Vehicle Lateral Control Method, Device, System, Electronic Device, and Storage Medium

Abstract

The present application relates to a vehicle lateral control method, device, system, electronic device, and storage medium. The vehicle lateral control method includes: obtaining vehicle speed information, road curvature information of the vehicle, and a first lateral position deviation between the vehicle and a preset trajectory reference point; generating a dynamic control weight of the vehicle based on a mapping relationship between the vehicle speed information and the road curvature information, and calculating a front wheel steering angle result according to the first lateral position deviation and the dynamic control weight; generating a lateral control result of the vehicle according to the front wheel steering angle result, and performing lateral control on the vehicle according to the lateral control result. By means of the present application, the problem of low stability of vehicle lateral control is solved, and accurate and stable vehicle lateral control is achieved.

Description

Technical Field

[0001] The present application relates to the field of autonomous driving technology, and particularly to a vehicle lateral control method, device, system, electronic device, and storage medium. Background Art

[0002] The trajectory tracking control of an autonomous vehicle is one of the key technologies for realizing vehicle autonomous driving. The lateral control function in trajectory tracking mainly controls the front wheel angle of the vehicle to reduce the lateral deviation between the vehicle and the trajectory, so as to make the vehicle travel along the planned trajectory; the tracking accuracy between the vehicle and the trajectory is the main consideration index for lateral control. In related technologies, the lateral motion control of autonomous driving is usually achieved by control methods such as pure tracking algorithms, proportional-integral-derivative control (PID control for short), and model predictive control. Among them, the control tracking accuracy of model predictive control is relatively good, but its algorithm for iteratively solving sequential quadratic programming has high requirements for hardware and its calculation speed is not easy to meet the real-time control requirements of vehicles. PID control is relatively simple, but it cannot cover all scenarios and its control asymptotic stability is general, resulting in low stability of vehicle lateral control.

[0003] Currently, for the problem of low stability of vehicle lateral control in related technologies, no effective solution has been proposed. Summary of the Invention

[0004] Embodiments of the present application provide a vehicle lateral control method, device, system, electronic device, and storage medium to at least solve the problem of low stability of vehicle lateral control in related technologies.

[0005] In a first aspect, embodiments of the present application provide a vehicle lateral control method, and the method includes:

[0006] Obtain the vehicle speed information, road curvature information, and the first lateral position deviation between the vehicle and a preset trajectory reference point;

[0007] Generate a dynamic control weight of the vehicle based on the mapping relationship between the vehicle speed information and the road curvature information, and calculate a front wheel angle result according to the first lateral position deviation and the dynamic control weight;

[0008] Generate a lateral control result of the vehicle according to the front wheel angle result, and perform lateral control on the vehicle according to the lateral control result.

[0009] In some of these embodiments, the generating the lateral control result of the vehicle according to the front wheel angle result includes:

[0010] Obtain the preview distance and the preset path planning trajectory, and calculate a preview point based on the vehicle speed information and the path planning trajectory;

[0011] Calculate a second lateral position deviation between the vehicle and the preview point according to the preview distance, and obtain a corner compensation result based on the second lateral position deviation;

[0012] Generate the lateral control result based on the front wheel corner result and the corner compensation result.

[0013] In some embodiments, the calculating the second lateral position deviation between the vehicle and the preview point according to the preview distance, and obtaining the corner compensation result based on the second lateral position deviation includes:

[0014] Obtain the vehicle heading angle deviation, and calculate a heading angle lateral deviation according to the preview distance and the vehicle heading angle deviation;

[0015] Calculate a first vertical distance between the preview point and the forward extension line of the vehicle center, and a second vertical distance between the rear axle center of the vehicle and the path planning trajectory; calculate the second lateral position deviation according to the first vertical distance, the second vertical distance and the heading angle lateral deviation;

[0016] Calculate an expected yaw rate according to the preview distance, the vehicle speed information and the second lateral position deviation, and calculate the corner compensation result based on the expected yaw rate.

[0017] In some embodiments, the generating the lateral control result based on the front wheel corner result and the corner compensation result includes:

[0018] Generate a target corner result based on the front wheel corner result and the corner compensation result;

[0019] Obtain the transmission ratio between the target corner result and the steering wheel, and generate the lateral control result according to the transmission ratio and the target corner result.

[0020] In some embodiments, the calculating the front wheel corner result according to the first lateral position deviation and the dynamic control weight includes:

[0021] Use a preset linear quadratic regulator (LQR) controller model to perform iterative solution calculation according to the first lateral position deviation and the dynamic control weight to obtain a target function value, and calculate the front wheel corner result according to the target function value.

[0022] In some of these embodiments, by using a preset LQR controller model, an objective function value is obtained through iterative solution calculation based on the first lateral position deviation and the dynamic control weight:

[0023] At least generate a state weight matrix based on the first lateral position deviation, and generate a control weight matrix based on the dynamic control weight;

[0024] Obtain a preset LQR state space equation and an objective function for indicating the constraint relationship between the state weight matrix and the control weight matrix, and use the LQR controller model to perform iterative solution on the objective function according to the LQR state space equation to obtain the objective function value.

[0025] In some of these embodiments, generating the dynamic control weight of the vehicle based on the mapping relationship between the vehicle speed information and the road curvature information includes:

[0026] Obtain historical vehicle speed information and historical road curvature information, and calculate corresponding preset control weight values according to the historical vehicle speed information and the historical road curvature information;

[0027] Obtain a preset mapping relationship table according to the historical vehicle speed information, the historical road curvature information, and the preset control weight values, perform a query process on the preset mapping relationship table according to the mapping relationship between the vehicle speed information and the road curvature information, and generate the dynamic control weight according to the queried preset control weight value.

[0028] In some of these embodiments, obtaining the first lateral position deviation between the vehicle and the preset trajectory reference point includes:

[0029] Obtain the vehicle state information of the vehicle, and obtain a path planning trajectory according to the vehicle state information; wherein, the path planning trajectory includes a first reference point generated based on the vehicle state information, and the first reference point is located in the global coordinate system;

[0030] Obtain the coordinate conversion relationship between the global coordinate system and the vehicle's ego coordinate system, and convert the first reference point to the ego coordinate system according to the coordinate conversion relationship to obtain a second reference point after coordinate conversion;

[0031] Calculate the trajectory point closest to the centroid position of the vehicle in the second reference point, determine the preset trajectory reference point based on the trajectory point, and calculate the first lateral position deviation.

[0032] In a second aspect, an embodiment of the present application provides a vehicle lateral control device, and the device includes: an acquisition module, a weight module, and a generation module;

[0033] The obtaining module is configured to obtain the vehicle speed information, road curvature information, and the first lateral position deviation between the vehicle and a preset trajectory reference point.

[0034] The weighting module is configured to generate a dynamic control weight of the vehicle based on the mapping relationship between the vehicle speed information and the road curvature information, and calculate a front wheel steering angle result according to the first lateral position deviation and the dynamic control weight.

[0035] The generating module is configured to generate a lateral control result of the vehicle according to the front wheel steering angle result, and perform lateral control on the vehicle according to the lateral control result.

[0036] In a third aspect, an embodiment of the present application provides a vehicle lateral control system, the system includes: a control device and a vehicle body;

[0037] The control device is connected to the vehicle body and is configured to execute the vehicle lateral control method as described in the first aspect above.

[0038] In a fourth aspect, an embodiment of the present application provides an electronic device, including a memory, a processor, and a computer program stored on the memory and executable on the processor, where when the processor executes the computer program, the vehicle lateral control method as described in the first aspect above is implemented.

[0039] In a fifth aspect, an embodiment of the present application provides a storage medium, on which a computer program is stored, and when the program is executed by a processor, the vehicle lateral control method as described in the first aspect above is implemented.

[0040] Compared with the related art, the vehicle lateral control method, device, system, electronic device, and storage medium provided by the embodiments of the present application obtain the vehicle speed information, road curvature information, and the first lateral position deviation between the vehicle and a preset trajectory reference point of the vehicle; generate a dynamic control weight of the vehicle based on the mapping relationship between the vehicle speed information and the road curvature information, and calculate a front wheel steering angle result according to the first lateral position deviation and the dynamic control weight; generate a lateral control result of the vehicle according to the front wheel steering angle result, and perform lateral control on the vehicle according to the lateral control result, solving the problem of low stability of vehicle lateral control and achieving precise and stable vehicle lateral control.

[0041] Details of one or more embodiments of the present application are set forth in the following drawings and description to make other features, objects, and advantages of the present application more concise and understandable. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] The accompanying drawings described herein are used to provide a further understanding of the present application, and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application, and do not constitute an improper limitation to the present application. In the drawings:

[0043] Figure 1 is an application environment diagram of a vehicle lateral control method according to an embodiment of the present application;

[0044] Figure 2 is a flowchart of a vehicle lateral control method according to an embodiment of the present application;

[0045] Figure 3 is a flowchart of another vehicle lateral control method according to an embodiment of the present application;

[0046] Figure 4 is a flowchart of a vehicle lateral control method according to a preferred embodiment of the present application;

[0047] Figure 5 is a structural block diagram of a vehicle lateral control device according to an embodiment of the present application;

[0048] Figure 6 is a structural block diagram of a vehicle lateral control system according to an embodiment of the present application;

[0049] Figure 7 is a structural diagram inside a computer device according to an embodiment of the present application. Detailed Embodiments

[0050] In order to make the objectives, technical solutions and advantages of the present application more clearly understood, the present application will be described and explained below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application, and are not used to limit the present application. All other embodiments obtained by those of ordinary skill in the art based on the embodiments provided in the present application without making creative efforts belong to the scope of protection of the present application. In addition, it can also be understood that although the efforts made in this development process may be complex and lengthy, for those of ordinary skill in the art related to the content disclosed in the present application, some design, manufacturing or production changes based on the technical content disclosed in the present application are only conventional technical means and should not be understood as insufficient disclosure of the present application.

[0051] References to "embodiments" in this application mean that the specific features, structures, or characteristics described in connection with the embodiments can be included in at least one embodiment of this application. The phrase appears in various places in the specification and does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment mutually exclusive with other embodiments. It is explicitly and implicitly understood by those of ordinary skill in the art that the embodiments described in this application can be combined with other embodiments without conflict.

[0052] Unless otherwise defined, the technical terms or scientific terms involved in this application shall have the ordinary meaning understood by those of ordinary skill in the technical field to which this application belongs. The words such as "a", "an", "one kind", "the" and the like involved in this application do not indicate a limitation in quantity and can represent a singular or plural number. The terms "include", "comprise", "have" and any variations thereof involved in this application are intended to cover non-exclusive inclusion; for example, a process, method, system, product or device that includes a series of steps or modules (units) is not limited to the listed steps or units, but may further include unlisted steps or units, or may further include other steps or units inherent to these processes, methods, products or devices. The words such as "connect", "be connected", "couple" and the like involved in this application are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. The "plurality" involved in this application means greater than or equal to two. "And / or" describes the association relationship of associated objects and indicates that three relationships can exist. For example, "A and / or B" can represent: A exists alone, A and B exist simultaneously, and B exists alone. The terms "first", "second", "third", etc. involved in this application are only used to distinguish similar objects and do not represent a specific order of the objects.

[0053] The vehicle lateral control method provided by this application can be applied to application scenarios such as vehicle autonomous driving and wheeled robot navigation control. Figure 1 is an application environment diagram of a vehicle lateral control method according to an embodiment of this application, as Figure 1As shown, vehicle 102 communicates with server 104 via a network. The data storage system can store the data that server 104 needs to process. The data storage system can be integrated on server 104, or placed in the cloud or on other network servers. Server 104 obtains the vehicle speed information, road curvature information of vehicle 102, and the first lateral position deviation between vehicle 102 and the preset trajectory reference point; this server 104 generates the dynamic control weight of vehicle 102 based on the mapping relationship between the vehicle speed information and the road curvature information, calculates the front wheel steering angle result according to the first lateral position deviation and the dynamic control weight, and finally generates the lateral control result for vehicle 102 according to the front wheel steering angle result, so as to perform lateral control on the vehicle according to the lateral control result. Among them, server 104 can be implemented by an independent server or a server cluster composed of multiple servers.

[0054] This embodiment provides a vehicle lateral control method. Figure 2 It is a flowchart of a vehicle lateral control method according to an embodiment of the present application, as Figure 2 shown. The process includes the following steps:

[0055] Step S210, obtain the vehicle speed information, road curvature information of the vehicle, and the first lateral position deviation between the vehicle and the preset trajectory reference point.

[0056] Among them, the above vehicle speed information refers to the real-time driving speed of the corresponding vehicle; the vehicle information can be obtained by real-time collection by sensing devices such as the vehicle's speed sensor. The road curvature information refers to the curvature information of the road when the corresponding vehicle travels to the current road; the road curvature information can be calculated from information such as the vehicle's motion state using technologies such as computer vision. The above preset trajectory reference point refers to the trajectory point adjacent to the vehicle on the pre-generated path planning trajectory. Then, by calculating the coordinate position offset relationship between the vehicle and the preset trajectory reference point, the above first lateral position deviation can be obtained.

[0057] Step S220, generate the dynamic control weight of the vehicle based on the mapping relationship between the vehicle speed information and the road curvature information, and calculate the front wheel steering angle result according to the first lateral position deviation and the dynamic control weight.

[0058] Among them, the dynamic control weight of the vehicle can be detected based on the above mapping relationship. Further, the generation of the dynamic control weight of the vehicle based on the mapping relationship between the vehicle speed information and the road curvature information further includes the following steps: obtaining a preset mapping relationship table; the preset mapping relationship table can be calculated and generated in advance according to historical vehicle speed information and historical road curvature information obtained from simulation experiment data or test data of the vehicle driving autonomously in areas such as parks; querying the preset mapping relationship table through the mapping relationship between the vehicle speed information and the road curvature information to obtain the above dynamic control weight.

[0059] Alternatively, the generation of the dynamic control weight of the vehicle based on the mapping relationship between the vehicle speed information and the road curvature information can also be implemented based on a neural network. For example, the vehicle speed information to be trained and the road curvature information to be trained can be obtained in advance according to simulation experiment data or test data of the vehicle driving autonomously in areas such as parks, and the vehicle speed information to be trained and the road curvature information to be trained are used as sample data, and the sample data is input into a preset neural network model for training and outputting a control weight value. After the sample data is iterated, a trained neural network model is obtained; then the current vehicle speed information and road curvature information are input into the neural network model, and thus the dynamic control weight corresponding to the mapping relationship between the vehicle speed information and the road curvature information can be output.

[0060] After calculating the dynamic control weight of the vehicle through the above steps, the feedback matrix K can be solved according to the motion control weight and the above first lateral position deviation, and the front wheel steering angle result can be calculated using the LQR controller model according to the feedback matrix K. It can be understood that by dynamically adjusting the control weight parameters in real time during the LQR control process, the control stability in different ego-vehicle states and different driving scenarios can be effectively improved.

[0061] Step S230, generating a lateral control result of the vehicle according to the front wheel steering angle result.

[0062] Among them, after calculating the front wheel steering angle result through the above steps S210 to S220, the rotation ratio between the front wheel steering angle that can be stored or calculated in advance and the steering wheel can be used to convert the front wheel steering angle result into the angle that the steering wheel needs to rotate, and the angle that the steering wheel needs to rotate is used as the lateral control result for the above vehicle. It can be understood that the lateral control result, that is, the angle that the steering wheel needs to rotate, can be sent to the steering execution control mechanism in the above vehicle, and the steering execution control mechanism performs a steering control operation on the steering wheel according to the angle that the steering wheel needs to rotate, so as to realize the lateral control of the above vehicle based on the lateral control result.

[0063] Through the above steps S210 to S230, a dynamic control weight is generated based on the mapping relationship between the vehicle speed information and the road curvature information, and the front wheel steering angle result is calculated according to the dynamic control weight and the obtained first lateral position deviation, thereby realizing the real-time dynamic adjustment of the control weight parameters, effectively improving the control accuracy and adaptability of autonomous driving, solving the problem of low stability of vehicle lateral control, and realizing an accurate and stable vehicle lateral control method.

[0064] In some embodiments, a vehicle lateral control method is provided. Figure 3 is a flowchart of another vehicle lateral control method according to an embodiment of the present application, as Figure 3 shown, this process includes Figure 2 [[ID=⑨]]steps S210 and S220 in, and in addition, the following steps are also included:

[0065] Step S310, obtain the preview distance and the preset path planning trajectory, and calculate the preview point according to the vehicle speed information and the path planning trajectory.

[0066] Among them, the above preview distance can be calculated according to the preset path planning trajectory and the vehicle speed information, which will not be elaborated here. After determining the preview distance through the above steps, the time interval for selecting the target point can be calculated according to the current vehicle speed information of the vehicle, that is, according to the timestamps of each trajectory point on the path planning trajectory and the timestamps of the vehicle positions of each point collected during the autonomous driving process of the current vehicle, determine the two trajectory points with the closest time, and then use methods such as linear interpolation to determine the above preview point on the path planning trajectory.

[0067] Step S320, calculate the second lateral position deviation between the vehicle and the preview point according to the preview distance, and obtain the steering angle compensation result according to the second lateral position deviation.

[0068] Specifically, according to the above preview distance, the coordinate position offset relationship between the vehicle and the preview point is calculated, and the above second lateral position deviation can be obtained. Then, based on the second lateral position deviation, the vehicle preview kinematic model is derived to obtain the expected yaw rate, and finally, based on the conversion relationship between the vehicle front wheel and the yaw rate, the expected front wheel steering angle compensation value is calculated based on the conversion relationship and the expected yaw rate, that is, the above steering angle compensation result is obtained.

[0069] Step S330, generate the lateral control result according to the front wheel steering angle result and the steering angle compensation result.

[0070] It can be understood that by compensating and correcting the above-mentioned front wheel angle result based on the above-mentioned angle compensation result, a more accurate target angle value can be generated, so that the final steering control amount, that is, the above-mentioned lateral control result, can be obtained based on the target angle value, and the vehicle's steering execution control mechanism can be instructed to achieve autonomous steering control of the vehicle's steering wheel based on the steering control amount.

[0071] Through the above steps S310 to S330, the second lateral position deviation between the vehicle and the preview point is calculated by setting the preview distance, and the front wheel angle compensation result is solved based on the second lateral position deviation, thereby effectively combining the lateral angle compensation method based on the preview point with the adaptive LQR lateral control method to achieve autonomous lateral control of the vehicle, improving the effect of achieving vehicle advance control in specific driving scenarios such as curves or lane changes, avoiding problems such as overshoot or swing in vehicle lateral control in different road scenarios, making vehicle trajectory tracking more accurate, and the stability and gradualness of vehicle control better, effectively improving the stability and accuracy of vehicle lateral control.

[0072] In some embodiments, the calculation of the second lateral position deviation between the vehicle and the preview point based on the preview distance and obtaining the angle compensation result based on the second lateral position deviation further include the following steps:

[0073] Step S321 , obtaining the vehicle heading angle deviation, and calculating the heading angle lateral deviation according to the preview distance and the vehicle heading angle deviation.

[0074] The vehicle heading angle deviation can be acquired by sensors on the vehicle. Specifically, the lateral heading angle deviation can be calculated using the preview distance and the trigonometric function calculation result of the vehicle heading angle deviation. The calculation formula for the lateral heading angle deviation is shown in Formula 1:

[0075] ΔL he =L ef ×Sin(Δθ) Formula 1

[0076] Among them, the above ΔL he Used to indicate the lateral deviation of the heading angle caused by the vehicle's heading angle; L ef It is used to indicate the preview distance mentioned above; Δθ is used to indicate the vehicle heading angle deviation.

[0077] Step S322: Calculate a first vertical distance between the preview point and the front extension of the vehicle center, and a second vertical distance between the center of the rear axle of the vehicle and the path planning trajectory; and calculate the second lateral position deviation based on the first vertical distance, the second vertical distance, and the lateral deviation of the heading angle.

[0078] Among them, the vertical distance from the above-mentioned preview point to the extension line in front of the vehicle center, that is, the above-mentioned first vertical distance, can be represented by Y1; the vertical distance from the center point of the vehicle's rear axle to the above-mentioned path planning trajectory, that is, the above-mentioned second vertical distance, can be represented by Y2. Then the calculation formula of the above-mentioned second lateral position deviation is shown in Formula 2:

[0079] ΔYL ef = Y1 - Y2 - L ef ×Sin(Δθ) Formula 2

[0080] In the above Formula 2, ΔYL ef is used to represent the above-mentioned second lateral position deviation.

[0081] Step S323, calculate the desired yaw rate based on the preview distance, the vehicle speed information, and the second lateral position deviation, and calculate the steering angle compensation result based on the desired yaw rate.

[0082] Specifically, using the vehicle preview kinematic model, the desired yaw rate and the steering angle compensation result can be calculated according to the above-mentioned second lateral position deviation. Among them, the vehicle preview kinematic model is as shown in the following Formulas 3 and 4:

[0083] as shown in Formulas 3 and 4:

[0084]

[0085]

[0086] In the above formulas, ω des is used to represent the above-mentioned desired yaw rate, V is used to represent the current vehicle speed information. δ Curv is used to represent the above-mentioned steering angle compensation result; it can be seen from Formula 4 that the value of δ Curv can be positive or negative. m is used to represent the vehicle mass; Cr is used to represent the rear wheel cornering stiffness of the vehicle, Cf is used to represent the front wheel cornering stiffness of the vehicle, lr is used to represent the distance from the center of the vehicle's rear axle to the vehicle's center of mass, lf is used to represent the distance from the center of the vehicle's front axle to the vehicle's center of mass; among them, m, C r 、C f 、l r and l f Each constant can be obtained and stored in advance through vehicle factory configuration information, etc.

[0087] Through the above steps S321 to S323, the above-mentioned second lateral position deviation is calculated based on the preview distance and the preview point, and using the vehicle preview kinematic model, the steering angle compensation result is calculated based on the second lateral position deviation, realizing previewing a certain distance in front of the vehicle during the vehicle driving process to solve the accurate vehicle preview error, and calculating the steering angle compensation result for the above-mentioned front wheel steering angle result based on this error, further improving the accuracy and stability of the vehicle lateral control.

[0088] In some of the embodiments, the generating the lateral control result according to the front wheel steering angle result and the steering angle compensation result further includes the following steps:

[0089] Step S331, generating a target steering angle result according to the front wheel steering angle result and the steering angle compensation result.

[0090] Specifically, calculation processing such as addition or multiplication can be performed on the front wheel steering angle result according to the calculated steering angle compensation result obtained above, and a compensated target steering angle result is generated. Taking the above formula 4 as an example, the steering angle compensation result calculated by formula 4 can be directly added to the above-mentioned front wheel steering angle result to generate the above-mentioned target steering angle result.

[0091] Step S332, obtaining the transmission ratio between the target steering angle result and the steering wheel, and generating the lateral control result according to the transmission ratio and the target steering angle result.

[0092] Among them, the transmission ratio between the front wheel steering angle and the steering wheel angle of the vehicle can be calculated in advance, and the target steering angle result is converted into the steering wheel rotation angle according to the transmission ratio; taking the steering wheel rotation angle as the above-mentioned lateral control result, and sending the steering wheel rotation angle to the steering execution control mechanism of the vehicle, and finally the steering execution control mechanism realizes the rotation control of the steering wheel based on the steering wheel rotation angle, thereby realizing the lateral control of the vehicle.

[0093] Through the above steps S331 to S332, the target steering angle result is obtained by preview compensation of the front wheel steering angle result through the steering angle compensation result, and the target steering angle result is converted into the steering wheel angle result based on the transmission ratio, so that the steering execution control mechanism can be instructed to control the vehicle steering based on the steering wheel angle result, making the efficiency and accuracy of the vehicle lateral control higher, which is beneficial to improving the efficiency and accuracy of the vehicle lateral control.

[0094] In some of the embodiments, the generating the dynamic control weight of the vehicle based on the mapping relationship between the vehicle speed information and the road curvature information further includes the following steps:

[0095] Step S221: Obtain the historical vehicle speed information and the historical road curvature information, and calculate the corresponding preset control weight value according to the historical vehicle speed information and the historical road curvature information.

[0096] Specifically, the obtaining methods of the above historical vehicle speed information and historical road curvature information can be as follows: Obtain the simulation experiment results, or use algorithms such as interpolation method to take values from a series of simulation experiment results or test data obtained through the test data of the vehicle's autonomous driving in the park or other working condition scenarios, so as to obtain the discrete historical vehicle speed information and historical road curvature information respectively corresponding preset control weight values in advance. Among them, the historical vehicle speed information, historical road curvature information, and preset control weight value calculated through the above methods can be statistical data in the form of mean or median values, etc.

[0097] Step S222: Obtain the preset mapping relationship table according to the historical vehicle speed information, the historical road curvature information, and the preset control weight value, perform query processing on the preset mapping relationship table according to the mapping relationship between the vehicle speed information and the road curvature information, and generate the dynamic control weight according to the preset control weight value queried.

[0098] Among them, the above preset mapping relationship table is used to indicate the corresponding relationship between the vehicle speed information, the road curvature information, and the control weight value; the preset mapping relationship table can be represented in the form of a chart. Table 1 is a two-dimensional table of a preset mapping relationship table, as shown in Table 1:

[0099] Table 1 Two-dimensional table of preset mapping relationship

[0100]

[0101] In the above Table 1, the first row of data is used to represent the above historical vehicle speed information, and the unit can be km / h; the first column of data is used to represent the above historical road curvature information, and the unit can be m -1; The data filled in the table where each row and column overlap are the preset control weight values corresponding to each historical vehicle speed information and each historical road curvature information. It can be understood that each data in the above-mentioned preset relationship two-dimensional table can be the actual vehicle calibration value; or, it can also be to first determine some calibration values, and then use algorithms such as the median method to determine the remaining data in the table. Based on the above Table 1, it can be known that the greater the road curvature, the greater the corresponding control weight value, and the greater the vehicle speed, the smaller the corresponding control weight value, so as to ensure that when the vehicle speed and curvature input externally change linearly, the control weight values in the above two-dimensional table also change linearly accordingly. Then, after obtaining the vehicle's current vehicle speed information and road curvature information through the above steps, the above preset mapping relationship table can be queried based on this vehicle speed information and this road curvature information, and finally a certain preset control weight value corresponding to the mapping relationship between this vehicle speed information and this road curvature information in the above preset mapping relationship table is queried. The queried preset control weight value is the above-mentioned dynamic control weight.

[0102] Through the above steps S221 to S222, by querying and processing the preset mapping relationship table based on the mapping relationship between the vehicle speed information and the road curvature information, the current dynamic control weight can be quickly and accurately queried, realizing a control weight parameter adjustment method with a small amount of calculation, and further improving the efficiency and accuracy of the vehicle lateral control method.

[0103] In some embodiments, the above step of calculating the front wheel steering angle result according to the first lateral position deviation and the dynamic control weight further includes the following steps: using a preset LQR controller model, iteratively solving and calculating a target function value according to the first lateral position deviation and the dynamic control weight, and calculating the front wheel steering angle result according to the target function value.

[0104] Furthermore, the above step of using a preset LQR controller model to iteratively solve and calculate a target function value according to the first lateral position deviation and the dynamic control weight further includes the following steps:

[0105] Step S223, generating a state weight matrix at least according to the first lateral position deviation, and generating a control weight matrix according to the dynamic control weight.

[0106] Among them, the above state weight matrix can be expressed as Q = diag[Q1, Q2, Q3, Q4]; diag[] is used to represent a diagonal matrix. Each matrix element Q1, Q2, Q3, Q4 on the diagonal of this matrix is respectively used to represent the first lateral position deviation, the change rate of the lateral position deviation, the heading error, and the change rate of the heading error; the change rate of the lateral position deviation can be calculated based on a series of first lateral position deviations obtained within a certain time period; the heading error and the change rate of the heading error can be calculated based on the above preset trajectory reference points and the information on the motion state of the vehicle collected in real time by the vehicle sensing device. The above control weight matrix can be expressed as R = [r]; r is used to represent the above dynamic control weight.

[0107] Step S224: Obtain the preset LQR state space equation and the objective function indicating the constraint relationship between the state weight matrix and the control weight matrix, and use the LQR controller model to iteratively solve the objective function according to the LQR state space equation to obtain the value of the objective function.

[0108] Specifically, the above LQR state space equation can be pre-constructed; the LQR state space equation is a discrete equation, as shown in Formula 5:

[0109] χ(k + 1) = A × χ(k) + B d ×u + C d Formula 5

[0110] In the above Formula 5, χ is used to represent the state matrix, u is used to represent the control matrix, A, B d , C d are the coefficients of the above state space equation, and k is a constant greater than 0. Through the above LQR controller module, iterative solution for the above objective function can obtain the value of the objective function J; among them, the objective function is as shown in Formula 6:

[0111] J = ∑(χ T Qχ + u T Ru) Formula 6

[0112] In the above Formula 6, χ T is used to represent the transpose matrix of the state matrix χ, u T is used to represent the transpose matrix of the control matrix u. Then, substitute the above Formula 5 into the above Formula 6, and use the LQR controller model to perform iterative calculation on Formula 6. Finally, the function value K with the smallest value in the value of the objective function J can be calculated, so as to solve and obtain the optimal solution K. According to the calculated value of K, conversion can be performed to obtain the above front wheel steering angle result, and the front wheel steering angle result can be expressed as δ LQR .

[0113] Through the above embodiments, the objective function is generated by dynamically controlling the weights, and the LQR controller model is used to iteratively solve the objective function to obtain the objective function value. Finally, the front wheel steering angle result is calculated based on the objective function value, thereby implementing the adaptive LQR lateral control method.

[0114] In some of the embodiments, obtaining the first lateral position deviation between the vehicle and the preset trajectory reference point further includes the following steps:

[0115] Step S211, obtaining the vehicle state information of the vehicle, and obtaining the path planning trajectory according to the vehicle state information; wherein, the path planning trajectory includes a first reference point generated based on the vehicle state information, and the first reference point is located in the global coordinate system.

[0116] Wherein, the vehicle state information may include the ego-vehicle motion state information and the ego-vehicle position state information; the vehicle state information can be obtained by real-time collection through vehicle sensing devices. Then, the path planning trajectory for the current map can be calculated based on the vehicle state information. It can be understood that each reference point in the path planning trajectory is located in the global coordinate system and serves as the above-mentioned first reference point.

[0117] Step S212, obtaining the coordinate transformation relationship between the global coordinate system and the ego-vehicle coordinate system of the vehicle, and transforming the first reference point to the ego-vehicle coordinate system according to the coordinate transformation relationship to obtain a second reference point after coordinate transformation.

[0118] Wherein, the transformation relationship between the global coordinate system and the ego-vehicle coordinate system can be obtained by camera calibration of the camera device of the vehicle; for example, the camera device can be calibrated through calibration objects such as calibration plates deployed on-site, and then the coordinate transformation relationship between the ego-vehicle coordinate system and the global coordinate system can be obtained. Then, the first reference point can be coordinate-transformed according to the coordinate transformation relationship to obtain a second reference point in the ego-vehicle coordinate system, so as to achieve the coordinate unity between each reference point on the path specification trajectory and the vehicle. In addition, the unified coordinate system is the ego-vehicle coordinate system with the ego-vehicle position as the origin, which is convenient for subsequent calculations in the ego-vehicle coordinate system and realizes the lateral control of the vehicle, and is beneficial to improving the accuracy of vehicle lateral control.

[0119] Step S213, calculating the trajectory point in the second reference point that is closest to the centroid position of the vehicle, determining the preset trajectory reference point based on the trajectory point, and calculating the first lateral position deviation.

[0120] Among them, the centroid position of the vehicle can be determined by the self-vehicle position state information described above. Specifically, two adjacent trajectory points closest to the centroid position of the vehicle can be calculated from the second reference points, and the preset trajectory reference point can be determined by using the linear interpolation method. Furthermore, the first lateral position deviation between the vehicle and the preset trajectory reference point can be calculated.

[0121] Through the above steps S211 to S213, by performing coordinate transformation on multiple first reference points on the path planning trajectory to obtain the second reference points in the self-vehicle coordinate system, the reference points on the path planning trajectory can be unified with the position information of the vehicle in the same coordinate system, which is beneficial to improving the calculation efficiency of the first lateral position deviation, thereby further improving the efficiency of vehicle lateral control.

[0122] The embodiments of the present application will be described in detail below in combination with actual application scenarios. Figure 4 is a flowchart of a vehicle lateral control method according to a preferred embodiment of the present application, as Figure 4 shown. The process includes the following steps:

[0123] Step S401, obtain the current self-vehicle position state information and self-vehicle motion state information; obtain the preset path planning trajectory. Among them, the self-vehicle position state information includes information such as the self-vehicle position or the vehicle centroid position information, heading angle, etc., and the self-vehicle motion state information includes information such as the self-vehicle speed, yaw rate, steering execution control mechanism, etc.

[0124] Step S402, select the current preset trajectory reference point according to the current self-vehicle position state information and self-vehicle motion state information; select the current preview point according to the path planning trajectory.

[0125] Step S403, calculate the lateral error, including the first lateral position deviation and the second lateral position deviation; specifically, calculate the vehicle centroid deviation based on the preset trajectory reference point, that is, the first lateral position deviation; calculate the position deviation caused by the heading or road curvature based on the preview point, that is, the second lateral position deviation.

[0126] Step S404, obtain the road curvature and vehicle speed information according to the self-vehicle position state information and the self-vehicle motion state information, and adjust the weight coefficient according to the road curvature and vehicle information to generate the current dynamic control weight of the vehicle.

[0127] Step S405, calculate and generate the front wheel steering angle result by using the LQR controller model according to the first lateral position deviation and the dynamic control weight; determine the preview distance and vehicle speed information according to the path planning trajectory, and calculate and generate the steering angle compensation result by using the vehicle preview kinematic model according to the preview distance, vehicle speed information and the second lateral position deviation.

[0128] Step S406: Calculate the steering wheel angle based on the front wheel angle result and the angle compensation result.

[0129] Step S407: Implement the lateral control of vehicle autonomous driving based on the steering wheel angle calculated in the above steps; based on the real-time feedback result of the autonomous driving vehicle, continue to obtain the self-vehicle position information, self-vehicle motion information, and path planning trajectory at the next moment, and implement the lateral control of vehicle autonomous driving until the vehicle stops or reaches the destination.

[0130] Through the above steps S401 to S407, calculate the lateral deviation caused by the vehicle sideslip angle and heading angle and the lateral position deviation caused by the road curvature in front of the vehicle according to the preview kinematic model, ensure the vehicle's early control, ensure the rapid convergence of control in the case of the vehicle entering a bend or vehicle swing, ensure the control stability and the accuracy of the tracking trajectory; at the same time, a method for dynamically adjusting the control weight based on the self-vehicle speed and road curvature as the basis for adjusting the LQR weight parameters is also proposed to ensure the stability of the LQR parameter adjustment strategy. Only based on the self-vehicle motion state and external road conditions can the bad control cycle be reduced, and the vehicle swing caused by overshoot in special road conditions such as large road curvature in a bend or lane change can be avoided, realizing the control stability in various scenarios.

[0131] It should be noted that the steps shown in the above process or the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and although the logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in a different order than here.

[0132] This embodiment also provides a vehicle lateral control device, which is used to implement the above embodiment and preferred implementation manners, and those that have been described will not be repeated. As used hereinafter, terms such as "module", "unit", "sub-unit", etc. can be a combination of software and / or hardware that can achieve a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, implementation in hardware, or a combination of software and hardware is also possible and contemplated.

[0133] Figure 5 is a structural block diagram of a vehicle lateral control device according to an embodiment of the present application, as Figure 5As shown in the figure, the device includes: an acquisition module 52, a weight module 54, and a generation module 56; the acquisition module 52 is configured to acquire the vehicle speed information, road curvature information, and the first lateral position deviation between the vehicle and a preset trajectory reference point; the weight module 54 is configured to generate a dynamic control weight for the vehicle based on the mapping relationship between the vehicle speed information and the road curvature information, and calculate a front wheel steering angle result according to the first lateral position deviation and the dynamic control weight; the generation module 56 is configured to generate a lateral control result for the vehicle according to the front wheel steering angle result, and perform lateral control on the vehicle according to the lateral control result.

[0134] Through the above embodiments, the weight module 54 generates a dynamic control weight through the mapping relationship between the vehicle speed information and the road curvature information, and calculates a front wheel steering angle result according to the dynamic control weight and the acquired first lateral position deviation, thereby realizing the real-time dynamic adjustment of the control weight parameters, effectively improving the accuracy and adaptability of autonomous driving control, solving the problem of low stability of vehicle lateral control, and realizing an accurate and stable vehicle lateral control device.

[0135] In some of the embodiments, the above generation module 56 is further configured to acquire a preview distance and a preset path planning trajectory, and calculate a preview point according to the vehicle speed information and the path planning trajectory; the generation module 56 calculates a second lateral position deviation between the vehicle and the preview point according to the preview distance, and obtains a steering angle compensation result according to the second lateral position deviation; the generation module 56 generates the lateral control result according to the front wheel steering angle result and the steering angle compensation result.

[0136] In some of the embodiments, the above generation module 56 is further configured to acquire a vehicle heading angle deviation, and calculate a heading angle lateral deviation according to the preview distance and the vehicle heading angle deviation; the generation module 56 calculates a first vertical distance between the preview point and the front extension line of the vehicle center, and a second vertical distance between the rear axle center of the vehicle and the path planning trajectory; the generation module 56 calculates the second lateral position deviation according to the first vertical distance, the second vertical distance, and the heading angle lateral deviation; the generation module 56 calculates an expected yaw rate according to the preview distance, the vehicle speed information, and the second lateral position deviation, and calculates the steering angle compensation result based on the expected yaw rate.

[0137] In some of the embodiments, the above generation module 56 is further configured to generate a target steering angle result according to the front wheel steering angle result and the steering angle compensation result; the generation module 56 acquires the transmission ratio between the target steering angle result and the steering wheel, and generates the lateral control result according to the transmission ratio and the target steering angle result.

[0138] In some of these embodiments, the above-mentioned weight module 54 is further configured to use a preset LQR controller model to iteratively solve and calculate an objective function value based on the first lateral position deviation and the dynamic control weight, and calculate the front wheel steering angle result based on the objective function value.

[0139] In some of these embodiments, the above-mentioned weight module 54 is further configured to generate a state weight matrix at least based on the first lateral position deviation, and generate a control weight matrix based on the dynamic control weight; the weight module 54 obtains a preset LQR state space equation, generates an objective function for indicating the constraint relationship between the state weight matrix and the control weight matrix according to the LQR state space equation, and iteratively solves the objective function by using the LQR controller model to obtain the objective function value.

[0140] In some of these embodiments, the above-mentioned weight module 54 is further configured to obtain historical vehicle speed information and historical road curvature information, and calculate a corresponding preset control weight value according to the historical vehicle speed information and the historical road curvature information; the weight module 54 obtains a preset mapping relationship table according to the historical vehicle speed information, the historical road curvature information and the preset control weight value, performs a query process on the preset mapping relationship table according to the mapping relationship between the vehicle speed information and the road curvature information, and generates the dynamic control weight according to the preset control weight value queried.

[0141] In some of these embodiments, the above-mentioned acquisition module 52 is further configured to obtain the vehicle state information of the vehicle, and obtain a path planning trajectory according to the vehicle state information; wherein, the path planning trajectory includes a first reference point generated based on the vehicle state information, and the first reference point is located in the global coordinate system; the acquisition module 52 obtains the coordinate transformation relationship between the global coordinate system and the vehicle's own vehicle coordinate system, and transforms the first reference point to the own vehicle coordinate system according to the coordinate transformation relationship to obtain a second reference point after coordinate transformation; the acquisition module 52 calculates the trajectory point closest to the centroid position of the vehicle in the second reference point, determines the preset trajectory reference point based on the trajectory point, and calculates the first lateral position deviation.

[0142] It should be noted that the above-mentioned various modules can be functional modules or program modules, and can be implemented either by software or by hardware. For the modules implemented by hardware, the above-mentioned various modules can be located in the same processor; or the above-mentioned various modules can also be located in different processors in any combined form.

[0143] This embodiment also provides a vehicle lateral control system. Figure 6 It is a structural block diagram of a vehicle lateral control system according to an embodiment of the present application, as Figure 6As shown in the figure, the system includes a control device 62 and a vehicle body 64. The control device 62 is connected to the vehicle body 64 and is used to execute any one of the vehicle lateral control methods in the above embodiments to control the automatic steering of the vehicle body 62. Among them, the above control device 62 can be a chip, a microprocessor or other devices integrated on the vehicle body 64 for controlling the vehicle body 64. Alternatively, the control device 62 can also be a device such as a server that communicates and is online with the vehicle body 64 through remote or local area network, etc., which will not be elaborated here.

[0144] Through the above embodiments, the control device generates a dynamic control weight based on the mapping relationship between the vehicle speed information and the road curvature information, and calculates the front wheel steering angle result according to the dynamic control weight and the obtained first lateral position deviation, thereby realizing the real-time dynamic adjustment of the control weight parameter, effectively improving the accuracy and adaptability of the automatic driving control, solving the problem of low stability of the vehicle lateral control, and realizing an accurate and stable vehicle lateral control system.

[0145] In some of these embodiments, a computer device is provided. The computer device can be a server. Figure 7 It is a structural diagram inside a computer device according to an embodiment of the present application, as Figure 7 shown. The computer device includes a processor, a memory, a network interface and a database connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store the lateral control results. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, it realizes the above vehicle lateral control method.

[0146] Those skilled in the art can understand that Figure 7 the structure shown in

[0147] is only a block diagram of some parts of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine some components, or have different component arrangements.

[0148] Optionally, the above electronic device may further include a transmission device and an input / output device, wherein the transmission device is connected to the above processor, and the input / output device is connected to the above processor.

[0149] Optionally, in this embodiment, the above processor may be configured to execute the following steps by a computer program:

[0150] S1. Obtain the vehicle speed information, road curvature information of the vehicle, and a first lateral position deviation between the vehicle and a preset trajectory reference point.

[0151] S2. Generate a dynamic control weight of the vehicle based on the mapping relationship between the vehicle speed information and the road curvature information, and calculate a front wheel steering angle result according to the first lateral position deviation and the dynamic control weight.

[0152] S3. Generate a lateral control result of the vehicle according to the front wheel steering angle result, and perform lateral control on the vehicle according to the lateral control result.

[0153] It should be noted that for the specific examples in this embodiment, reference may be made to the examples described in the above embodiments and optional implementation manners, and details are not described herein again.

[0154] In addition, in combination with the vehicle lateral control method in the above embodiments, an embodiment of the present application can be implemented by providing a storage medium. A computer program is stored on the storage medium; when the computer program is executed by a processor, any one of the vehicle lateral control methods in the above embodiments is implemented.

[0155] Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by instructing relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above methods. Among them, any reference to a memory, storage, database, or other medium used in the embodiments provided in the present application can include non-volatile and / or volatile memories. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), Rambus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and Rambus dynamic RAM (RDRAM), etc.

[0156] Those skilled in the art should understand that the technical features of the above embodiments can be combined arbitrarily. For the sake of brevity of description, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, it should be considered as the scope described in this specification.

[0157] The above embodiments merely represent several implementation manners of the present application. The description thereof is relatively specific and detailed, but it should not be construed as a limitation on the scope of the invention patent. It should be noted that for those of ordinary skill in the art, without departing from the concept of the present application, several modifications and improvements can still be made, and these all belong to the protection scope of the present application. Therefore, the protection scope of the patent of the present application should be subject to the appended claims.

Claims

1. A vehicle lateral control method, characterized in that, The method includes: Obtaining the vehicle speed information, road curvature information of the vehicle, and a first lateral position deviation between the vehicle and a preset trajectory reference point; the preset trajectory reference point is a trajectory point adjacent to the vehicle on a pre-generated path planning trajectory; calculating the coordinate position offset relationship between the vehicle and the preset trajectory reference point to obtain the first lateral position deviation; Generating a dynamic control weight of the vehicle based on the mapping relationship between the vehicle speed information and the road curvature information, including: Obtaining historical vehicle speed information and historical road curvature information, and calculating corresponding preset control weight values according to the historical vehicle speed information and the historical road curvature information; obtaining a preset mapping relationship table according to the historical vehicle speed information, the historical road curvature information, and the preset control weight values, performing a query process on the preset mapping relationship table according to the mapping relationship between the vehicle speed information and the road curvature information, and generating the dynamic control weight according to the queried preset control weight values; Calculating a front wheel steering angle result according to the first lateral position deviation and the dynamic control weight; Generating a lateral control result of the vehicle according to the front wheel steering angle result, and performing lateral control on the vehicle according to the lateral control result.

2. The vehicle lateral control method according to claim 1, characterized in that: The generating the lateral control result of the vehicle according to the front wheel steering angle result includes: Obtaining a preview distance and a preset path planning trajectory, and calculating a preview point according to the vehicle speed information and the path planning trajectory; Calculating a second lateral position deviation between the vehicle and the preview point according to the preview distance, and obtaining a steering angle compensation result according to the second lateral position deviation; Generating the lateral control result according to the front wheel steering angle result and the steering angle compensation result.

3. The vehicle lateral control method according to claim 2, wherein, The calculating the second lateral position deviation between the vehicle and the preview point according to the preview distance, and obtaining the steering angle compensation result according to the second lateral position deviation includes: Obtaining a vehicle heading angle deviation, and calculating a heading angle lateral deviation according to the preview distance and the vehicle heading angle deviation; Calculating a first vertical distance between the preview point and the front extension line of the vehicle center, and a second vertical distance between the rear axle center of the vehicle and the path planning trajectory; calculating the second lateral position deviation according to the first vertical distance, the second vertical distance, and the heading angle lateral deviation; Calculating an expected yaw rate according to the preview distance, the vehicle speed information, and the second lateral position deviation, and calculating the steering angle compensation result based on the expected yaw rate.

4. The vehicle lateral control method according to claim 2, characterized in that: The generating the lateral control result according to the front wheel steering angle result and the steering angle compensation result includes: Generating a target steering angle result according to the front wheel steering angle result and the steering angle compensation result; Obtaining a transmission ratio between the target steering angle result and the steering wheel, and generating the lateral control result according to the transmission ratio and the target steering angle result.

5. The vehicle lateral control method according to claim 1, wherein The calculating the front wheel steering angle result according to the first lateral position deviation and the dynamic control weight includes: Using a preset LQR controller model, an objective function value is obtained through iterative solution calculation based on the first lateral position deviation and the dynamic control weight, and a front wheel steering angle result is calculated based on the objective function value.

6. The vehicle lateral control method according to claim 5, characterized in that: The use of the preset LQR controller model to perform iterative solution calculation based on the first lateral position deviation and the dynamic control weight to obtain the objective function value: Generate a state weight matrix based at least on the first lateral position deviation, and generate a control weight matrix based on the dynamic control weight; Obtain a preset LQR state space equation and an objective function indicating the constraint relationship between the state weight matrix and the control weight matrix, and use the LQR controller model to perform iterative solution of the objective function according to the LQR state space equation to obtain the objective function value.

7. The vehicle lateral control method according to any one of claims 1 to 6, characterized in that Obtaining the first lateral position deviation between the vehicle and the preset trajectory reference point includes: Obtain the vehicle state information of the vehicle, and obtain a path planning trajectory according to the vehicle state information; wherein, the path planning trajectory includes a first reference point generated based on the vehicle state information, and the first reference point is located in the global coordinate system; Obtain the coordinate transformation relationship between the global coordinate system and the vehicle's own vehicle coordinate system, and transform the first reference point to the own vehicle coordinate system according to the coordinate transformation relationship to obtain a second reference point after coordinate transformation; Calculate the trajectory point closest to the centroid position of the vehicle among the second reference points, determine the preset trajectory reference point based on the trajectory point, and calculate the first lateral position deviation.

8. A vehicle lateral control device, characterized in that, The device includes: an acquisition module, a weight module, and a generation module; The acquisition module is configured to acquire the vehicle speed information, road curvature information of the vehicle, and the first lateral position deviation between the vehicle and the preset trajectory reference point; The weight module is configured to generate the dynamic control weight of the vehicle based on the mapping relationship between the vehicle speed information and the road curvature information, and calculate the front wheel steering angle result according to the first lateral position deviation and the dynamic control weight; The weight module is further configured to acquire historical vehicle speed information and historical road curvature information, and calculate the corresponding preset control weight value according to the historical vehicle speed information and the historical road curvature information; obtain a preset mapping relationship table according to the historical vehicle speed information, the historical road curvature information, and the preset control weight value, perform query processing on the preset mapping relationship table according to the mapping relationship between the vehicle speed information and the road curvature information, and generate the dynamic control weight according to the queried preset control weight value; The generation module is configured to generate a lateral control result of the vehicle according to the front wheel steering angle result, and perform lateral control on the vehicle according to the lateral control result.

9. A vehicle lateral control system, characterized in that, The system includes: a control device and a vehicle body; The control device is connected to the vehicle body and is configured to execute the vehicle lateral control method according to any one of claims 1 to 7.

10. An electronic device, comprising a memory and a processor, characterized in that, A computer program is stored in the memory, and the processor is configured to run the computer program to execute the vehicle lateral control method according to any one of claims 1 to 7.

11. A storage medium, characterized in that, A computer program is stored in the storage medium, wherein the computer program is configured to execute the vehicle lateral control method according to any one of claims 1 to 7 when running.

Images