Hinged vehicle parking control method, device and equipment

Abstract

The embodiment of the invention provides an articulated vehicle parking control method, device and equipment, and the method comprises the steps: determining a first distance based on the monitoring parameters of a tractor and a semitrailer, the first distance being the distance from the hinged point of the tractor and the semitrailer to the midpoint of the rear axle of the semitrailer; determining a first included angle according to the first distance and path parameters in the parking process of the semitrailer, wherein the first angle is an included angle between a longitudinal axis of the semitrailer and a speed vector of a hinge point; determining a front wheel steering angle parameter of the tractor according to the first distance and the first included angle; and carrying out parking control operation on the tractor and the semitrailer based on the front wheel steering angle parameter of the tractor. By means of the corresponding relation between the first included angle and the front wheel rotating angle parameter of the tractor, parking of the hinged type vehicle can be effectively controlled.

Description

Technical Field

[0001] This application relates to the field of vehicle control, and specifically to an articulated vehicle parking control method, device, and equipment. Background Technology

[0002] Intelligent vehicles are typically equipped with fully automated parking systems, which can automatically control the vehicle to complete parking operations. This has become the most effective means of solving the parking difficulties of passenger cars. Currently, domestic and international autonomous driving companies are attempting to use fully automated parking systems to address the difficulty of reversing articulated vehicles into parking spaces. Common articulated vehicles include tractor units in the front and semi-trailers in the rear. The kinematic model of articulated vehicles contains unknown parameters and exhibits characteristics such as high nonlinearity, strong coupling, and cascading transmission. Furthermore, articulated vehicles are prone to folding and instability during reversing into parking spaces. These issues make effective control of articulated vehicle parking difficult. Summary of the Invention

[0003] In view of this, this application provides a method, apparatus and equipment for controlling the parking of articulated vehicles, so as to solve the problem of difficulty in controlling the automatic parking of articulated vehicles in the prior art.

[0004] In a first aspect, embodiments of this application provide an articulated vehicle parking control method, including:

[0005] A first distance is determined based on the monitoring parameters of the tractor and the semi-trailer. The first distance is the distance from the articulation point of the tractor and the semi-trailer to the midpoint of the rear axle of the semi-trailer.

[0006] The first included angle is determined based on the first distance and the path parameters during the parking process of the semi-trailer. The first angle is the angle between the longitudinal axis of the semi-trailer and the velocity vector of the hinge point.

[0007] The front wheel steering angle parameters of the tractor are determined based on the first distance and the first included angle.

[0008] The parking control operation is performed on the tractor and the semi-trailer based on the front wheel steering angle parameters of the tractor.

[0009] In one optional embodiment, determining the first distance based on monitoring parameters of the tractor and semi-trailer includes:

[0010] An approximate solution for the first distance is obtained based on an adaptive genetic algorithm;

[0011] The approximate solution of the first distance is used as the initial value of the quasi-Newton method, and the monitoring parameters are processed based on the quasi-Newton method to obtain the optimal solution of the first distance.

[0012] In one optional embodiment, obtaining an approximate solution for the first distance based on an adaptive genetic algorithm includes:

[0013] Encode the first distance to obtain an initial population related to the first distance;

[0014] Calculate the fitness of each individual in the current population;

[0015] Genetic manipulation is performed on each individual in the current population based on fitness to obtain a new population, and the step of calculating the fitness of each individual in the current population is performed again.

[0016] After the iteration is completed, the individual with the highest fitness is determined as the approximate solution for the first distance.

[0017] In one optional embodiment, the step of using the approximate solution of the first distance as the initial value of the quasi-Newton method and processing the monitoring parameters based on the quasi-Newton method to obtain the optimal solution of the first distance includes:

[0018] Determine the initial search direction and search step size;

[0019] The approximate solution of the first distance is updated based on the search direction and the search step size;

[0020] If the updated distance parameters meet the preset conditions, the current distance parameters are determined as the optimal solution for the first distance. If the updated distance parameters do not meet the preset conditions, the steps of determining the initial search direction and search step size are re-executed.

[0021] In an optional embodiment, determining the first included angle based on the first distance and the path parameters during the semi-trailer parking process includes:

[0022] Determine the turning radius of the semi-trailer during parking;

[0023] The first included angle is determined based on the turning radius and the first distance.

[0024] In an optional embodiment, determining the front wheel steering angle parameters of the tractor based on the first distance and the first included angle includes:

[0025] The rate of change of the first included angle is determined based on the monitoring parameters;

[0026] The front wheel steering angle parameters of the tractor are determined based on the rate of change of the first included angle and the second distance, where the second distance is the distance from the midpoint of the rear axle of the tractor to the hinge point.

[0027] In one optional embodiment, the parking control operation of the tractor and the semi-trailer based on the front wheel steering angle parameters of the tractor includes:

[0028] Determine the desired curvature of the midpoint of the rear axle of the semi-trailer;

[0029] The semi-trailer is controlled to travel a preset distance with the desired curvature, and the first included angle is updated.

[0030] Secondly, embodiments of this application provide an articulated vehicle parking control device, comprising:

[0031] The first determining module is used to determine a first distance based on the monitoring parameters of the tractor and the semi-trailer, wherein the first distance is the distance from the articulation point of the tractor and the semi-trailer to the midpoint of the rear axle of the semi-trailer;

[0032] The second determining module is used to determine a first included angle based on the first distance and the path parameters during the parking process of the semi-trailer, wherein the first angle is the angle between the longitudinal axis of the semi-trailer and the velocity vector of the hinge point;

[0033] The third determining module is used to determine the front wheel steering angle parameters of the tractor vehicle based on the first distance and the first included angle.

[0034] The control module is used to perform parking control operations on the tractor and the semi-trailer based on the front wheel steering angle parameters of the tractor.

[0035] Thirdly, embodiments of this application provide an electronic device, including a memory for storing computer program instructions and a processor for executing the program instructions, wherein when the computer program instructions are executed by the processor, the electronic device is triggered to execute the method described in any of the first aspects above.

[0036] Fourthly, embodiments of this application provide a computer-readable storage medium including a stored program, wherein, when the program is executed, it controls the device where the computer-readable storage medium is located to perform the method described in any of the first aspects.

[0037] Fifthly, embodiments of this application provide a computer program product comprising executable instructions that, when executed on a computer, cause the computer to perform the method described in any of the first aspects.

[0038] The solution provided in this application involves determining a first distance based on monitoring parameters of the tractor and semi-trailer. This first distance is the distance from the articulation point of the tractor and semi-trailer to the midpoint of the semi-trailer's rear axle. A first angle is determined based on the first distance and path parameters during the semi-trailer's parking process. This first angle is the angle between the semi-trailer's longitudinal axis and the velocity vector at the articulation point. The front wheel steering angle parameters of the tractor are then determined based on the first distance and the first angle. Parking control operations are performed on the tractor and semi-trailer based on these front wheel steering angle parameters. By establishing the correspondence between the first angle and the tractor's front wheel steering angle parameters, effective control of the articulated vehicle's parking can be achieved. Attached Figure Description

[0039] To more clearly illustrate the technical solutions of the embodiments of this application, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0040] Figure 1 A schematic diagram illustrating an articulated vehicle parking control method provided in this application embodiment;

[0041] Figure 2 A schematic flowchart illustrating an articulated vehicle parking control method provided in an embodiment of this application;

[0042] Figure 3 A schematic diagram illustrating another articulated vehicle parking control method provided in an embodiment of this application;

[0043] Figure 4 A schematic flowchart of another articulated vehicle parking control method provided in an embodiment of this application;

[0044] Figure 5 This is a schematic diagram of the structure of an articulated vehicle parking control system provided in an embodiment of this application;

[0045] Figure 6 A schematic diagram of the structure of an articulated vehicle parking control device provided in an embodiment of this application;

[0046] Figure 7 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Detailed Implementation

[0047] To better understand the technical solution of this application, the embodiments of this application will be described in detail below with reference to the accompanying drawings.

[0048] It should be understood that the described embodiments are merely some, not all, of the embodiments in this application. All other embodiments obtained by those skilled in the art based on the embodiments in this application without inventive effort are within the scope of protection of this application.

[0049] The terminology used in the embodiments of this application is for the purpose of describing particular embodiments only and is not intended to be limiting of this application. The singular forms “a,” “the,” and “the” used in the embodiments of this application and the appended claims are also intended to include the plural forms unless the context clearly indicates otherwise.

[0050] It should be understood that the term "and / or" used in this article is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, or B existing alone. Additionally, the character " / " in this article generally indicates that the preceding and following related objects have an "or" relationship.

[0051] Articulated vehicles typically consist of a tractor unit and a semi-trailer. The tractor unit provides power at the front, while the semi-trailer is positioned behind it. The front end of the semi-trailer connects to the rear end of the tractor unit, and this connection point is called the articulation point. The kinematic model of an articulated vehicle contains unknown parameters and exhibits characteristics such as high nonlinearity, strong coupling, and cascading transmission. Furthermore, articulated vehicles are prone to folding and instability during reversing into parking spaces. To address these issues, this application provides a parking control method for articulated vehicles. This method can be applied to onboard equipment mounted on a tractor unit, solving the problem of difficult-to-control parking of articulated vehicles.

[0052] Figure 1 This is a schematic diagram illustrating an example of an articulated vehicle parking control method provided in an embodiment of this application. Figure 1 As shown, arrow 101 points to the model of the tractor unit, and arrow 102 points to the model of the semi-trailer. Coordinate systems OXY and Axy are established with respect to the ground and the tractor unit, respectively. An angle rotating counterclockwise around the origin is defined as a positive angle, and an angle rotating clockwise is defined as a negative angle. Specifically, the tractor unit's yaw angle is θ1, the tractor unit's front wheel rotation angle is δ, the semi-trailer's yaw angle is θ2, the tractor unit-semi-trailer angle is β, the distance from the center of the tractor unit's front axle to the center of its rear axle is L1, the distance from hinge point P to the midpoint B of the semi-trailer's rear axle is L2, the distance from the midpoint A of the tractor unit's rear axle to hinge point P is M1, the velocity vector of the midpoint A of the tractor unit's rear axle is v2, the velocity vector of the midpoint B of the semi-trailer's rear axle is v2, and the velocity vector of hinge point P is v2. p .

[0053] In this embodiment, the distance L2 from the articulation point P to the midpoint B of the semi-trailer's rear axle is a key value. The on-board equipment needs to calculate the distance parameter L2 based on known parameters. The calculation process of the distance parameter L2 mainly includes: (1) first using the global search advantage of the adaptive genetic algorithm to identify an approximate solution for the distance parameter; (2) using the identification result of the adaptive genetic algorithm as the initial value of the quasi-Newton method, and then using the local search advantage of the quasi-Newton method to identify the optimal solution for the distance parameter.

[0054] Figure 2 This is a flowchart illustrating an articulated vehicle parking control method provided in an embodiment of this application. Figure 2 As shown, the method may include:

[0055] Step 201: Encode distance parameters and create an initial population;

[0056] Step 202: Determine the fitness level of each individual in the current population;

[0057] Step 203: Based on selection, adaptive crossover, and mutation operations, a new population is obtained;

[0058] Step 204: Determine whether the current iteration count meets the termination condition. If it does, proceed to step 204; otherwise, return to step 202.

[0059] Step 205: Output an approximate solution for the distance parameters and initialize the quasi-Newton method;

[0060] Step 206, calculate the search direction;

[0061] Step 207: Calculate the search step size;

[0062] Step 208: Calculate the distance parameters for the next time step;

[0063] Step 209: Determine whether the preset conditions are met;

[0064] Step 210: Output the optimal solution for the distance parameters.

[0065] Steps 201 to 205 above are the process of identifying an approximate solution for the distance parameter by utilizing the global search advantage of the adaptive genetic algorithm. Step 205 can output an approximate solution for the distance parameter L2. Steps 206 to 210 are the process of identifying an optimal solution for the distance parameter by utilizing the local search advantage of the quasi-Newton method. Step 210 can output an optimal solution for the distance parameter L2.

[0066] The following section describes in detail the process of calculating the optimal solution for the distance parameters using the quasi-Newton method. (Refer to...) Figure 1 Establish a base point translational coordinate system with the midpoint B of the semi-trailer's rear axle as the center. Using the base point method, we can determine the velocity vector v at the hinge point P. pThe velocity vector v2 of the midpoint B of the rear axle of the semi-trailer is equal to the velocity vector of the hinge point P relative to the translational coordinate system of the base point. The sum of these values, when further applied to the orthogonal decomposition of velocities, yields the yaw rate of the semi-trailer as:

[0067]

[0068] The velocity relationship can be obtained from trigonometric formulas.

[0069]

[0070] Combining equations (1) and (2), the rate of change of the angle between the tractor and the semi-trailer can be obtained.

[0071]

[0072] The yaw rate of the tractor can be expressed as

[0073]

[0074] Substituting equation (4) into equation (3), we get

[0075]

[0076] Furthermore, equation (6) can be simplified to:

[0077]

[0078] Discretizing equation (6) using the fourth-order Runge-Kutta integral method, we can obtain the system equation as follows:

[0079]

[0080] In the formula, the calculation step size h and the coefficients K1, K2, K3 and K4 can be expressed as follows:

[0081]

[0082] In the formula, t f N and N are the sampling duration and the number of sampling points, respectively.

[0083] Let x = L2 be the distance parameter to be identified, then equation (7) can be rewritten as follows:

[0084]

[0085] If the criterion for estimating the distance parameter to be identified is minimizing the sum of squared residuals, then the optimization objective function can be written as follows:

[0086]

[0087] Using Taylor's formula in x kApplying a second-order approximation to the optimization objective function f(x) described by equation (10), we have:

[0088]

[0089] The extreme points of f(x) can be approximated using the second-order approximation of f(x).

[0090]

[0091] From equation (12), the iterative formula for solving the extreme points of f(x) can be obtained as follows:

[0092]

[0093] In the formula, The gradient vector; This is the Hessian matrix.

[0094] To avoid calculating the Hessian matrix h during the iteration process k Using a matrix H that does not contain second derivatives k+1 Replace the Hessian matrix in equation (13). Let and Δx k =x k+1 -x k The approximate matrix H of the Hessian matrix k+1 satisfy

[0095] Δg k =H k+1 Δx k (14)

[0096] Assume H k+1 =H k +ΔH k And ΔH k It can be represented as Then from equation (14) we have

[0097]

[0098] Let αμ T Δx k =1, μ=Δg k and Make ΔH k It satisfies the symmetry requirement, and can be obtained from equation (15).

[0099]

[0100]

[0101] Depend on achievable

[0102]

[0103] Further analysis yields...

[0104]

[0105] Considering the search direction used in the actual update process is d k =-H k -1 g k Using the Sherman-Morrison formula, H is given. k+1 -1 With H k -1 The iterative relationship between them is

[0106]

[0107] In summary, the iterative steps for obtaining the distance parameters to be identified can specifically include:

[0108] (a) Given the initial point of the distance parameter to be identified and the allowable errors x0 and ε, let H k =I and k=0;

[0109] (b) Calculate the search direction d k =-H k -1 g k ;

[0110] (c) From point x k Depart, along d k Perform a one-dimensional search to obtain the optimal step size λ. k =argminf(x k +λd k And update the distance parameter x. k+1 =x k +λ k d k ;

[0111] (d) Determine the precision; if |g k+1 If the value is less than ε, the iteration stops; otherwise, proceed to (e).

[0112] (e)Δg k =g k+1 -g k Δx k =x k+1 -x k ;

[0113] (f)k=k+1, enter (b).

[0114] The above describes the operation process of the quasi-Newton method. In step (a), an initial point for the distance parameter needs to be given. The quasi-Newton method has poor global search capability, and if the value of the initial point is not set reasonably, it will directly affect the final output. To address this problem, this application first identifies an approximate solution for the distance parameter based on the global search advantage of the adaptive genetic algorithm, and then uses this approximate solution as the initial point in step (a) above before executing the steps of the quasi-Newton method.

[0115] The following section further describes the specific operation process of the adaptive genetic algorithm. Using [L... min，j L max，j The value range of the distance parameter to be identified is represented by [ ], and the correspondence between the solution space of the distance parameter to be identified and the search space based on the Gray array is established through Gray encoding. The Gray encoding of the distance parameter to be identified is as follows:

[0116] L j =L min，j +E j d j (20)

[0117] In the formula, d j =(L max，j -L min，j ) / (2 m -1) is the length of the subinterval; E j Less than 2 m Any decimal search step can be expressed as

[0118]

[0119] In the formula, {g(j,k)|k=1,2,...,m} is the Gray array. It is the XOR operator.

[0120] Furthermore, let M represent the initial population size, and let the initial population generated based on Hamming distance be...

[0121] G ij ≥(ml)i,j=1,2,...,N,i≠j (22)

[0122] In the formula, G ij Let l = int(m / 2) be the Hamming distance and the minimum Hamming distance between any two individuals in the population, respectively.

[0123] Based on the residual definition, the individual fitness F is:

[0124]

[0125] Furthermore, based on equation (23), the transition probability P from the current individual i to the new individual j is obtained. k for

[0126]

[0127] In the formula, F(i) is the fitness of individual i before crossover mutation; F(j) is the fitness of individual j after crossover mutation; T0 is the initial temperature; and v is the cooling rate.

[0128] To further improve the search capability of the algorithm, this invention is based on the average fitness of the population. The fitness F of individuals in the population, the maximum fitness F0 of all individuals in the population, and the maximum fitness F′ of all individuals in the population undergoing crossover are automatically adjusted to adjust the crossover probability P. c And the probability of mutation P m The adjustment process for both can be represented as follows:

[0129]

[0130] In summary, this application combines the advantages of the strong global search capability of the heuristic intelligent search algorithm (adaptive genetic algorithm) and the strong local search capability of the numerical optimization algorithm (quasi-Newton method). First, the adaptive genetic algorithm is used to identify an approximate solution for the distance parameter. The identification result of the adaptive genetic algorithm is used as the initial value of the quasi-Newton method. Then, the local search advantage of the quasi-Newton method is used to identify the optimal solution for the distance parameter, laying the foundation for subsequent precise control of articulated vehicle parking.

[0131] In the parking control of articulated vehicles, path tracking of the semi-trailer is required in the time domain. This application decouples the tractor-semi-trailer parking control problem into a top-level path tracking control sub-problem for the semi-trailer and a bottom-level angle tracking control sub-problem for the tractor. The predicted semi-trailer path tracking error in the time domain is transformed into a series of velocity vectors v between the semi-trailer's longitudinal axis and the articulation point P. p The desired angle; the velocity vector v between the longitudinal axis of the semi-trailer and the hinge point P. p The tracking control problem of the desired angle is transformed into a constrained optimization problem. By solving the constrained optimization problem, the control quantity of the front wheel steering angle of the tractor is obtained, thereby realizing the velocity vector v between the longitudinal axis of the semi-trailer and the hinge point P. p The goal is to achieve precise tracking of the angle and ensure that the articulated vehicle remains in a stable state during reversing into a parking space, preventing folding and instability and improving the success rate of reversing into a parking space.

[0132] Reference Figure 3 A pure tracking algorithm is used to make the semi-trailer turn from the midpoint B of the rear axle of the semi-trailer with a fixed turning radius R2. k Once the vehicle reaches the pre-aiming point G on the planned path, then...

[0133]

[0134] In the formula, l d This is the aiming distance.

[0135] Further simplification of equation (26) yields the midpoint B of the rear axle of the semi-trailer. k The expected curvature is

[0136]

[0137] Based on point B k The desired curvature yields the velocity vector v between the semi-trailer's longitudinal axis and the hinge point P. p The expected angle is

[0138]

[0139] Subsequently, a pure tracking algorithm was used to guide the semi-trailer at the desired curvature ρ. k Traveling a distance Δs, we obtain the midpoint B of the semi-trailer's rear axle at time k+1. k+1 The pose information is then used to calculate the velocity vector v between the longitudinal axis of the semi-trailer and the hinge point P at time k+1 using equation (28). p The expected angle. Continuing in this manner, based on a pure tracking algorithm, the semi-trailer path tracking error in the predicted time domain is transformed into a series of velocity vectors v between the semi-trailer's longitudinal axis and the hinge point P. p The expected angle γ k，ref k = 0, ..., N. The following establishes the velocity vector v between the semi-trailer's longitudinal axis and the hinge point P. p The dynamic relationship between the included angle and the steering angle of the tractor's front wheels, and the velocity vector v between the longitudinal axis of the semi-trailer and the articulation point P. p The tracking control problem of the desired angle is transformed into a constrained optimization problem. By solving the constrained optimization problem, the control quantity of the front wheel steering angle of the tractor is obtained, thereby realizing the velocity vector v between the longitudinal axis of the semi-trailer and the hinge point P. p Precise tracking of the desired angle.

[0140] like Figure 4 As shown, the rate of change of the angle between the tractor and the semi-trailer is obtained based on the kinematic relationship.

[0141]

[0142] The yaw rate of the tractor can be expressed as

[0143]

[0144] Substituting equation (30) into equation (29) yields the velocity vector v between the longitudinal axis of the semi-trailer and the hinge point P. p The expected rate of change of the included angle is

[0145]

[0146] Considering that the distance L1 from the center of the front axle to the center of the rear axle of the tractor is greater than the distance M1 from the midpoint A of the rear axle to the hinge point P, then we have

[0147]

[0148] Substituting equation (32) into equation (31) yields

[0149]

[0150] Further simplification of equation (33) yields

[0151]

[0152] Discretizing equation (34) using the fourth-order Runge-Kutta integral method, we can obtain the system equation as follows:

[0153]

[0154] In the formula, the calculation step size h and the coefficients K1, K2, K3 and K4 can be expressed as follows:

[0155]

[0156] In the formula, t f N and N represent the prediction duration and the number of discrete points for model prediction control, respectively.

[0157] Therefore, the velocity vector v between the longitudinal axis of the semi-trailer and the hinge point P is established. p The desired angle tracking control problem is

[0158]

[0159] In the formula, δ k，max and δ k，min γ represents the upper and lower boundaries of the steering angle of the tractor's front wheels; k，max and γ k，min The velocity vector v between the longitudinal axis of the semi-trailer and the hinge point P p The upper and lower boundaries of the included angle can be represented as

[0160]

[0161] In the formula, R min This is the minimum turning radius of the midpoint of the rear axle of the tractor unit corresponding to the maximum front wheel turning angle.

[0162] In summary, by solving equation (37), the velocity vector v between the longitudinal axis of the semi-trailer and the hinge point P is described. p The desired angle tracking control problem yields the control value of the front wheel steering angle of the tractor, thereby enabling the control of the velocity vector v between the longitudinal axis of the semi-trailer and the articulation point P. p Precise tracking of the desired angle.

[0163] In this embodiment, the velocity vector v between the longitudinal axis of the semi-trailer and the hinge point P is... p There is a dynamic relationship between the included angle and the steering angle of the tractor's front wheels. By controlling the steering angle of the tractor's front wheels, the velocity vector v at the articulation point P can be controlled. p The angle is used to control the semi-trailer's travel path.

[0164] Figure 4 This is a flowchart illustrating an articulated vehicle parking control method provided in an embodiment of this application. Figure 4 As shown, the method may include:

[0165] Step 401: Determine the first distance based on the monitoring parameters of the tractor and the semi-trailer. The first distance is the distance from the articulation point of the tractor and the semi-trailer to the midpoint of the rear axle of the semi-trailer.

[0166] Step 402: Determine the first included angle based on the first distance and the path parameters during the semi-trailer parking process. The first angle is the angle between the longitudinal axis of the semi-trailer and the velocity vector of the articulation point.

[0167] Step 403: Determine the front wheel steering angle parameters of the tractor vehicle based on the first distance and the first included angle;

[0168] Step 404: Perform parking control operations on the tractor and semi-trailer based on the front wheel steering angle parameters of the tractor.

[0169] The test parameters specifically refer to parameters related to the tractor and semi-trailer; for details, please refer to [link / reference needed]. Figure 1 And the descriptions in formulas (1) to (25) above.

[0170] Accordingly, this application also provides an articulated vehicle parking control system, which can be installed on the aforementioned vehicle-mounted equipment, as shown in the reference. Figure 5 The system may include: a perception module 510, a semi-trailer parameter approximate solution identification module 520, a semi-trailer parameter optimal solution identification module 530, a semi-trailer top-level path tracking control module 540, a semi-trailer bottom-level angle tracking control module 550, a planning module 560, and a positioning module 570.

[0171] The perception module 510 is used to acquire detection parameters of the tractor and semi-trailer during parking. The planning module 560 and the positioning module 570 are used to assist other modules in vehicle control. The semi-trailer parameter approximate solution identification module 520 is used to determine an approximate solution for the first distance based on an adaptive genetic algorithm. This result is output to the semi-trailer parameter optimal solution identification module 530, which is used to determine the optimal solution for the first distance based on a quasi-Newton method. Subsequently, based on a hierarchical architecture, the tractor-semi-trailer path tracking control problem is decoupled into a top-level path tracking control sub-problem for the semi-trailer and a bottom-level angle tracking control sub-problem for the tractor. The top-level path tracking control module 540 for the semi-trailer uses a pure tracking algorithm to transform the path tracking error of the semi-trailer in the predicted time domain into a series of expected angles between the longitudinal axis of the semi-trailer and the velocity vector at the articulation point. The bottom-level angle tracking control module 550 for the tractor achieves accurate tracking of the expected angle between the longitudinal axis of the semi-trailer and the velocity vector at the articulation point by solving a constraint optimization problem. This ensures that the articulated vehicle always operates within a stable state during the reversing process, preventing the articulated vehicle from folding and becoming unstable during reversing and improving the success rate of reversing into a parking space.

[0172] Figure 6 This is a schematic diagram of an articulated vehicle parking control device provided in an embodiment of this application. This device can be deployed in vehicle-mounted equipment, such as… Figure 6 As shown, the device may include: a first determining module 610, a second determining module 620, a third determining module 630, and a control module 640.

[0173] The first determining module 610 is used to determine a first distance based on the monitoring parameters of the tractor and the semi-trailer. The first distance is the distance from the articulation point of the tractor and the semi-trailer to the midpoint of the rear axle of the semi-trailer.

[0174] The second determining module 620 is used to determine the first included angle based on the first distance and the path parameters during the semi-trailer parking process. The first angle is the angle between the longitudinal axis of the semi-trailer and the velocity vector of the hinge point.

[0175] The third determining module 630 is used to determine the front wheel steering angle parameters of the tractor based on the first distance and the first included angle.

[0176] The control module 640 is used to perform parking control operations on the tractor and semi-trailer based on the front wheel steering angle parameters of the tractor.

[0177] For specific procedures, please refer to the description of the formula calculation above.

[0178] Corresponding to the above embodiments, this application also provides an electronic device that can be used to implement the above-described vehicle-mounted device. Figure 7This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. The electronic device 700 may include a processor 701, a memory 702, and a communication unit 703. These components communicate through one or more buses. Those skilled in the art will understand that the structure of the electronic device shown in the figure does not constitute a limitation on the embodiment of this application. It may be a bus topology or a star topology, and may include more or fewer components than shown, or combine certain components, or have different component arrangements.

[0179] The communication unit 703 is used to establish a communication channel, enabling the electronic device to communicate with other devices. It receives user data from other devices or sends user data to other devices.

[0180] The processor 701 serves as the control center of the electronic device, connecting various parts of the device via various interfaces and lines. It executes software programs, instructions, and / or modules stored in the memory 702, and calls data stored in the memory to perform various functions and / or process data. The processor may be composed of integrated circuits (ICs), such as a single packaged IC or multiple packaged ICs with the same or different functions connected together. For example, the processor 701 may consist only of a central processing unit (CPU). In this embodiment, the CPU may have a single processing core or include multiple processing cores.

[0181] The memory 702 is used to store the execution instructions of the processor 701. The memory 702 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk or optical disk.

[0182] When the execution instructions in memory 702 are executed by processor 701, the electronic device 700 is able to perform some or all of the steps in the above embodiments.

[0183] In a specific implementation, this application also provides a computer storage medium, which may store a program that, when executed, may include some or all of the steps of the various embodiments of the articulated vehicle parking control method provided in this application. The storage medium may be a magnetic disk, optical disk, read-only memory (ROM), or random access memory (RAM), etc.

[0184] In a specific implementation, this application also provides a computer program product, wherein the computer program product includes executable instructions, which, when executed on a computer, cause the computer to perform some or all of the steps in various embodiments of the articulated vehicle parking control method provided in this application.

[0185] This application also provides a non-transitory computer-readable storage medium that stores computer instructions that cause the computer to execute the articulated vehicle parking control method provided in this application.

[0186] The aforementioned non-transitory computer-readable storage medium may be any combination of one or more computer-readable media. A computer-readable medium may be a computer-readable signal medium or a computer-readable storage medium. A computer-readable storage medium may be, for example,—but not limited to—an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of computer-readable storage media (a non-exhaustive list) include: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM), or flash memory, optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this document, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in connection with an instruction execution system, apparatus, or device.

[0187] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals may take various forms, including—but not limited to—electromagnetic signals, optical signals, or any suitable combination thereof. Computer-readable signal media may also be any computer-readable medium other than computer-readable storage media, capable of transmitting, propagating, or transmitting programs for use by or in connection with an instruction execution system, apparatus, or device.

[0188] The program code contained on a computer-readable medium may be transmitted using any suitable medium, including—but not limited to—wireless, wire, optical fiber, RF, etc., or any suitable combination thereof.

[0189] Those skilled in the art will clearly understand that the techniques in the embodiments of this application can be implemented using software plus necessary general-purpose hardware platforms. Based on this understanding, the technical solutions in the embodiments of this application, or the parts that contribute to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments of this application or some parts of the embodiments.

[0190] The same or similar parts between the various embodiments in this specification can be referred to mutually. In particular, the device embodiments and terminal embodiments are basically similar to the method embodiments, so the description is relatively simple, and the relevant parts can be referred to the description in the method embodiments.

Claims

1. A method for controlling the parking of articulated vehicles, characterized in that, include: A first distance is determined based on the monitoring parameters of the tractor and the semi-trailer. The first distance is the distance from the articulation point of the tractor and the semi-trailer to the midpoint of the rear axle of the semi-trailer. The first included angle is determined based on the first distance and the path parameters during the parking process of the semi-trailer. The first angle is the angle between the longitudinal axis of the semi-trailer and the velocity vector of the hinge point. The front wheel steering angle parameters of the tractor are determined based on the first distance and the first included angle. The parking control operation is performed on the tractor and the semi-trailer based on the front wheel steering angle parameters of the tractor.

2. The method according to claim 1, characterized in that, The determination of the first distance based on monitoring parameters of the tractor and semi-trailer includes: An approximate solution for the first distance is obtained based on an adaptive genetic algorithm; The approximate solution of the first distance is used as the initial value of the quasi-Newton method, and the monitoring parameters are processed based on the quasi-Newton method to obtain the optimal solution of the first distance.

3. The method according to claim 2, characterized in that, The approximate solution for the first distance obtained based on the adaptive genetic algorithm includes: Encode the first distance to obtain an initial population related to the first distance; Calculate the fitness of each individual in the current population; Genetic manipulation is performed on each individual in the current population based on fitness to obtain a new population, and the step of calculating the fitness of each individual in the current population is performed again. After the iteration is completed, the individual with the highest fitness is determined as the approximate solution for the first distance.

4. The method according to claim 2, characterized in that, The step of using the approximate solution of the first distance as the initial value of the quasi-Newton method and processing the monitoring parameters based on the quasi-Newton method to obtain the optimal solution of the first distance includes: Determine the initial search direction and search step size; The approximate solution of the first distance is updated based on the search direction and the search step size; If the updated distance parameters meet the preset conditions, the current distance parameters are determined as the optimal solution for the first distance. If the updated distance parameters do not meet the preset conditions, the steps of determining the initial search direction and search step size are re-executed.

5. The method according to claim 1, characterized in that, Determining the first included angle based on the first distance and the path parameters during the semi-trailer parking process includes: Determine the turning radius of the semi-trailer during parking; The first included angle is determined based on the turning radius and the first distance.

6. The method according to claim 1, characterized in that, Determining the front wheel steering angle parameters of the tractor based on the first distance and the first included angle includes: The rate of change of the first included angle is determined based on the monitoring parameters; The front wheel steering angle parameters of the tractor are determined based on the rate of change of the first included angle and the second distance, where the second distance is the distance from the midpoint of the rear axle of the tractor to the hinge point.

7. The method according to claim 1, characterized in that, The parking control operation for the tractor and the semi-trailer based on the front wheel steering angle parameters of the tractor includes: Determine the desired curvature of the midpoint of the rear axle of the semi-trailer; The semi-trailer is controlled to travel a preset distance with the desired curvature, and the first included angle is updated.

8. An articulated vehicle parking control device, characterized in that, include: The first determining module is used to determine a first distance based on the monitoring parameters of the tractor and the semi-trailer, wherein the first distance is the distance from the articulation point of the tractor and the semi-trailer to the midpoint of the rear axle of the semi-trailer; The second determining module is used to determine a first included angle based on the first distance and the path parameters during the parking process of the semi-trailer, wherein the first angle is the angle between the longitudinal axis of the semi-trailer and the velocity vector of the hinge point; The third determining module is used to determine the front wheel steering angle parameters of the tractor vehicle based on the first distance and the first included angle. The control module is used to perform parking control operations on the tractor and the semi-trailer based on the front wheel steering angle parameters of the tractor.

9. An electronic device, characterized in that, The device includes a memory for storing computer program instructions and a processor for executing the program instructions, wherein when the computer program instructions are executed by the processor, the electronic device performs the method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes a stored program, wherein, when the program is executed, it controls the device on which the computer-readable storage medium is located to perform the method according to any one of claims 1 to 7.

Images