Aming at the challenges that trajectory planning and tracking control of autonomous vehicles struggle to respond to dynamic obstacles in real-time under urban road conditions and the insufficient robustness of complex traffic environments, this paper proposes a trajectory optimization method that integrates hierarchical planning and dynamic replanning. It first generates a coarse path using fast linear programming, then refines the path using an improved artificial potential field method and numerical optimization. A trajectory replanning module is designed to predict dynamic obstacle trends and adjust the path in real-time. Lateral control uses Model Predictive Control (MPC) based on the Frenet coordinate system, and longitudinal control uses a dual PID controller. Simulation results show that, in the straight-road static obstacle avoidance scenario, the proposed method starts obstacle avoidance approximately 45 m before reaching the obstacle. In the overtaking scenario, its speed fluctuation is about 5 km/h, lower than 17.5 km/h for GD-APF and 11 km/h for D-RRT. The lateral acceleration is mainly maintained within −1 to 1 m/s². Moreover, the maximum lateral tracking error is 0.84 m, and the longitudinal speed error is controlled within 1 m/s. These results indicate that the proposed method achieves good comprehensive performance in path smoothness, dynamic obstacle avoidance, and trajectory tracking accuracy.

To address the issues of strong search blindness and poor path feasibility in the traditional Bi-RRT* algorithm, this paper proposes an improved approach named GC-APF-Bi-RRT* (Bi-RRT* based on Guided Connection and Artificial Potential Field). The algorithm first establishes a collision model for vehicles considering four-wheel steering vehicles. It then overcomes the problems of sampling difficulties and reciprocating paths by extracting environmental guide points and employing a search-based connection strategy constrained by direction consistency. Furthermore, an improved APF integrated with a goal-distance factor is introduced to guide the tree growth direction. Finally, greedy pruning and B-spline smoothing techniques are applied to optimize the trajectory. Simulation results demonstrate that in complex environments, compared to traditional RRT, RRT*, RRT-Connect, Bi-RRT*, and Goal-Biased RRT*, the proposed algorithm reduces path length by 19.45%, 9.94%, 13.85%, 4.10%, and 3.61%, respectively, and shortens search time by 62.57%, 65.15%, 0.97%, 66.63%, and 71.28%, respectively.

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.