Vehicle trajectory control method in s-shaped curve, vehicle, and storage medium

Abstract

The application provides a driving track control method of a vehicle in an S-shaped curve, a vehicle and a storage medium, and relates to the technical field of intelligent driving. A discrete point set is fitted into a target curve of an Nth order polynomial, and since N is greater than or equal to 5, the shape of the real lane boundary can be more accurately and completely represented, and the reliability is high. Since the shape of the real lane boundary can be more accurately and completely represented, the target curve can be accurately identified as an S-shaped curve. In the case of identifying that the target curve is an S-shaped curve, the discrete point set of the S-shaped curve and the current motion state data of the vehicle are input into a preconfigured model predictive control algorithm to output a target driving track that minimizes the sum of the steering angles when the vehicle drives in the lane of the S-shaped curve, so that the lateral swing of the vehicle is small, the driving stability is high, and the driving safety and the driving experience of the user are further improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of intelligent driving, and particularly relates to a driving track control method of a vehicle in an S-shaped curve, a vehicle and a storage medium. BACKGROUND

[0002] Intelligent driving is a technology that combines advanced sensors, control systems, artificial intelligence and machine learning techniques, aiming to enable vehicles to safely drive without or with only a small amount of human intervention. In intelligent driving technology based on scene recognition, a vehicle can collect a discrete point set of a lane boundary, and then fit a lane curve based on a cubic polynomial. Since the cubic polynomial cannot accurately express the shape of the lane line, in order to avoid the vehicle from running out of the lane and causing safety accidents, the vehicle needs to be controlled to travel along the center line of the lane curve of the cubic polynomial. However, the safety of intelligent driving of the vehicle is still relatively low, and in the process of the vehicle traveling along the center line of the lane curve of the cubic polynomial, the sum of the turning angles of the vehicle is large, resulting in large lateral swing of the vehicle, low driving stability, low driving safety and poor driving experience. SUMMARY

[0003] The present application provides a driving track control method of a vehicle in an S-shaped curve, a vehicle and a storage medium, which are used to solve the problems of large lateral swing of the vehicle, low driving stability, low driving safety and poor driving experience in the prior art.

[0004] In a first aspect, the present application provides a driving track control method of a vehicle in an S-shaped curve, applied to a vehicle. The method provided by the present application comprises:

[0005] obtaining a discrete point set of a lane boundary in front of the vehicle;

[0006] fitting the discrete point set into a target curve, wherein the target curve is an N-th order polynomial, and N is greater than or equal to 5;

[0007] identifying whether the target curve is an S-shaped curve;

[0008] in a case where it is identified that the target curve is an S-shaped curve, inputting the discrete point set of the S-shaped curve and current motion state data of the vehicle into a pre-configured model predictive control algorithm to output a target driving track that minimizes the sum of the steering angles of the vehicle when the vehicle travels in the lane of the S-shaped curve, wherein the constraint conditions of the model predictive control algorithm include that the single steering angle of the vehicle when traveling in the lane of the S-shaped curve is lower than a set angle threshold, and the driving track of the vehicle cannot coincide with the lane boundary;

[0009] in a case where the vehicle reaches a starting point of the lane of the S-shaped curve, controlling the vehicle to travel in the lane of the S-shaped curve based on the target driving track.

[0010] In some embodiments, the discrete point set of the lane boundary in front of the vehicle is obtained by:

[0011] determining whether the vehicle is loaded with a high-precision map in front of a preset distance;

[0012] if the high-precision map is loaded, a coordinate point set of the lane boundary in front of the vehicle is extracted from the high-precision map as the discrete point set.

[0013] In some embodiments, the discrete point set of the lane boundary in front of the vehicle is obtained by:

[0014] determining whether the vehicle is loaded with a high-precision map in front of a preset distance;

[0015] if the high-precision map is not loaded, a road image in front of the vehicle is collected;

[0016] a lane image is segmented from the road image in front, and a pixel point set of the lane boundary is extracted from the lane image as the discrete point set.

[0017] In some embodiments, the target curve is identified as an S-shaped curve by:

[0018] detecting the curvature of each discrete point of the target curve;

[0019] in a case where the number of times of positive and negative sign reversals of the curvature is greater than or equal to 2, and the distance extended by the discrete points of each group of the same sign of the curvature is greater than a set distance threshold, the target curve is determined as an S-shaped curve.

[0020] In some embodiments, the target curve is identified as an S-shaped curve by:

[0021] the target curve is input into a pre-trained S-shaped curve identification model to identify whether the target curve is an S-shaped curve, wherein the S-shaped curve identification model is trained by inputting a plurality of training samples into a neural network, each training sample includes a historical target curve, and the historical target curve is labeled with a label of whether it is an S-shaped curve.

[0022] In some embodiments, when N=5, the expression of the Nth order polynomial is y(x)=a5x 5 +a4x 4 +a3x 3 +a2x 2 +a1x, and satisfies y(x0) ’ =0, y(x n ) ’ =0, wherein y(x0) ’ is the slope of the starting point of the target curve, and y(x n ) ’The slope of the end point of the target curve, [x, y(x)] is the coordinate of the discrete point, and a1, a2, a3, a4, and a5 are different fitting coefficients.

[0023] In some embodiments, the constraint condition of the model predictive control algorithm further includes:

[0024] The speed of the vehicle is within a preset speed threshold range, and the acceleration of the vehicle is within a preset acceleration threshold range.

[0025] In a second aspect, the present application provides a vehicle, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to enable the vehicle to perform the method provided in the first aspect of the present application.

[0026] In a third aspect, the present application further provides a storage medium, which stores a computer program, wherein the computer program is executed by a processor to enable the vehicle to perform the method provided in the first aspect of the present application.

[0027] In a fourth aspect, the present application further provides a computer program product, which comprises a computer program, wherein the computer program is executed to enable the vehicle to perform the method provided in the first aspect of the present application.

[0028] The present application provides a driving trajectory control method of a vehicle in an S-shaped curve, a vehicle, and a storage medium. The discrete point set is fitted into a target curve of an Nth order polynomial. Since N is greater than or equal to 5, the shape of the real lane boundary can be more accurately and completely represented, and the reliability is high. Since the shape of the real lane boundary can be more accurately and completely represented, the target curve can be accurately identified as an S-shaped curve.

[0029] In a case where the target curve is identified as an S-shaped curve, the discrete point set of the S-shaped curve and the current motion state data of the vehicle are input into a preconfigured model predictive control algorithm to output a target driving trajectory that minimizes the sum of the steering angles of the vehicle when driving in the lane of the S-shaped curve. The constraint condition of the model predictive control algorithm includes that the single steering angle of the vehicle driving in the lane of the S-shaped curve is lower than a set angle threshold, and the driving trajectory of the vehicle cannot coincide with the lane boundary. In a case where the vehicle reaches the starting point of the lane of the S-shaped curve, the vehicle is controlled to drive in the lane of the S-shaped curve based on the target driving trajectory. Since the sum of the steering angles of the vehicle driving along the target driving trajectory is small, the lateral swing of the vehicle is small, the driving stability is high, and the driving safety and the driving experience of the user are further improved. BRIEF DESCRIPTION OF DRAWINGS

[0030] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings needed in the embodiments or prior art description. Obviously, the drawings in the following description are some embodiments of the present application, and for those skilled in the art, other drawings can also be obtained without creative labor.

[0031] Figure 1 The flow chart of the driving track control method of the vehicle in the S-shaped curve provided by the embodiments of the present application;

[0032] Figure 2 The schematic diagram of the driving state of the vehicle in the S-shaped curve provided by the embodiments of the present application;

[0033] Figure 3 The functional module block diagram of the driving track control device of the vehicle in the S-shaped curve provided by the embodiments of the present application. DETAILED DESCRIPTION

[0034] Hereinafter, the embodiments of the present disclosure will be described with reference to the accompanying drawings. However, it should be understood that these descriptions are merely exemplary and are not intended to limit the scope of the present disclosure. In addition, in the following description, the description of well-known structures and techniques has been omitted to avoid unnecessary confusion of the concept of the present disclosure.

[0035] In the drawings, various structural schematic diagrams according to the embodiments of the present disclosure are shown. These drawings are not drawn to scale, in which some details are exaggerated for the purpose of clear expression, and some details can be omitted. The shapes of various regions, layers shown in the drawings, and their relative size, positional relationship may deviate in actuality due to manufacturing tolerance or technical limitation, and the skilled in the art can additionally design regions / layers with different shapes, sizes, relative positions according to actual needs.

[0036] In the context of the present disclosure, when a layer / element is referred to as being located "on" another layer / element, the layer / element can be directly located on the other layer / element, or there can be an intermediate layer / element between them. In addition, if a layer / element is located "on" another layer / element in one orientation, it can be located "under" the other layer / element when the orientation is reversed.

[0037] Hereinafter, the technical solutions of the present application and how the technical solutions of the present application solve the above technical problems will be described in detail with specific embodiments. The following specific embodiments can be combined with each other, and the same or similar concepts or processes can not be described again in some embodiments. The embodiments of the present application will be described below with reference to the drawings.

[0038] The embodiment of the application provides a driving track control method of a vehicle in an S-shaped curve, and is applied to the vehicle. Figure 1 As shown in the figure, the method provided by the embodiment of the application comprises the following steps.

[0039] S101: acquiring a discrete point set of a lane boundary in front of the vehicle.

[0040] The specific implementation of S101 includes but is not limited to the following two modes.

[0041] The first mode: judging whether the vehicle is loaded with a high-definition map (HD map) of a preset distance in front; if the vehicle is loaded with the high-definition map, a coordinate point set of the lane boundary in front of the vehicle is extracted from the high-definition map as the discrete point set. It can be understood that the vehicle can load the high-definition map of the preset distance (such as 2 km) in front from the cloud every preset time length (such as 1 min) or every distance (such as 20 m) of driving, if the network signal is good, the high-definition map of the preset distance in front can be successfully loaded, if the network signal is poor, the high-definition map of the preset distance in front fails to be loaded. Therefore, it is necessary to judge whether the vehicle is loaded with the high-definition map of the preset distance in front. Since the coordinate point set of the lane boundary of the high-definition map has high precision, the coordinate point set of the lane boundary of the high-definition map is preferentially taken as the discrete point set.

[0042] The second mode: judging whether the vehicle is loaded with the high-definition map of the preset distance in front; if the vehicle is not loaded with the high-definition map, a road image in front is collected; for example, the road image in front can be collected through a front-view camera on the vehicle. Then, a lane image is segmented from the road image in front, and a pixel point set of the lane boundary is extracted from the lane image as the discrete point set.

[0043] S102: fitting the discrete point set into a target curve, wherein the target curve is an N-th order polynomial, and N≥5.

[0044] For example, when N=5, the expression of the N-th order polynomial is y(x) = a5x 5 +a4x 4 +a3x 3 +a2x 2 +a1x, and y(x0) ’ =0, y(x n ) ’ =0, wherein y(x0) ’ is the slope of the starting point of the target curve, that is, the first derivative of y(x0) is y(x0) ’ ; y(x n ) ’ is the slope of the terminal point of the target curve, that is, the first derivative of y(x n ) ’ is y(xn , y(x) ] are coordinates of the discrete points, and a1, a2, a3, a4, a5 are different fitting coefficients. It should be noted that the coordinates of each discrete point in the discrete point set satisfy the above quintic polynomial. Understandably, [x0, y(x0)] is the starting point of the target curve, and [x n , y(x n )] is the end point of the target curve. In addition, y(x0)" = 0, y(x n )" = 0 can also be satisfied, and y(x0)" is the second derivative of y(x0), y(x n )" is the second derivative of y(x n ), [x, y(x)] are coordinates of the discrete points, and a1, a2, a3, a4, a5 are different fitting coefficients.

[0045] In addition, the polynomial in the case of N = 6 or N = 7 is the same as the polynomial in the case of N = 5, and will not be repeated here. Understandably, since N ≥ 5, the shape of the real lane boundary can be more accurately and completely characterized, and the reliability is high.

[0046] S103: Identify whether the target curve is an S-shaped curve, and if so, execute S104.

[0047] Exemplarily, the specific implementation of S103 includes but is not limited to the following two ways:

[0048] The first kind: detecting the curvature of each discrete point of the target curve; in the case that the number of times of positive and negative sign reversal of the curvature is greater than or equal to 2, and the distance extended by the discrete points of each group of the same sign curvature is greater than a set distance threshold, it is determined that the target curve is an S-shaped curve. Understandably, the curvature of the curve refers to the turning rate of the tangent direction angle to the arc length for a point on the curve. Generally, the curvature of the S curve changes from positive (left turn) to negative (right turn), and then from negative (right turn) to positive (left turn), or from negative (right turn) to positive (left turn), and then from positive (left turn) to negative (right turn). Therefore, when the number of times of positive and negative sign reversal of the curvature (such as 2 times, 3 times, or 4 times, etc.) is greater than or equal to 2, it indicates that the curvature of the target curve has been reversed twice. In addition, in order to ensure reliability, it is also necessary to determine that the distance extended by the discrete points of each group of the same sign curvature is greater than a set distance threshold (such as 30m or 50m), and then determine that the target curve is an S-shaped curve.

[0049] Secondly, the target curve is input into a pre-trained S-shaped curve recognition model to identify whether the target curve is an S-shaped curve. The S-shaped curve recognition model is trained by inputting a plurality of training samples into a neural network, each of which includes a historical target curve and is labeled with whether it is an S-shaped curve. For example, a label of "1" represents that the historical target curve is an S-shaped curve, and a label of "0" represents that the historical target curve is not an S-shaped curve.

[0050] It can be understood that, since the above-mentioned quintic polynomial can more accurately and completely represent the shape of the real lane boundary, the target curve can be accurately identified as an S-shaped curve.

[0051] S104: In the case where the target curve is identified as an S-shaped curve, the discrete point set of the S-shaped curve and the current motion state data of the vehicle are input into a pre-configured model predictive control algorithm to output a target driving trajectory that minimizes the sum of steering angles when the vehicle drives in the lane of the S-shaped curve.

[0052] Exemplarily, the current motion state data of the vehicle can include, but is not limited to, the current position, the current speed, etc. The constraint conditions of the model predictive control algorithm include that the single steering angle of the vehicle driving in the lane of the S-shaped curve is lower than a set angle threshold, and the driving trajectory of the vehicle cannot coincide with the lane boundary. In some embodiments, the constraint conditions of the model predictive control algorithm can also include that the speed of the vehicle is within a preset speed threshold (such as 80 km / h), and the acceleration of the vehicle is within a preset acceleration threshold.

[0053] The model predictive control algorithm MPC (Model Predictive Control) is an advanced control method that guides the current control decision by predicting the future behavior of the system. It establishes a mathematical model of a dynamic system, combines the operating constraints and performance indicators of the system, and generates control inputs by optimizing the future state, such as outputting a target driving trajectory that minimizes the sum of steering angles when the vehicle drives in the lane of the S-shaped curve by using a quadratic programming QP (Quadratic Programming) algorithm or an interior point optimizer IPOPT (Interior Point OPTimizer) nonlinear optimization solver.

[0054] S105: In the case where the vehicle reaches the starting point of the lane of the S-shaped curve, the vehicle is controlled to drive in the lane of the S-shaped curve based on the target driving trajectory.

[0055] Exemplarily, the driving state of the vehicle 101 in the lane 102 of the S-shaped curve can be as shown in FIG. 2. Figure 2As shown, it is to be noted that the vehicle 101 exceeds the lane boundary 103 when driving in the S-shaped curve lane 102.

[0056] In summary, the vehicle driving trajectory control method in an S-shaped curve lane provided by the embodiments of the present application fits the discrete point set into a target curve of an Nth order polynomial, and since N≥5, the real lane boundary shape can be more accurately and completely characterized, and the reliability is high. Since the real lane boundary shape can be more accurately and completely characterized, the target curve can be accurately identified as an S-shaped curve.

[0057] In the case where the target curve is identified as an S-shaped curve, the discrete point set of the S-shaped curve and the current motion state data of the vehicle are input into a preconfigured model predictive control algorithm to output a target driving trajectory that minimizes the sum of steering angles of the vehicle when driving in the S-shaped curve lane, wherein the constraint conditions of the model predictive control algorithm include that the single steering angle of the vehicle when driving in the S-shaped curve lane is lower than a set angle threshold, and the driving trajectory of the vehicle cannot coincide with the lane boundary. In the case where the vehicle reaches the starting point of the S-shaped curve lane, the vehicle is controlled to drive in the S-shaped curve lane based on the target driving trajectory. Since the sum of steering angles of the vehicle when driving along the target driving trajectory is small, the lateral swing of the vehicle is small, the driving stability is high, and the driving safety and the user's driving experience are further improved.

[0058] Please refer to Figure 3 The embodiments of the present application also provide a vehicle driving trajectory control device in an S-shaped curve lane, which is configured in a vehicle. It is to be noted that the basic principle and the generated technical effects of the vehicle driving trajectory control device in an S-shaped curve lane provided by the embodiments of the present application are the same as those of the above-mentioned embodiments, and for brief description, the part not mentioned in the embodiments of the present application can refer to the corresponding content in the above-mentioned embodiments. As Figure 3 As shown, the device provided by the embodiments of the present application includes a data acquisition unit, a curve fitting unit, a curve identification unit, and a trajectory output unit, wherein,

[0059] The data acquisition unit is configured to acquire a discrete point set of a lane boundary in front of the vehicle.

[0060] The curve fitting unit is configured to fit the discrete point set into a target curve, wherein the target curve is an Nth order polynomial, and N≥5.

[0061] The curve identification unit is configured to identify whether the target curve is an S-shaped curve.

[0062] a trajectory output unit, configured to, in a case where the target curve is identified as the S-shaped curve, input the discrete point set of the S-shaped curve and the current motion state data of the vehicle into a pre-configured model predictive control algorithm to output a target trajectory that minimizes a sum of steering angles of the vehicle when the vehicle travels in the lane of the S-shaped curve, wherein a constraint condition of the model predictive control algorithm comprises that a single steering angle of the vehicle when the vehicle travels in the lane of the S-shaped curve is lower than a set angle threshold, and the travel trajectory of the vehicle cannot coincide with the lane boundary.

[0063] a travel control unit, configured to, in a case where the vehicle reaches a starting point of the lane of the S-shaped curve, control the vehicle to travel in the lane of the S-shaped curve based on the target trajectory.

[0064] In some embodiments, the data acquisition unit is specifically configured to determine whether the vehicle is loaded with a high-precision map in a preset distance in front of the vehicle; and if the vehicle is loaded with the high-precision map, extract a set of coordinate points of a lane boundary in front of the vehicle from the high-precision map as the discrete point set.

[0065] In other embodiments, the data acquisition unit is further specifically configured to determine whether the vehicle is loaded with a high-precision map in a preset distance in front of the vehicle; and if the vehicle is not loaded with the high-precision map, capture a road image in front of the vehicle; segment a lane image from the road image in front of the vehicle, and extract a set of pixel points of a lane boundary from the lane image as the discrete point set.

[0066] In some embodiments, the curve identification unit is specifically configured to detect a curvature of each discrete point of the target curve; and in a case where a number of times of positive and negative sign reversals of the curvature is greater than or equal to 2, and a distance extended by the discrete points of each group of curvatures with the same sign is greater than a set distance threshold, determine that the target curve is the S-shaped curve.

[0067] In other embodiments, the curve identification unit is further specifically configured to input the target curve into a pre-trained S-shaped curve identification model to identify whether the target curve is the S-shaped curve.

[0068] wherein the S-shaped curve identification model is obtained by inputting a plurality of training samples into a neural network, and each training sample comprises a historical target curve and a label indicating whether the historical target curve is the S-shaped curve.

[0069] In some embodiments, when N=5, the expression of the Nth polynomial is y(x)=a5x 5 +a4x 4 +a3x 3 +a2x 2 +a1x, and satisfies y(x0) ’ =0, y(x n ) ’ =0, wherein y(x0)’ slope of the starting point of the target curve, y(x n ) ’ slope of the ending point of the target curve, [x, y(x)] is the coordinate of the discrete point, and a1, a2, a3, a4, and a5 are different fitting coefficients, respectively.

[0070] In some embodiments, the constraint condition of the model predictive control algorithm further includes:

[0071] The speed of the vehicle is within a preset speed threshold range, and the acceleration of the vehicle is within a preset acceleration threshold range.

[0072] In addition, an embodiment of the present application provides a vehicle, including a memory, a processor, and a computer program stored in the memory and executable on the processor, and when the processor executes the computer program, the vehicle executes the method provided by the above-mentioned embodiments of the present application.

[0073] In addition, an embodiment of the present application further provides a storage medium, the storage medium stores a computer program, and when the computer program is executed by a processor, the vehicle executes the method provided by the above-mentioned embodiments of the present application.

[0074] In addition, an embodiment of the present application further provides a computer program product, including a computer program, when the computer program is executed, the vehicle executes the method provided by the above-mentioned embodiments of the present application.

[0075] In the above description, the technical details such as the composition of each layer are not described in detail. However, those skilled in the art should understand that the layers, regions, etc. of the required shape can be formed by various technical means. In addition, those skilled in the art can also design methods that are not exactly the same as the methods described above in order to form the same structure. In addition, although each embodiment is described above, this does not mean that the measures in each embodiment cannot be used advantageously in combination.

[0076] Although the preferred embodiments of the present application have been described, those skilled in the art can make further changes and modifications to these embodiments once they understand the basic inventive concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications falling within the scope of the present application.

[0077] Obviously, those skilled in the art can make various modifications and variations to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application also intends to include these modifications and variations.

Claims

1. A method of controlling a travel trajectory of a vehicle in an S-shaped curve, characterized by, The method is applied to a vehicle and comprises: acquiring a discrete point set of a lane boundary in front of the vehicle; fitting the discrete point set into a target curve, wherein the target curve is an Nth order polynomial, N≥5; identifying whether the target curve is an S-shaped curve; in a case where the target curve is identified as an S-shaped curve, inputting a discrete point set of the S-shaped curve and current motion state data of the vehicle into a preconfigured model predictive control algorithm to output a target driving trajectory that minimizes a sum of steering angles of the vehicle when driving in a lane of the S-shaped curve, wherein constraint conditions of the model predictive control algorithm include that a single steering angle of the vehicle when driving in the lane of the S-shaped curve is lower than a set angle threshold, and a driving trajectory of the vehicle cannot coincide with the lane boundary; in a case where the vehicle reaches a starting point of the lane of the S-shaped curve, controlling the vehicle to drive in the lane of the S-shaped curve based on the target driving trajectory.

2. The method of claim 1, wherein, The acquiring of the discrete point set of the lane boundary in front of the vehicle comprises: determining whether the vehicle is loaded with a high-precision map in a preset distance in front of the vehicle; if the high-precision map is loaded, extracting a coordinate point set of the lane boundary in front of the vehicle from the high-precision map as the discrete point set.

3. The method of claim 1, wherein, The acquiring of the discrete point set of the lane boundary in front of the vehicle comprises: determining whether the vehicle is loaded with a high-precision map in a preset distance in front of the vehicle; if the high-precision map is not loaded, collecting a front road image; segmenting a lane image from the front road image, and extracting a pixel point set of the lane boundary from the lane image as the discrete point set.

4. The method of claim 1, wherein, The identifying of whether the target curve is an S-shaped curve comprises: detecting curvatures of each discrete point of the target curve; in a case where a number of times of positive and negative sign reversals of the curvatures is greater than or equal to 2, and a distance extended by discrete points of each group of curvatures with the same sign is greater than a set distance threshold, determining that the target curve is an S-shaped curve.

5. The method of claim 1, wherein, The identifying of whether the target curve is an S-shaped curve comprises: inputting the target curve into a pre-trained S-shaped curve identification model to identify whether the target curve is an S-shaped curve, wherein the S-shaped curve identification model is trained by inputting a plurality of training samples into a neural network, each of the training samples comprises a historical target curve, and the historical target curve is labeled with a label of whether it is an S-shaped curve.

6. The method of claim 1, wherein, When N = 5, the expression of the Nth polynomial is y(x) = a5x 5 + a4x 4 + a3x 3 + a2x 2 + a1x, and satisfies y(x0) ’ = 0, y(x n ) ’ = 0, wherein y(x0) ’ is the slope of the starting point of the target curve, y(x n ) ’ is the slope of the end point of the target curve, and [x, y(x)] is the coordinate of the discrete point, a1, a2, a3, a4, and a5 are different fitting coefficients, respectively.

7. The method according to any of claims 1 to 6, characterized in that The constraint conditions of the model predictive control algorithm further comprise: a speed of the vehicle is within a preset speed threshold range, and an acceleration of the vehicle is within a preset acceleration threshold range.

8. A vehicle comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, The processor executes the computer program, so that the vehicle executes the method according to any one of claims 1 to 7.

9. A storage medium storing a computer program, characterized by The computer program is executed by the processor, so that the vehicle executes the method according to any one of claims 1 to 7.

10. A computer program product comprising a computer program which, when executed by a processor, causes a vehicle to execute the method according to any one of claims 1 to 7.

Images