent application situation, patent applicant distribution, patent technology composition. It combs the development of key branches of high definition map and localization technologies, and finally puts forward some suggestions for the development of high definition map and localization technologies.

The ownership of electric vehicle(EV) is rapidly increasing, and charging issues caused by grid abnormal power are consequently emerging. EV adaptability testing has become a hot technology urgently needed in the industry. Grid adaptability testing technology can be applied to vehicle charging systems or AC charging piles, DC charging piles, in vehicle chargers, and high integration charging assemblies to improve the development quality of charging ecological products. To deeply adapt to the demands for charging of users in different scenarios, the automotive industry needs to comprehensively analyze the differences in global power grid systems, sort out the principles of abnormal power grids, and develop testing plans covering user charging conditions in terms of power grid systems, power grid drop, power grid steep rise, and power grid harmonics. Electric vehicle charging products should be fully validated before launch to avoid potential abnormal charging problems about the power grid.

In order to analyze the current development status and trends of intelligent manufacturing scenarios in automotive industry, a macro analysis of automotive intelligent manufacturing scenarios is conducted based on the selection of automotive companies in the list of “2023 Intelligent Manufacturing Demonstration Factories and Excellent Scenarios”. This study is carried out from 3 dimensions: regional distribution, excellent scenarios, and typical scenarios by analyzing the content of intelligent manufacturing scenarios from 3 aspects: product lifecycle, production process, and supply chain. The development of intelligent manufacturing scenarios in the automotive industry reveals the following trends: In the short term, the focus of intelligent manufacturing in the automotive industry remains on the “production process.” There is a growing demand to explore the implementation of intelligent manufacturing scenarios in the “product lifecycle” and “supply chain”.