To address issues such as long planning time and low success rate in automated parking under complex scenarios, this paper proposes a parallel parking path planning algorithm based on a Smart Probability Map-enhanced Bidirectional Rapidly-exploring Random Tree* (SPM-Bi-RRT*). 3 types of complex parking scenarios are defined: narrow parking spaces, constrained passageways, and obstacle-present environments. A simplified vehicle collision detection model is established using the vector cross product method. The sampling strategy is innovatively improved by hierarchically partitioning the sampling space to reduce computational complexity. A probability map is constructed based on repulsive bias and prior paths to guide algorithmic sampling. Path extension is performed using improved Reeds-Shepp curves with adaptive dynamic step sizes. Finally, path smoothing and optimization are achieved through pruning and cubic B-spline curves. Simulation results show that the proposed SPM-Bi-RRT* algorithm can generate smooth, collision-free paths in all three complex parking scenarios. Compared with the original RRT* algorithm, the search time is reduced by 56.67%, 49.63%, and 58.42%, respectively, and the path length is shortened by 7.74%, 3.84%, and 3.65%.

Aiming at the problem of localization error caused by Non-Line-Of-Sight (NLOS) in the digital key scenario of smart cars, a supervised learning-based classification model is constructed by analyzing the time-domain feature differences of the Channel Impact Response (CIR) dataset to identify the NLOS signals using a Convolutional Neural Network (CNN). Moreover the structure of the CNN network is optimized by considering the limitations of the vehicle-side hardware resources, and the effectiveness and robustness of the Ultra-Wideband (UWB) localization system are verified through real vehicle tests. The experimental results show that the accuracy of the UWB localization system incorporating deep learning and multi-modal localization algorithms is significantly improved compared with the localization trajectory without NLOS recognition processing.

As core components of automotive electronic systems, the reliability of automotive-grade chips directly determines vehicle safety and service life. Traditional accelerated aging models are primarily designed for conventional industrial and consumer electronics testing scenarios and do not fully account for the complex and variable operating conditions found in automotive applications. Consequently, reliability verification of automotive-grade chips suffers from issues such as low accuracy in life prediction, poor alignment with failure mechanisms, and significant deviations in test results. Based on the AEC-Q100 automotive standard, this paper systematically reviews the typical failure mechanisms of automotive-grade chips, classic accelerated aging models, and automotive application scenarios. It analyzes future trends in aging model development to provide theoretical support and engineering references for the reliability assessment, test plan design, and product optimization of automotive-grade chips.

Given the current lack of integrated testing solutions for distributed vision and LiDAR systems in Electromagnetic Susceptibility (EMS) testing of Advanced Driver Assistance Systems (ADAS), and the safety risks associated with multi-sensor coordination in complex electromagnetic environments, this paper proposes a vehicle-based EMS testing method for ADAS systems. By using point cloud digital signal injection technology to simulate the characteristics of LiDAR point cloud scenes, the paper constructs high-precision test scenarios using PreScan and Simulink, and employs a pass-band filtering algorithm to reduce noise in the point cloud data. The test results show that the pass-through filtering algorithm reduces the number of point clouds by 22 851 while preserving target features, thereby significantly reducing the computational load on the equipment. At the same time, the sensor hardware-in-the-loop platform successfully activated all sensors during functional activation testing under Adaptive Cruise Control (ACC) conditions in a semi-anechoic chamber. The speed and relative distance recognition accuracy of the millimeter-wave radar, camera, and LiDAR all met the expected requirements, validating the effectiveness and reliability of the proposed solution.

To address the issue of poor accuracy and low efficiency in diagnosing inter turn short circuit faults of motors in new energy vehicles under variable operating conditions due to lack of data, this paper proposes a fault diagnosis method based on Attention Mechanism Optimized Multi-Scale Convolutional Neural Networks (Attention-MCNN) combined with transfer learning. Firstly, an inter- turn short circuit experimental platform for permanent magnet synchronous motors is established to collect raw three-phase current data, and construct a labeled dataset. Secondly, the Attention-MCNN network structure and parameters are determined through ablation experiments, and the network is trained to obtain a pre-trained network model. Finally, transfer learning is introduced to freeze the pre-trained model and fine tune the network by inputting labeled data under other operating conditions. A network model with the ability to recognize the characteristics of target domain data is obtained to achieve the diagnosis of inter turn short circuit faults in new energy vehicle motors. The experimental results show that the proposed method has an average fault diagnosis accuracy of 95.67%, with a detection time of about 5 s, demonstrating lower data dependency compared with traditional methods.

To address the issue of low detection accuracy for small pedestrian targets, a pedestrian detection model tailored for complex scenes is proposed based on the DETR algorithm. In the feature extraction stage, the SENet attention mechanism is introduced to enhance channel discrimination ability. By combining image Relative Position Encoding (iRPE) with absolute position encoding, the model's perception of global context and local details is improved. After training on a self-built dataset, experimental results show that the pedestrian recognition accuracy of the proposed scheme reaches 97.2%, with false detection rate and missed detection rate of only 1.7% and 1.1%, respectively. It performs excellently in handling complex scenes such as multi-scale pedestrians, partial occlusion, and low visibility, and its detection performance is significantly better than traditional methods.

To address the issues of single-type detection and poor adaptability in detecting distant small targets and low-light scenes for road surface irregularity recognition, this paper proposes an improved YOLOv10-based detection algorithm. The SPPF module is replaced with a Focal Modulation network to enhance small-target detection accuracy. The CPA-Enhancer is introduced to improve detection performance under low-light conditions. The Shape-IoU loss function is adopted to optimize localization precision. Experimental results on a self-built dataset demonstrate that the improved model achieves a 3.08% higher mAP@0.5 than the original model. Real-vehicle deployment further verifies the effectiveness of the proposed model, demonstrating its capability for real-time detection of 7 types of road surface irregularities, including speed bumps, potholes, and vibrating markings.

To improve the accuracy and robustness of 3D object detection from a Bird's-Eye View (BEV) in multi-camera visual perception for autonomous driving, this paper proposes a multi-view image object detection method based on an improved BEVFormer. To introduce perspective-based regional auxiliary supervision at the image feature level, using BEV annotations to impose projection constraints on the image view, thereby guiding the backbone network to learn fine-grained local features for 3D spatial localization. This paper establishes instance-level consistency constraints, at the BEV representation level and explicitly enforces the consistency of BEV features for the same physical object across different viewpoints based on a contrastive learning mechanism, thereby mitigating instance-level feature drift caused by view transformations. Furthermore, this paper trains and evaluates the proposed method using the nuScenes dataset and conduct a comparative analysis with various typical multi-view 3D object detection algorithms. The experimental results show that, compared to the BEVFormer baseline model, the proposed method achieves improvements of 1.6 percentage points and 0.4 percentage points in mean Average Precision (mAP) and the Normalized Detection Score (NDS), respectively, while reducing the average localization error by 8.7 percentage points, thereby validating the effectiveness of this method for the BEV detection task using multi-view images.

To address the uncertainty of driving intentions among general vehicles in complex traffic environments, this paper proposes a path planning method based on delayed decision-making. This method generates a trajectory tree comprising an initial shared trajectory segment and branching trajectories corresponding to different potential actions of social vehicles; employs a Gaussian mixture model to predict the probability of social vehicle driving intentions; and determines branching points based on the state deviations of the predicted trajectories. Depending on the requirements of different scenarios, delayed decision-making mechanisms are incorporated into both path planning and speed planning to implement lane-changing and deceleration-based yielding strategies. The results of the joint simulation using MATLAB/Simulink and Carsim indicate that, compared to traditional methods that generate a single trajectory, the proposed approach reduces lateral velocity, acceleration, and their rates of change by 9.2%, 51.7%, and 63.6%, respectively, in lane-changing avoidance scenarios, thereby improving the smoothness of the lane-changing process and ride comfort. In deceleration avoidance scenarios, longitudinal acceleration and its rate of change are reduced by 35% and 61.5%, respectively, significantly improving the smoothness of the deceleration process.

To improve the spatial coverage and timeliness of expressway traffic state estimation, this paper proposes a joint state estimation method that integrates observational data with a traffic flow model based on the Kalman filter. Intelligent Connected Vehicle (ICV) probe data are used as observational inputs. Based on Cooperative Adaptive Cruise Control (CACC) and the Intelligent Driver Model (IDM), the motion behaviors of ICV and human-driven vehicles in mixed traffic flow are simulated, and traffic density is estimated using the Cell Transmission Model (CTM). Validation using SUMO simulations and NGSIM field data shows that the estimation error of the proposed method decreases significantly as the ICV penetration rate increases. Specifically, the Mean Absolute Percentage Error (MAPE) is below 20% at a 20% penetration rate; the estimation accuracy improves further at 40%; and when the penetration rate reaches 80%, the MAPE is reduced by 16.54% compared with statistical estimation methods. The proposed method achieves high estimation accuracy and robustness, which is suitable for traffic state estimation in complex traffic environments.