Vehicle control method and system, electronic equipment and storage medium

Abstract

The invention provides a vehicle control method and system, electronic equipment and a storage medium, and belongs to the technical field of automatic control, and the method comprises the steps: obtaining a current position and a steering type of a vehicle, and obtaining a vehicle path curve; according to the current position and all the sub-path segments, a reference point closest to the current position on the vehicle path curve is determined; the real-time curvature of the reference point is calculated, and the position deviation and the angle deviation between the current position and the reference point are calculated; and the real-time curvature, the position deviation and the angle deviation are substituted into a preset control model corresponding to the steering type, and the control quantity used for controlling vehicle steering is obtained. According to the method, through the path smoothing method based on curve fitting and calculation of the real-time curvature, the position deviation and the angle deviation, the real-time curvature, the position deviation and the angle deviation are substituted into the kinematics control model corresponding to the vehicle steering type, the accurate steering control quantity is generated, and the precision and stability of vehicle path control are effectively improved under the condition of a complex path.

Description

Technical Field

[0001] The present invention relates to the technical field of automatic control, and particularly to a vehicle control method, system, electronic device, and storage medium. Background Art

[0002] With the rapid development of autonomous driving technology, path tracking control of vehicles in complex road environments has become one of the key technologies.

[0003] Currently, autonomous vehicles generally adopt a control method based on a predetermined path, obtaining the real-time position of the vehicle through sensors and comparing it with the preset path to achieve precise navigation and steering. However, existing technologies mostly approximate curved paths as a series of short straight-line segments, relying on high-frequency position information sampling and simple path tracking algorithms for control. This method can maintain a good control effect under low-curvature and low-speed driving conditions, but under high-curvature or complex road conditions, due to path approximation errors and limitations of control algorithms, it is often difficult to achieve precise path tracking, resulting in large lateral deviations and unstable heading adjustments during vehicle driving.

[0004] Therefore, how to improve the accuracy and stability of vehicle path control under complex path conditions has become a technical problem that urgently needs to be solved. Summary of the Invention

[0005] The present invention provides a vehicle control method, system, electronic device, and storage medium to solve the defects in the prior art and achieve improving the accuracy and stability of vehicle path control under complex path conditions.

[0006] The present invention provides a vehicle control method, including the following steps: Obtain the current position and steering type of the vehicle, and obtain the vehicle path curve; the vehicle path curve is obtained by fitting a plurality of preset vehicle passing points; Determine the reference point on the vehicle path curve that is closest to the current position according to the current position and all sub-path segments; the sub-path segments are obtained by segmenting the vehicle path curve according to all the preset vehicle passing points; Calculate the real-time curvature at the reference point, and calculate the position deviation and angle deviation between the current position and the reference point; Substitute the real-time curvature, the position deviation, and the angle deviation into the control model corresponding to the steering type, and solve the control model to obtain the control quantity for controlling the vehicle steering.

[0007] A vehicle control method provided according to the present invention, determining a reference point closest to the current position on the vehicle path curve according to the current position and all sub-path segments, specifically includes: Establish a corresponding first local coordinate system for each of the sub-path segments, with the origin of the first local coordinate system set at the starting passing point of the corresponding sub-path segment, and the x-axis direction of the first local coordinate system pointing from the starting point of the previous sub-path segment to the starting point of the subsequent sub-path segment; Convert the current position into each of the first local coordinate systems, and calculate the lateral offset of the converted current position in each of the local coordinate systems; Select the sub-path segment with the smallest lateral offset from all the lateral offsets; Determine the reference point closest to the current position from the selected sub-path segment.

[0008] A vehicle control method provided according to the present invention, calculating the real-time curvature at the reference point, specifically includes: Extract the first derivative and the second derivative of the vehicle path curve at the reference point; Calculate the real-time curvature at the reference point according to the first derivative and the second derivative according to the definition formula of curvature.

[0009] A vehicle control method provided according to the present invention, calculating the position deviation and the angle deviation between the current position and the reference point, specifically includes: Establish a second local coordinate system with the reference point as the origin and the tangent direction of the reference point as the x-axis at the reference point; Calculate the tangent inclination angle of the reference point in the world coordinate system; Convert the current position into the second local coordinate system according to the tangent inclination angle to obtain the converted abscissa and the converted ordinate of the vehicle in the second local coordinate system; Obtain the current heading angle of the vehicle in the world coordinate system; Take the converted ordinate as the position deviation, and take the angle difference between the current heading angle and the tangent inclination angle as the angle deviation.

[0010] A vehicle control method provided according to the present invention, the method further includes: Perform cubic B-spline curve fitting on a plurality of the preset vehicle passing points to obtain the vehicle path curve; wherein, the B-spline curve adopts non-uniform node setting, the node parameters are allocated by the centripetal parameterization method, and the head and tail end nodes are set in the form of multiple coincidences of the head and tail nodes, and the node parameters are determined by the cumulative value of the square roots of the Euclidean distances between adjacent preset vehicle passing points.

[0011] A vehicle control method provided by the present invention, the steering type includes Ackermann steering type, and the control quantity includes a first control parameter; substituting the real-time curvature, the position deviation, and the angle deviation into a preset control model corresponding to the steering type to obtain a control quantity for controlling vehicle steering, specifically including: Obtain the current speed and the front and rear wheelbase of the vehicle; Substitute the current speed, the front and rear wheelbase, the real-time curvature, the position deviation, and the angle deviation into a first kinematic model of a vehicle based on the Ackermann steering type, and solve the first kinematic model according to a preset method to obtain the first control parameter.

[0012] A vehicle control method provided by the present invention, the steering type further includes articulated steering type, and the control quantity further includes a second control parameter; substituting the real-time curvature, the position deviation, and the angle deviation into a preset control model corresponding to the steering type to obtain a control quantity for controlling vehicle steering, specifically further including: Obtain the current speed, the front wheelbase, and the rear wheelbase of the vehicle; Substitute the current speed, the front wheelbase, the rear wheelbase, the real-time curvature, the position deviation, and the angle deviation into a second kinematic model of a vehicle based on the articulated steering type, and solve the second kinematic model according to a preset method to obtain the second control parameter.

[0013] According to a vehicle control method provided by the present invention, the preset method is any one of a linear quadratic regulation control method and a model predictive control method.

[0014] The present invention further provides a vehicle control system, including the following modules: An acquisition module, configured to acquire the current position and the steering type of the vehicle, and acquire a vehicle path curve; the vehicle path curve is obtained by fitting a plurality of preset vehicle passing points; A first processing module, configured to determine a reference point on the vehicle path curve that is closest to the current position according to the current position and all sub-path segments; the sub-path segments are obtained by segmenting the vehicle path curve according to all the preset vehicle passing points; A second processing module, configured to calculate the real-time curvature at the reference point, and calculate the position deviation and the angle deviation between the current position and the reference point; A third processing module, configured to substitute the real-time curvature, the position deviation, and the angle deviation into a control model corresponding to the steering type, and solve the control model to obtain a control quantity for controlling vehicle steering.

[0015] The present invention also provides an electronic device, including a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the program, the vehicle control method described in any one of the above is implemented.

[0016] The present invention also provides a non-transitory computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the vehicle control method described in any one of the above is implemented.

[0017] The present invention also provides a computer program product, including a computer program. When the computer program is executed by a processor, the vehicle control method described in any one of the above is implemented.

[0018] In summary, one or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages: By obtaining the current position and steering type of the vehicle and obtaining the vehicle path curve, it is possible to identify the input information required for path tracking according to the current state of the vehicle, ensuring the real-time performance and accuracy of control calculation. Further, according to the current position of the vehicle and all sub-paths of the path curve, a reference point closest to the current position on the vehicle path curve is determined, where the sub-path segment is obtained by segmenting the path curve. Through this segmented search method, the search range can be effectively reduced, the calculation efficiency can be improved, and at the same time, through the refined positioning of the local path segment, it is ensured that the closest reference point can be found quickly and accurately, avoiding the accumulation of path deviation caused by inaccurate search. Based on this reference point, the real-time curvature of the path, the position deviation and the angle deviation between the current position and the reference point are calculated. Through the calculation of the real-time curvature, the local bending characteristics of the path can be accurately described, providing a feedforward quantity for subsequent control and improving the response ability on the curved path. And through the calculation of the position deviation and the angle deviation, the lateral displacement error and the heading difference between the vehicle and the path can be accurately measured, providing real-time error information for vehicle control and ensuring the dynamic monitoring and correction of the deviation state of the vehicle. Finally, substituting the real-time curvature, the position deviation, and the angle deviation into the preset control model corresponding to the steering type, and by solving this model, a control quantity for controlling the vehicle steering can be generated. Among them, for different vehicle steering types, such as Ackermann steering and articulated steering, corresponding kinematic control models are respectively used for solution. By introducing the real-time curvature as a feedforward control term and combining the feedback adjustment of the position deviation and the angle deviation, the precise control of vehicle path tracking is realized. This control method can not only improve the real-time performance and accuracy, but also effectively improve the accuracy and stability of vehicle path control under complex path conditions. Description of the Drawings

[0019] To more clearly illustrate the technical solutions in the present invention or the prior art, the following will briefly introduce the accompanying drawings required in the description of the embodiments or the prior art. Obviously, the accompanying drawings in the following description are some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other accompanying drawings can also be obtained based on these drawings.

[0020] Figure 1 It is one of the flow schematic diagrams of the vehicle control method provided by the present invention.

[0021] Figure 2 It is another flow schematic diagram of the vehicle control method provided by the present invention.

[0022] Figure 3 It is the third flow schematic diagram of the vehicle control method provided by the present invention.

[0023] Figure 4 It is the fourth flow schematic diagram of the vehicle control method provided by the present invention.

[0024] Figure 5 It is the fifth flow schematic diagram of the vehicle control method provided by the present invention.

[0025] Figure 6 It is the sixth flow schematic diagram of the vehicle control method provided by the present invention.

[0026] Figure 7 It is the seventh flow schematic diagram of the vehicle control method provided by the present invention.

[0027] Figure 8 It is the structural schematic diagram of the vehicle control system provided by the present invention.

[0028] Figure 9 It is the structural schematic diagram of the electronic device provided by the present invention. Detailed implementation manners

[0029] To make the objectives, technical solutions and advantages of the present invention clearer, the following will clearly and completely describe the technical solutions in the present invention in conjunction with the accompanying drawings in the present invention. Obviously, the described embodiments are some, but not all, of the embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art without creative efforts based on the embodiments in the present invention belong to the scope protected by the present invention.

[0030] It should be noted that in the description of the present invention, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements not only includes those elements, but also includes other elements not expressly listed, or also includes elements inherent to such process, method, article or device. Without further limitation, an element defined by the statement "including one..." does not exclude the existence of additional identical elements in the process, method, article or device including the said element. The orientation or positional relationship indicated by terms such as "upper", "lower", etc. is based on the orientation or positional relationship shown in the drawings, and is only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the system or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and thus cannot be construed as a limitation on the present invention. For those of ordinary skill in the art, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0031] The terms "first", "second", etc. in the present invention are used to distinguish similar objects, rather than to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged under appropriate circumstances, so that the embodiments of the present invention can be implemented in an order other than those illustrated or described herein, and the objects distinguished by "first", "second", etc. are usually of the same category, and do not limit the number of objects. For example, the first object can be one or multiple. In addition, "and / or" means at least one of the connected objects, and the character " / ", generally represents an "or" relationship between the associated objects before and after.

[0032] The following is combined with Figures 1-9 to describe the vehicle control method, system, electronic device and storage medium provided by the present invention.

[0033] Figure 1 is one of the flow diagrams of the vehicle control method provided by the present invention. As Figure 1 shown, it includes but is not limited to the following steps: Step 101: Obtain the current position and steering type of the vehicle, and obtain the vehicle path curve; the vehicle path curve is obtained by fitting a plurality of preset vehicle passing points.

[0034] This solution is mainly applied to the automatic control of agricultural machinery vehicles, loading and unloading vehicles, mining area transport vehicles, etc. During the path tracking control of vehicles of the above types, it is first necessary to obtain the current position and steering type of the vehicle, and construct a path curve suitable for vehicle navigation. In this solution, the steering types include Ackermann steering type and articulated steering type. The reason for this is that in the scenario of autonomous driving, the vehicle needs to identify its own position in real time and perform precise control according to the preset path, and the quality of the path curve directly affects the accuracy of path tracking and the control effect. If the path curve is discontinuous or has insufficient accuracy, especially in the scenario of a curved path, it is easy to cause the vehicle to deviate from the preset path, resulting in a decline in control performance and even safety problems. In this application, multiple preset vehicle passing points can be fitted by methods such as B-spline curves and Bezier curves. However, for vehicle control, the performance of B-spline curves is the best. Therefore, in order to construct a path curve with high precision, continuity and suitability for vehicle control, this application proposes a solution to fit multiple preset vehicle passing points by B-spline curves.

[0035] In a possible implementation manner, referring to Figure 2 , Figure 2 is the second flowchart of the vehicle control method provided by the present invention. As Figure 2 shown, the method for obtaining the vehicle path curve specifically includes step 201: Step 201: Perform cubic B-spline curve fitting on multiple preset vehicle passing points to obtain a vehicle path curve; wherein, the B-spline curve adopts a non-uniform node setting, the node parameters are allocated by the centripetal parameterization method, and the head and tail end nodes are set in the form of multiple coincidences of the head and tail nodes, and the node parameters are determined by the cumulative value of the square roots of the Euclidean distances between adjacent preset vehicle passing points.

[0036] During the vehicle path tracking control process, in order to obtain a vehicle path curve with high precision, continuity and smoothness, it is necessary to perform cubic B-spline curve fitting on multiple preset vehicle passing points. The reason for this is that the core of vehicle path control lies in the accuracy and stability of path tracking, and the quality of the path curve directly affects the subsequent real-time curvature calculation, position deviation judgment and steering control effects. Existing methods often approximate the path as short straight line segments. Although the calculation is simple, it will introduce large path errors under high curvature or complex paths, resulting in a decline in control accuracy, obvious jitter and deviation during vehicle driving, and unable to meet the requirements of autonomous driving for smooth paths. Therefore, through cubic B-spline curve fitting, the above problems can be effectively solved, and a continuous, smooth and high-precision path curve can be provided.

[0037] Specifically, when fitting the vehicle path curve, multiple preset vehicle passing points are used as the basic input first. These passing points represent the key points on the planned path of the vehicle. To ensure the smoothness of the fitted curve and the continuity of the path, a cubic B-spline curve is used for fitting. The cubic B-spline curve can not only meet the continuity, but also has good smoothness and local adjustability, that is, when adjusting a certain control point, it will only affect the curve shape in the local area, and will not damage the structure of the overall curve, thereby improving the stability of the path curve.

[0038] In terms of node parameter setting, in order to accurately reflect the spatial distribution between each passing point, a non-uniform node setting is adopted, and the node parameters are allocated by the centripetal parameterization method. The centripetal parameterization method uses the cumulative value of the square roots of the Euclidean distances between adjacent vehicle passing points as the node parameters, so as to adjust the node interval according to the actual distance between the passing points, avoiding the curve fitting error problem caused by uniform distribution, and making the path curve more conform to the actual path. Specifically, the centripetal parameterization method can improve the fitting accuracy at the dense distribution of path points, and maintain sufficient smoothness in the sparse area of path points, so that the overall shape of the path curve is more natural.

[0039] In addition, in order to make the path curve consistent with the tangent direction of the actual path at the starting point and the ending point, a special setting of multi-fold coincidence of the head and tail nodes (i.e., the Clamped form) is adopted for the head and tail nodes. In this form, the head and tail nodes are repeated three times respectively (corresponding to the cubic B-spline curve), so as to force the curve to coincide with the tangent direction of the passing points at the starting point and the ending point. This setting can effectively avoid unreasonable bending or curvature mutation of the path curve at the head and tail endpoints, and ensure the continuity and smooth transition of the path curve.

[0040] More specifically, the B-spline curve is described by the degree p, the knots and the control points , where the degree p, the number of knots m + 1, and the number of control points n + 1 satisfy m = n + p + 1.

[0041] The points on the B-spline curve are ; where is the basis function, is the control point, can be obtained from the following recurrence formula: When , ; When , ; Since the following mainly discusses the cases of p = 1, p = 2, and p = 3, when p = 1, ; ; When p = 2, ; ; ; When p = 3, ; ; ; ; , .

[0042] According to the above formula derivation, the following important properties can be obtained: For , when , and , only a total of p + 1 basis functions are zero. Therefore, ; In particular, when , only a total of p basis functions are zero. Therefore, .

[0043] Furthermore, the derivative of the B-spline basis function is: ; ; Let , then the following can be obtained: ; For the clamped B-spline form, , , when both of these two cases are treated as 0, the final form of the derivative of the B-spline is: ; The derivative of the p-th order "Clamped" B-spline is a (p - 1)-th order B-spline, and the number of control points of the derivative is 1 less than that of the B-spline, and the number of knots is 2 less than that of the B-spline. The head and tail knots of the original knot sequence are removed respectively. Therefore, the derivative curve is also a "Clamped" B-spline.

[0044] According to the definition of B-spline curve, assume that multiple preset vehicle passing points are respectively . The centripetal parameter method with better performance is adopted for the value selection of nodes, that is, the parameter u of the current value point is the accumulated value of the square roots of the lengths of all previous value points , and at the same time, the Clamped form is adopted, that is, the first and last nodes are repeated p + 1 times, and the first and last endpoints are the first and last two control points. The nodes are as follows: ; The remaining is to solve the control points ; First, establish the fitting equation. B-spline curve has an important property, that is, each node will map to the corresponding point on the curve while satisfying , that is: ; ; ; ; ; ; ; It can be known that ; Written in matrix form as follows, ; The reason why the first row and the last row in the above coefficient matrix are expressed as is that the spline curve adopts the Clamped form, so its first and last endpoints are the first and last control points.

[0045] When p = 3, the number of the above equations is ones, and the number of unknowns is ones. To solve completely, 2 more equations are needed, and the derivative vectors of the first and last points can provide 2 more equations; Given 3 points , estimate .

[0046] From , a quadratic curve passing through 3 points can be fitted. The equation is as follows, ; The derivative vector with respect to the parameter t is: ; When is the case, ; Let and ; ; When is the case, ; When is the case, Referring to the centripetal parameter method, the parameter t can be determined as follows: ; According to the derivative principle of the B-spline curve, we can obtain: ; ; That is ; Then the fitting equation is: ; Solving the above system of equations can obtain the control points of the curve, and then the vehicle path curve can be obtained.

[0047] Step 102: Determine the reference point on the vehicle path curve that is closest to the current position according to the current position and all sub-path segments; the sub-path segments are obtained by segmenting the vehicle path curve based on all preset vehicle passing points.

[0048] In vehicle path tracking control, in order to achieve high-precision tracking of the vehicle on the target path, it is necessary to first determine the corresponding point on the path curve of the vehicle, that is, the reference point closest to the current position. This step is crucial because the real-time deviation calculation and subsequent control decisions of the vehicle depend on the accurate positioning of the reference point. If the closest reference point cannot be determined quickly and accurately, the accuracy of path tracking will be greatly reduced, resulting in the vehicle deviating from the target path, especially in complex curved paths, there may be large lateral offsets or control delays. Therefore, by segmenting the path curve and searching for the closest point based on the local coordinate system, the calculation efficiency can be effectively improved and the accuracy of the result can be guaranteed.

[0049] In a possible implementation, referring to Figure 3 , Figure 3 is the third schematic diagram of the process of the vehicle control method provided by the present invention. As Figure 3 shown, step 102 specifically includes steps 301-304: Step 301: Establish a corresponding first local coordinate system for each sub-path segment. The origin of the first local coordinate system is set at the starting passing point of the corresponding sub-path segment, and the x-axis direction of the first local coordinate system is from the starting point of the previous sub-path segment to the starting point of the subsequent sub-path segment.

[0050] Specifically, first segment the vehicle path curve to form multiple sub-path segments. Each sub-path segment corresponds to two adjacent preset vehicle passing points, that is . This segmentation process can not only ensure that the local characteristics of the path curve are relatively simple, facilitating coordinate transformation and deviation calculation, but also provide natural starting points and direction information for the establishment of the local coordinate system.

[0051] For each sub-path segment, establish a first local coordinate system based on its starting passing point. The origin of this local coordinate system is set at the starting passing point of the corresponding sub-path segment , and the starting passing point is the starting point of the sub-path segment, that is, the first preset vehicle passing point of the sub-path segment. The x-axis direction of the local coordinate system is from the starting point of the previous sub-path segment to the starting point of the subsequent sub-path segment. Specifically, by calculating the vector direction between the starting point of the sub-path segment and the starting point of the subsequent sub-path segment, the inclination angle of the tangent direction can be obtained , and then the x-axis direction of the local coordinate system can be determined. On this basis, using the definition of the local coordinate system, the vehicle position in the world coordinate system can be converted into the current local coordinate system, simplifying the subsequent deviation calculation and matching process.

[0052] Step 302: Convert the current position into each first local coordinate system and calculate the lateral offset of the converted current position in each local coordinate system.

[0053] During the vehicle path tracking control process, in order to accurately determine the relationship between the current vehicle position and the path curve, especially for matching within the local path range, it is necessary to convert the current vehicle position into each first local coordinate system and calculate the lateral offset in each local coordinate system. The reason for coordinate transformation is that directly calculating the deviation between the vehicle and the path in the world coordinate system has a high computational complexity and is not easy to optimize. Especially in the sub-paths after the path curve is segmented, the coordinate system switching and unified calculation of the offset are particularly important. By mapping the current vehicle position into the local coordinate system corresponding to the sub-path, the calculation logic of the position deviation can be effectively simplified, improving the real-time performance and accuracy of the calculation.

[0054] Specifically, first according to the first local coordinate system established in Step 301, the origin of this coordinate system is located at the starting passing point of the sub-path segment , and its x-axis direction is from the starting point of the previous sub-path segment to the starting point of the subsequent sub-path segment, and the tangent inclination angle is The current position of the vehicle is represented in the world coordinate system as , and in order to express the position of the vehicle in the local coordinate system, the coordinate mapping is completed through the following coordinate transformation formula: ; where represents the projection of the vehicle along the x-axis direction in the local coordinate system, that is, the longitudinal position; represents the projection of the vehicle along the y-axis direction in the local coordinate system, that is, the lateral position offset.

[0055] After the coordinate transformation is completed, focus on the lateral offset of the vehicle in the local coordinate system, because the lateral offset can reflect the lateral deviation between the current position of the vehicle and the tangent direction of the sub-path. By performing the same coordinate transformation on the local coordinate systems of multiple sub-path segments, a set of lateral offsets of the vehicle in all local coordinate systems can be obtained. The key to this step is to eliminate the problem of deviation accumulation caused by the curvature of the path curve in the world coordinate system through the unified definition of the local coordinate system and the tangent direction, thereby simplifying the calculation logic of the offset and improving the accuracy of offset comparison.

[0056] Step 303: Select the sub-path segment with the minimum lateral offset from all the lateral offsets.

[0057] Since in a curved path or complex environment, the global search has a large computational amount and poor real-time performance. Therefore, by comparing the lateral offsets of each sub-path segment and selecting the sub-path segment with the minimum lateral offset, the search range can be effectively reduced, and the calculation efficiency and path matching accuracy can be improved.

[0058] Specifically, the current position of the vehicle has been mapped to the first local coordinate system of each sub-path segment through coordinate transformation in step 302, and the corresponding lateral offset has been calculated in each local coordinate system. Since the smaller the value of the lateral offset, the closer the vehicle is to the corresponding sub-path segment, therefore, by comparing the lateral offsets of all sub-path segments, the sub-path segment closest to the vehicle can be quickly determined.

[0059] Step 304: Determine the reference point closest to the current position from the selected sub-path segment.

[0060] Specifically, in the selected sub-path segment, the corresponding node interval is defined by the starting passing point and the ending passing point. On this sub-path segment, the path parameter u is subdivided, that is, the continuous path curve is discretized into several tiny path points, and the coordinates corresponding to each path point can be obtained by solving the B-spline curve equation.

[0061] Subsequently, the coordinates of the current position of the vehicle Calculate the Euclidean distance from the coordinates of each discrete path point on the sub-path segment. By traversing the Euclidean distances of all discrete path points, select the path point with the smallest distance as the nearest reference point of the vehicle's current position on the path curve. The corresponding path parameter is also determined simultaneously and used as the input parameter for subsequent path feature calculation.

[0062] Step 103: Calculate the real-time curvature at the reference point, and calculate the position deviation and angle deviation between the current position and the reference point.

[0063] During the vehicle path tracking control process, in order to achieve high-precision path control of the vehicle's current position, it is necessary to calculate the real-time curvature of the path curve at the nearest reference point, and further determine the position deviation and angle deviation between the vehicle's current position and the reference point. The reason for performing this step is that the real-time curvature can accurately reflect the local geometric characteristics of the path, and the position deviation and angle deviation can describe the deviation degree between the vehicle and the path. These key parameters are important inputs for generating control quantities in the subsequent vehicle control model. If these parameters cannot be accurately calculated, it will cause the control system to be unable to adjust the vehicle's steering in a timely manner, especially in curved paths or complex dynamic environments, resulting in problems such as a decrease in path tracking accuracy and a deterioration of system stability.

[0064] In a possible implementation manner, referring to Figure 4 , Figure 4 is the fourth flow chart of the vehicle control method provided by the present invention. As Figure 4 shown, the method for calculating the real-time curvature at the reference point specifically includes steps 401-402: Step 401: Extract the first derivative and second derivative of the vehicle path curve at the reference point.

[0065] During the vehicle path tracking control process, in order to accurately calculate the real-time curvature of the path curve at the nearest reference point, it is first necessary to extract the first derivative and second derivative of the path curve at this point. The reason for performing this operation is that the calculation of the real-time curvature depends on the geometric characteristics of the path at this point, and the first derivative and second derivative respectively reflect the tangent direction of the path and the degree of curve bending. Only by accurately extracting these derivative values can the accuracy of the curvature calculation be ensured, thereby providing high-precision data support for the subsequent steering control of the vehicle.

[0066] Specifically, the path curve is obtained by fitting a cubic B-spline curve, and its mathematical expression is: ; where represents the point coordinates at parameter u on the path curve, is the cubic B-spline basis function, Let \(P_i\) be the control points and \(n\) be the number of control points. To extract the first - order and second - order derivatives, the above cubic B - spline curve needs to be differentiated.

[0067] According to the derivative property of the B - spline curve, the first - order derivative of the path curve can be expressed as: ; where is the derivative of the cubic B - spline basis function. Further, differentiating the first - order derivative again, the second - order derivative of the path curve can be obtained: ; where is the second - order derivative of the cubic B - spline basis function. The solution processes of these two derivatives will cause the degree of the B - spline curve to decrease and the knot sequence of the basis function to change, but the reconstruction of the control points can ensure the continuity and accuracy of the derivative curve and the original curve.

[0068] In actual calculations, first, according to the path parameter corresponding to the nearest reference point determined in step 304, substitute it into the first - order derivative expression and the second - order derivative expression , then the first - order derivative and the second - order derivative of the path curve at this point can be solved. The first - order derivative represents the components of the path tangent direction vector, including the x - direction derivative and the y - direction derivative ; the second - order derivative represents the trend of curvature change, including the x - direction second - order derivative and the y - direction second - order derivative .

[0069] The effects of extracting the first - order and second - order derivatives are reflected in the following aspects: On the one hand, the first - order derivative provides the tangent direction information of the path, providing basic data for subsequent establishment of the local coordinate system, calculation of the tangent inclination angle, and vehicle deviation; on the other hand, the second - order derivative provides the trend of curvature change of the path, which is the core input data for curvature calculation and can accurately describe the bending degree of the path at this point. The extraction process of these derivative information depends on the mathematical properties of the B - spline curve, which can ensure the continuity and smoothness of the calculation results and avoid the oscillation phenomenon generated by traditional polynomial curves in high - order derivative calculations.

[0070] Step 402: Calculate the real - time curvature at the reference point according to the first - order and second - order derivatives and the definition formula of curvature.

[0071] Specifically, substitute the first derivative and the second derivative into the definition formula of curvature , and calculate the real-time curvature at the reference point. The specific calculation formula is as follows: ; where: and represent the tangent direction vector components of the path at the reference point; and represent the second derivative of the path at the reference point, reflecting the bending trend of the path. The absolute value of the real-time curvature is larger, indicating that the bending degree of the path at this point is higher; when , the path is a straight line at this point.

[0072] By calculating the real-time curvature, the local geometric characteristics of the path curve at the nearest reference point can be effectively reflected. The effects of this calculation are reflected in two aspects: on the one hand, as a feedforward input in the vehicle control model, the real-time curvature can provide early steering adjustment information for the control system in the case of large changes in path curvature, reducing the path tracking error caused by curvature mutations; on the other hand, the accuracy of the real-time curvature depends on the high-order derivative characteristics of the B-spline curve, avoiding problems such as numerical oscillations or discontinuities in the process of calculating path curvature, thereby improving the stability and robustness of the system.

[0073] In a possible implementation manner, referring to Figure 5 , Figure 5 is the fifth schematic flow chart of the vehicle control method provided by the present invention. As shown in Figure 5 , the method for calculating the position deviation and angle deviation between the current position and the reference point specifically includes steps 501-505: Step 501: Establish a second local coordinate system with the reference point as the origin and the tangent direction of the reference point as the x-axis at the reference point.

[0074] In the process of vehicle path tracking control, in order to accurately describe the position relationship between the current position of the vehicle and the nearest reference point, a new second local coordinate system needs to be established at the reference point. The reason for this is that the local coordinate system can transform the complex world coordinate system problem into local coordinate calculation, simplifying the calculation logic of the deviation between the vehicle and the path. Especially for the curvature and local geometric characteristics of the path, the construction of the local coordinate system can more intuitively express the position deviation and angle deviation between the vehicle and the path. By establishing the second local coordinate system, subsequent coordinate transformation and deviation calculation can be carried out more efficiently, and accurate input data can be provided for the control model. The second local coordinate system takes the nearest reference point as the origin, the x-axis direction of which is along the tangent direction of the path curve at this reference point, and the y-axis direction is perpendicular to the x-axis, following the right-hand coordinate system rule.

[0075] Step 502: Calculate the tangent inclination angle of the reference point in the world coordinate system.

[0076] Specifically, the inclination angle of the tangent direction can be calculated through the first derivative of the path curve at the reference point: ; where and respectively represent the first derivatives of the path curve in the x - direction and y - direction at the nearest reference point.

[0077] Step 503: Convert the current position to the second local coordinate system according to the tangent inclination angle, and obtain the transformed abscissa and transformed ordinate of the vehicle in the second local coordinate system.

[0078] Specifically, the core of constructing the second local coordinate system is to convert the current position of the vehicle in the world coordinate system to the second local coordinate system with the reference point as the origin. The essence of this conversion is to rotate and translate the coordinates of the vehicle's current position relative to the reference point. The specific conversion formula is: ; where is the transformed abscissa of the vehicle in the second local coordinate system, is the transformed ordinate of the vehicle in the second local coordinate system.

[0079] Through this conversion, the longitudinal coordinate and the lateral coordinate of the vehicle in the local coordinate system can more intuitively represent the deviation relationship between the vehicle and the path.

[0080] Step 504: Obtain the current heading angle of the vehicle in the world coordinate system.

[0081] Specifically, the current heading angle of the vehicle can usually be measured in real - time by a heading angle sensor or gyroscope installed on the vehicle body. For Ackermann - steering vehicles, the heading angle can be directly calculated from the front - wheel steering angle and the vehicle body direction; for articulated - steering vehicles, the heading angle can be estimated from the articulation angle between the front and rear vehicle bodies and the vehicle body attitude information. In practical applications, this data is usually output in real - time by the vehicle's attitude sensor or vehicle - mounted controller to ensure the measurement accuracy and real - time performance of the heading angle.

[0082] Step 505: Take the transformed ordinate as the position deviation, and take the angle difference between the current heading angle and the tangent inclination angle as the angle deviation.

[0083] Specifically, the calculation of the position deviation and the angle deviation of the vehicle is based on the results in the previous steps: directly taking as the position deviation of the vehicle : ; Among them, the position deviation reflects the lateral distance error between the vehicle and the path, and its sign can indicate the direction in which the vehicle deviates from the path.

[0084] In addition, the calculation formula for the angle deviation is: Among them, the angle deviation reflects the included angle between the actual heading of the vehicle and the tangent direction of the path, and can directly describe the direction deviation of the vehicle. If the angle deviation is large, the vehicle needs to quickly adjust its heading in order to return to the correct driving trajectory.

[0085] Through the above calculation process, the position deviation and the angle deviation jointly describe the deviation state between the vehicle and the path. The position deviation provides lateral position information, and the angle deviation provides heading offset information. The two complement each other and can comprehensively reflect the real-time path tracking error of the vehicle. These deviation parameters will be used as the key inputs of the subsequent vehicle control model to ensure that the control system can generate appropriate control quantities according to the actual deviations, so as to effectively adjust the direction and attitude of the vehicle and eliminate the position and angle errors.

[0086] Step 104: Substitute the real-time curvature, the position deviation, and the angle deviation into the preset control model corresponding to the steering type to obtain the control quantity for controlling the vehicle steering.

[0087] In the process of vehicle path tracking control, in order to ensure that the vehicle can accurately drive along the path curve, it is necessary to substitute these key parameters, namely the real-time curvature, the position deviation, and the angle deviation obtained from the previous calculation, into the preset control model corresponding to the vehicle steering type to solve for the control quantity for controlling the vehicle steering. The reason for this is that different types of vehicles (such as Ackermann steering vehicles and articulated steering vehicles) have different kinematic characteristics, and it is necessary to solve for the control quantity according to their specific steering models in order to effectively compensate for the path tracking deviation and adjust the vehicle attitude in real time. Without this step, the control system will not be able to generate appropriate steering instructions according to the current path tracking state of the vehicle, resulting in increased path deviation or unstable tracking.

[0088] In a possible implementation manner, referring to Figure 6 , Figure 6 is the sixth schematic diagram of the flow of the vehicle control method provided by the present invention, asFigure 6 As shown, when the steering type is the Ackermann steering type, step 104 at this time includes steps 601-602: Step 601: Obtain the current speed and the front and rear wheelbase of the vehicle.

[0089] Specifically, the current speed is usually obtained in real time through the vehicle's on-board speed sensor. The speed sensor can accurately measure the longitudinal speed of the vehicle, ensuring the real-time and accuracy of the speed information. During path tracking, the vehicle speed is the core input of the dynamic term in the control model, which affects the change rate of the vehicle deviation and the control response speed of the system. If the vehicle speed is obtained inaccurately or lagged, it will directly affect the execution effect of the control system, resulting in the vehicle being unable to smoothly track the path.

[0090] In addition, the front and rear wheelbase L of the Ackermann steering vehicle is an inherent parameter of the vehicle, which is usually determined during the vehicle design stage and stored in the vehicle's control system. The front and rear wheelbase is an important geometric parameter that determines the steering performance of the vehicle and affects the front wheel angle required during path tracking. Specifically, the larger the wheelbase, the larger the turning radius of the vehicle and the relatively lower steering sensitivity; conversely, the smaller the wheelbase, the more flexible the vehicle can turn, but the stability is relatively reduced. Therefore, accurately obtaining the wheelbase parameter of the vehicle can ensure an accurate description of the vehicle's kinematic characteristics by the control model.

[0091] Step 602: Substitute the current speed, the front and rear wheelbase, the real-time curvature, the position deviation, and the angle deviation into the first kinematic model of the vehicle based on the Ackermann steering type, and solve the first kinematic model according to the preset method to obtain the first control parameter.

[0092] Specifically, the lateral control of the vehicle with the Ackermann steering type is based on the standard kinematic model, which takes the real-time state parameters of the vehicle as inputs and describes the position deviation of the vehicle , the angle deviation , the real-time curvature , the current speed , the front and rear wheelbase L, and the relationship between the first control parameter (i.e., the front wheel angle). The form of the kinematic model is as follows: ; In actual calculations, the system will dynamically update the position deviation , the angle deviation and the real-time curvature by combining the current position and heading angle measured by the sensor with the path tangent direction and curvature. Substitute these parameters with the current speed Substitute it together with the front and rear wheelbase L into the above kinematic model. In order to solve the optimal first control parameter (i.e., the front wheel steering angle), , a preset method is used for solving. In this solution, the preset method is any one of the Linear Quadratic Regulator (LQR) and the Model Predictive Control (MPC).

[0093] In the LQR control method, the goal is to generate the optimal first control parameter (i.e., the front wheel steering angle) by minimizing the state error and control energy consumption of the vehicle. The specific steps include: Linearize the kinematic model to obtain a linear model of the vehicle deviation state; Design a cost function, usually including the weighting of position deviation, angle deviation, and control quantity; Solve the optimal control law to obtain the first control parameter (i.e., the front wheel steering angle) for real-time adjustment of the vehicle direction.

[0094] In the MPC control method, the system predicts the future motion trajectory based on the current state of the vehicle and generates the first control parameter (i.e., the front wheel steering angle) through the method of rolling optimization. The MPC method can fully consider the system constraints (such as the maximum front wheel steering angle and speed limit), has stronger adaptability to path tracking, and is especially suitable for high-dynamic scenarios.

[0095] By substituting the real-time curvature, position deviation, angle deviation, and the current speed and front and rear wheelbase of the vehicle into the kinematic model of the Ackermann steering vehicle and using the LQR or MPC method to solve, the system can generate the optimal first control parameter (i.e., the front wheel steering angle). The effects of this process are reflected in two aspects: on the one hand, the path curvature, as a feedforward factor, enables the control system to adjust the steering of the vehicle in advance and reduce the path tracking delay; on the other hand, combined with the feedback control of position deviation and angle deviation, the system can effectively eliminate lateral and heading errors and achieve high-precision path tracking of the vehicle.

[0096] In a possible implementation, refer to Figure 7 , Figure 7 is the seventh schematic diagram of the process of the vehicle control method provided by the present invention. As Figure 7 shown, when the steering type is the articulated steering type, step 104 at this time includes steps 701-702: Step 701: Obtain the current speed, front wheelbase, and rear wheelbase of the vehicle.

[0097] Specifically, the current speed of the articulated steering vehicle It is usually measured in real time by an on-vehicle speed sensor. The speed sensor can provide the speed information of the vehicle's longitudinal movement in real time, ensuring the accuracy and timeliness of the input data. In an articulated steering vehicle, the current speed is one of the key inputs for dynamically adjusting the control quantity, which affects the deviation change rate of the vehicle and the response speed of the system.

[0098] In addition, the front wheelbase and the rear wheelbase of an articulated steering vehicle are inherent geometric parameters of the vehicle, which are usually determined during the vehicle design stage and stored in the database of the vehicle control system. These two parameters determine the kinematic geometric relationship between the front and rear bodies of the vehicle. Especially when the vehicle performs a steering operation, the angle of the articulation point will cause an offset between the vehicle's tail and the path tracking target, and the different lengths of the front and rear wheelbases have a direct impact on the compensation ability for this offset. Therefore, accurately obtaining the front wheelbase and the rear wheelbase can ensure that the control model accurately describes the motion characteristics of the articulated steering vehicle, and further provide real and effective data support for the calculation of the control quantity.

[0099] Step 702: Substitute the current speed, the front wheelbase, the rear wheelbase, the real-time curvature, the position deviation, and the angle deviation into the second kinematic model of the vehicle based on the articulated steering type, and solve the second kinematic model according to the preset method to obtain the second control parameter.

[0100] Specifically, the lateral control of an articulated steering type vehicle is based on a standard kinematic model, which takes the real-time state parameters of the vehicle as inputs and describes the relationship between the position deviation , the angle deviation , the real-time curvature , the current speed , the front wheelbase , the rear wheelbase and the second control parameter (i.e., the articulation angle). The form of the kinematic model is as follows: ; In actual calculations, the system will dynamically update the position deviation , the angle deviation and the real-time curvature by combining the currently measured position and heading angle of the vehicle with the path tangent direction and curvature. Substitute these parameters together with the current speed , the front wheelbase , the rear wheelbase into the above kinematic model. In order to solve the optimal second control parameter (i.e., the articulation angle) , a preset method is used for solving. In this solution, the preset method is any one of the Linear Quadratic Regulator (LQR) and the Model Predictive Control (MPC).

[0101] In the LQR control method, the system designs a cost function to minimize the state deviation and control energy consumption of the vehicle. The cost function usually includes the position deviation , the angle deviation and the change in the articulation angle. On this basis, the system linearizes the kinematic model of the articulated steering vehicle, solves the optimal control law, and obtains the second control parameter (i.e., the articulation angle) to minimize the vehicle deviation and ensure stable path tracking.

[0102] In the MPC control method, the system uses the current state information of the vehicle to predict the future motion trajectory and rolling optimizes the second control parameter (i.e., the articulation angle). The advantage of the MPC method is that it can simultaneously consider the vehicle's constraint conditions, such as the maximum value of the articulation angle and the speed limit, during the path tracking process, so as to ensure that the control quantity of the system conforms to the actual vehicle motion characteristics, especially suitable for complex working conditions with large path curvatures or frequent dynamic changes.

[0103] Through the above method, the system can generate the optimal second control parameter (i.e., the articulation angle) applicable to the articulated steering vehicle, which is used to adjust the steering angle between the front and rear car bodies of the vehicle in real time to ensure that the vehicle travels smoothly along the target path. The effects of this process are reflected in two aspects: on the one hand, by taking the real-time curvature of the path as the feedforward quantity, the system can respond to the bending changes of the path in advance and improve the response speed of path tracking; on the other hand, combined with the feedback control of the position deviation and the angle deviation, the system can effectively eliminate the deviation during the dynamic driving process and improve the accuracy and stability of path tracking.

[0104] Referring to Figure 8 , Figure 8 is the structural schematic diagram of the vehicle control system provided by the present invention. The system includes: An acquisition module, configured to acquire the current position and steering type of the vehicle, and acquire the vehicle path curve; the vehicle path curve is obtained by fitting multiple preset vehicle passing points; A first processing module, configured to determine the reference point on the vehicle path curve that is closest to the current position according to the current position and all sub-path segments; the sub-path segments are obtained by segmenting the vehicle path curve according to all preset vehicle passing points; A second processing module, configured to calculate the real-time curvature at the reference point, and calculate the position deviation and angle deviation between the current position and the reference point; The third processing module is used to substitute the real-time curvature, position deviation, and angle deviation into the control model corresponding to the steering type, solve the control model, and obtain the control quantity for controlling the vehicle steering.

[0105] In a possible implementation manner, the first processing module is further used to: Establish a corresponding first local coordinate system for each sub-path segment. The origin of the first local coordinate system is set at the starting passing point of the corresponding sub-path segment, and the x-axis direction of the first local coordinate system is from the starting point of the previous sub-path segment to the starting point of the next sub-path segment; Convert the current position into each first local coordinate system and calculate the lateral offset of the converted current position in each local coordinate system; Select the sub-path segment with the minimum lateral offset from all the lateral offsets; Determine the reference point closest to the current position from the selected sub-path segment.

[0106] In a possible implementation manner, the second processing module is further used to: Extract the first derivative and the second derivative of the vehicle path curve at the reference point; Calculate the real-time curvature at the reference point according to the first derivative and the second derivative according to the definition formula of curvature.

[0107] In a possible implementation manner, the second processing module is further used to: Establish a second local coordinate system with the reference point as the origin and the tangent direction at the reference point as the x-axis at the reference point; Calculate the tangent inclination angle of the reference point in the world coordinate system; Convert the current position into the second local coordinate system according to the tangent inclination angle to obtain the converted abscissa and the converted ordinate of the vehicle in the second local coordinate system; Obtain the current heading angle of the vehicle in the world coordinate system; Take the converted ordinate as the position deviation and take the angle difference between the current heading angle and the tangent inclination angle as the angle deviation.

[0108] In a possible implementation manner, the first processing module is further used to perform cubic B-spline curve fitting on multiple preset vehicle passing points to obtain a vehicle path curve; wherein, the B-spline curve adopts non-uniform node settings, the node parameters are allocated by the centripetal parameterization method, and the head and tail nodes are set in the form of multiple coincidences of the head and tail nodes, and the node parameters are determined by the cumulative value of the square roots of the Euclidean distances between adjacent preset vehicle passing points.

[0109] In a possible implementation manner, the acquisition module is further used to acquire the current speed and the front and rear wheelbases of the vehicle; The third processing module is further configured to substitute the current speed, the front and rear wheelbase, the real-time curvature, the position deviation, and the angle deviation into a first kinematic model of a vehicle based on the Ackermann steering type, and solve the first kinematic model according to a preset method to obtain a first control parameter.

[0110] In a possible implementation manner, the obtaining module is further configured to obtain the current speed, the front wheelbase, and the rear wheelbase of the vehicle; The third processing module is further configured to substitute the current speed, the front wheelbase, the rear wheelbase, the real-time curvature, the position deviation, and the angle deviation into a second kinematic model of a vehicle based on the articulated steering type, and solve the second kinematic model according to a preset method to obtain a second control parameter.

[0111] It should be noted that the vehicle control system provided by the present invention can execute the vehicle control method of any of the above embodiments during specific operation, and details thereof are not described in this embodiment.

[0112] Figure 9 is a schematic structural diagram of an electronic device provided by the present invention. As Figure 9 shown, the electronic device may include: a processor 910 (processor), a communication interface 920 (Communications Interface), a memory 930 (memory), and a communication bus 940. Among them, the processor 910, the communication interface 920, and the memory 930 communicate with each other through the communication bus 940. The processor 910 can call the logical instructions in the memory 930 to execute the vehicle control method, and the method includes: obtaining the current position and steering type of the vehicle, and obtaining the vehicle path curve; the vehicle path curve is obtained by fitting a plurality of preset vehicle passing points; determining a reference point on the vehicle path curve that is closest to the current position according to the current position and all sub-path segments; the sub-path segments are obtained by segmenting the vehicle path curve according to all preset vehicle passing points; calculating the real-time curvature at the reference point, and calculating the position deviation and angle deviation between the current position and the reference point; substituting the real-time curvature, the position deviation, and the angle deviation into a preset control model corresponding to the steering type to obtain a control amount for controlling the vehicle steering.

[0113] In addition, when the logical instructions in the above-mentioned memory 930 are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or a part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods in various embodiments of the present invention. The foregoing storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memories (ROM, Read-Only Memory), random access memories (RAM, Random Access Memory), magnetic disks, or optical discs that can store program codes.

[0114] On the other hand, the present invention also provides a computer program product. The computer program product includes a computer program stored on a non-transitory computer-readable storage medium. The computer program includes program instructions. When the program instructions are executed by a computer, the computer can execute the vehicle control methods provided in the above-mentioned various embodiments. The method includes: obtaining the current position and steering type of the vehicle, and obtaining the vehicle path curve; the vehicle path curve is obtained by fitting a plurality of preset vehicle passing points; determining, according to the current position and all sub-path segments, a reference point on the vehicle path curve that is closest to the current position; the sub-path segments are obtained by segmenting the vehicle path curve according to all preset vehicle passing points; calculating the real-time curvature at the reference point, and calculating the position deviation and angle deviation between the current position and the reference point; substituting the real-time curvature, position deviation, and angle deviation into a preset control model corresponding to the steering type to obtain a control amount for controlling the vehicle steering.

[0115] In yet another aspect, the present invention also provides a non-transitory computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor 910, it is configured to execute the vehicle control methods provided in the above-mentioned various embodiments. The method includes: obtaining the current position and steering type of the vehicle, and obtaining the vehicle path curve; the vehicle path curve is obtained by fitting a plurality of preset vehicle passing points; determining, according to the current position and all sub-path segments, a reference point on the vehicle path curve that is closest to the current position; the sub-path segments are obtained by segmenting the vehicle path curve according to all preset vehicle passing points; calculating the real-time curvature at the reference point, and calculating the position deviation and angle deviation between the current position and the reference point; substituting the real-time curvature, position deviation, and angle deviation into a preset control model corresponding to the steering type to obtain a control amount for controlling the vehicle steering.

[0116] The system embodiments described above are merely illustrative. The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed to multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment. Those of ordinary skill in the art can understand and implement it without creative efforts.

[0117] Through the description of the above embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on such an understanding, the essence of the above technical solution, or the part that contributes to the prior art, can be embodied in the form of a software product. The computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods of each embodiment or some parts of the embodiments.

[0118] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit them. Although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements for some of the technical features. And these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A vehicle control method, characterized in that: include: Get the current position and steering type of the vehicle, and obtain the vehicle path curve; The vehicle path curve is obtained by fitting a plurality of preset vehicle passing points; Determine, based on the current position and all sub-path segments, a reference point on the vehicle path curve that is closest to the current position; The sub-path segments are obtained by segmenting the vehicle path curve according to all the preset vehicle passing points; Calculating the real-time curvature at the reference point, and calculating the position deviation and angle deviation between the current position and the reference point; The real-time curvature, the position deviation and the angle deviation are substituted into a control model corresponding to the steering type, and the control model is solved to obtain a control amount for controlling the steering of the vehicle.

2. The vehicle control method according to claim 1, characterized in that: The determining, based on the current position and all sub-path segments, a reference point on the vehicle path curve that is closest to the current position specifically includes: Establishing a corresponding first local coordinate system for each sub-path segment, wherein the origin of the first local coordinate system is set at the starting point of the corresponding sub-path segment, and the x-axis direction of the first local coordinate system is from the starting point of the previous sub-path segment to the starting point of the next sub-path segment; Convert the current position to each of the first local coordinate systems, and calculate the lateral offset of the converted current position in each of the local coordinate systems; selecting a sub-path segment having a minimum lateral offset from among all said lateral offsets; A reference point closest to the current position is determined from the selected sub-path segments.

3. The vehicle control method according to claim 1, characterized in that: The calculating the real-time curvature at the reference point specifically includes: Extracting a first-order derivative and a second-order derivative of the vehicle path curve at the reference point; The real-time curvature at the reference point is calculated according to the first-order derivative and the second-order derivative in accordance with a definition formula of curvature.

4. The vehicle control method according to claim 1, characterized in that: The calculating the position deviation and the angle deviation between the current position and the reference point specifically includes: Establishing a second local coordinate system at the reference point with the reference point as the origin and a tangent direction along the reference point as the x-axis; Calculating the tangent inclination angle of the reference point in the world coordinate system; Converting the current position to the second local coordinate system according to the tangent inclination angle to obtain a converted horizontal coordinate and a converted vertical coordinate of the vehicle in the second local coordinate system; Get the current heading angle of the vehicle in the world coordinate system; The converted ordinate is used as the position deviation, and the angle difference between the current heading angle and the tangent inclination angle is used as the angle deviation.

5. The vehicle control method according to claim 1, characterized in that: The method further comprises: A cubic B-spline curve is fitted for a plurality of the preset vehicle passing points to obtain the vehicle path curve; wherein the B-spline curve adopts a non-uniform node setting, the node parameters are allocated by a centripetal parameterization method, and the head and tail nodes are set in a multiple overlap form of the head and tail nodes, and the node parameters are determined by the cumulative value of the square root of the Euclidean distance between adjacent preset vehicle passing points.

6. The vehicle control method according to claim 1, characterized in that: The steering type includes an Ackerman steering type, and the control amount includes a first control parameter; the real-time curvature, the position deviation, and the angle deviation are substituted into a preset control model corresponding to the steering type to obtain a control amount for controlling the steering of the vehicle, specifically including: Get the current speed and front and rear wheelbase of the vehicle; The current speed, the front and rear wheelbase, the real-time curvature, the position deviation, and the angle deviation are substituted into a first kinematic model of a vehicle based on an Ackerman steering type, and the first kinematic model is solved according to a preset method to obtain the first control parameter.

7. The vehicle control method according to claim 1, characterized in that: The steering type includes an articulated steering type, the control amount includes a second control parameter; the real-time curvature, the position deviation, and the angle deviation are substituted into a preset control model corresponding to the steering type to obtain a control amount for controlling the steering of the vehicle, specifically including: Get the current speed, front wheelbase and rear wheelbase of the vehicle; The current speed, the front wheelbase, the rear wheelbase, the real-time curvature, the position deviation and the angle deviation are substituted into a second kinematic model of a vehicle based on an articulated steering type, and the second kinematic model is solved according to a preset method to obtain the second control parameters.

8. The vehicle control method according to claim 6 or 7, characterized in that: The preset method is any one of a linear quadratic regulation control method and a model predictive control method.

9. A vehicle control system, characterized in that: include: An acquisition module is used to obtain the current position and steering type of the vehicle and obtain the vehicle path curve; The vehicle path curve is obtained by fitting a plurality of preset vehicle passing points; A first processing module, configured to determine a reference point on the vehicle path curve that is closest to the current position based on the current position and all sub-path segments; The sub-path segments are obtained by segmenting the vehicle path curve according to all the preset vehicle passing points; A second processing module, used to calculate the real-time curvature at the reference point, and calculate the position deviation and angle deviation between the current position and the reference point; The third processing module is used to substitute the real-time curvature, the position deviation and the angle deviation into a control model corresponding to the steering type, and solve the control model to obtain a control amount for controlling the steering of the vehicle.

10. An electronic device comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that: When the processor executes the computer program, the vehicle control method according to any one of claims 1 to 8 is implemented.

11. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the vehicle control method according to any one of claims 1 to 8 is implemented.

12. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the vehicle control method according to any one of claims 1 to 8 is implemented.

Images