Research on Path Planning and Path Tracking Control of Autonomous Vehicles Based on Improved APF and SMC.

Path planning and tracking control is an essential part of autonomous vehicle research. In terms of path planning, the artificial potential field (APF) algorithm has attracted much attention due to its completeness. However, it has many limitations, such as local minima, unreachable targets, and inadequate safety. This study proposes an improved APF algorithm that addresses these issues. Firstly, a repulsion field action area is designed to consider the velocity of the nearest obstacle. Secondly, a road repulsion field is introduced to ensure the safety of the vehicle while driving. Thirdly, the distance factor between the target point and the virtual sub-target point is established to facilitate smooth driving and parking. Fourthly, a velocity repulsion field is created to avoid collisions. Finally, these repulsive fields are merged to derive a new formula, which facilitates the planning of a route that aligns with the structured road. After path planning, a cubic B-spline path optimization method is proposed to optimize the path obtained using the improved APF algorithm. In terms of path tracking, an improved sliding mode controller is designed. This controller integrates lateral and heading errors, improves the sliding mode function, and enhances the accuracy of path tracking. The MATLAB platform is used to verify the effectiveness of the improved APF algorithm. The results demonstrate that it effectively plans a path that considers car kinematics, resulting in smaller and more continuous heading angles and curvatures compared with general APF planning. In a tracking control experiment conducted on the Carsim-Simulink platform, the lateral error of the vehicle is controlled within 0.06 m at both high and low speeds, and the yaw angle error is controlled within 0.3 rad. These results validate the traceability of the improved APF method proposed in this study and the high tracking accuracy of the controller.

Research on Yaw Stability Control Strategy for Distributed Drive Electric Trucks.

With the advancement of vehicle electrification and intelligence, distributed drive electric trucks have emerged as the preferred choice for heavy-duty electric trucks. However, the control of yaw stability remains a significant issue. To tackle this concern, this study introduces a layered control strategy for yaw moment. Specifically, the upper layer utilizes a yaw moment controller based on linear quadratic regulator (LQR) to compute the additional yaw moment required. Additionally, in order to enhance the performance of the yaw moment controller, the weight matrix in LQR is optimized using a hybrid Genetic Algorithm and Particle Swarm Optimization algorithm (GA-PSO). The lower layer consists of a torque distribution layer, which establishes an objective function for minimizing tire utilization rate. Quadratic Programming algorithm is then employed to compute the optimal torque distribution value, thereby improving the vehicle's stability. Subsequently, the stability control effects of the vehicle are simulated and compared on the Matlab/Simulink Trucksim joint simulation platform using four control strategies: the proposed control strategy, SMC, LQR, and without yaw moment control. These simulations are conducted under two working conditions: serpentine and double lane change. The results demonstrate that the proposed approach reduces the average yaw rate by 14.4%, 19.6%, and 42.15% while optimizing the average sideslip angle by 25.9%, 24.8%, and 52.3% in comparison to the other three control strategies. Consequently, the proposed control strategy significantly enhances the driving stability of the vehicle. Furthermore, the optimized allocation method reduces the average tire utilization rate by 42.6% in contrast to the average allocation method, thereby improving the stability control margin of the vehicle. These findings successfully validate the efficiency of the yaw stability control strategy presented in this article.

An object detection algorithm combining self-attention and YOLOv4 in traffic scene.

Automobile intelligence is the trend for modern automobiles, of which environment perception is the key technology of intelligent automobile research. For autonomous vehicles, the detection of object information, such as vehicles and pedestrians in traffic scenes is crucial to improving driving safety. However, in the actual traffic scene, there are many special conditions such as object occlusion, small objects, and bad weather, which will affect the accuracy of object detection. In this research, the SwinT-YOLOv4 algorithm is proposed for detecting objects in traffic scenes, which is based on the YOLOv4 algorithm. Compared with a Convolutional neural network (CNN), the vision transformer is more powerful at extracting vision features of objects in the image. The CNN-based backbone in YOLOv4 is replaced by the Swin Transformer in the proposed algorithm. The feature-fusing neck and predicting head of YOLOv4 is remained. The proposed model was trained and evaluated in the COCO dataset. Experiments show that our method can significantly improve the accuracy of object detection under special conditions. Equipped with our method, the object detection precision for cars and person is improved by 1.75%, and the detection precision for car and person reach 89.04% and 94.16%, respectively.

A Lightweight Vehicle-Pedestrian Detection Algorithm Based on Attention Mechanism in Traffic Scenarios.

Object detection is a critical technology of environmental perception for autonomous driving vehicle. The Convolutional Neural Network has gradually become a powerful tool in the field of vehicle detection because of its powerful ability of feature extraction. In aiming to reach the balance between speed and accuracy of detection in complex traffic scenarios, this paper proposes an improved lightweight and high-performance vehicle-pedestrian detection algorithm based on the YOLOv4. Firstly, the backbone network CSPDarknet53 is replaced by MobileNetv2 to reduce the number of parameters and raise the capability of feature extraction. Secondly, the method of multi-scale feature fusion is used to realize the information interaction among different feature layers. Finally, a coordinate attention mechanism is added to focus on the region of interest in the image by way of weight adjustment. The experimental results show that this improved model has a great performance in vehicle-pedestrian detection in traffic scenarios. Experimental results on PASCAL VOC datasets show that the improved model's mAP is 85.79% and speed is 35FPS, which has an increase of 4.31% and 16.7% compared to YOLOv4. Furthermore, the improved YOLOv4 model maintains a great balance between detection accuracy and speed on different datasets, indicating that it can be applied to vehicle-pedestrian detection in traffic scenarios.

Index finger motor imagery EEG pattern recognition in BCI applications using dictionary cleaned sparse representation-based classification for healthy people.

Electroencephalogram (EEG)-based motor imagery (MI) brain-computer interface (BCI) has shown its effectiveness for the control of rehabilitation devices designed for large body parts of the patients with neurologic impairments. In order to validate the feasibility of using EEG to decode the MI of a single index finger and constructing a BCI-enhanced finger rehabilitation system, we collected EEG data during right hand index finger MI and rest state for five healthy subjects and proposed a pattern recognition approach for classifying these two mental states. First, Fisher's linear discriminant criteria and power spectral density analysis were used to analyze the event-related desynchronization patterns. Second, both band power and approximate entropy were extracted as features. Third, aiming to eliminate the abnormal samples in the dictionary and improve the classification performance of the conventional sparse representation-based classification (SRC) method, we proposed a novel dictionary cleaned sparse representation-based classification (DCSRC) method for final classification. The experimental results show that the proposed DCSRC method gives better classification accuracies than SRC and an average classification accuracy of 81.32% is obtained for five subjects. Thus, it is demonstrated that single right hand index finger MI can be decoded from the sensorimotor rhythms, and the feature patterns of index finger MI and rest state can be well recognized for robotic exoskeleton initiation.

An Improved Spectral Background Subtraction Method Based on Wavelet Energy.

Most spectral background subtraction methods rely on the difference in frequency response of background compared with characteristic peaks. It is difficult to extract accurately the background components from the spectrum when characteristic peaks and background have overlaps in frequency domain. An improved background estimation algorithm based on iterative wavelet transform (IWT) is presented. The wavelet entropy principle is used to select the best wavelet basis. A criterion based on wavelet energy theory to determine the optimal iteration times is proposed. The case of energy dispersive X-ray spectroscopy is discussed for illustration. A simulated spectrum with a prior known background and an experimental spectrum are tested. The processing results of the simulated spectrum is compared with non-IWT and it demonstrates the superiority of the IWT. It has great significance to improve the accuracy for spectral analysis.