Aiming at the problems of control stability of the intelligent vehicle lateral control method, single test conditions, etc., a lateral control method with feedforward + predictive LQR is proposed, which can better adapt to the problem of intelligent vehicle lateral tracking control under complex working conditions. Firstly, the vehicle dynamics tracking error model is built by using the two degree of freedom vehicle dynamics model, then the feedforward controller, predictive controller and LQR controller are designed separately based on the path tracking error model, and the lateral control system is built. Secondly, based on the YOLO-v3 algorithm, the environment perception system under the urban roads is established, and the road information is collected, the path equation is fitted and sent to the control system. Finally, the joint simulation is carried out based on CarSim software and a Matlab/Simulink control model, and tested combined with hardware in the loop test platform. The results of simulation and hardware-in-loop test show that the transverse controller with feedforward + predictive LQR can effectively improve the accuracy of distance error control and course error control compared with the transverse controller with feedforward + LQR control, LQR controller and MPC controller on the premise that the vehicle can track the path in real time.

Intelligent Vehicle Lateral Control Method Based on Feedforward + Predictive LQR Algorithm

As the main objective influencing factor on the brake safety of autonomous vehicles, pavement texture information is directly related to road surface antiskid performance. However, in the brake system of autonomous vehicles, the influence of road surface adhesion characteristics on braking stability is seldomly considered. To study the braking stability of autonomous vehicles on curved sections under different road conditions, the advanced close-range photogrammetry system was utilized to extract the road surface texture information. Thereafter, the power spectral density (PSD) of the road surface was calculated by MATLAB to obtain the pavement adhesion coefficient curves based on the Persson friction theory model under different road conditions. Considering the pavement adhesion characteristics, the braking model of autonomous vehicles was built in Simulink, and then, the braking performance on curved sections was analyzed with CarSim/Simulink cosimulation. The results indicate that, according to the adhesion coefficient of different asphalt pavement types under different road conditions, the ranking order is open-grade friction course (OGFC) > stone matrix asphalt (SMA) > dense-graded asphalt concrete (AC). In addition, both the maximum lateral offset distances and the maximum lateral forces of the tires decrease as the curve radius gradually increases under different road conditions. It can also be found that there is a relatively uniform vertical forces distribution of the tire when the curve radius is no less than 100 m, and the limit speed of the vehicle varies parabolically with increasing in curve radius. Compared with dry road, the reduction of vehicle braking deceleration is more significant and the yaw rate is greater on wet road. Last but not least, the braking comfort with a radius of 200 m is the best according to the comfort index (CI) in International Standard ISO, in which the comfort level can be sorted into six levels.

/pdf/evaluation-on-braking-stability-of-autonomous-vehicles-3us8mp44.pdf

Evaluation on Braking Stability of Autonomous Vehicles Running along Curved Sections Based on Asphalt Pavement Adhesion Properties

Vehicle detection and classification are necessary components in a variety of useful applications related to traffic, security, and autonomous driving systems Many studies have focused on recognizing vehicles from the point of view of a single perspective, such as the rear of other cars from the driving seat, but not from all possible perspectives, including the aerial view In addition, they are usually given prior knowledge of a specific kind of vehicle, such as the fact that it is a car, as opposed to being a bus, before deducing other information about it One of the popular classification techniques used is boosting, where weak classifiers are combined to form a strong classifier However, most boosting applications consider complex classification problems to be a combination of binary problems This paper explores in detail the development of a multi-class classifier that recognizes vehicles of any type, from any view, without prior information, and without breaking the task into binary problems Instead, a single multi-class application of the GentleBoost algorithm is used This system is compared to a similar system built from a combination of separate classifiers that each classifies a single vehicle The results show that a single, multi-class classifier clearly outperforms a combination of separate classifiers, and proves that a simple boosting classifier is sufficient for vehicle recognition, given any type of vehicle from any perspective of viewing, without the need of representing the problem as a complex 3D model

/pdf/multiclass-vehicle-classification-across-different-2rdy3o3283.pdf

Multiclass Vehicle Classification Across Different Environments

An intelligent cleaning vehicle improves the efficiency of road cleaning to a great extent. In this case, road garbage recognition is fundamental and crucial. Usually, the pebbles are too small, and the sand has an inconspicuous boundary and unfixed shape on the roads. These issues make the stones and sand too hard to be detected by a garbage recognition system. Hence, we designed a novel semantic segmentation network that acquires the areas and categories of road garbage. We designed a Deep Supervision and High Fusion (DSHF) block to improve the road garbage segmentation accuracy. The designed block with a backbone network of HFCN and UNet++ is comparable with a model that only has either a deep supervision block or a high fusion block. According to the collected road garbage segmentation dataset comprising four categories (stones, leaves, sand and bottles), the model we designed has improved the metric value of MPA by 3% over the state-of-art methods and achieved the highest MIoU (Mean Intersection over Union) with the value of 77.92%. The results of our experiments show that the semantic segmentation of road garbage is feasible and that the proposed DSHF block is practical for improving the segmentation effect of road garbage. 

Road Garbage Segmentation With Deep Supervision and High Fusion Network for Cleaning Vehicles

With the less humanized trend of manufacturing production line gradually progressing, real-time recording and tracking of workpieces information have become an essential way to implement efficient management. To collect and identify the workpiece marker is of great significance for product information statistics and quality traceability. Aiming at the problems of inaccurately positioning, difficultly segmenting, and slowly recognizing for capturing the marker of disc workpieces distributed circularly, this study proposes a projection segmentation algorithm based on polar coordinate inverse transformation to locate and separate the circularly arranged marker and extract the total separated characters. The features of the directional gradient histogram (HOG) of characters are used as the input of the support vector machine (SVM) model, and after training, a workpiece marker recognition classifier is obtained. The experiment results show that the recognition accuracy of markers composed of letters and numbers is over 97% by the proposed method. Our proposed method outperformed state-of-the-art approaches in achieving higher recognition accuracy rate with the SVM classifier.

Marker Identification of Disc Workpiece Based on HOG-SVM Classifier

With the development of automobile industry, the license plate, as the unique identifier of the vehicle, plays an important role in vehicle management. License plate recognition technology is mainly realized by image processing technology. It mainly includes image preprocessing, license plate positioning, character segmentation and other processes. In the actual process of license plate recognition, it is often impossible to accurately recognize the license plate due to the positional relationship such as angle. Therefore, this paper proposes a license plate recognition program based on the capsule network. First, through image preprocessing, license plate positioning, and character segmentation, and then use capsule neural network for training and simulation in order to achieve the object of accurate character recognition.

Design of license plate recognition system based on capsule network

In order to realize the path tracking of autonomous vehicles, this paper first simplifies the complex structure of the vehicle into a two-degree-of-freedom kinematic and dynamic vehicle model. based on PID control, the vehicle path tracking controller is designed to calculate the lateral deviation between the expected path and the actual path, and outputs the front wheel rotation angle through the controller, so that the autonomous vehicle can travel well according to the expected path. The control system model is built in the MATLAB/Simulink, and the vehicle path tracking control system is simulated and verified jointly with the CarSim software platform. Simulation results show that the designed control strategy can ensure the path tracking performance of intelligent vehicles at different speeds, and has good tracking accuracy, real-time performance and vehicle driving stability.

https://robots.iopscience.iop.org/article/10.1088/1757-899X/892/1/012050/pdf

Driverless simulation of path tracking based on PID control

Research on pavement garbage detection based on machine vision

Research on visual vehicle detection and tracking based on deep learning

https://robots.iopscience.iop.org/article/10.1088/1757-899X/892/1/012048/pdf

Yaoming Zhang

Papers

Design of license plate recognition system based on capsule network

Driverless simulation of path tracking based on PID control

Research on pavement garbage detection based on machine vision

Research on visual vehicle detection and tracking based on deep learning

Control strategy and simulation verification of hardware-in-the-loop system of automotive steering device