At present, low-end electric vehicle do not have direct slope signal information. To address this issue, this article proposed a road slope estimation algorithm based on the existing CAN bus signals. Firstly, vehicle speed signal and longitudinal acceleration signal values input from CAN were preprocessed, and a Kalman filtering equation was constructed based on the relationship between slope, vehicle speed and longitudinal acceleration, to estimate the road slope. Then, the impact of noise variance parameters on the slop estimation results was analyzed, and an adaptive tuning Kalman filter was designed to optimize the slope estimation results. Finally, the vehicle test was conducted, verifying the accuracy and real-time performance of the ramp estimation algorithm.

The 3D point cloud object detection algorithm based on deep learning is prone to issues such as inability to maintain network performance and poor transferability when changing scenes or devices. To address this issue, this article proposes an Accurate, Flexible, and highly transferable two-stage 3D point cloud object detection algorithm (AF3D). In the first stage of the AF3D detection algorithm, a segmented fitting algorithm is used to remove the road surface from the collected laser point cloud, then DBSCAN algorithm is used to cluster non-ground point clouds and obtain several clustering clusters. In the second stage of the AF3D detection algorithm, a point cloud fully connected network PFC-Net is established, and features are extracted and classified. Through experiments, it has been proven that this algorithm can achieve good detection performance on public KITTI datasets, and the detection accuracy for cars, pedestrians, and cyclists on real vehicle datasets is 69.74%, 41.25%, and 54.33%, respectively, indicating good transferability.

A method for optimizing the layout of carbon fiber composite floorings for BIW was proposed to enhance precision, efficiency, and structural lightweight. Initially, BIW finite element model was established and its efficiency was validated. Subsequently, material parameters for the carbon fiber composite were obtained through mechanical performance testing, followed by conceptual designing and modeling of the flooring layout. Subsequent utilization of continuous variable optimization determined the thickness, block shapes, and layers of the flooring, employing a discretization and rounding strategy to achieve discrete layer numbers for each layup angle. The optimization results show that the Particle Swarm Optimization-Bacteria Foraging Optimization (PSO-BFO) algorithm proposed herein improves flooring quality, static bending stiffness and BIW lightweight coefficient by 34.4%, 6.0% and 5.3%, respectively.

In response to the privacy leakage issues in the data sharing process among the fleet vehicles in Vehicular Social Network (VSN), this paper proposed a ciphertext policy attribute-based encryption scheme. Firstly, utilizing attribute-based encryption techniques, the scheme ensures that only authorized vehicles can access the data, thereby preventing privacy leakage during the fleet vehicle data sharing process. To address the issue of high time complexity in generating access policies during fleet vehicle data sharing, and low data sharing efficiency, an access tree was constructed to design the access policies. The access tree was then transformed into an access matrix using roadside units, enabling fast generation of access policies. Experimental analysis shows that this scheme achieves secure data sharing among fleet vehicles in VSNs, the proposed access policy generation approach effectively reduces the computational overhead for vehicles.

In order to enhance the understanding of the dynamic environment of autonomous vehicles and to improve road driving safety, this article proposed a vehicle trajectory prediction STGTF model based on the Gated Recurrent Unit (GRU) and Transformer that used the GRU to extract the historical trajectory features of vehicles, and used a two-layer Multi-Headed Attention (MHA) mechanism to extract the spatio-temporal interaction features of vehicles, generating the predicted trajectories. The experimental results show that the Root-Mean-Square Error (RMSE) of the predicted results decrease by 7.3% on average, STGTF model has different degrees of improvement compared with other existing methods for both short-term prediction and long-term prediction, proving validity of this model.

To study the applicability of different data correlation evaluation methods for virtual evaluation of far side occupant protection condition, firstly, the dynamic response of 11 simulation and test data was determined by analyzing far side occupant basic data of two vehicle models, CORrelation and Analysis (CORA) and ISO/TS 18571 methods were further applied for correlation evaluation, and error analysis method was used to analyze the response with significant differences in the correlation evaluation results, and it is concluded that ISO/TS 18571 method provides more reasonable validation results than CORA method.

As the battery temperature shows a high distribution in the middle and low distribution around during the operation of electric vehicles, it affects the battery service life. To this end, a steady-state heat conduction structure design method based on Floating Projection Topology Optimization (FPTO) is proposed using the geometric mean temperature as the objective function, and the maximum temperature and temperature difference of the power battery pack under single and multiple operating conditions are comparatively analyzed by means of an arithmetic example, which demonstrates that the obtained topological configuration can effectively reduce the maximum temperature and temperature difference in the heat dissipation process during the multiple operating conditions, so as to make the temperature distribution uniform. Finally, the method is applied to the power battery pack support structure, and the results show that the method effectively reduces the temperature without increasing the volume of the battery pack structure, optimizes the distribution of materials, and realizes lightweight of the overall structure of the battery pack.

In view of the strong coupling of each control factor in the lateral control of autonomous vehicles, it is difficult for the control method relying on the ideal model to completely decouple and migrate from the simulation environment to the actual vehicle, and the problem that the convergence speed of the reinforcement learning method in the lateral control of autonomous vehicles is not ideal, the fuzzy inference machine and the similarity of the simulation reinforcement learning in the lateral control factors of vehicles are used to combine the two. A fuzzy inference machine is used as the initialization condition for simulated reinforcement learning, and provide guidance for the learning process, thus achieving rapid convergence of the learning process. The MATLAB/Carla simulation and vehicle test are applied to verify the control method. The results show that the method can significantly reduce the number of simulation reinforcement learning iterations, achieve better vehicle lateral control performance in 500 full path iterations, and achieve good control effect in both simulation and real environment on the basis of not relying on the ideal mathematical model and not having to carry out in-depth optimization of the fuzzy inference device.

There are insufficient vehicle-vehicle interaction and poor matching between planning and control in the decision-making model of high-speed autonomous vehicles. In order to solve these problems, a closed-loop lane change decision model based on Stackelberg game was constructed. Faulty vehicle response was incorporated into lane changing decision while introducing driving style feature. The multi-objective decision-making cost function was optimized. Particle Swam Optimization (PSO) algorithm was used to solve the game decision model, and the vehicle state was predicted by using a kinematic model that considers the influence of center of mass sideslip angle. A nonlinear model predictive planning controller based on dynamic risk potential field method was designed. The simulation test results show that the closed-loop lane-changing decision-making model proposed in this paper can effectively combine the interaction behavior and driving style characteristics of vehicles to make correct decision-making instructions and implement corresponding motion planning and control.

In order to solve the shortcomings of traditional object detection and tracking algorithms, such as low detection accuracy, poor global perception ability, poor recognition ability of occlusion and small target objects, this paper proposed a vehicle tracking method based on YOLOv5 and DeepSORT algorithm improved by lightweight Transformer. Firstly, the EfficientFormerV2 model was used to improve the YOLOv5 algorithm model to enhance the target detection ability of the vehicle, and then the advantages of the Swin model were used to improve the Re-Identification module in the DeepSORT multi-target tracking algorithm to enhance the tracking ability and accuracy of the vehicle. Finally, the dataset KITTI and VeRi were used to carry out comparative experiments and ablation experiments. The results show that under complex conditions, the performance of the proposed method is significantly improved in vehicle occlusion and small target recognition, with an average accuracy of 96.7%, an increase of 9.547% in target tracking, and a reduction of 26.4% in the total number of ID switching.