To systematically summarize the research status of multi-source fusion environmental perception technology for intelligent vehicles, this paper compares and analyzes the principles and characteristics of various sensors including cameras, Light Detection and Ranging (LiDAR), and millimeter-wave radar. The environmental perception technologies based on single-sensor approaches (such as camera-based object detection and LiDAR point cloud processing) and multi-sensor fusion strategies (data-level, feature-level, and decision-level) are reviewed with their technical bottlenecks and challenges. Typical algorithm cases are also discussed to explore their application effectiveness. The research findings indicate that: single sensors exhibit inherent limitations, such as cameras’ dependency on illumination conditions and LiDAR’s high cost with insufficient semantic information acquisition capability, as well as multi-sensor fusion technology significantly enhances environmental perception robustness through complementary advantages, yet challenges like data heterogeneity and insufficient real-time performance still remain unresolved. To meet the perception demands of complex scenarios, future development will focus on intelligent multi-modal fusion algorithms, cost-effective sensor integration, and V2X collaborative perception technologies.

To meet the demand for precise environmental perception in intelligent driving, this paper focuses on the application and development of intelligent driving environment perception sensors, analyzing their foundational position in system architecture. It discusses the working mechanisms, application scenarios, and advantages and disadvantages of various sensors such as visual sensors, LiDAR, millimeter-wave radar, and ultrasonic radar, analyzing the impact of multi-sensor fusion on improving perception accuracy and autonomous driving reliability. In the future, environmental perception sensor technology for intelligent vehicles will focus on 6 major directions: new sensing materials, intelligent adaptability, energy-efficient design, fault diagnosis, real-time calibration, and environmental impact suppression. Sensors will continue to evolve towards miniaturization, integration, and adaptive low-power design. Breakthroughs will be made in areas such as high-precision vehicle cameras, solid-state LiDAR, and innovative integration of ultrasonic radar, aiming to enhance sensing accuracy, real-time performance, and reliability to meet the increasingly complex demands of driving environments.

Through the literature review of PID control, robust control, sliding mode control and model predictive control, the characteristics of each method’s application in autonomous driving are analyzed. PID control is simple to implement but limited in complex environments. Robust control can deal with uncertainty and interference, but the design tends to be conservative. Sliding mode control offers rapid response and strong resistance to disturbances, yet it may cause chattering issues. Model predictive control provides precise trajectory optimization which requires high computational resources. The study shows that PID control is suitable for simple environments, robust control is suitable for situations requiring high stability, sliding mode control is applied to tasks that require for rapid adjustments, and model predictive control is suitable for scenarios that demand high precision. Future research will focus on integratiing multi-strategy to improve performance, adapt to various working conditions, and ensure stability and accuracy. Moreover, it is also necessary to develop efficient real-time algorithms, combine machine learning to enhance adaptability, improve control efficiency and reliability, and achieve accurate path tracking.

In order to improve the efficiency and quality of parking path planning, a study on intelligent driving parking path planning algorithms has been conducted. By reviewing the parking planning methods from recent domestic and international academic research, based on their characteristics the parking path planning algorithms are categorized into 5 types: graph search algorithms, sampling-based algorithms, intelligent algorithms, curve interpolation algorithms, and optimal control algorithms. The advantages and disadvantages of these 5 types of algorithms are analyzed, and the application of fusion algorithms in specific environments is explored. The rationality and effectiveness of existing solutions are evaluated in terms of planning efficiency and path curvature. Furthermore, future development trends in parking path planning algorithms are discussed. The study concludes the following: (1) Graph search algorithms offer the advantages of globally optimal paths and good real-time performance but suffer from poor path continuity and high complexity in high-dimensional spaces. (2) Sampling-based algorithms have the advantages of probabilistic completeness and high search efficiency in high-dimensional spaces but have large memory consumption, significant randomness, and cannot guarantee path curvature. (3) Intelligent algorithms have strong learning capabilities based on samples and strong iteration capabilities but have high training costs, poor dynamic adaptability, and poor real-time performance. (4) Curve interpolation algorithms based on optimization are easy to calculate but cannot guarantee the continuity of curvature. (5) Optimal control algorithms based on optimization can handle complex optimization problems but cannot guarantee timeliness and are prone to falling into local minima. Fusion algorithms through complementary advantages can better adapt to vehicle constraints and environmental constraints, achieving efficient and safe parking path planning.

To address the issues of poor tracking accuracy and driving stability caused by uncertain model parameters, modeling errors, and external disturbances, this paper proposes a motion control method for intelligent vehicles based on horizontal and longitudinal dual preview PID compensation. Firstly, an LQR（Linear Quadratic Regulator lateral motion controller is established using a path tracking error model to address angle compensation. This is achieved through a lateral previewing PID controller, utilizing the lateral deviation of the preview point as input. Secondly, a longitudinal motion controller is designed based on model-independent fuzzy theory to track vehicle speed. A previewing PID controller is established to compensate for vehicle speed using the longitudinal deviation of the preview point as input. Finally, the proposed method is validated through simulation under with uniform accelerated double lane shift. Simulation results demonstrate that the intelligent vehicle motion controller based on horizontal and longitudinal dual preview PID compensation achieves higher tracking accuracy and driving stability under conditions of high speed and large curvature during double lane shifts.

When using the Random Forest (RF) algorithm to estimate the road adhesion coefficient, there are issues such as insufficient optimization of feature selection during model construction and insufficient diversity in the ensemble of decision trees. To address this issue, a method based on Particle Swarm Optimization (PSO) algorithm to improve RF is proposed, and the algorithmic process is presented. An RF model for estimating the road adhesion coefficient is established, and the PSO algorithm is used to optimize the parameter configuration of RF, including key factors such as the number of features of each tree and the number of trees, so as to enhance the diversity and generalization capabilities of the model. At last, a joint simulation model is built on the MATLAB/Simulink platform for experiments. The comparative experimental results show that the random forest road adhesion coefficient estimation method based on PSO-RF can overcome the limitations of the traditional RF methods, and both the estimation accuracy and stability have been significantly improved.

To address signal crosstalk and reflection phenomena caused by the wiring layout of automotive Printed Circuit Boards (PCBs), a simulation software Cadence is utilized to model the reflection phenomena of high-speed signal lines. The causes of signal reflection are analyzed, and impedance matching schemes for reflection are employed in the termination design. The effects of 4 different types of terminations, namely series termination, Thevenin termination, RC termination, and diode termination, on the signal quality in transmission lines are compared. Additionally, enhancements are made to power integrity through optimized power plane design, which significantly enhances the Electromagnetic Compatibility (EMC) performance of the PCB. The study demonstrates that signal integrity, power integrity, and electromagnetic interference are interrelated and mutually constraining. Conducting reliability designs for these 3 aspects by combining stimulation data can significantly improve the EMC performance of PCBs.

Aiming at the Electromagnetic Interference (EMI) caused by DC/DC converter in switching power supply, the electromagnetic interference source of DC/DC converter is proposed and analyzed, and the EMI propagation path generated by the converter is constructed. The conducted interference under the influence of pure circuit and Printed Circuit Board (PCB) is compared and analyzed, and the measures of adding Π filter to suppress the electromagnetic interference of DC/DC converters are proposed, and the simulation of CST software is used to verify the suppression results. The results show that the suppression method proposed in this paper can effectively suppress the electromagnetic interference of switching power supply.