Semitrailer parking control method and apparatus, and storage medium and computer device

Abstract

The present application relates to the technical field of automatic control. Disclosed are a semitrailer parking control method and apparatus, and a storage medium and a computer device, which mainly can improve the tractor-semitrailer towing dolly-semitrailer parking efficiency and safety. The method comprises: acquiring real-time towing status data of a towing apparatus that corresponds to a semitrailer to be controlled, real-time dolly status data of a semitrailer towing dolly that corresponds to said semitrailer, and real-time semitrailer status data that corresponds to said semitrailer, wherein the towing apparatus is connected to the semitrailer towing dolly, the semitrailer towing dolly is connected to said semitrailer, and by means of the semitrailer towing dolly, the towing apparatus tows said semitrailer; on the basis of the real-time towing status data, the real-time dolly status data and the real-time semitrailer status data, determining a driving strategy for the towing apparatus at the next moment; and on the basis of the driving strategy, performing parking control on said semitrailer.

Description

Semi-trailer parking control methods, devices, storage media and computer equipment

[0001] This application claims priority to Chinese Patent Application No. 202410495399.9, filed on April 24, 2024, entitled “Semi-trailer parking control method, apparatus, storage medium and computer equipment”, the entire contents of which are incorporated herein by reference. Technical Field

[0002] This application relates to the field of automatic control technology, and in particular to a semi-trailer parking control method, device, storage medium and computer equipment. Background Technology

[0003] With the continuous development of society, more and more transportation businesses need to use tractor-trailer tractor-trailer-semi-trailers. Due to the complex shape of the tractor-trailer tractor-trailer-semi-trailer, parking has become an urgent problem to be solved.

[0004] Currently, parking is typically done manually using a tractor-trailer-towing platform-semi-trailer. However, due to varying driving skills, this often results in repeated attempts to park, reducing parking efficiency. Furthermore, driver negligence can cause the tractor-trailer-towing platform-semi-trailer to fold and become unstable during parking, leading to lower safety.

[0005] Application content

[0006] This application provides a semi-trailer parking control method, device, storage medium, and computer equipment, mainly to improve the parking efficiency and safety of the tractor-semi-trailer tractor-semi-trailer.

[0007] According to the first aspect of this application, a semi-trailer parking control method is provided, comprising:

[0008] The system acquires real-time traction status data of the traction device corresponding to the semi-trailer to be controlled, real-time platform status data of the semi-trailer to be controlled, and real-time semi-trailer status data corresponding to the semi-trailer to be controlled. The traction device is connected to the semi-trailer to be controlled, the semi-trailer to be controlled is connected to the semi-trailer to be controlled, and the traction device tows the semi-trailer to be controlled through the semi-trailer to be controlled.

[0009] Based on the real-time traction status data, the real-time trailer status data, and the real-time semi-trailer status data, the driving strategy of the traction device at the next moment is determined;

[0010] Based on the driving strategy, parking control is performed on the semi-trailer to be controlled.

[0011] Optionally, determining the driving strategy of the traction device at the next moment based on the real-time traction status data, the real-time trailer status data, and the real-time semi-trailer status data includes:

[0012] The real-time traction status data, the real-time trailer status data, and the real-time semi-trailer status data are input into a preset path tracking control model to predict the driving strategy and obtain the first driving strategy.

[0013] The real-time traction status data, the real-time trailer status data, and the real-time semi-trailer status data are input into a preset secondary controller for driving strategy prediction to obtain a second driving strategy;

[0014] Based on the first driving strategy and the second driving strategy, the driving strategy of the traction device at the next moment is determined.

[0015] Optionally, before inputting the real-time traction status data, the real-time trailer status data, and the real-time semi-trailer status data into a preset path tracking control model for driving strategy prediction to obtain a first driving strategy, the method further includes:

[0016] The sample traction status data of the sample traction device corresponding to the sample semi-trailer, the sample trailer status data of the sample semi-trailer traction platform corresponding to the sample semi-trailer, and the sample semi-trailer status data corresponding to the sample semi-trailer are used as sample independent variables, and the front wheel rotation angle of the sample traction device is used as the sample dependent variable. A preset path tracking control model is constructed using a preset speed decomposition algorithm.

[0017] Before inputting the real-time traction status data, the real-time trailer status data, and the real-time semi-trailer status data into a preset secondary controller for driving strategy prediction to obtain a second driving strategy, the method further includes:

[0018] The parking path corresponding to the sample semi-trailer is tracked and controlled using a preset activation set algorithm to obtain the predicted independent and dependent variables of the semi-trailer to be controlled during the parking process.

[0019] An error function for parking uncertainty is constructed centered on the predicted independent variable and the predicted dependent variable, and a preset secondary controller is constructed based on the error function.

[0020] Optionally, the step of using the sample traction state data of the sample traction device corresponding to the sample semi-trailer, the sample trailer state data of the sample semi-trailer traction platform corresponding to the sample semi-trailer, and the sample semi-trailer state data corresponding to the sample semi-trailer as sample independent variables, and the front wheel angle of the sample traction device as the sample dependent variable, and constructing a preset path tracking control model using a preset speed decomposition algorithm includes:

[0021] The sample traction state data of the sample traction device corresponding to the sample semi-trailer, the sample trailer state data of the sample semi-trailer traction platform corresponding to the sample semi-trailer, and the sample semi-trailer state data corresponding to the sample semi-trailer are used as the sample independent variables, and the front wheel rotation angle of the sample traction device is used as the sample dependent variable to construct the kinematic equation of traction device-semi-trailer traction platform-semi-trailer.

[0022] The kinematic equations are decomposed into velocity equations using a preset velocity decomposition method.

[0023] The velocity decomposition equation is discretized using a pre-defined fourth-order Runge-Kutta integral discretization algorithm to obtain the discretized equation.

[0024] Based on the discretized equations, a preset path tracking control model is constructed.

[0025] Optionally, the step of using a preset activation set algorithm to track and control the parking path corresponding to the sample semi-trailer, and obtaining the predicted independent and dependent variables of the semi-trailer to be controlled during the parking process, includes:

[0026] The parking path corresponding to the sample semi-trailer is tracked and controlled using a preset activation set algorithm to obtain the path tracking control function;

[0027] The path tracking control function is expanded within a preset neighborhood range using a preset expansion algorithm to obtain the expanded tracking control function;

[0028] Based on the aforementioned expanded tracking control function, the predictive independent variables and predictive dependent variables in the semi-trailer parking control process are determined;

[0029] The construction of the error function for parking uncertainty centered on the predicted independent variable and the predicted dependent variable includes:

[0030] Based on the predicted independent variable and the predicted dependent variable, a nominal kinematic equation is constructed;

[0031] Based on the nominal kinematic equations, an error function for parking uncertainty is constructed.

[0032] Optionally, the first driving strategy is the first front wheel angle and the first front wheel steering of the traction device at the next moment, and the second driving strategy is the second front wheel angle and the second front wheel steering of the traction device at the next moment; determining the driving strategy of the traction device at the next moment based on the first driving strategy and the second driving strategy includes:

[0033] Determine the first weighting coefficient corresponding to the first front wheel steering angle and the second weighting coefficient corresponding to the second front wheel steering angle;

[0034] Taking the preset direction as positive, based on the first weighting coefficient, the second weighting coefficient, the first front wheel steering, and the second front wheel steering, the first front wheel angle and the second front wheel angle are added together to obtain the planned front wheel angle and the planned front wheel steering of the traction device at the next moment.

[0035] Optionally, the step of parking control of the semi-trailer to be controlled based on the driving strategy includes:

[0036] Based on the planned front wheel angle and planned front wheel steering, a control command for the front wheel rotation of the traction device is generated;

[0037] Based on the front wheel rotation control command, the angle control and steering control of the front wheel of the traction device are executed to achieve parking control of the semi-trailer to be controlled.

[0038] According to a second aspect of this application, a semi-trailer parking control device is provided, comprising:

[0039] The acquisition unit is used to acquire real-time traction status data of the traction device corresponding to the semi-trailer to be controlled, real-time platform status data of the semi-trailer towing platform corresponding to the semi-trailer to be controlled, and real-time semi-trailer status data corresponding to the semi-trailer to be controlled. The traction device is connected to the semi-trailer towing platform, the semi-trailer towing platform is connected to the semi-trailer to be controlled, and the traction device tows the semi-trailer to be controlled through the semi-trailer towing platform.

[0040] The determining unit is used to determine the driving strategy of the traction device at the next moment based on the real-time traction status data, the real-time trailer status data, and the real-time semi-trailer status data.

[0041] The control unit is used to perform parking control on the semi-trailer to be controlled based on the driving strategy.

[0042] According to a third aspect of this application, a computer-readable storage medium is provided, on which a computer program is stored, which, when executed by a processor, implements the above-described semi-trailer parking control method.

[0043] According to a fourth aspect of this application, a computer device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the above-described semi-trailer parking control method.

[0044] According to the semi-trailer parking control method, device, storage medium, and computer equipment provided in this application, compared with the current method of parking by manually controlling the tractor-semi-trailer traction platform-semi-trailer, this application obtains real-time traction status data of the traction device corresponding to the semi-trailer to be controlled, real-time platform status data of the semi-trailer traction platform corresponding to the semi-trailer to be controlled, and real-time semi-trailer status data corresponding to the semi-trailer to be controlled. The traction device is connected to the semi-trailer traction platform, and the semi-trailer traction platform is connected to the semi-trailer to be controlled. The traction device pulls the semi-trailer to be controlled through the semi-trailer traction platform. Then, based on the real-time traction status data, real-time platform status data, and real-time platform status data, the method, device, storage medium, and computer equipment provided in this application, the method, device, storage medium, and computer equipment control semi-trailer parking ... The semi-trailer status data is used to determine the driving strategy of the traction device in the next moment. Finally, based on the driving strategy, parking control is performed on the semi-trailer to be controlled. By using the real-time traction status data of the traction device, the real-time towing platform status data of the traction platform, and the real-time semi-trailer status data of the semi-trailer to be controlled, the driving strategy of the traction device in the next moment is automatically calculated. Finally, parking control is performed on the semi-trailer to be controlled according to the driving strategy. This can avoid the time wasted by manually controlling the parking of the tractor-semi-trailer traction platform-semi-trailer, thereby improving the parking efficiency of the tractor-semi-trailer traction platform-semi-trailer. At the same time, it can also avoid the folding and instability caused by manual parking, thereby improving parking safety. Attached Figure Description

[0045] The accompanying drawings, which are included to provide a further understanding of this application and form part of this application, illustrate exemplary embodiments of this application and are used to explain this application, but do not constitute an undue limitation of this application. In the drawings:

[0046] Figure 1 shows a flowchart of a semi-trailer parking control method provided in an embodiment of this application;

[0047] Figure 2 shows a flowchart of another semi-trailer parking control method provided in an embodiment of this application;

[0048] Figure 3 illustrates a schematic diagram of the process of constructing the kinematic equations of a tractor-semi-trailer tractor-semi-trailer according to an embodiment of this application;

[0049] Figure 4 shows a speed decomposition diagram of the connection point between the tractor-semi-trailer tractor platform-semi-trailer provided in an embodiment of this application.

[0050] Figure 5 shows a schematic diagram of a semi-trailer parking control device provided in an embodiment of this application;

[0051] Figure 6 shows a schematic diagram of another semi-trailer parking control device provided in an embodiment of this application;

[0052] Figure 7 shows a schematic diagram of the physical structure of a computer device provided in an embodiment of this application. Detailed Implementation

[0053] The present application will be described in detail below with reference to the accompanying drawings and embodiments. It should be noted that, unless otherwise specified, the embodiments and features described in the embodiments of the present application can be combined with each other.

[0054] Currently, the method of parking by manually controlling the tractor-semi-trailer tractor-trailer-semi-trailer results in repeated attempts to park, thus reducing the parking efficiency of the tractor-semi-trailer tractor-trailer-semi-trailer system.

[0055] To address the aforementioned problems, this application provides a semi-trailer parking control method, as shown in Figure 1. The method includes:

[0056] 101. Obtain real-time traction status data of the traction device corresponding to the semi-trailer to be controlled, real-time platform status data of the semi-trailer towing platform corresponding to the semi-trailer to be controlled, and real-time semi-trailer status data corresponding to the semi-trailer to be controlled. The traction device is connected to the semi-trailer towing platform, the semi-trailer towing platform is connected to the semi-trailer to be controlled, and the traction device tows the semi-trailer to be controlled through the semi-trailer towing platform.

[0057] The traction device can be a tractor vehicle; real-time traction status data refers to: the real-time coordinates of the midpoint of the rear axle of the traction device in the geodetic coordinate system, the real-time yaw angle of the traction device, the real-time front wheel rotation angle of the traction device, the real-time distance from the center of the front axle to the center of the rear axle of the traction device, the real-time angle between the traction device and the semi-trailer traction platform, and the real-time distance from the midpoint of the rear axle of the traction device to the articulation point; real-time platform status data refers to: the real-time coordinates of the center point of the traction seat of the semi-trailer traction platform in the geodetic coordinate system, the real-time yaw angle of the semi-trailer traction platform, and the real-time distance from the articulation point to the center point of the traction seat of the semi-trailer traction platform; real-time semi-trailer status data refers to: the real-time coordinates of the midpoint of the rear axle of the semi-trailer in the geodetic coordinate system, the real-time yaw angle of the semi-trailer, the real-time angle between the semi-trailer traction platform and the semi-trailer, and the real-time distance from the center point of the traction seat of the semi-trailer traction platform to the midpoint of the rear axle of the semi-trailer.

[0058] In this embodiment, a parking control system is used to park a semi-trailer. The parking control system includes a perception fusion module, a local map rasterization module, a reversing parking path planning module, and a reversing parking path tracking control module. The perception fusion module outputs environmental information, real-time traction status data, real-time trailer status data, and real-time semi-trailer status data detected by multiple sensors including ultrasonic waves, lidar, and cameras. It also inputs the environmental information into the local map rasterization module. The local map rasterization module uses a raster scanning algorithm to convert the environmental information of the tractor-semi-trailer-trailer-towing platform into a local raster map. The reversing parking path planning module then uses the raster map as the basis for its operation. The system uses a map, real-time traction status data, real-time trailer status data, and real-time semi-trailer status data to plan a reversing parking path. The reversing parking path tracking and control module then controls the reversing parking of the tractor-semi-trailer-trailer platform based on the planned path. By using real-time traction status data, trailer status data, and semi-trailer status data, the system automatically calculates the traction device's driving strategy for the next moment. Finally, based on this strategy, the system controls the parking of the semi-trailer, avoiding the time wasted on manual parking and improving parking efficiency. This application embodiment is mainly applicable to scenarios involving parking control of tractor-semi-trailer platform-semi-trailer. The executing entity in this application embodiment is a device or equipment capable of parking control of tractor-semi-trailer platform-semi-trailer, which can be located on a server side.

[0059] 102. Based on real-time traction status data, real-time trailer status data, and real-time semi-trailer status data, determine the driving strategy of the traction device in the next moment.

[0060] The driving strategy at the next moment refers to the front wheel angle and steering of the traction device at the next moment.

[0061] In the embodiments of this application, a preset path tracking control model and a predictive secondary controller are first established. The conversion value of real-time traction status data, real-time trailer status data, and real-time semi-trailer status data are predicted using the path tracking control model and the preset secondary controller, respectively, to obtain a first driving strategy and a second driving strategy. Finally, based on the first and second driving strategies, the driving strategy of the traction device at the next moment is determined so that parking control of the semi-trailer to be controlled can be performed according to the driving strategy at the next moment. Thus, by using the preset path tracking control model and the predictive secondary controller to predict the driving strategy, the prediction accuracy and efficiency of the driving strategy can be improved, thereby improving the accuracy and efficiency of parking control of the tractor-semi-trailer traction trailer-semi-trailer.

[0062] 103. Based on the driving strategy, perform parking control on the semi-trailer to be controlled.

[0063] For example, in the embodiments of this application, if the predicted driving strategy of the traction device in the next moment is: the front wheels of the traction device turn left at an angle of 30°, then the traction device is ultimately controlled based on the steering and angle of the front wheels of the traction device to achieve parking control of the tractor-semi-trailer tractor-trailer. Thus, by using the real-time traction status data of the traction device, the real-time tractor status data of the tractor, and the real-time semi-trailer status data of the semi-trailer to be controlled, the driving strategy of the traction device in the next moment is automatically calculated. Finally, based on this driving strategy, parking control of the semi-trailer to be controlled is performed, avoiding the time wasted by manually controlling the parking of the tractor-semi-trailer tractor-trailer, thereby improving the parking efficiency of the tractor-semi-trailer tractor-trailer.

[0064] According to the semi-trailer parking control method provided in this application, compared with the current method of parking by manually controlling the tractor-semi-trailer tractor-trailer platform, this application obtains real-time traction status data of the traction device corresponding to the semi-trailer to be controlled, real-time platform status data of the semi-trailer tractor corresponding to the semi-trailer to be controlled, and real-time semi-trailer status data, wherein the traction device is connected to the semi-trailer tractor platform, the semi-trailer tractor platform is connected to the semi-trailer to be controlled, and the traction device pulls the semi-trailer to be controlled through the semi-trailer tractor platform; then, based on the real-time traction status data, the real-time platform status data, and the real-time semi-trailer status data... The system determines the driving strategy of the traction device in the next moment; and finally, based on the driving strategy, it performs parking control on the semi-trailer to be controlled. This is achieved by automatically calculating the driving strategy of the traction device in the next moment using real-time traction status data of the traction device, real-time towing platform status data of the traction platform, and real-time semi-trailer status data of the semi-trailer to be controlled. This avoids the time wasted by manually controlling the traction vehicle-semi-trailer traction platform-semi-trailer parking, thus improving the parking efficiency of the traction vehicle-semi-trailer traction platform-semi-trailer system. Simultaneously, it avoids the folding and instability caused by manual parking, thereby improving parking safety.

[0065] Furthermore, to better illustrate the above data classification process, as a refinement and extension of the above embodiments, this application provides another semi-trailer parking control method, as shown in Figure 2. The method includes:

[0066] 201. Obtain real-time traction status data of the traction device corresponding to the semi-trailer to be controlled, real-time platform status data of the semi-trailer towing platform corresponding to the semi-trailer to be controlled, and real-time semi-trailer status data corresponding to the semi-trailer to be controlled. The traction device is connected to the semi-trailer towing platform, the semi-trailer towing platform is connected to the semi-trailer to be controlled, and the traction device tows the semi-trailer to be controlled through the semi-trailer towing platform.

[0067] Specifically, real-time traction status data of the traction device corresponding to the semi-trailer to be controlled, real-time towing platform status data of the semi-trailer to be controlled, and real-time semi-trailer status data can be obtained through measuring instruments such as sensors. Then, parking control of the semi-trailer to be controlled can be realized based on the above real-time status data.

[0068] 202. Input the real-time traction status data, real-time trailer status data, and real-time semi-trailer status data into the preset path tracking control model to predict the driving strategy and obtain the first driving strategy.

[0069] In this embodiment of the application, in order to improve the prediction accuracy of the model, it is first necessary to train and construct a preset path tracking control model. Based on this, the method includes: taking the sample traction state data of the sample traction device corresponding to the sample semi-trailer, the sample trailer state data of the sample semi-trailer traction platform corresponding to the sample semi-trailer, and the sample semi-trailer state data corresponding to the sample semi-trailer as sample independent variables, and the front wheel rotation angle of the sample traction device as the sample dependent variable, and constructing a preset path tracking control model using a preset speed decomposition algorithm. The specific process of constructing a preset path tracking control model using a preset velocity decomposition algorithm includes: using sample traction state data of the sample traction device corresponding to the sample semi-trailer, sample trailer state data of the sample semi-trailer traction platform corresponding to the sample semi-trailer, and sample semi-trailer state data corresponding to the sample semi-trailer as sample independent variables, and the front wheel rotation angle of the sample traction device as the sample dependent variable, to construct the kinematic equations of the traction device-semi-trailer traction platform-semi-trailer; using the preset velocity decomposition method to perform velocity decomposition on the kinematic equations to obtain velocity decomposition equations; using the preset fourth-order Runge-Kutta integral discretization algorithm to discretize the velocity decomposition equations to obtain discretized equations; and constructing a preset path tracking control model based on the discretized equations.

[0070] Specifically, firstly, the sample traction state data of the sample traction device corresponding to the sample semi-trailer, the sample trailer state data of the sample semi-trailer traction platform corresponding to the sample semi-trailer, and the sample semi-trailer state data corresponding to the sample semi-trailer are used as sample independent variables, and the front wheel rotation angle of the sample traction device is used as the sample dependent variable. A kinematic equation for the traction device-semi-trailer traction platform-semi-trailer is constructed. Based on this kinematic equation, a functional relationship between the traction device speed and the semi-trailer speed is established using a preset velocity decomposition method, resulting in a velocity decomposition equation. This velocity decomposition equation is then discretized. Finally, based on the discretized equation, a preset path tracking control model is constructed, using data such as the semi-trailer rear axle midpoint coordinates and yaw angle, the angle between the traction device and the semi-trailer traction platform, and the angle between the semi-trailer traction platform and the semi-trailer as independent variables, and the front wheel rotation angle and steering of the traction device as dependent variables. The specific formula for constructing the preset path tracking control model is shown below:

[0071] Wherein, if the sample traction state data is: the coordinates of the midpoint of the rear axle of the sample traction device in the geodetic coordinate system OXY are (x1, y1), the yaw angle of the sample traction device is θ1, the distance from the midpoint of the rear axle of the sample traction device to the hinge point is M1, the front wheel rotation angle of the sample traction device is δ, the angle between the sample traction device and the sample semi-trailer traction platform is β1, and the distance from the center of the front axle to the center of the rear axle of the sample tractor is L1, and the sample trailer platform state data is: the coordinates of the center point of the traction seat of the sample semi-trailer traction platform in the geodetic coordinate system OXY are (x2, y2), the yaw angle of the sample semi-trailer traction platform ... to the hinge point is M1, the front wheel rotation angle of the sample traction device is δ, the angle between the sample traction device and the sample semi-trailer traction platform is β1, and the distance from the center of the front axle to the center of the rear axle is L1, and the sample trailer platform state data is: the coordinates of the center point of the traction seat of the sample semi The angle is θ2, the angle between the sample semi-trailer tractor and the sample semi-trailer is β2, the distance from the center point of the tractor seat of the sample semi-trailer tractor to the midpoint of the rear axle of the sample semi-trailer is L3, the distance from the hinge point p1 to the center point p2 of the tractor seat of the sample semi-trailer tractor is L2, and the state data of the sample semi-trailer are: the coordinates of the midpoint of the rear axle of the sample semi-trailer in the geodetic coordinate system OXY are (x3, y3), and the yaw angle of the sample semi-trailer is θ3. Then the kinematic equation of the tractor-semi-trailer tractor-semi-trailer can be described as shown in the following formula (1): The process of constructing the kinematic equation is shown in Figure 3:

[0072] Where v1 represents the speed of the sample traction device, v2 represents the speed of the hinge point p1, and v3 represents the speed of the center point p2 of the traction seat of the sample semi-trailer traction platform, as shown in Figure 4. Applying the velocity decomposition method to the hinge point P1 and the center point P2 of the traction seat of the sample semi-trailer traction platform, we can obtain the following formula (2):

[0073] Where v2 represents the velocity of hinge point p1, and v3 represents the velocity of the center point p2 of the towing seat of the sample semi-trailer traction platform. Further, by further refining the above formula (2), we can obtain

[0074] Substituting equation (3) into equation (1), we obtain the following velocity decomposition equation (4):

[0075] Define the independent variables of the system samples as x = [y3 θ3 β1 β2] T If the dependent variable of the sample is u=[δ], then equation (4) can be simplified to the velocity decomposition equation (5) as shown: y=f(x,u) (5)

[0076] Where y and f() represent the functional relationship between the sample independent variable and the sample dependent variable. Furthermore, by using the pre-set fourth-order Runge-Kutta integral discretization equation (5), the discretization equation can be obtained as shown in formula (6):

[0077] Where h represents the computational step size of the discretization equation, K1, K2, K3, and K4 are the discretization coefficients in the discretization equation, and x k The independent variables at time k during the parking control process include: sample traction state data, sample trailer state data, and sample semi-trailer state data, u. k The dependent variable at time k during the parking control process is the front wheel steering angle of the traction device, x. k+1 The independent variables at time k+1, h, and K1, K2, K3, and K4 can be expressed as shown in the following formula (7):

[0078] Among them, t f Let N represent the prediction time for parking predictive control, and N represent the number of discrete points on the parking path. Further, based on the above formulas, the preset path tracking control model for the tractor-semi-trailer tractor-semi-trailer is established as follows:

[0079] Where x*,u* represents the calculation formula for the driving strategy in the preset path tracking control model, that is, x*,u* represents the first driving strategy calculated by the preset path tracking control model, p N (x N ), p k (x k ) and q k (u k This can be expressed as the following formula: p N (x N )=(x N -x N,ref ) T Q N (x N -x N,ref (9) p k (x k)=(x k -x k,ref ) T Q k (x k -x k,ref (10)

[0080] In the formula, x k,ref k = 0, 1, ..., N are the reference values ​​for the independent variables, i.e., the reference values ​​for real-time traction status data, real-time trailer status data, and real-time semi-trailer status data; N is the total number of real-time status data; k is the k-th real-time status data; x k This represents the actual values ​​of real-time traction status data, real-time trailer status data, and real-time semi-trailer status data, x. N，ref x represents the standardized value of real-time traction status data, real-time trailer status data, and real-time semi-trailer status data. N This represents the previous value of the real-time traction status data, real-time trailer status data, and real-time semi-trailer status data. k Q represents the front wheel steering angle of the traction device at time k. n Let Q represent the weight matrix of the independent variables at time n. k R represents the weight matrix of the independent variables at time k. k Let u represent the dependent variable weight matrix at time k. k Let x represent the dependent variable (the front wheel angle of the traction device) at time k. start Let x represent the independent variable at the initial time. k+1 Let represent the independent variable at time k+1.

[0081] Therefore, through the above formulas (1)-(7), the prediction formula (8) of the driving strategy in the preset path tracking control model can be derived, and finally the first driving strategy of the traction device can be predicted through the preset path tracking control model.

[0082] 203. Input the real-time traction status data, real-time trailer status data, and real-time semi-trailer status data into the preset secondary controller to predict the driving strategy and obtain the second driving strategy.

[0083] In this embodiment of the application, in order to improve the prediction accuracy of the preset secondary controller, it is first necessary to train and construct the preset secondary controller. Based on this, the method includes: using a preset activation set algorithm to track and control the parking path corresponding to the sample semi-trailer, and obtaining the predicted independent variable and predicted dependent variable of the semi-trailer to be controlled during the parking process; constructing an error function of parking uncertainty with the predicted independent variable and the predicted dependent variable as the center, and constructing the preset secondary controller based on the error function. The process of determining the predicted independent and dependent variables of the semi-trailer to be controlled during parking includes: using a preset activation set algorithm to track and control the parking path corresponding to the sample semi-trailer to obtain a path tracking control function, wherein the path tracking control function is expanded within a preset neighborhood using a preset expansion algorithm to obtain an expanded tracking control function; based on the expanded tracking control function, determining the predicted independent and dependent variables in the semi-trailer parking control process, wherein the process of constructing an error function of parking uncertainty centered on the predicted independent and dependent variables includes: constructing a nominal kinematic equation based on the predicted independent and dependent variables; and constructing an error function of parking uncertainty based on the nominal kinematic equation.

[0084] Specifically, in constructing the preset secondary controller, it is necessary to utilize the construction process of the preset path tracking control model. Specifically, a preset activation set algorithm can be used to track and control the parking path in the preset path tracking control model construction process. This allows the path of the preset path tracking control model to be rewritten according to the control process, resulting in a path tracking control function. Then, a preset expansion algorithm is used to expand the path tracking control function within a preset neighborhood, obtaining the expanded tracking control function. The expanded tracking control function is then used to determine the predicted independent and dependent variables in the parking process. Based on the predicted independent and dependent variables, a nominal kinematic equation is constructed. Based on the nominal kinematic equation, an error function for parking uncertainty is constructed. Finally, based on the error function, the preset secondary controller is constructed. The specific construction formula is shown below:

[0085] based on and For p in formulas (9), (10), and (11) in step 202 N (x N ), p k (x k ) and q k (u k )exist Expanding within the neighborhood, i.e., tracking control of the parking path, yields the path tracking control functions as shown in formulas (12), (13), and (14):

[0086] Where, δx N This indicates the changes in various status data (traction status data, trailer status data, and semi-trailer status data) during the semi-trailer parking process. δx represents the standard value of each state data. k This represents the actual change in the value of each state data point. δu represents the standard value of each state data. k This indicates the change in the steering angle of the front wheel of the traction device. R represents the standard value of the front wheel steering angle of the traction device. k This represents the weight matrix of the dependent variable at time k, which is the weight matrix of the front wheel rotation angle of the traction device at time k.

[0087] Furthermore, based on and For g(x) in formula (8) in step 202 k ,u k Within the preset neighborhood range A first-order Taylor expansion within the domain yields the expanded tracking control function, as shown in equation (15):

[0088] Wherein, g(x) k ,u k ) indicates expanding the tracking control function. Let k represent the partial derivative with respect to the independent variable at time k. Let k represent the partial derivative with respect to the independent variable at time k. Let k represent the nominal value of the tracking control function at time k. Further, by rearranging formula (15), we can obtain formula (16):

[0089] In the formula, w k Denotes the uncertainty introduced by the first-order Taylor expansion process, satisfying |w k |≤b w b w Indicates the preset error threshold, δx k+1 The change of the independent variable at the next moment is represented by the formula (8). Further, based on formulas (12), (13), (14) and (16) in step 202, the path tracking control problem of the tractor-semi-trailer tractor-trailer described by formula (8) is rewritten as shown in formula (17). According to formula (17), the predicted independent variable and predicted dependent variable in the semi-trailer parking control process are:

[0090] Among them, (δx k ) *Let represent the predictive independent variables in the semi-trailer parking control process, where the predictive independent variables can be further expressed as: (δu k ) * Let represent the predictive dependent variable in the semi-trailer parking control process, where the predictive dependent variable can be further expressed as: x k,max u represents the maximum value of the actual values ​​of each state data. k,max This represents the maximum angle of the front wheels of the semi-trailer at this moment, x. k,min u represents the minimum actual value of each state data. k,min This represents the minimum front wheel angle of the semi-trailer at this moment, and δx0 represents the change in the initial state data. Further, based on the predicted independent variables... and predict dependent variable The nominal operational equations are constructed as shown in equation (18):

[0091] Among them, y m Let the nominal kinematic equations be represented. Then, based on the nominal kinematic equations, the error function between the actual independent variables and the predicted independent variables of the preset secondary controller is defined as shown in formula (19):

[0092] Among them, D w Let (17) represent the error function. Based on equation (18) and equation (17), we can obtain the following formula (20):

[0093] in, The data represents the various state data of the next time step, including the traction state data, trailer state data, and semi-trailer state data of the next time step. In order to make the actual independent variables within the error converge to the neighborhood of the predicted sub-variables, the following preset secondary controller is designed, as shown in formula (21):

[0094] In the formula, K k Let Δu be the feedback matrix, representing the second driving strategy, i.e., the steering and angle of the front wheels of the traction device. The sign of Δu can be used to determine the steering angle of the front wheels of the traction device. Furthermore, in order to verify the prediction results of the preset secondary controller, the formula of the preset secondary controller described in equation (21) can be substituted into equation (20) to obtain the following formula (22):

[0095] From equation (22) and |w k |≤b w It can be deduced Combining equations (17) and (19), we can obtain the following formula (23):

[0096] Furthermore, combining equation (21), we can obtain the following formula (24):

[0097] From formula (24), we can see that as long as we predict the independent variable... and predict dependent variable If equations (23) and (24) are satisfied, then the change in the independent variable δx k and the change in dependent variable δu k The constraints must be met. Therefore, ignoring the uncertainty w... k Under the premise that equation (17) can be transformed into the following equation (25):

[0098] in, This represents the correction independent variable in the semi-trailer parking control process. Let A, C, and d represent the correction dependent variables in the semi-trailer parking control process. x and d u They can be represented as

[0099] Furthermore, The standard value representing each verification status data, The standard value of the front wheel steering angle data for traction device verification is given. The problem described by equation (25) is solved using the activation set method. Equation (25) is rewritten as the following formula (26):

[0100] Where δ represents the vector to be optimized, Z k Let g represent the weight matrix. k Let E represent the weight vector, I represent the set of equality constraints, and h represent the set of inequality constraints. i b represents the constraint coefficient. i This represents a constraint constant, and i represents the index.

[0101] The calculation steps of the activation set method are as follows: First, initialize the iterative semi-trailer starting point σ0 and the working set W0, such that i∈W0, we have Make have Here, it is assumed that the working set for the m-th iteration is W. m Solving the following equality-constrained optimization problem yields s. m s m This represents the optimal increment in the m-th iteration.

[0102] Where, σ m Let represent the optimal solution in the m-th iteration, and s represent the increment in the m-th iteration. Further simplification of equation (27) yields the following formula (28):

[0103] In the formula, Y m =Z k σ m +g k s represents the increment of the m-th iteration, W m Representing the working set, the optimality condition of the optimization formula (28) is further shown in the following formula (29):

[0104] In the formula, λ i ,i∈W m For Lagrange multipliers, Y m Let L(s,λ) represent the intermediate variable, which is the Lagrangian function and can be expressed as shown in the following formula (30):

[0105] Equation (29) can be further simplified to obtain

[0106] Where H represents the coefficient matrix, and s can be obtained by further solving equation (31). m s m Let s represent the optimal increment in the m-th iteration. m =0, calculate the Lagrange multiplier λ i ,i∈W m If λ i ≥0, i∈W m ∩I, output the optimal solution σ m , σ m If the optimal solution is found in the m-th iteration, stop the iteration; otherwise, update the working set W. m+1 =W m / {i|arg(λ i <0, i∈W m ∩I)},σ m+1 =σ m , σ m+1 Let s represent the optimal solution in the (m+1)th iteration. m ≠0, calculate step size β m This represents the preset verification step size of the secondary controller, and σ is calculated. m+1 =σ m +β m s m If it exists Update working set W m+1 =W m ∪{i}; otherwise, W k+1 =W k Set m = m + 1; this allows for optimization of the preset secondary controller.

[0107] 204. Based on the first driving strategy and the second driving strategy, determine the driving strategy of the traction device at the next moment.

[0108] The first driving strategy is the first front wheel angle and the first front wheel steering of the traction device at the next moment, and the second driving strategy is the second front wheel angle and the second front wheel steering of the traction device at the next moment.

[0109] In this embodiment of the application, after calculating the first driving strategy of the traction device at the next moment using a preset path tracking control model and the second driving strategy of the traction device at the next moment using a preset secondary controller, it is necessary to comprehensively analyze the first driving strategy and the second driving strategy to obtain the driving strategy of the traction device at the next moment. Based on this, step 204 specifically includes: determining the first weight coefficient corresponding to the first front wheel angle and the second weight coefficient corresponding to the second front wheel angle; taking a preset direction as the positive direction, and based on the first weight coefficient, the second weight coefficient, the first front wheel steering, and the second front wheel steering, adding the first front wheel angle and the second front wheel angle to obtain the planned front wheel angle and the planned front wheel steering of the traction device at the next moment.

[0110] The preset direction is set according to actual needs. Specifically, firstly, the first weighting coefficient corresponding to the first front wheel angle and the second weighting coefficient corresponding to the second front wheel angle are determined. Then, based on the first and second weighting coefficients, the first and second front wheel angles are added together to obtain the planned front wheel angle and planned front wheel steering of the traction device at the next moment. For example, if the first weighting coefficient is 0.3, the second weighting coefficient is 0.7, the first front wheel angle is -10°, and the second front wheel angle is +3°, and positive values ​​are positive (leftward) and negative values ​​are negative (rightward), then 0.3 × (-10°) + 0.7 × 3° = -0.9, which means that the planned front wheel angle of the traction device at the next moment is 0.9° and the planned front wheel steering is rightward, that is, the front wheels of the traction device should be automatically controlled to turn 0.9° to the right.

[0111] 205. Based on the driving strategy, perform parking control on the semi-trailer to be controlled.

[0112] In this embodiment of the application, after obtaining the driving strategy of the traction device at the next moment, it is necessary to perform parking control on the semi-trailer to be controlled according to the driving strategy. Based on this, step 205 specifically includes: generating a front wheel rotation control command for the traction device based on the planned front wheel angle and the planned front wheel steering; and executing the angle control and steering control of the front wheels of the traction device based on the front wheel rotation control command to realize parking control on the semi-trailer to be controlled.

[0113] Specifically, based on the planned front wheel angle and the planned front wheel steering, control commands for the front wheel angle and steering of the traction device are generated. Finally, based on the front wheel angle control command, the angle control of the front wheels of the traction device is realized. At the same time, based on the front wheel steering control command, the steering control of the front wheels of the traction device is realized.

[0114] According to another semi-trailer parking control method provided in this application, compared with the current method of parking by manually controlling the tractor-semi-trailer tractor-trailer platform, this application obtains real-time traction status data of the traction device corresponding to the semi-trailer to be controlled, real-time platform status data of the semi-trailer tractor corresponding to the semi-trailer to be controlled, and real-time semi-trailer status data, wherein the traction device is connected to the semi-trailer tractor platform, the semi-trailer tractor platform is connected to the semi-trailer to be controlled, and the traction device tractions the semi-trailer to be controlled through the semi-trailer tractor platform; then, based on the real-time traction status data, the real-time platform status data, and the real-time semi-trailer status data... According to the data, the driving strategy of the traction device in the next moment is determined; finally, based on the driving strategy, parking control is performed on the semi-trailer to be controlled. Thus, by using the real-time traction status data of the traction device, the real-time towing platform status data of the traction platform, and the real-time semi-trailer status data of the semi-trailer to be controlled, the driving strategy of the traction device in the next moment is automatically calculated. Finally, according to the driving strategy, parking control is performed on the semi-trailer to be controlled. This can avoid the time wasted by manually controlling the parking of the tractor-semi-trailer traction platform-semi-trailer, thereby improving the parking efficiency of the tractor-semi-trailer traction platform-semi-trailer. At the same time, it can also avoid the folding and instability caused by manual parking, thereby improving parking safety.

[0115] Furthermore, as a specific implementation of Figure 1, this application embodiment provides a semi-trailer parking control device, as shown in Figure 5. The device includes: an acquisition unit 31, a determination unit 32, and a control unit 33.

[0116] The acquisition unit 31 can be used to acquire real-time traction status data of the traction device corresponding to the semi-trailer to be controlled, real-time platform status data of the semi-trailer towing platform corresponding to the semi-trailer to be controlled, and real-time semi-trailer status data corresponding to the semi-trailer to be controlled. The traction device is connected to the semi-trailer towing platform, the semi-trailer towing platform is connected to the semi-trailer to be controlled, and the traction device tows the semi-trailer to be controlled through the semi-trailer towing platform.

[0117] The determining unit 32 can be used to determine the driving strategy of the traction device at the next moment based on the real-time traction status data, the real-time trailer status data, and the real-time semi-trailer status data.

[0118] The control unit 33 can be used to perform parking control on the semi-trailer to be controlled based on the driving strategy.

[0119] In specific application scenarios, in order to determine the driving strategy of the traction device at the next moment, as shown in Figure 6, the determining unit 32 includes a prediction module 321 and a determining module 322.

[0120] The prediction module 321 can be used to input the real-time traction status data, the real-time trailer status data, and the real-time semi-trailer status data into a preset path tracking control model to predict the driving strategy and obtain a first driving strategy.

[0121] The prediction module 321 can also be used to input the real-time traction status data, the real-time trailer status data, and the real-time semi-trailer status data into a preset secondary controller to predict the driving strategy and obtain a second driving strategy.

[0122] The determining module 322 can be used to determine the driving strategy of the traction device at the next moment based on the first driving strategy and the second driving strategy.

[0123] In specific application scenarios, in order to construct a preset path tracking control model and a preset secondary controller, the determining unit 32 also includes a construction module 323.

[0124] The construction module 323 can be used to construct a preset path tracking control model by taking the sample traction status data of the sample traction device corresponding to the sample semi-trailer, the sample trailer status data of the sample semi-trailer traction platform corresponding to the sample semi-trailer, and the sample semi-trailer status data corresponding to the sample semi-trailer as sample independent variables and the front wheel rotation angle of the sample traction device as sample dependent variable.

[0125] The construction module 323 can also be used to track and control the parking path corresponding to the sample semi-trailer using a preset activation set algorithm, to obtain the predicted independent variable and predicted dependent variable of the semi-trailer to be controlled during the parking process; to construct an error function of parking uncertainty with the predicted independent variable and the predicted dependent variable as the center, and to construct a preset secondary controller based on the error function.

[0126] In specific application scenarios, in order to build a preset path tracking control model, the construction module 323 can be used to construct the kinematic equations of the traction device-semi-trailer traction platform-semi-trailer by taking the sample traction state data of the sample traction device corresponding to the sample semi-trailer, the sample trailer platform state data of the sample semi-trailer corresponding to the sample semi-trailer, and the sample semi-trailer state data of the sample semi-trailer as sample independent variables and the front wheel rotation angle of the sample traction device as sample dependent variable; decompose the kinematic equations into velocity using a preset velocity decomposition method to obtain velocity decomposition equations; discretize the velocity decomposition equations using a preset fourth-order Runge-Kutta integral discretization algorithm to obtain discretized equations; and construct the preset path tracking control model based on the discretized equations.

[0127] In a specific application scenario, in order to construct the error function, the construction module 323 can be used to track and control the parking path corresponding to the sample semi-trailer using a preset activation set algorithm to obtain a path tracking control function; expand the path tracking control function in a preset neighborhood using a preset expansion algorithm to obtain an expanded tracking control function; determine the predicted independent variable and predicted dependent variable in the semi-trailer parking control process based on the expanded tracking control function; construct a nominal kinematic equation based on the predicted independent variable and the predicted dependent variable; and construct an error function for parking uncertainty based on the nominal kinematic equation.

[0128] In specific application scenarios, in order to determine the driving strategy of the traction device at the next moment, the determining module 322 can be used to determine the first weight coefficient corresponding to the first front wheel turning angle and the second weight coefficient corresponding to the second front wheel turning angle; taking the preset direction as the positive direction, based on the first weight coefficient, the second weight coefficient, the first front wheel steering, and the second front wheel steering, the first front wheel turning angle and the second front wheel turning angle are added together to obtain the planned front wheel turning angle and the planned front wheel steering of the traction device at the next moment.

[0129] In a specific application scenario, in order to control the parking of the semi-trailer to be controlled, the control unit 33 includes a generation module 331 and a control module 332.

[0130] The generation module 331 can be used to generate front wheel rotation control commands for the traction device based on the planned front wheel angle and the planned front wheel steering.

[0131] The control module 332 can be used to perform angle control and steering control of the front wheels of the traction device based on the front wheel rotation control command, so as to realize parking control of the semi-trailer to be controlled.

[0132] It should be noted that other corresponding descriptions of the various functional modules involved in the semi-trailer parking control device provided in this application embodiment can be found in the corresponding description of the method shown in Figure 1, and will not be repeated here.

[0133] Based on the method shown in Figure 1, this application also provides a computer-readable storage medium storing a computer program that, when executed by a processor, performs the following steps: acquiring real-time traction status data of the traction device corresponding to the semi-trailer to be controlled, real-time trailer status data of the semi-trailer traction platform corresponding to the semi-trailer to be controlled, and real-time semi-trailer status data corresponding to the semi-trailer to be controlled, wherein the traction device is connected to the semi-trailer traction platform, the semi-trailer traction platform is connected to the semi-trailer to be controlled, and the traction device tractions the semi-trailer to be controlled through the semi-trailer traction platform; determining the driving strategy of the traction device at the next moment based on the real-time traction status data, the real-time trailer status data, and the real-time semi-trailer status data; and performing parking control on the semi-trailer to be controlled based on the driving strategy.

[0134] Based on the embodiments of the method shown in Figure 1 and the device shown in Figure 5, this application also provides a physical structure diagram of a computer device, as shown in Figure 7. The computer device includes: a processor 41, a memory 42, and a computer program stored in the memory 42 and executable on the processor. Both the memory 42 and the processor 41 are mounted on a bus 43. When the processor 41 executes the program, it performs the following steps: acquiring real-time traction status data of the traction device corresponding to the semi-trailer to be controlled, real-time platform status data of the semi-trailer traction platform corresponding to the semi-trailer to be controlled, and real-time semi-trailer status data corresponding to the semi-trailer to be controlled. The traction device is connected to the semi-trailer traction platform, and the semi-trailer traction platform is connected to the semi-trailer to be controlled. The traction device tractions the semi-trailer to be controlled through the semi-trailer traction platform. Based on the real-time traction status data, the real-time platform status data, and the real-time semi-trailer status data, the driving strategy of the traction device at the next moment is determined. Based on the driving strategy, parking control is performed on the semi-trailer to be controlled.

[0135] Through the technical solution of this application, this application obtains real-time traction status data of the traction device corresponding to the semi-trailer to be controlled, real-time trailer traction platform status data of the semi-trailer to be controlled, and real-time semi-trailer status data of the semi-trailer to be controlled. The traction device is connected to the semi-trailer traction platform, and the semi-trailer traction platform is connected to the semi-trailer to be controlled. The traction device tractions the semi-trailer to be controlled through the semi-trailer traction platform. Then, based on the real-time traction status data, the real-time trailer traction platform status data, and the real-time semi-trailer status data, it determines... The driving strategy of the traction device in the next moment is determined; finally, based on the driving strategy, parking control is performed on the semi-trailer to be controlled. Thus, by using the real-time traction status data of the traction device, the real-time towing platform status data of the traction platform, and the real-time semi-trailer status data of the semi-trailer to be controlled, the driving strategy of the traction device in the next moment is automatically calculated. Finally, according to the driving strategy, parking control is performed on the semi-trailer to be controlled. This can avoid the time wasted by manually controlling the parking of the tractor-semi-trailer traction platform-semi-trailer, thereby improving the parking efficiency of the tractor-semi-trailer traction platform-semi-trailer.

[0136] Obviously, those skilled in the art should understand that the modules or steps of this application described above can be implemented using general-purpose computing devices. They can be centralized on a single computing device or distributed across a network of multiple computing devices. Optionally, they can be implemented using computer-executable program code, thereby storing them in a storage device for execution by a computing device. In some cases, the steps shown or described can be performed in a different order than those presented here, or they can be fabricated as separate integrated circuit modules, or multiple modules or steps can be fabricated as a single integrated circuit module. Thus, this application is not limited to any particular combination of hardware and software.

[0137] The above description is merely a preferred embodiment of this application and is not intended to limit this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of protection of this application.

Claims

1. A parking control method for a semi-trailer, wherein, include: The system acquires real-time traction status data of the traction device corresponding to the semi-trailer to be controlled, real-time platform status data of the semi-trailer to be controlled, and real-time semi-trailer status data, wherein the traction device is connected to the semi-trailer to be controlled, the semi-trailer to be controlled is connected to the semi-trailer to be controlled, and the traction device tows the semi-trailer to be controlled through the semi-trailer to be controlled. Based on the real-time traction status data, the real-time trailer status data, and the real-time semi-trailer status data, the driving strategy of the traction device at the next moment is determined; Based on the driving strategy, parking control is performed on the semi-trailer to be controlled.

2. The method according to claim 1, wherein, The step of determining the driving strategy of the traction device at the next moment based on the real-time traction status data, the real-time trailer status data, and the real-time semi-trailer status data includes: The real-time traction status data, the real-time trailer status data, and the real-time semi-trailer status data are input into a preset path tracking control model to predict the driving strategy and obtain the first driving strategy. The real-time traction status data, the real-time trailer status data, and the real-time semi-trailer status data are input into a preset secondary controller for driving strategy prediction to obtain a second driving strategy; Based on the first driving strategy and the second driving strategy, the driving strategy of the traction device at the next moment is determined.

3. The method according to claim 2, wherein, Before inputting the real-time traction status data, the real-time trailer status data, and the real-time semi-trailer status data into a preset path tracking control model for driving strategy prediction to obtain a first driving strategy, the method further includes: The sample traction status data of the sample traction device corresponding to the sample semi-trailer, the sample trailer status data of the sample semi-trailer traction platform corresponding to the sample semi-trailer, and the sample semi-trailer status data corresponding to the sample semi-trailer are used as sample independent variables, and the front wheel rotation angle of the sample traction device is used as the sample dependent variable. A preset path tracking control model is constructed using a preset speed decomposition algorithm. Before inputting the real-time traction status data, the real-time trailer status data, and the real-time semi-trailer status data into a preset secondary controller for driving strategy prediction to obtain a second driving strategy, the method further includes: The parking path corresponding to the sample semi-trailer is tracked and controlled using a preset activation set algorithm to obtain the predicted independent and dependent variables of the semi-trailer to be controlled during the parking process. An error function for parking uncertainty is constructed centered on the predicted independent variable and the predicted dependent variable, and a preset secondary controller is constructed based on the error function.

4. The method according to claim 3, wherein, The process involves using sample traction state data of the sample traction device corresponding to the sample semi-trailer, sample trailer state data of the sample semi-trailer traction platform corresponding to the sample semi-trailer, and sample semi-trailer state data corresponding to the sample semi-trailer as sample independent variables, and the front wheel angle of the sample traction device as the sample dependent variable. A preset path tracking control model is constructed using a preset speed decomposition algorithm, including: The sample traction state data of the sample traction device corresponding to the sample semi-trailer, the sample trailer state data of the sample semi-trailer traction platform corresponding to the sample semi-trailer, and the sample semi-trailer state data corresponding to the sample semi-trailer are used as the sample independent variables, and the front wheel rotation angle of the sample traction device is used as the sample dependent variable to construct the kinematic equation of traction device-semi-trailer traction platform-semi-trailer. The kinematic equations are decomposed into velocity equations using a preset velocity decomposition method. The velocity decomposition equation is discretized using a pre-defined fourth-order Runge-Kutta integral discretization algorithm to obtain the discretized equation. Based on the discretized equations, a preset path tracking control model is constructed.

5. The method according to claim 3, wherein, The method of tracking and controlling the parking path of the sample semi-trailer using a preset activation set algorithm yields the predicted independent and dependent variables of the semi-trailer during the parking process, including: The parking path corresponding to the sample semi-trailer is tracked and controlled using a preset activation set algorithm to obtain the path tracking control function; The path tracking control function is expanded within a preset neighborhood range using a preset expansion algorithm to obtain the expanded tracking control function; Based on the aforementioned expanded tracking control function, the predictive independent variables and predictive dependent variables in the semi-trailer parking control process are determined; The construction of the error function for parking uncertainty centered on the predicted independent variable and the predicted dependent variable includes: Based on the predicted independent variable and the predicted dependent variable, a nominal kinematic equation is constructed; Based on the nominal kinematic equations, an error function for parking uncertainty is constructed.

6. The method according to claim 2, wherein, The first driving strategy is the first front wheel angle and the first front wheel steering of the traction device at the next moment, and the second driving strategy is the second front wheel angle and the second front wheel steering of the traction device at the next moment; determining the driving strategy of the traction device at the next moment based on the first driving strategy and the second driving strategy includes: Determine the first weighting coefficient corresponding to the first front wheel steering angle and the second weighting coefficient corresponding to the second front wheel steering angle; Taking the preset direction as positive, based on the first weighting coefficient, the second weighting coefficient, the first front wheel steering, and the second front wheel steering, the first front wheel angle and the second front wheel angle are added together to obtain the planned front wheel angle and the planned front wheel steering of the traction device at the next moment.

7. The method according to claim 1, wherein, The parking control of the semi-trailer to be controlled based on the driving strategy includes: Based on the planned front wheel angle and planned front wheel steering, a control command for the front wheel rotation of the traction device is generated; Based on the front wheel rotation control command, the angle control and steering control of the front wheel of the traction device are executed to achieve parking control of the semi-trailer to be controlled.

8. A parking control device for a semi-trailer, wherein, include: The acquisition unit is used to acquire real-time traction status data of the traction device corresponding to the semi-trailer to be controlled, real-time platform status data of the semi-trailer towing platform corresponding to the semi-trailer to be controlled, and real-time semi-trailer status data corresponding to the semi-trailer to be controlled. The traction device is connected to the semi-trailer towing platform, the semi-trailer towing platform is connected to the semi-trailer to be controlled, and the traction device tows the semi-trailer to be controlled through the semi-trailer towing platform. The determining unit is used to determine the driving strategy of the traction device at the next moment based on the real-time traction status data, the real-time trailer status data, and the real-time semi-trailer status data. The control unit is used to perform parking control on the semi-trailer to be controlled based on the driving strategy.

9. A computer-readable storage medium having a computer program stored thereon, wherein, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 7.

10. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 7.

Images