Road crack tracking adaptive fuzzy control method and device based on cross entropy

Through the adaptive fuzzy control method based on cross entropy, the fuzzy PID controller and cross entropy optimization are used to solve the problem of low tracking accuracy in automatic repair of road surface cracks, and efficient and safe road crack trajectory repair is achieved.

CN118915423APending Publication Date: 2024-11-08CHANGAN UNIV
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202410960807.3
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-07-17
Publication Date
2024-11-08

AI Technical Summary

Technical Problem

The prior art has problems such as low maintenance efficiency, low operating accuracy, and high safety hazards in the automatic repair of road cracks, making it difficult to effectively track and repair complex road crack trajectory.

Method used

Adaptive fuzzy control method based on cross entropy is adopted. The mobile robot collects road crack images, extracts feature pixel information points, calculates the lateral pixel error and error change rate, and inputs the fuzzy PID controller for adaptive fuzzy control to achieve the Accurate tracking of road crack trajectories.

Benefits of technology

It improves the robot's tracking effect on road crack trajectory, enhances stability and robustness, realizes efficient visual tracking control, and improves the accuracy and safety of automatic repair.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118915423A_ABST
    Figure CN118915423A_ABST
Patent Text Reader

Abstract

The invention discloses a road crack tracking adaptive fuzzy control method and device based on cross entropy. The method comprises the following steps: acquiring a road crack image by using a mobile robot; obtaining a road crack mask image from the road crack image, extracting feature pixel information points in a road crack set area from the road crack mask image, obtaining transverse pixel errors of the feature pixel information points, and calculating a transverse pixel error change rate through the transverse pixel errors; inputting the transverse pixel error and the transverse pixel error change rate into a fuzzy PID (Proportion Integration Differentiation) controller, modeling the mobile robot, and performing adaptive fuzzy control on the mobile robot; the controlled mobile robot forms an unmanned mobile robot, the unmanned mobile robot carries out road tracking on a road crack track, parameters of a tracking controller are adjusted and optimized by adopting cross entropy optimization iteration, fuzzy logic is constructed to explore improvement of robustness, wide evaluation is carried out in a road crack scene, and the road crack tracking accuracy is improved. And the advanced high-efficiency performance is obtained.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The invention belongs to the technical fields of robot control, motion modeling and crack tracking, and relates to a road crack tracking adaptive fuzzy control method and device based on cross entropy. Background Art

[0002] Roads are the main infrastructure of the transportation industry and play a key role in the operation of the national economy. The maintenance and management of roads is an issue of increasing concern. Cracks are the most common form of pavement disease and threaten road safety. Timely and adequate maintenance can protect the pavement structure and significantly extend the service life of the road. At present, the repair of pavement cracks mainly relies on manual identification and sealing. There are disadvantages such as low maintenance efficiency, low operation accuracy, and great safety hazards. It is easy to affect the normal traffic flow and cause traffic accidents. Therefore, automatic repair of pavement cracks has become an important demand in the road maintenance industry. The geometric characteristics of pavement cracks are relatively complex, the width is generally measured in millimeters, and the characteristics are relatively subtle. Existing pavement crack repairs rarely involve tracking the trajectory of pavement cracks. The automatic repair of pavement cracks puts higher requirements on the tracking of crack trajectories.

[0003] In recent years, autonomous mobile robot (AMR) technology has been widely used in industry and research. Mobile robots are able to move from one site to another while performing complex activities. Software with integrated sensors, such as infrared, ultrasonic, camera, global positioning system (GPS), and magnetic sensors, is used to drive mobile robots. As AGV / AMR technology develops, this technology will be applied. In the field of civil engineering, disease repair is a research trend. AGV / AMR recognition accuracy and algorithm processing seeds are two major issues that need to be studied. Unmanned construction and intelligent disease repair still have challenges. Motion vision recognition and control based on autonomous mobile devices are of great significance to the automatic repair of pavement cracks. Summary of the invention

[0004] The present invention provides a road crack tracking adaptive fuzzy control method and device based on cross entropy, so as to achieve a better tracking effect of the robot for its foot end trajectory and improve its stability and robustness.

[0005] In order to solve the above technical problems, the present invention adopts the following technical solutions:

[0006] The present invention provides a road crack tracking adaptive fuzzy control method based on cross entropy, comprising: using a mobile robot to collect road crack images; obtaining a road crack mask image from the road crack image, extracting characteristic pixel information points in a road crack setting area from the road crack mask image, obtaining the lateral pixel error of the characteristic pixel information point, and calculating the lateral pixel error change rate through the lateral pixel error; inputting the lateral pixel error and the lateral pixel error change rate into a fuzzy PID controller, modeling the mobile robot, and performing adaptive fuzzy control on the mobile robot; the controlled mobile robot constitutes an unmanned mobile robot, and the unmanned mobile robot performs road tracking on the road crack trajectory.

[0007] Furthermore, the mobile robot is modeled using a skid-steering kinematics model to convey the movement of the wheels, each wheel being an independent driving wheel.

[0008] Furthermore, the kinematic model describes its motion by linear velocity and angular velocity;

[0009] The kinematic model is expressed by a virtual equivalent model, which is expressed as follows according to the driving wheel speed:

[0010]

[0011] Where: v c represents the linear velocity of motion, ω c represents the linear velocity of motion, v r represents the right wheel speed of the equivalent model, v l represents the left wheel speed of the equivalent model, d LR Indicates the distance between the left and right wheels of the equivalent model.

[0012] Furthermore, the adaptive fuzzy control uses cross entropy optimization iteration to adjust the parameters of the fuzzy PID controller.

[0013] Furthermore, the parameters of the fuzzy PID controller are:

[0014] K′ P =K P +ΔK P

[0015] K I ′=K I +ΔK I

[0016] K D ′=K D +ΔK D

[0017] Among them, K P , K I , KD are the initial proportional, integral and differential adjustment parameters of the adaptive fuzzy controller, ΔK P , ΔK I , ΔK D are the online adjustment parameters of the controller’s proportion, integration and differentiation, respectively, K P ′,K I ′,K′ D They are the proportional, integral and differential adjustment parameters of the controller output respectively.

[0018] Furthermore, the input parameters of the fuzzy PID controller include error e, error change rate dex, angle θ and angle change rate dθ, and the output of the fuzzy PID controller is ΔK P1 , ΔK I1 , ΔK D1 and ΔK P2 , ΔK I2 , ΔK D2 ; where ΔK P1 , ΔK I1 , ΔK D1 are the online adjustment parameters of the proportion, integration and differentiation of error and error change rate respectively; ΔK P2 , ΔK I2 , ΔK D2 It is the online adjustment parameter of the proportion, integration and differentiation of the angle and the angle change rate.

[0019] Furthermore, the unmanned mobile robot tracks the trajectory of road cracks, including: during the tracking process, the unmanned mobile robot adjusts its position and posture in real time and tracks the cracks.

[0020] The present invention also provides a road crack tracking adaptive fuzzy control device based on cross entropy, including an acquisition module, used to use a mobile robot to collect road crack images; a calculation module, used to obtain a road crack mask image from the road crack image, extract characteristic pixel information points in a set area of ​​the road crack from the road crack mask image, obtain the lateral pixel error of the characteristic pixel information point, and calculate the lateral pixel error change rate through the lateral pixel error; an optimization module, used to input the lateral pixel error and the lateral pixel error change rate into a fuzzy PID controller, model the mobile robot, and perform adaptive fuzzy control on it; an execution module, used to control the mobile robot to form an unmanned mobile robot, and the unmanned mobile robot performs road tracking on the road crack trajectory.

[0021] The present invention also provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. The special feature of the computer device is that when the processor executes the computer program, the steps of any one of the above-mentioned methods for adaptive fuzzy control of road crack tracking based on cross entropy are implemented.

[0022] The present invention also provides a computer-readable storage medium, which stores a computer program, characterized in that when the computer program is executed by a processor, the computer program implements the steps of any of the above-mentioned cross-entropy-based road crack tracking adaptive fuzzy control methods.

[0023] Compared with the prior art, the present invention has the following beneficial technical effects:

[0024] The present invention discloses a cross-entropy based adaptive fuzzy control method for road crack tracking, utilizes an unmanned mobile robot to visually track road cracks, establishes a fuzzy PID controller, integrates visual servoing and tracking control into the system, and achieves efficient performance of visual tracking.

[0025] The present invention discloses a cross-entropy based adaptive fuzzy control method for road crack tracking, which uses cross-entropy optimization iteration to tune the parameters of the tracking controller and constructs fuzzy logic to explore the improvement of robustness. It is widely evaluated in road crack scenarios and achieves advanced and efficient performance. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] Figure 1 A flow chart of a cross-entropy-based adaptive fuzzy control method for road crack tracking according to the present invention;

[0027] Figure 2 is a simplified equivalent schematic diagram of visual tracking of an unmanned mobile robot in an embodiment of the present invention;

[0028] Figure 3 A top view of a camera in an unmanned mobile robot according to an embodiment of the present invention;

[0029] Figure 4 A diagram of the cross entropy optimization process in an embodiment of the present invention;

[0030] Figure 5 This is a working principle diagram of a fuzzy PID controller in an embodiment of the present invention;

[0031] Figure 6 A tracking trajectory diagram of an unmanned mobile robot in an embodiment of the present invention;

[0032] Figure 7 This is a working principle diagram of a road crack tracking adaptive fuzzy control method based on cross entropy of the present invention. DETAILED DESCRIPTION

[0033] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0034] The present invention provides a road crack tracking adaptive fuzzy control method based on cross entropy, combined with Figure 1 , Figure 2 , Figure 3 and Figure 7 ,The method specifically includes using a mobile robot to collect road crack images.

[0035] The mobile robot is a differential drive robot. The four wheels are independent drive wheels, providing strong power and great flexibility. It can adapt to subtle and complex road crack scenes and has stable walking ability. At the same time, the mobile robot needs to be equipped with high-definition cameras, laser scanners or other image acquisition devices with sufficient resolution and sensitivity to capture the subtle features of the road surface, including the shape, size and location of the cracks, and ensure the continuity and stability of image acquisition. The camera on the mobile robot faces downward and is parallel to the ground. The path tracking application uses a 2D Cartesian coordinate system, such as Figure 3 As shown, the inertial system is X F Y F F, coordinate system X of the mobile robot D Y D D is fixed on the mobile robot, the height from the ground is h, and the camera frame is C X C Y C. The mobile robot is considered to be a rigid body with wheels on the ground, using the generalized coordinate vector It is defined as m = [x, y, θ] T ,in is the Cartesian position on the plane, X is the coordinate system of the mobile robot D Y D The x-axis of D is relative to the inertial frame X F Y F The direction of the x-axis of F.

[0036] For road crack identification and tracking, the information that needs to be extracted from the red, green, and blue RGB images captured by the camera is the location of the pixel points of the road cracks when the mobile robot moves. Based on this information, alignment operations can be performed while moving on the road. One way to obtain this information is to use image segmentation techniques and extract the centroid of the region of interest ROI. The ROI is outlined based on the hue saturation value HSV image for further image processing, and this area is the focus of our analysis of the crack characteristics of the acquired image. The ROI focuses on the key target of the road cracks pre-drawn with chalk, thereby reducing processing time and improving accuracy.

[0037] A robust segmentation algorithm that combines the conversion from RGB color space to HSV color space and an image segmentation optimization algorithm based on density filtering. In the HSV model, brightness and color information are separated, while hue and saturation components are closely related to the way people perceive color. To convert the RGB model to the HSV model, first scale the values ​​of the R, G, and B components to a range between 0 and 1, that is, divide by 255. After the conversion, V and S are both between 0 and 1, and H is between 0° and 360°. The calculated result may be less than 0. If it is less than 0, add 360.

[0038] A road crack mask image is obtained from the road crack image, characteristic pixel information points in a set road crack area are extracted from the road crack mask image, lateral pixel errors of the characteristic pixel information points are obtained, and a lateral pixel error change rate is calculated through the lateral pixel errors.

[0039] Specifically, the original RGB image is converted into an HSV image, the road crack features are identified, the surrounding background in the image is separated from the road crack area, and converted into a mask image to obtain the required set area of ​​the road cracks. Finally, the road cracks in the set area are saved, and the set area is 1 / 3 to 2 / 3 of the image height. At the same time, the depth image is processed, the depth value of each pixel in the image is calculated, and the depth point cloud data of the crack pixels is output.

[0040] The lateral pixel error and the lateral pixel error change rate are input into the fuzzy PID controller, the mobile robot is modeled and adaptive fuzzy control is performed on it; meanwhile, the kinematic model describes its motion through linear velocity and angular velocity.

[0041] Specifically, in order to simplify the motion model, two assumptions are made: one is that the wheels of the mobile robot will not spin when rolling; the other is that the center of mass COM is not necessarily located on the geometric horizontal symmetry line, but on the axial symmetry line of the mobile robot. At the same time, the mass distribution of the mobile robot body is uniform, such as Figure 2As shown, the geometric center of the mobile robot is the origin of X-CENTER-Y, and COM is the origin of the coordinate system X-COM-Y. The x-axes of the two coordinate systems coincide, the y-axes are parallel, and the distance from COM to CENTER is dcc. The mobile robot moves forward along the positive x-axis, the positive y-axis is perpendicular to the left, and the positive z-axis is perpendicular to the paper plane, satisfying the right-hand rule, and there is an instantaneous rotation center ICR.

[0042] The motion of the mobile robot is described only by the linear velocity and angular velocity [vc, ωc]T; the angular velocity and linear velocity exist at the position of the COM point along the x-axis, and the ICR is located on the y-axis in the coordinate system X-COM-Y. If the kinematic model is expressed by a virtual equivalent model, the simplified model of the mobile robot is expressed as follows: According to the speed of the virtual left and right driving wheels, the simplified forward kinematic model determines the speed of the geometric COM as:

[0043]

[0044] Among them, v c represents the linear velocity of motion, ω c represents the linear velocity of motion, v r represents the right wheel speed of the equivalent model, v l represents the left wheel speed of the equivalent model, d LR Indicates the distance between the left and right wheels of the equivalent model.

[0045] Then we get:

[0046]

[0047] Adaptive fuzzy control is performed, specifically: the fuzzy PID controller is a two-input three-output system, including two sub-controllers, one for distance and the other for angle, such as Figure 4 , 5 , 6, the input parameters are error e, error change rate dex, angle θ and angle change rate dθ, and the output of the fuzzy PID controller is ΔK P1 , ΔK I1 , ΔK D1 , which are the online adjustment parameters of the proportion, integration, and differentiation of the error and error change rate, and ΔK P2 , ΔK I2 , ΔK D2 , which are the online adjustment parameters of the proportion, integral and differential of the angle and the angle change rate, respectively. The input data is provided to the fuzzification system and suggestions are made. ΔK is adjusted online by the defuzzification system. P1 , ΔK I1 , ΔK D1 and ΔK P2 , ΔK I2 , ΔK D2The output value of the fuzzy PID controller is shown in Figure 1. The membership functions of the fuzzy PID controller input and output are expressed as negative N, zero Z, and positive P. The purpose of these rules is to correct the direction and move the robot to follow the cracks in the road. Finally, the defuzzification process is performed using the centroid method and the PID parameters are output.

[0048] The PID parameters are:

[0049] K P ′=K P +ΔK P

[0050] K I ′=K I +ΔK I

[0051] K′ D =K D +ΔK D

[0052] Where ΔK P , ΔK I and ΔK D It is the setting value generated by the fuzzy PID controller during the operation of the mobile robot. The initial parameter K P , K I , K D , are the initial proportional, integral, and differential adjustment parameters of the adaptive fuzzy controller, respectively. The adaptive fuzzy control is to find the minimum φ on χ, and let φ be a real function on χ. Then x* satisfies the minimum value: γ*=φ(x*)=minx∈χ|φ(x). In each iteration, a sequence of (x1,x2,...xN) and (γ1,γ2,...γN) is generated so that γ converges to γ* and x converges to x*, and the probability l(γ) of the event Ev={x∈χ|φ(x)≥γ} is estimated.

[0053] Image center coordinates and mobile robot X D Y D D) The error between the center points is ex; dex is the change between the current error and the previous error; θ is X D Y D The x-axis of D is relative to the inertial frame X F Y F The direction of the x-axis of F; dθ is the change between the current θ and the previous θ. ΔKP, ΔKI and ΔKD are adjusted through fuzzy logic.

[0054] The controlled mobile robot constitutes an unmanned mobile robot, and the unmanned mobile robot performs road tracking on the trajectory of the road crack.

[0055] The Intel RealSense D435i camera provides raw data and depth images to the mobile robot, helping it detect and classify objects in the work area. The mobile robot uses various sensors to collect information about the surrounding environment. The encoder converts the displacement and angle changes into photoelectric pulses or digital signals through photoelectric conversion, which are used to measure displacement, speed, and acceleration.

[0056] It uses ROS based on Linux environment, provides services that can be used to control various series of robots, and enhances the ability to interact with different environments according to specific tasks. It has good compatibility with Ubuntu18.04 and is configured with ROS robot software environment based on Linux system Ubuntu18.04. The source code is written, compiled and debugged in C++ and Python.

[0057] Furthermore, the channel for the mobile robot to run the ROS client is formed by the ROS master node, which is configured on the fuzzy PID controller. ROS nodes can subscribe and publish topics to other ROS nodes at the same time. The control node publishes the speed topic / cmd_vel to the processing node, and the robot chassis subscribes to the speed topic to drive four brushless motors to control VT-UMbot to track road cracks. The control system and the robot four-wheel differential chassis use a control navigation CAN to universal serial bus USB serial communication module to facilitate communication between the upper and lower computers. A Huawei wireless router is used to communicate with the control system.

[0058] Fuzzification is the process of converting the determined value of the input quantity of the fuzzy PID controller into the corresponding fuzzy language variable value, and the fuzzy language variable value is a fuzzy set. The membership value of the precise input quantity to each language value is used as the fuzzification result through the triangular membership function. The control experience knowledge of the operator or field expert is expressed in the form of rules described in language, and the rule base constituting the fuzzy control system is compared. After knowing the fuzzy relationship implied in the language control rule, the output situation can be determined based on the fuzzy relationship and input situation. It transforms the fuzzy set of the input variable into the fuzzy set of the output variable, and then makes inferences.

[0059] The present invention also provides a road crack tracking adaptive fuzzy control device based on cross entropy, including: an acquisition module, used to use a mobile robot to acquire road crack images; a calculation module, used to obtain a road crack mask image from the road crack image, extract characteristic pixel information points within a set area of ​​the road crack from the road crack mask image, obtain the lateral pixel error of the characteristic pixel information point, and calculate the lateral pixel error change rate through the lateral pixel error; an optimization module, used to input the lateral pixel error and the lateral pixel error change rate into a fuzzy PID controller, model the mobile robot, and perform adaptive fuzzy control on it; an execution module, used to control the mobile robot to form an unmanned mobile robot, and the unmanned mobile robot performs road tracking on the road crack trajectory.

[0060] It should be noted that the road crack tracking adaptive fuzzy control device based on cross entropy provided by the present invention can implement method steps consistent with the above method, so it will not be repeated here.

[0061] The present invention also provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. The special feature of the computer device is that when the processor executes the computer program, the steps of a road crack tracking adaptive fuzzy control method based on cross entropy described in any one of the above embodiments are implemented.

[0062] In another embodiment of the present invention, a terminal device is provided, the terminal device includes a processor and a memory, the memory is used to store a computer program, the computer program includes program instructions, and the processor is used to execute the program instructions stored in the computer storage medium. The processor may be a central processing unit Central Processing Unit, CPU, or other general-purpose processors, digital signal processors Digital Signal Processor, DSP, Application Specific Integrated Circuit Application Specific Integrated Circuit, ASIC, Field-Programmable Gate Array Field-Programmable Gate Array, FPGA or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, etc., which is the computing core and control core of the terminal, which is suitable for implementing one or more instructions, and is specifically suitable for loading and executing one or more instructions to implement the corresponding method flow or corresponding function.

[0063] The present invention also provides a computer-readable storage medium, which stores a computer program, characterized in that when the computer program is executed by a processor, the computer program implements the steps of a road crack tracking adaptive fuzzy control method based on cross entropy described in any one of the above embodiments.

[0064] In another embodiment of the present invention, the present invention also provides a storage medium, specifically a computer-readable storage medium Memory, which is a memory device in a terminal device for storing programs and data. It can be understood that the computer-readable storage medium here can include both the built-in storage medium in the terminal device and the extended storage medium supported by the terminal device. The computer-readable storage medium provides a storage space, which stores the operating system of the terminal. In addition, one or more instructions suitable for being loaded and executed by the processor are also stored in the storage space. These instructions can be one or more computer programs including program codes. It should be noted that the computer-readable storage medium here can be a high-speed RAM memory, or a non-volatile memory, such as at least one disk memory. The processor can load and execute one or more instructions stored in the computer-readable storage medium to implement the corresponding steps of the method for collaborative control of intelligent connected vehicles in the scenario of unsignalized intersections in the above-mentioned embodiment.

[0065] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media including but not limited to disk storage, CD-ROM, optical storage, etc., which contain computer-usable program codes.

[0066] The present application is described with reference to the flowcharts and / or block diagrams of the methods, device systems, and computer program products according to the embodiments of the present application. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of the processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0067] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0068] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0069] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

Claims

1. A road crack tracking adaptive fuzzy control method based on cross entropy, characterized in that: include: Using mobile robots to collect road crack images; Obtaining a road crack mask image from the road crack image, extracting characteristic pixel information points in a set road crack area from the road crack mask image, obtaining a lateral pixel error of the characteristic pixel information point, and calculating a lateral pixel error change rate through the lateral pixel error; Inputting the lateral pixel error and the lateral pixel error change rate into a fuzzy PID controller, modeling the mobile robot, and performing adaptive fuzzy control on it; The controlled mobile robot constitutes an unmanned mobile robot, and the unmanned mobile robot performs road tracking on the trajectory of the road crack.

2. The cross entropy-based adaptive fuzzy control method for road crack tracking according to claim 1, characterized in that: The mobile robot is modeled using a skid-steering kinematics model to convey the movement of the wheels, each of which is an independent driving wheel.

3. The cross-entropy based adaptive fuzzy control method for road crack tracking according to claim 2, characterized in that: The kinematic model describes its motion by linear velocity and angular velocity; The kinematic model is expressed by a virtual equivalent model, which is expressed as follows according to the driving wheel speed: Where: v c represents the linear velocity of motion, ω c represents the linear velocity of motion, v r represents the right wheel speed of the equivalent model, v l represents the left wheel speed of the equivalent model, d LR Indicates the distance between the left and right wheels of the equivalent model.

4. The cross-entropy based adaptive fuzzy control method for road crack tracking according to claim 3 is characterized by: The adaptive fuzzy control uses cross entropy optimization iteration to adjust the parameters of the fuzzy PID controller.

5. The cross-entropy based adaptive fuzzy control method for road crack tracking according to claim 4, characterized in that: The parameters of the fuzzy PID controller are: K P ′=K P +ΔK P K I ′=K I +ΔK I K D ′=K D +ΔK D Among them, K P , K I , K D are the initial proportional, integral and differential adjustment parameters of the adaptive fuzzy controller, ΔK P , ΔK I , ΔK D are the online adjustment parameters of the controller’s proportion, integration and differentiation, respectively, K′ P , K′ I , K′ D They are the proportional, integral and differential adjustment parameters of the controller output respectively.

6. The cross-entropy based adaptive fuzzy control method for road crack tracking according to claim 5, characterized in that: The input parameters of the fuzzy PID controller include error e, error change rate dex, angle θ and angle change rate dθ. The output of the fuzzy PID controller is ΔK P1 , ΔK I1 , ΔK D1 and ΔK P2 , ΔK I2 , ΔK D2 ; Among them, ΔK P1 , ΔK I1 , ΔK D1 are the online adjustment parameters of the proportion, integration and differentiation of error and error change rate respectively; ΔK P2 , ΔK I2 , ΔK D2 It is the online adjustment parameter of the proportion, integration and differentiation of the angle and the angle change rate.

7. The cross-entropy based adaptive fuzzy control method for road crack tracking according to claim 6, characterized in that: The unmanned mobile robot tracks the crack trajectory on the road, including: during the tracking process, the unmanned mobile robot adjusts its position and posture in real time and tracks the crack.

8. A road crack tracking adaptive fuzzy control device based on cross entropy, characterized in that: include: A collection module, used for collecting road crack images using a mobile robot; A calculation module is used to obtain a road crack mask image from a road crack image, extract characteristic pixel information points in a set road crack area from the road crack mask image, obtain a lateral pixel error of the characteristic pixel information point, and calculate a lateral pixel error change rate through the lateral pixel error; an optimization module, for inputting the lateral pixel error and the lateral pixel error change rate into a fuzzy PID controller, modeling the mobile robot, and performing adaptive fuzzy control on the mobile robot; The execution module is used to control the mobile robot to form an unmanned mobile robot, and the unmanned mobile robot tracks the trajectory of the road crack.

9. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the road crack tracking adaptive fuzzy control method based on cross entropy are implemented as described in any one of claims 1 to 7.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the road crack tracking adaptive fuzzy control method based on cross entropy as described in any one of claims 1 to 7 are implemented.