Transportation electrification is accelerating worldwide as part of the concerted effort to achieve carbon neutrality within the transportation sector. However, some challenges still need to be overcome. Government financial support in the new energy vehicle (NEV) markets, in regions and countries such as the European Union, the United States, China, and Japan, directly incentivizes research and development (R&D) and signals technology strategy emphasis of each country. To gain a comprehensive understanding of the distinct national approaches to realizing the shared goal of global carbon neutrality, this study has established an analytical framework. It aims to critically assess the policies and incentives that propel the industrial and technological routes for decarbonizing transportation, all under the overarching guidance of government-led R&D strategies within the NEV markets. Publicly available papers, reports, and roadmaps are analyzed. The findings of this investigation indicate that the future development of the NEV market is driven by carbon–neutral policies within the regions and countries covered in this study. Key areas of development focus include advanced batteries, more efficient motors, and clean hydrogen, but each country has a distinct strategy and organization. This strategic and organizational review can provide insights and suggestions that can facilitate tangible interventions in supporting the ongoing advancement of NEV technology.

The objective of this study is to investigate the potential reduction of polarization in proton exchange membrane fuel cells (PEMFCs) through the design optimization of flow channel. The impact of structural parameters and surface properties of the bipolar plate flow channels on the PEMFC performance is thoroughly examined on a commercial scale PEMFC with an active area of 203.49 cm2. The fabrication of bipolar plate flow channels with different structural and wetting properties is achieved using a novel ultrafast laser technique and a conventional milling method. Single cell stack is assembled and subjected to polarization curve tests. The findings indicate that decreasing the width of the flow channels generally improves the performance of commercial-scale PEMFCs. The minimum allowable channel width is dependent on the length of the flow channels. Interestingly, flow channels with higher hydrophilicity and surface adhesion do not necessarily lead to poorer water removal capability, which may be attributed to the formation of a thin water film on superhydrophilic channel surfaces. This research provides valuable insights into the design of optimal flow fields for commercial-scale PEMFCs.

Highly integrated and efficient electric drive technology for improving the comprehensive performance of electric vehicles stands as a prominent research focus. This paper proposes a novel dual-motor coupling electric drive axle incorporating torque vectoring (TV) technology, aiming to enhance driving maneuverability and further improve vehicle efficiency. Firstly, the configuration of the dual-motor coupling drive-axle is analyzed, introducing its four operational modes: main drive motor independent drive mode, TV motor independent drive mode, dual-motor torque coupling drive mode, and torque vectoring drive mode. Subsequently, to unlock the energy-saving potential of the dual-motor coupling drive system, optimization of the drive-mode division is conducted. This optimization selects the work mode with minimal energy consumption under the specified speed and torque requirements. The switching logic thresholds for optimal work mode boundaries and their buffer zones, designed to mitigate frequent switchover, are established in the equivalent external characteristic map of the dual motors. Finally, the co-simulation validates the torque vectoring function and driving economy. Results indicate that positive or negative torque vectoring can be strategically employed to enhance driving maneuverability or stability, respectively. The optimized multi-mode driving of the proposed dual-motor coupling electric drive-axle demonstrates a reduction in energy consumption by 7.28%, 7.35%, and 8.54% under NEDC, FTP-75, and CLTC work conditions, respectively, in comparison with a single-motor drive-axle with equal total power.

Nowadays, with increased sensor perception performance for Advanced Driver Assistance Systems (ADAS), scenario-based simulation is becoming more frequent to manage the complexity of reality in terms of cost and time. The perception system provides the basis for the vehicle guidance algorithms calculation, but the simulation of ADAS sensors is a challenging task in virtual testing. Literature reports the magnitude of relevant modelling approaches and data-driven models becoming increasingly important. A basic method is to fit the sensor output in the virtual environment with high-fidelity measurements of real-world scenarios, thus a direct relation can be established between real and synthetic sensor data. To prove the suitability of a method, it is necessary to quantify the gap between simulation and reality to determine the performance of different models. In this work, authors address this problem and visualize the gap by introducing a multi-level evaluation approach that combines Model Generalization Ability Evaluation and Case Implicit Performance Evaluation. The former directly evaluates the model’s overall performance, while the latter is used for specific cases in simulation. The study shows that this combined evaluation approach provides an in-depth framework for evaluating sensor models to make the differences apparent.

Predicting vehicle trajectories using deep learning has seen substantial progress in recent years. However, making autonomous vehicles pay attention to their surrounding vehicles with the consideration of social interaction remains an open problem, especially in long-term prediction scenarios. Unlike autonomous vehicles, human drivers continuously observes and analyzes interactive information between their vehicle and other traffic participants for long-term route planning. To alleviate the challenge that the trajectory prediction should be interaction-aware, this study proposes a multi-head attention mechanism to boost the trajectory prediction performance by globally exploiting the interactive information. The multi-dimensional spatial interactive information encoded with the vehicle type and size can assign different weights of surrounding vehicles to realize the interaction of diverse trajectories. Furthermore, the model is based on a simple data pre-processing method, surpassing the traditional grid data processing approach. In the experiment, the proposed model achieves significant prediction performance. Surprisingly, this proposed multi-head trajectory prediction model outperforms state-of-the-art models, particularly in long-term prediction metrics. The code for this model is accessible at: https://github.com/pengpengjun/hybrid attention.

Cooperative adaptive cruise control (CACC) is acknowledged as an efficient solution to relieve traffic congestion while ensuring traffic safety. This paper aims to improve traffic efficiency via both the effective following spacing policy and the CACC with platoon kinematics. Firstly, the correlation mechanism of safety spacing policy and time headway policy is analyzed, a versatile generic spacing model is established, and an efficient spacing policy is proposed by leveraging the concept of safety redundancy. Secondly, based on the “virtual centroid” of the platoon, the CACC upper control strategy with platoon kinematics is proposed to improve traffic efficiency. The strategy is complemented by the design of a sliding mode controller, which precisely allocates longitudinal acceleration. Additionally, a lower controller is developed to track the desired acceleration accurately and rapidly under various driving and braking conditions. Thirdly, eight typical scenarios for urban traffic are reconstructed via three-layer decompositions, and the index named synchronization is proposed to evaluate the performance of CACC with platoon kinematics. Finally, a simulation test is conducted, demonstrating that the proposed CACC strategy synchronously responds to the kinematics of the preceding platoon, reducing the accumulation of response delay, ensuring both vehicle following safety and efficiency.

The key issues for roadside sensing system (RSS) include achieving accuracy and real-time sharing of over-horizon perception information. This study proposes a novel and efficient framework dedicated to multi-object detection from the roadside perspective. Firstly, compared to other backbones, the mobile net-based model has superior performance and speed as results of the network parameters obtained from network architecture search (NAS), developed to increase the forward inference speed. Secondly, a method of optimization based on the coordinate attention mechanism is developed to increase the long-range dependence of neural networks on spatial information. Thirdly, the traditional convolution operation in the attention mechanism is optimized by the depthwise over-parameterized convolution (DOPC) to improve the capability of extracting features from high-dimensional feature space. Finally, the lightweight single-stage multi-target detection model from the roadside perspective based on DCM3-YOLOv4 is developed. The test results show that the optimized one-stage lightweight multiple object detection model DCM3-YOLOv4 on the RS-UA dataset produces a mean average precision (mAP) value of 0.930 and a network model with parameter size of 31.12 Million. The inference time is 96.13 ms, which is faster than another basic model on the same platform. The proposed methods can be utilized in a wide range of applications, where the accuracy and speed requirements of RSS must be met.

As parking scenarios become narrower, vehicles often cannot enter the parking lot in one step. This paper presents a multi-maneuver vertical parking trajectory planning and tracking control strategy based on a predefined geometric set method. Firstly, to minimize the space required for parking, a multi-constraint nonlinear programming path function model based on arc-line-arc is established to find the key points of the path for vehicles to enter the parking space while considering the vehicle structure and road boundary constraints comprehensively. Secondly, the double-S speed planner carries out the speed planning. Finally, based on the vehicle–road deviation prediction model, an MPC lateral motion controller with the steering system delay compensation is established. A vehicle speed-tracking controller is designed on the basis of PID control. The proposed parking planning and control strategy is then tested on the autonomous vehicle platform to verify its feasibility and effectiveness. The results demonstrate that the proposed method can solve the problem of multi-maneuver vertical parking trajectory planning and tracking control in narrow environments. Under the action of the lateral and longitudinal controller, the vehicle can be safely and accurately guided to track the parking trajectory into the parking space. The lateral error is controlled within 0.054 m, and the heading deviation is controlled within 0.02 rad.

In the context of highway merging scenarios where ramp vehicles encounter rear vehicles on the main lane, a significant challenge arises due to the competition for the right of way, exacerbated by the stochastic nature of driving styles. This situation can lead to traffic congestion and even collisions if not managed effectively. To address these issues, this paper presents an optimal cooperative merging strategy based on Bayesian Nash Equilibrium for connected and automated vehicles. The approach begins by analyzing the inherent randomness in driving styles exhibited at on-ramps. Specifically, a Principal Component Analysis method is applied to extract key features with lower dimensions. These features are then used to estimate the probability distributions of driving styles for both ramp and mainline vehicles. Subsequently, a cooperative merging model is developed, taking into account the obtained probability distributions of driving styles. This model leverages the Markov Bayesian Game Decision Process framework to represent the decision-making interactions between mainline and ramp vehicles. Furthermore, a Deep Reinforcement Learning Framework integrated with Bayesian Game is proposed, to learn and derive the optimal cooperative merging strategy under stochastic driving styles. Simulation results indicate that the proposed model can make feasible and reasonable decisions at on-ramps, effectively avoiding collision accidents caused by stochastic driving styles.

In order to improve speed tracking accuracy and ensure longitudinal stability control in vehicles under conditions of parameter uncertainty and external interference, this study introduces a modified sliding mode control (SMC) method. The proposed method replaces the reaching rate function in conventional SMC with a saturation function, which effectively reduces the chattering phenomenon in the control process. The longitudinal modified SMC method consists of two stages for both driving and braking control, designed according to the longitudinal vehicle dynamics model. Within the first stage, the control law determines the engine torque or brake torque; while the second stage oversees the modulation of throttle opening or brake pressure. To ensure a smooth transition between driving and braking modes, switching rules are defined predicated on predefined thresholds governing the driving or braking torque and speed errors. The stability of this control system is verified through Lyapunov stability analysis. To validate the effectiveness and practicality of the algorithm, simulations are performed using CarSim/Simulink, and experiments are conducted on a hybrid Lincoln MKZ. Results from both simulations and experiments demonstrate that the modified SMC method improves speed tracking accuracy and longitudinal control stability, even when dealing with rapidly changing speeds. Moreover, the algorithm exhibits a remarkable ability to resist external interference, making it a reliable solution for real-world applications.

Hybrid bonded-riveted joint has poor corrosion resistance under salt spray environment, especially for dissimilar materials. The study investigates the strength degradation mechanism of carbon fiber reinforced polymer and aluminium alloy (CFRP-Al) hybrid bonded-riveted joints under salt spray environment, and it proposes a method to improve corrosion resistance of CFRP-Al hybrid bonded-riveted joints. The study found that the strength degradation of CFRP-Al hybrid joints under salt spray environment was mainly attributed to the decrease in bonding strength at the aluminum/adhesive interface. Comparison results further showed that the diffusion of corrosive medium along the aluminum/adhesive bonding interface caused a 33.3% decrease in joint strength, while the accelerated electrochemical corrosion of the aluminum surface caused a 59.3% decrease in joint strength. Applying laser to modify the surface characteristics of aluminum resulted in a 46% increase in the maximum shear loads of CFRP-Al hybrid bonded-riveted joints before salt spray exposure and a 45% increase after salt spray exposure. It has been found that laser surface treatment produced rough microstructures on aluminum surface, which increases the bonding area between adhesive and aluminum alloy, effectively preventing the diffusion of corrosive medium along the bonding interface. Furthermore, a dense oxide layer was formed by laser surface treatment on aluminum surface, which contributed to slow down the galvanic corrosion between CFRP and aluminum. Consequently, an apparently improvement was observed in the bearing capacity and corrosion resistance of CFRP-Al hybrid bonded-riveted joints.

The automotive industry’s trend towards lightweighting has led to a widespread usage of high-strength steels (HSS), which poses challenges for resistance spot welding (RSW) process in auto body manufacturing. One such challenge is the frequent occurrence of the initial gap (IG), which can negatively impact the consistency of the RSW process for HSS. This study aims to reveal this impact by comparing multi-sensor process signals, weld surface morphology, nugget size, and its growth process under standard and two-sided IG conditions. A comprehensive analysis of energy input and contact status is performed to investigate the influence mechanism of IG condition on nugget growth and process signal evolution. The study found that the IG disturbance reduces the initial contact area of the sheet-to-sheet interface in comparison to the standard condition. This results in a faster rise in the sheet temperature, an earlier peak in the resistance signal, and a greater susceptibility to expulsion at the early stage of the welding process. During the subsequent process, there is a significant increase in the contact area of both sheet-to-sheet and electrode-to-sheet interfaces, leading to a decrease in dynamic resistance signal and heat generation. Consequently, the nugget size and electrode displacement signal are smaller than the standard ones. Furthermore, the larger contact area along the gap constraint direction causes more heat generation, ultimately resulting in a larger nugget dimension and indentation size in this particular direction. This research can provide guidance for online monitoring and control for the RSW process of HSS.