Vehicle front wheel turning angle determination method and device, electronic equipment and storage medium

Abstract

This application provides a method, apparatus, electronic device, and storage medium for determining the front wheel steering angle of a vehicle. The method includes: acquiring dynamic information and steady-state information of the vehicle at the current moment; wherein the dynamic information characterizes the vehicle's driving and steering conditions, and the steady-state information characterizes the vehicle's steady-state yaw condition; determining first steering information of the vehicle based on the dynamic information, and determining second steering information of the vehicle based on the steady-state information; wherein both the first steering information and the second steering information characterize the estimated front wheel steering angle of the vehicle; and determining the front wheel steering angle information of the vehicle at the current moment based on the first steering information and the second steering information. This method combines two estimated values ​​of the front wheel steering angle to improve the accuracy of front wheel steering angle determination.

Description

Technical Field

[0001] This application relates to the field of artificial intelligence, and in particular to a method, apparatus, electronic device, and storage medium for determining the steering angle of the front wheels of a vehicle. Background Technology

[0002] The front wheel steering angle is an important parameter in the process of vehicle driving, which can directly affect the vehicle's driving direction and control the vehicle's trajectory.

[0003] If the front wheel steering angle cannot be accurately measured, it may lead to understeer or oversteer, thus threatening driving safety. This is especially true when the SBW (Steering By Wire) system malfunctions, as the front wheel steering cannot be accurately detected, affecting driving safety. Summary of the Invention

[0004] This application provides a method, apparatus, electronic device, and storage medium for determining the front wheel steering angle of a vehicle, in order to improve the accuracy of front wheel steering angle determination.

[0005] In a first aspect, embodiments of this application provide a method for determining the steering angle of a vehicle's front wheels, comprising:

[0006] Acquire the vehicle's dynamics and steady-state information at the current moment; wherein the dynamics information represents the vehicle's driving and steering, and the steady-state information represents the vehicle's steady-state yaw.

[0007] Based on the dynamic information, first steering information of the vehicle is determined, and based on the steady-state information, second steering information of the vehicle is determined; wherein, both the first steering information and the second steering information characterize the estimated front wheel steering angle of the vehicle;

[0008] Based on the first steering information and the second steering information, the front wheel steering angle information of the vehicle at the current moment is determined.

[0009] Secondly, embodiments of this application provide a device for determining the steering angle of a vehicle's front wheels, comprising:

[0010] An information acquisition unit is used to acquire the vehicle's dynamic information and steady-state information at the current moment; wherein, the dynamic information represents the vehicle's driving and steering conditions, and the steady-state information represents the vehicle's steady-state yaw conditions;

[0011] A steering determination unit is configured to determine first steering information of the vehicle based on the dynamic information, and to determine second steering information of the vehicle based on the steady-state information; wherein both the first steering information and the second steering information characterize the estimated front wheel steering angle of the vehicle;

[0012] Angle determination unit is used to determine the front wheel angle information of the vehicle at the current moment based on the first steering information and the second steering information.

[0013] Thirdly, embodiments of this application provide an electronic device, including: a memory and a processor;

[0014] The memory stores computer-executed instructions;

[0015] The processor executes computer execution instructions stored in the memory, causing the processor to perform the method described in the first aspect above.

[0016] Fourthly, embodiments of this application provide a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, are used to implement the method described in the first aspect above.

[0017] Fifthly, embodiments of this application provide a computer program product, including a computer program that, when executed by a processor, implements the method described in the first aspect above.

[0018] This application provides a method, apparatus, electronic device, and storage medium for determining the front wheel steering angle of a vehicle. By acquiring the vehicle's dynamic information and steady-state information, the vehicle's dynamic characteristics and steady-state features can be obtained. Based on the vehicle's dynamic characteristics, a front wheel steering angle can be estimated. Based on the vehicle's steady-state characteristics, a front wheel steering angle can also be estimated. Combining these two estimation results, the final front wheel steering angle is determined, effectively improving the accuracy of the vehicle's front wheel steering angle determination and facilitating precise vehicle control. Attached Figure Description

[0019] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0020] Figure 1 A flowchart illustrating a method for determining the front wheel steering angle of a vehicle, provided in an embodiment of this application;

[0021] Figure 2 A flowchart illustrating a method for determining the front wheel steering angle of a vehicle, provided in an embodiment of this application;

[0022] Figure 3 A flowchart illustrating a method for determining the front wheel steering angle of a vehicle, provided in an embodiment of this application;

[0023] Figure 4 A schematic diagram of a device for determining the front wheel steering angle of a vehicle provided in an embodiment of this application;

[0024] Figure 5 A schematic diagram of a device for determining the front wheel steering angle of a vehicle provided in an embodiment of this application;

[0025] Figure 6 A schematic diagram of the structure of the electronic device provided in this application.

[0026] The accompanying drawings illustrate specific embodiments of this application, which will be described in more detail below. These drawings and descriptions are not intended to limit the scope of the concept in any way, but rather to illustrate the concept of this application to those skilled in the art through reference to particular embodiments. Detailed Implementation

[0027] To make the objectives, technical solutions, and advantages of this application clearer, the embodiments of this application will be described in further detail below with reference to the accompanying drawings.

[0028] It should be understood that the described embodiments are merely some, not all, of the embodiments in this application. All other embodiments obtained by those skilled in the art based on the embodiments in this application without inventive effort are within the scope of protection of this application.

[0029] In the following description, when referring to the accompanying drawings, the same numbers in different drawings denote the same or similar elements unless otherwise indicated. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this application as detailed in the appended claims.

[0030] In the description of this application, it should be understood that the terms "first," "second," "third," etc., are used only to distinguish similar objects and are not necessarily used to describe a specific order or sequence, nor should they be construed as indicating or implying relative importance. Those skilled in the art can understand the specific meaning of the above terms in this application according to the specific circumstances. Furthermore, in the description of this application, unless otherwise stated, "multiple" refers to two or more. "And / or" describes the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, or B existing alone. The character " / " generally indicates that the preceding and following related objects have an "or" relationship.

[0031] It should be noted that, due to space limitations, this application specification does not exhaustively list all possible implementation methods. Those skilled in the art, after reading this application specification, should be able to deduce that, as long as the technical features do not contradict each other, any combination of technical features can constitute an optional implementation method. The following provides a detailed description of each embodiment.

[0032] Front wheel steering angle is a crucial parameter in vehicle dynamics and control systems, permeating all aspects of basic driving and autonomous driving. It plays a vital role in multiple dimensions, including ensuring vehicle safety, improving control precision, verifying system reliability, and driving technological innovation.

[0033] However, directly measuring the front wheel steering angle using sensors can be affected by environmental interference such as mud, water, and electromagnetic noise. Especially for vehicles equipped with a Side-by-Side Wheel Warping (SBW) system, when the SBW system malfunctions, the accuracy of the front wheel steering angle estimation will be severely affected, resulting in a large estimation error and consequently impacting the vehicle's safe driving.

[0034] This application provides a method, apparatus, electronic device, and storage medium for determining the front wheel steering angle of a vehicle, aiming to solve the above-mentioned technical problems in the prior art.

[0035] The technical solution of this application and how the technical solution of this application solves the above-mentioned technical problems are described in detail below with specific embodiments. These specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described again in some embodiments. The embodiments of this application will now be described with reference to the accompanying drawings.

[0036] Figure 1 This is a flowchart illustrating a method for determining the front wheel steering angle of a vehicle according to an embodiment of this application. This method can be executed by a device for determining the front wheel steering angle of a vehicle. Figure 1 As shown, the method includes the following steps:

[0037] S101. Obtain the vehicle's dynamics and steady-state information at the current moment; wherein, the dynamics information represents the vehicle's driving and steering, and the steady-state information represents the vehicle's steady-state yaw.

[0038] For example, a vehicle may be equipped with various sensors, such as speed sensors and acceleration sensors. These sensors allow for the real-time acquisition of the vehicle's dynamic and steady-state information while the vehicle is in motion. When it is necessary to estimate the front wheel steering angle, the vehicle's dynamic and steady-state information at the current moment can be obtained.

[0039] Dynamic information characterizes a vehicle's driving and steering behavior. For example, dynamic information may include the vehicle's mass, speed, acceleration, yaw rate, front axle lateral stiffness, and rear axle lateral stiffness. Steady-state information characterizes the vehicle's steady-state yaw behavior. For example, steady-state information may include steady-state yaw rate and speed. Dynamic and steady-state information may contain the same or different data.

[0040] S102. Based on the dynamic information, determine the first steering information of the vehicle, and based on the steady-state information, determine the second steering information of the vehicle; wherein, both the first steering information and the second steering information characterize the estimated front wheel steering angle of the vehicle.

[0041] For example, the front wheel steering angle of the vehicle can be estimated based on dynamic information and steady-state information, respectively. The front wheel steering angle estimated based on the dynamic information is determined as the first steering information, and the front wheel steering angle estimated based on the steady-state information is determined as the second steering information.

[0042] Algorithms for determining the first and second steering information can be pre-set. For example, an XYZ coordinate axis can be established with the vehicle as the center. The X-axis can be the direction of vehicle travel, i.e., the longitudinal direction of the vehicle; the Y-axis is the lateral direction of the vehicle; and the Z-axis can be the direction perpendicular to the ground. The dynamic information can include the vehicle's mass, lateral velocity, moment of inertia about the Z-axis, moment of inertia of the front steering system, and damping of the front steering system. By performing differential calculations on the dynamic information, the first steering information can be obtained.

[0043] For the second steering information, the motion relationship between the steady-state yaw rate and the front wheel steering angle can be pre-constructed. The steady-state yaw rate in the steady-state information is substituted into this motion relationship, and the calculated front wheel steering angle is the second steering information.

[0044] Alternatively, actual front wheel steering angle, dynamics information, and steady-state information of the vehicle over a historical period can be collected in advance as training data. A first model and a second model are pre-constructed; both are neural network models. The input to the first model can be dynamics information, and the output is first steering information. The input to the second model can be steady-state information, and the output is second steering information. The first model is trained based on the front wheel steering angle and dynamics information from the training data, and the second model is trained based on the front wheel steering angle and steady-state information from the training data. Based on the trained first and second models, the first steering information and the second steering information can be obtained respectively. In this embodiment, the model structure of the first and second models is not specifically limited.

[0045] S103. Based on the first steering information and the second steering information, determine the front wheel steering angle information of the vehicle at the current moment.

[0046] For example, after obtaining the first steering information and the second steering information, the first steering information and the second steering information can be combined, that is, the two estimated front wheel steering angles can be combined to determine the final front wheel steering angle, which is used as the front wheel steering angle information at the current moment, so as to realize the real-time estimation of the front wheel steering angle.

[0047] For example, the weights of the first steering information and the second steering information can be preset. Based on the preset weights, the first steering information and the second steering information are weighted and summed to calculate the front wheel steering angle information at the current moment.

[0048] In this embodiment, the first steering information is the estimated front wheel steering angle obtained based on the vehicle dynamics model, and the second steering information is the estimated front wheel steering angle obtained based on the vehicle kinematics model. Combining these two estimates yields the final estimated front wheel steering angle. After determining the front wheel steering angle, the vehicle's direction of travel can be changed, enabling maneuvers such as turning and lane changing, thus achieving autonomous driving.

[0049] This application provides a method for determining the front wheel steering angle of a vehicle. By acquiring the vehicle's dynamic information and steady-state information, the vehicle's dynamic characteristics and steady-state features can be obtained. Based on the vehicle's dynamic characteristics, a front wheel steering angle can be estimated. Based on the vehicle's steady-state characteristics, a front wheel steering angle can also be estimated. Combining these two estimation results, the final front wheel steering angle is determined, effectively improving the accuracy of the vehicle's front wheel steering angle determination and facilitating precise vehicle control.

[0050] Figure 2 A flowchart illustrating a method for determining the front wheel steering angle of a vehicle, as provided in this application embodiment, is shown below. Figure 2 As shown, in this embodiment... Figure 1 Based on the embodiments, a method for determining the front wheel steering angle of a vehicle is described in detail, the method including:

[0051] S201. Obtain the vehicle's dynamics and steady-state information at the current moment; wherein, the dynamics information represents the vehicle's driving and steering, and the steady-state information represents the vehicle's steady-state yaw.

[0052] For example, this step can refer to step S101 above, and will not be repeated here.

[0053] S202. Based on the dynamic information and a preset artificial intelligence model, determine the predicted steering angle of the vehicle; wherein, the preset artificial intelligence model is a pre-built neural network model used to predict the front wheel steering angle of the vehicle based on the dynamic information; and determine the first steering information of the vehicle based on the dynamic information and the predicted steering angle.

[0054] For example, an AI (Artificial Intelligence) model is pre-built and trained. In this embodiment, the model structure of the AI ​​model is not specifically limited. Dynamic information is input into the AI ​​model, and the output of the AI ​​model is a predicted steering angle. That is, the AI ​​model can first predict the steering angle of the vehicle's front wheels. Then, combining the dynamic information and the predicted steering angle value from the AI ​​model, the vehicle's first steering information is determined. In other words, the AI ​​model's predicted steering angle value can be used as a reference to calculate the first steering information, avoiding excessive errors in the first steering information and improving the accuracy of its determination.

[0055] The AI ​​model is pre-trained. Its input data is dynamic information, and its output data is the front wheel steering angle. Therefore, the training data to be collected can include the vehicle's actual dynamic information and the actual front wheel steering angle at a given historical time. The actual dynamic information is then input into the AI ​​model to obtain the predicted front wheel steering angle. The predicted front wheel steering angle is compared with the actual front wheel steering angle to determine whether the AI ​​model has been successfully trained.

[0056] The system can also generate vehicle dynamics information and corresponding front wheel steering angles based on a preset simulation model. For example, the preset simulation model can be a simulation model based on a steer-by-wire vehicle. The input data of this simulation model can be the dynamics information set by the user according to actual needs, and the output data can be the front wheel steering angle calculated based on the input dynamics information. The input and output data of the simulation model are used as the training data for the AI ​​model. For example, the vehicle speed in the simulation model can be set to [-50, -40, -30, ..., 0, 10, 20, 30, 40, ..., 150] km / h, and the longitudinal acceleration can be set to [-12, -9, -8, ..., 0, 1, 2, 3, ..., 12] m / s². 2 Yaw rate is [-50, -40, -30, ..., 0, ..., 30, 40, 50] deg / s, sideslip angle is [-50, -40, -30, ..., 0, ..., 30, 40, 50] deg, and yaw rate acceleration is [-100, -80, -60, ..., 0, ..., 60, 80, 100] deg / s 2 The lateral acceleration is [-12, -9, -8, ..., 0, 1, 2, 3, ..., 12] m / s² 2 The system takes the dynamic information set as input and the actual value of the front wheel steering angle as output. Different combinations of vehicle speed, longitudinal acceleration, yaw rate, sideslip angle, yaw rate acceleration, and lateral acceleration can correspond to different front wheel steering angles. The input and output values ​​of the simulation model are then input into the AI ​​model.

[0057] The AI ​​model can be trained on various scenarios, with the primary training scenario being high-frequency and large-amplitude yaw rates and sideslip angles. That is, the dynamic information set can be high-frequency and large-amplitude yaw rates and large sideslip angles, enabling the AI ​​model to accurately predict the front wheel steering angle in such highly unsteady scenarios. In this embodiment, the training process of the AI ​​model is not specifically limited. Through AI training, more accurate front wheel steering angle predictions can be obtained when the vehicle enters a highly unsteady state. After the AI ​​model training is complete, the dynamic information input to the AI ​​model includes vehicle speed, longitudinal acceleration, yaw rate, sideslip angle, yaw rate acceleration, and lateral acceleration.

[0058] When combining dynamic information and steering angle prediction, if the vehicle is currently in a large unsteady state, the steering angle prediction can be referred more; if the vehicle is in a steady state, the steering angle prediction can be referred less.

[0059] In this embodiment, determining the vehicle's first steering information based on dynamic information and steering angle prediction includes: acquiring a preset first steering angle model and a preset second steering angle model; wherein, the preset first steering angle model represents the functional relationship between dynamic information and front wheel steering angle, and the preset second steering angle model represents the functional relationship between dynamic information, steering angle prediction, and front wheel steering angle; and determining the vehicle's first steering information based on a preset extended Kalman filter algorithm using the dynamic information, steering angle prediction, preset first steering angle model, and preset second steering angle model.

[0060] Specifically, a first steering angle model and a second steering angle model are pre-set. The first steering angle model represents the functional relationship between dynamic information and the front wheel steering angle, while the second steering angle model represents the functional relationship between dynamic information, the predicted steering angle, and the front wheel steering angle. That is, the first steering angle model can be a calculation formula containing dynamic information and the front wheel steering angle, and the second steering angle model can be a calculation formula containing dynamic information, the predicted steering angle, and the front wheel steering angle.

[0061] The dynamic information is substituted into the first steering angle model, and the dynamic information and the predicted steering angle are substituted into the second steering angle model. A preset extended Kalman filter algorithm is used to calculate the first and second steering angle models, and the calculation result is the first steering information. The first steering angle model is used as the state equation, and the second steering angle model is used as the output equation. In the extended Kalman filter, the estimated value of the front wheel steering angle, i.e., the first steering information, can be obtained by calculating based on the state equation and the output equation. In this embodiment, the calculation process of the extended Kalman filter is not specifically limited, and the first steering angle model is a five-dimensional state equation.

[0062] The advantage of this setup is that by using an extended Kalman filter and combining the state equation and the output equation, the accuracy of determining the first steering information is improved, which in turn improves the accuracy of determining the front wheel steering angle information.

[0063] In this embodiment, the preset first turning angle model is characterized as follows:

[0064]

[0065] Among them, v y Characterizing the lateral velocity of a vehicle, w represents the derivative of the lateral velocity with time. z Characterizing yaw rate, Characterizing yaw acceleration, δ f Characterizes the front wheel steering angle, Characterizing the angular velocity of the front wheels, Characterizing the front wheel angular acceleration, δ r Characterizing the rear wheel steering angle, The rear wheel angular velocity is represented by m, and the vehicle mass is represented by v. x C represents the longitudinal velocity of a vehicle. f C characterizes the lateral stiffness of the front axle. r L characterizes the lateral stiffness of the rear axle. f L represents the distance from the center of gravity to the front axle. r J represents the distance from the center of gravity to the rear axle. z L represents the moment of inertia of a vehicle about the Z-axis. x Characterized by drag distance, B s Characterizing the damping of the front steering system, J s W represents the moment of inertia of the front steering system. f W represents the wheelbase of the front axle. r L represents the wheelbase of the rear axle. y Characterized by the radius of the wiping action, ΔF fxb ΔF represents the difference in braking force between the left and right sides of the front axle. fxd ΔF represents the difference in driving force between the left and right sides of the front axle. rxb ΔF represents the difference in braking force between the left and right sides of the rear axle. rxd It represents the difference in driving force between the left and right sides of the rear axle.

[0066] Specifically, dynamic equations for five states are pre-constructed, including the lateral velocity v. y Yaw rate, also known as yaw rate w z Front wheel steering angle δ f Front wheel steering rate Rear wheel steering angle δ r The dynamic equations for these five states are as follows:

[0067]

[0068] Among them, K s For the stiffness of the front steering system, M s The total frictional torque of the front steering system. Transforming these five dynamic equations yields the form of the first steering angle model, which is the state equation. The vehicle's lateral velocity, yaw rate, vehicle mass, longitudinal velocity, lateral stiffness of the front axle, lateral stiffness of the rear axle, distance from the center of gravity to the front axle, distance from the center of gravity to the rear axle, moment of inertia about the Z-axis, trail distance, damping of the front steering system, moment of inertia of the front steering system, track width of the front axle, track width of the rear axle, contact radius, difference in braking force between the left and right sides of the front axle, difference in driving force between the left and right sides of the front axle, difference in braking force between the left and right sides of the rear axle, difference in driving force between the left and right sides of the rear axle, stiffness of the front steering system, and total frictional torque of the front steering system are all considered dynamic information.

[0069] The advantage of this setup is that by establishing a five-dimensional state-space equation, factors such as the rear wheel steering angle and the imbalance of longitudinal driving force of the wheel-end driven vehicle are further considered, thereby improving the estimation accuracy of the front wheel steering angle.

[0070] In this embodiment, the preset second corner model is characterized as follows:

[0071]

[0072] Among them, v y w represents the lateral velocity of a vehicle. z Characterized by yaw rate, δ f Characterizes the front wheel steering angle, Characterizing the angular velocity of the front wheel, δ r Characterizing the rear wheel steering angle, The predicted steering angle is represented by m, and the vehicle mass is represented by v. x C represents the longitudinal velocity of a vehicle. f C characterizes the lateral stiffness of the front axle. r L characterizes the lateral stiffness of the rear axle. f L represents the distance from the center of gravity to the front axle. r a represents the distance from the center of gravity to the rear axle. y Characterizes lateral acceleration.

[0073] Specifically, output equations for five state data types are constructed as the second turning angle model. The second turning angle model... This is the AI ​​model's prediction of the front wheel steering angle, which can be used to assist in determining the first steering information. In both the first and second steering angle models, the data obtainable are all dynamic information. For example, dynamic information may include lateral velocity, yaw rate, vehicle mass, longitudinal velocity, lateral stiffness, distance from the center of gravity to the front axle, distance from the center of gravity to the rear axle, and lateral acceleration. From these five state data points, the front wheel steering angle can be calculated based on the state equation and output equation, thus obtaining the estimated front wheel steering angle, i.e., the first steering information.

[0074] The advantage of this setup is that, in some scenarios, the estimation results of the extended Kalman filter are inaccurate. By combining the state equation with the output equation, and combining the output equation with the AI ​​model, the estimation accuracy can be effectively improved.

[0075] In this embodiment, the dynamic information includes sideslip angle and yaw rate. Based on the dynamic information, the predicted steering angle, the preset first steering angle model, and the preset second steering angle model, the first steering information of the vehicle is determined using the extended Kalman filter algorithm. This includes: determining the vehicle's measurement noise based on the sideslip angle and yaw rate; wherein the measurement noise characterizes the reliability of the predicted steering angle value; and determining the vehicle's first steering information based on the measurement noise, dynamic information, the predicted steering angle, the preset first steering angle model, and the preset second steering angle model using the extended Kalman filter algorithm.

[0076] Specifically, when the steering angle predictions from the AI ​​model are incorporated into the extended Kalman filter (EPF), the EPF's calculation results are affected by measurement noise. Measurement noise is a parameter that varies dynamically with the vehicle; the principle is that the larger the yaw rate and sideslip angle, the smaller the measurement noise. In other words, the higher the steady-state condition, the greater the measurement noise. Under high dynamic, i.e., non-steady-state conditions, the EPF relies more on the AI ​​model to predict the vehicle's front wheel steering angle, reducing its dependence on the Kalman filter. In other words, the lower the measurement noise, the higher the reliability of the AI ​​model's steering angle predictions; conversely, the higher the measurement noise, the lower the reliability of the AI ​​model's steering angle predictions.

[0077] The correlation between yaw rate, sideslip angle, and measurement noise can be preset. After determining the vehicle's current yaw rate and sideslip angle, the corresponding measurement noise can be found based on the preset correlation. The measurement noise is then introduced into an extended Kalman filter, which calculates the first steering information based on the measurement noise. Table 1 shows the correlation between yaw rate, sideslip angle, and measurement noise.

[0078] Table 1. Correlation between yaw rate, sideslip angle, and measurement noise.

[0079]

[0080] Taking Table 1 as an example, the measurement noise is the highest when both sideslip angle and yaw rate are 0, which is 10,000,000.

[0081] The advantage of this setup is that the AI ​​model is used to predict the front wheel steering angle of a vehicle in high dynamic and high frequency scenarios. By introducing measurement noise, the reliability of the steering angle prediction value of the AI ​​model can be determined, thereby improving the computational accuracy of the extended Kalman filter.

[0082] S203. Obtain a preset third steering angle model; wherein, the preset third steering angle model represents the functional relationship between steady-state information and front wheel steering angle, and the steady-state information includes at least one of yaw rate, longitudinal speed of the vehicle, and characteristic speed; based on the steady-state information and the preset third steering angle model, determine the second steering information of the vehicle based on a preset recursive least squares method.

[0083] For example, a third steering angle model is pre-set, which represents the functional relationship between steady-state information and front wheel steering angle. The steady-state information may include yaw rate, vehicle longitudinal speed, and characteristic vehicle speed. That is, the third steering angle model may be a calculation formula containing yaw rate, vehicle longitudinal speed, characteristic vehicle speed, and front wheel steering angle.

[0084] The third turning angle model is a one-dimensional state equation. Steady-state information is substituted into the third turning angle model, and a preset recursive least squares method is used to calculate the third turning angle model after substitution. The calculation result is the second turning information. In this embodiment, the calculation process of the recursive least squares method is not specifically limited.

[0085] The advantage of this setup is that it establishes a one-dimensional state equation based on the vehicle's steady-state characteristics and uses the recursive least squares method to estimate the front wheel steering angle, thereby achieving estimation of the front wheel steering angle from different angles and improving the accuracy of front wheel steering angle determination.

[0086] In this embodiment, the execution order of S202 and S203 is not specifically limited.

[0087] In this embodiment, the preset third corner model is characterized as follows:

[0088]

[0089] Among them, w z The yaw rate is represented by L, the wheelbase of the vehicle is represented by v. x Characterizing longitudinal velocity, v cx Characteristic vehicle speed, δ f It represents the front wheel steering angle.

[0090] Specifically, the equation applicable to the recursive least squares method is in the form Y = Ax. In this embodiment, Y is equivalent to w. z A is equivalent to x is equivalent to δ f .

[0091] Based on the aforementioned one-dimensional state equation, the estimated value of the front wheel steering angle is obtained through the recursive least squares method, which serves as the second steering information.

[0092] The advantage of this setup is that it establishes the kinematic relationship between the steady-state yaw rate and the front wheel steering angle, enabling the estimation of the front wheel steering angle based on the vehicle kinematics model and improving the accuracy of the front wheel steering angle determination.

[0093] S204. Based on the first steering information and the second steering information, determine the front wheel steering angle information of the vehicle at the current moment.

[0094] For example, this step can refer to step S103 above, and will not be repeated here.

[0095] This application provides a method for determining the front wheel steering angle of a vehicle. By acquiring the vehicle's dynamic information and steady-state information, the vehicle's dynamic characteristics and steady-state features can be obtained. Based on the vehicle's dynamic characteristics, a front wheel steering angle can be estimated. Based on the vehicle's steady-state characteristics, a front wheel steering angle can also be estimated. Combining these two estimation results, the final front wheel steering angle is determined, effectively improving the accuracy of the vehicle's front wheel steering angle determination and facilitating precise vehicle control.

[0096] Figure 3 A flowchart illustrating a method for determining the front wheel steering angle of a vehicle, as provided in this application embodiment, is shown below. Figure 3 As shown, in this embodiment... Figure 1 Based on the embodiments, a method for determining the front wheel steering angle of a vehicle is described in detail, the method including:

[0097] S301. Obtain the vehicle's dynamics and steady-state information at the current moment; wherein, the dynamics information represents the vehicle's driving and steering, and the steady-state information represents the vehicle's steady-state yaw.

[0098] For example, this step can refer to step S101 above, and will not be repeated here.

[0099] S302. Based on the dynamic information, determine the first steering information of the vehicle, and based on the steady-state information, determine the second steering information of the vehicle; wherein, both the first steering information and the second steering information characterize the estimated front wheel steering angle of the vehicle.

[0100] For example, this step can refer to step S102 above, and will not be repeated here.

[0101] S303. Based on a preset low-pass filter, first target information is selected from the first steering information; wherein, the first target information represents a signal in the first steering information that is less than a preset first frequency threshold.

[0102] For example, the vehicle dynamics equations exhibit significant delays and noise in the high-frequency response; the vehicle kinematics equations show significant impacts on the estimation results at low frequencies due to sensor measurement errors. The vehicle dynamics equations are calculated using a Kalman filter, while the kinematics equations are calculated using recursive least squares. In other words, in the first steering information, the Kalman filter itself is relatively complex, processes signals slowly, and experiences delays in processing high-frequency signals, exhibiting hysteresis, but it offers high accuracy. In the second steering information, the signal processing speed is fast, but inaccurate, especially for low-frequency signals, where sensor errors further reduce accuracy. Therefore, it is necessary to filter out the high-frequency components of the first steering information and the low-frequency components of the second steering information.

[0103] A low-pass filter is pre-set to filter out the high-frequency response components in the first steering information, retaining more accurate low-frequency estimation results. For example, a first frequency threshold can be pre-set to retain signals in the first steering information that are less than or equal to the first frequency threshold, while signals that are greater than the first frequency threshold are filtered out. The retained information is the first target information.

[0104] S304. Based on a preset high-pass filter, filter out the second target information from the second steering information; wherein, the second target information represents the signal in the second steering information that is greater than a preset second frequency threshold.

[0105] For example, a high-pass filter is pre-set to filter out the portion of the second steering information with large low-frequency errors, retaining the portion with better high-frequency response. For instance, a second frequency threshold can be pre-set to retain signals in the second steering information that are greater than or equal to the second frequency threshold, while signals that are less than the second frequency threshold are filtered out. The retained information is the second target information.

[0106] The first frequency threshold and the second frequency threshold can be the same or different. For example, both the first frequency threshold and the second frequency threshold can be set to 100Hz. In this embodiment, there is a greater tendency to retain data in the first steering information; therefore, the first frequency threshold can be set relatively high to retain more low-frequency components.

[0107] In this embodiment, the execution order of S303 and S304 is not specifically limited.

[0108] S305. Based on the first target information and the second target information, determine the front wheel steering angle information of the vehicle at the current moment.

[0109] For example, after obtaining the first target information and the second target information, the first target information and the second target information can be combined to obtain the front wheel steering angle information of the vehicle at the current moment. For instance, the first target information and the second target information can be weighted and summed according to preset weights to obtain the front wheel steering angle information.

[0110] In this embodiment, the front wheel steering angle information can be calculated using the following formula:

[0111]

[0112] Where, δ fc The information is the front wheel steering angle, τ is the preset time constant, s is the complex frequency variable, and δ is the front wheel steering angle. fK For the first target information, δ fR This is the second target information.

[0113] In this embodiment, a five-dimensional state-space equation is established, taking into account the influence of factors such as rear wheel steering angle and imbalance of longitudinal driving force at the wheel ends on existing estimation models, thus improving the applicability of front wheel steering angle estimation. An AI model is introduced to predict the front wheel steering angle of the vehicle under high dynamic and high-frequency scenarios, solving the problem of poor estimation accuracy of the front wheel steering angle in high dynamic scenarios and improving the coverage of the AI ​​model across all scenarios. Combining the front wheel steering angle estimation based on the vehicle dynamics model with that based on the vehicle kinematics model improves the estimation accuracy of the front wheel steering angle in conventional vehicle operating scenarios and enhances the real-time performance of the estimation.

[0114] This application provides a method for determining the front wheel steering angle of a vehicle. By acquiring the vehicle's dynamic information and steady-state information, the vehicle's dynamic characteristics and steady-state features can be obtained. Based on the vehicle's dynamic characteristics, a front wheel steering angle can be estimated. Based on the vehicle's steady-state characteristics, a front wheel steering angle can also be estimated. Combining these two estimation results, the final front wheel steering angle is determined, effectively improving the accuracy of the vehicle's front wheel steering angle determination and facilitating precise vehicle control.

[0115] Figure 4 This is a schematic diagram of the structure of a device for determining the front wheel steering angle of a vehicle, provided in an embodiment of this application. Figure 4 As shown, the vehicle front wheel steering angle determination device 40 provided in this embodiment includes: an information acquisition unit 401, a steering determination unit 402, and a steering angle determination unit 403.

[0116] The information acquisition unit 401 is used to acquire the vehicle's dynamic information and steady-state information at the current moment; wherein, the dynamic information represents the vehicle's driving and steering conditions, and the steady-state information represents the vehicle's steady-state yaw conditions.

[0117] The steering determination unit 402 is used to determine first steering information of the vehicle based on the dynamic information, and to determine second steering information of the vehicle based on the steady-state information; wherein both the first steering information and the second steering information characterize the estimated front wheel steering angle of the vehicle;

[0118] The steering angle determination unit 403 is used to determine the front wheel steering angle information of the vehicle at the current moment based on the first steering information and the second steering information.

[0119] Figure 5 A structural block diagram of a device for determining the front wheel steering angle of a vehicle provided in this application embodiment is shown below. Figure 5 As shown, the vehicle front wheel steering angle determination device 50 includes an information acquisition unit 501, a steering determination unit 502, and a steering angle determination unit 503. The steering determination unit 502 includes a first determination module 5021 and a second determination module 5022.

[0120] The first determining module 5021 is used to determine the predicted steering angle of the vehicle based on the dynamic information and a preset artificial intelligence model; wherein the preset artificial intelligence model is a pre-built neural network model used to predict the front wheel steering angle of the vehicle based on the dynamic information; and to determine the first steering information of the vehicle based on the dynamic information and the predicted steering angle.

[0121] The second determining module 5022 is used to obtain a preset third steering angle model; wherein the preset third steering angle model represents the functional relationship between steady-state information and front wheel steering angle, and the steady-state information includes at least one of yaw rate, longitudinal speed of the vehicle, and characteristic vehicle speed; based on the steady-state information and the preset third steering angle model, the second steering information of the vehicle is determined based on a preset recursive least squares method.

[0122] In one example, the first determining module 5021 is specifically used for:

[0123] Obtain a preset first steering angle model and a preset second steering angle model; wherein, the preset first steering angle model represents the functional relationship between dynamic information and front wheel steering angle, and the preset second steering angle model represents the functional relationship between dynamic information, steering angle prediction value, and front wheel steering angle;

[0124] Based on the dynamic information, the predicted steering angle, the preset first steering angle model, and the preset second steering angle model, the first steering information of the vehicle is determined using a preset extended Kalman filter algorithm.

[0125] In one example, the preset first turning angle model is represented as:

[0126]

[0127] Among them, v y Characterizing the lateral velocity of a vehicle, w represents the derivative of the lateral velocity with time. z Characterizing yaw rate, Characterizing yaw acceleration, δ f Characterizes the front wheel steering angle, Characterizing the angular velocity of the front wheels, Characterizing the front wheel angular acceleration, δ r Characterizing the rear wheel steering angle, The rear wheel angular velocity is represented by m, and the vehicle mass is represented by v. x C represents the longitudinal velocity of a vehicle. f C characterizes the lateral stiffness of the front axle. r L characterizes the lateral stiffness of the rear axle. f L represents the distance from the center of gravity to the front axle. r J represents the distance from the center of gravity to the rear axle. z L represents the moment of inertia of a vehicle about the Z-axis. x Characterized by drag distance, B s Characterizing the damping of the front steering system, J s W represents the moment of inertia of the front steering system. f W represents the wheelbase of the front axle. r L represents the wheelbase of the rear axle. y Characterized by the radius of the wiping action, ΔF fxb ΔF represents the difference in braking force between the left and right sides of the front axle. fxd ΔF represents the difference in driving force between the left and right sides of the front axle. rxb ΔF represents the difference in braking force between the left and right sides of the rear axle. rxd It represents the difference in driving force between the left and right sides of the rear axle.

[0128] In one example, the predefined second corner model is represented as:

[0129]

[0130] Among them, v y w represents the lateral velocity of a vehicle. z Characterized by yaw rate, δ f Characterizes the front wheel steering angle, Characterizing the angular velocity of the front wheel, δ r Characterizing the rear wheel steering angle, The predicted steering angle is represented by m, and the vehicle mass is represented by v. x C represents the longitudinal velocity of a vehicle. f C characterizes the lateral stiffness of the front axle. r L characterizes the lateral stiffness of the rear axle. fL represents the distance from the center of gravity to the front axle. r a represents the distance from the center of gravity to the rear axle. y Characterizes lateral acceleration.

[0131] In one example, the dynamic information includes sideslip angle and yaw rate; the first determining module 5021 is specifically used for:

[0132] The measured noise of the vehicle is determined based on the sideslip angle and the yaw rate; wherein the measured noise characterizes the reliability of the steering angle prediction value;

[0133] Based on the measured noise, the dynamic information, the predicted steering angle, the preset first steering angle model, and the preset second steering angle model, the first steering information of the vehicle is determined using the extended Kalman filter algorithm.

[0134] In one example, the predefined third corner model is represented as:

[0135]

[0136] Among them, w z The yaw rate is represented by L, the wheelbase of the vehicle is represented by v. x Characterizing longitudinal velocity, v cx Characteristic vehicle speed, δ f It represents the front wheel steering angle.

[0137] In one example, the corner determination unit 503 is specifically used for:

[0138] Based on a preset low-pass filter, first target information is filtered out from the first steering information; wherein, the first target information represents a signal in the first steering information that is less than a preset first frequency threshold.

[0139] Based on a preset high-pass filter, second target information is filtered out from the second steering information; wherein, the second target information represents a signal in the second steering information that is greater than a preset second frequency threshold;

[0140] Based on the first target information and the second target information, the front wheel steering angle information of the vehicle at the current moment is determined.

[0141] The device for determining the front wheel angle of a vehicle provided in this embodiment can execute the method provided in the above-described method embodiment. Its implementation principle and technical effect are similar, and will not be described in detail here.

[0142] Figure 6 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Figure 6As shown, the electronic device 60 provided in this embodiment includes at least one processor 601 and a memory 602. Optionally, the device 60 further includes a communication component 603. The processor 601, memory 602, and communication component 603 are connected via a bus 604.

[0143] In a specific implementation, at least one processor 601 executes computer execution instructions stored in memory 602, causing at least one processor 601 to perform the above-described method.

[0144] The specific implementation process of processor 601 can be found in the above method embodiments, and its implementation principle and technical effect are similar. It will not be repeated here.

[0145] In the above embodiments, it should be understood that the processor can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), etc. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the method disclosed in this invention can be directly implemented by a hardware processor, or implemented by a combination of hardware and software modules within the processor.

[0146] The memory may include random access memory (RAM) and may also include non-volatile memory (NVM), such as at least one disk storage device.

[0147] The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. Buses can be categorized as address buses, data buses, control buses, etc. For ease of illustration, the buses shown in the accompanying drawings are not limited to a single bus or a single type of bus.

[0148] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the above-described method.

[0149] This application also provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, implement the above-described method.

[0150] The aforementioned readable storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk. The readable storage medium can be any available medium accessible to a general-purpose or special-purpose computer.

[0151] An exemplary readable storage medium is coupled to a processor, enabling the processor to read information from and write information to the readable storage medium. Of course, the readable storage medium can also be a component of the processor. The processor and the readable storage medium can reside in an Application Specific Integrated Circuit (ASIC). Alternatively, the processor and the readable storage medium can exist as discrete components in the device.

[0152] The division of units is merely a logical functional division; in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be indirect coupling or communication connection through some interfaces, devices, or units, and may be electrical, mechanical, or other forms.

[0153] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0154] In addition, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0155] If a function is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0156] Those skilled in the art will understand that all or part of the steps of the above-described method embodiments can be implemented by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When executed, the program performs the steps of the above-described method embodiments; and the aforementioned storage medium includes various media capable of storing program code, such as ROM, RAM, magnetic disks, or optical disks.

[0157] Finally, it should be noted that other embodiments of the invention will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This invention is intended to cover any variations, uses, or adaptations of the invention that follow the general principles of the invention and include common knowledge or customary techniques in the art not disclosed herein, and is not limited to the precise structures described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of the invention is limited only by the appended claims.

Claims

1. A method for determining the steering angle of a vehicle's front wheels, characterized in that, include: Acquire the vehicle's dynamics and steady-state information at the current moment; wherein the dynamics information represents the vehicle's driving and steering, and the steady-state information represents the vehicle's steady-state yaw. Based on the dynamic information, first steering information of the vehicle is determined, and based on the steady-state information, second steering information of the vehicle is determined; wherein, both the first steering information and the second steering information characterize the estimated front wheel steering angle of the vehicle; Based on the first steering information and the second steering information, the front wheel steering angle information of the vehicle at the current moment is determined.

2. The method according to claim 1, characterized in that, Based on the dynamics information, the first steering information of the vehicle is determined, including: Based on the dynamic information, and using a preset artificial intelligence model, the predicted steering angle of the vehicle is determined; wherein, the preset artificial intelligence model is a pre-built neural network model used to predict the front wheel steering angle of the vehicle based on the dynamic information. Based on the dynamic information and the predicted steering angle, the first steering information of the vehicle is determined.

3. The method according to claim 2, characterized in that, Based on the dynamic information and the predicted steering angle, the first steering information of the vehicle is determined, including: Obtain a preset first steering angle model and a preset second steering angle model; wherein, the preset first steering angle model represents the functional relationship between dynamic information and front wheel steering angle, and the preset second steering angle model represents the functional relationship between dynamic information, steering angle prediction value, and front wheel steering angle; Based on the dynamic information, the predicted steering angle, the preset first steering angle model, and the preset second steering angle model, the first steering information of the vehicle is determined using a preset extended Kalman filter algorithm.

4. The method according to claim 3, characterized in that, The preset first turning angle model is characterized as follows: Among them, v y Characterizing the lateral velocity of a vehicle, w represents the derivative of the lateral velocity with time. z Characterizing yaw rate, Characterizing yaw acceleration, δ f Characterizes the front wheel steering angle, Characterizing the angular velocity of the front wheels, Characterizing the front wheel angular acceleration, δ r Characterizing the rear wheel steering angle, The rear wheel angular velocity is represented by m, and the vehicle mass is represented by v. x C represents the longitudinal velocity of a vehicle. f C characterizes the lateral stiffness of the front axle. r L characterizes the lateral stiffness of the rear axle. f L represents the distance from the center of gravity to the front axle. r J represents the distance from the center of gravity to the rear axle. z L represents the moment of inertia of a vehicle about the Z-axis. x Characterized by drag distance, B s Characterizing the damping of the front steering system, J s W represents the moment of inertia of the front steering system. f W represents the wheelbase of the front axle. r L represents the wheelbase of the rear axle. y Characterized by the radius of the wiping action, ΔF fxb ΔF represents the difference in braking force between the left and right sides of the front axle. fxd ΔF represents the difference in driving force between the left and right sides of the front axle. rxb ΔF represents the difference in braking force between the left and right sides of the rear axle. rxd It represents the difference in driving force between the left and right sides of the rear axle.

5. The method according to claim 3, characterized in that, The preset second turning angle model is characterized as follows: Among them, v y w represents the lateral velocity of a vehicle. z Characterized by yaw rate, δ f Characterizes the front wheel steering angle, Characterizing the angular velocity of the front wheel, δ r Characterizing the rear wheel steering angle, The predicted steering angle is represented by m, and the vehicle mass is represented by v. x C represents the longitudinal velocity of a vehicle. f C characterizes the lateral stiffness of the front axle. r L characterizes the lateral stiffness of the rear axle. f L represents the distance from the center of gravity to the front axle. r a represents the distance from the center of gravity to the rear axle. y Characterizes lateral acceleration.

6. The method according to claim 3, characterized in that, The dynamic information includes sideslip angle and yaw rate; based on the dynamic information, the predicted steering angle, the preset first steering angle model, and the preset second steering angle model, the first steering information of the vehicle is determined using an extended Kalman filter algorithm, including: The measured noise of the vehicle is determined based on the sideslip angle and the yaw rate; wherein the measured noise characterizes the reliability of the steering angle prediction value; Based on the measured noise, the dynamic information, the predicted steering angle, the preset first steering angle model, and the preset second steering angle model, the first steering information of the vehicle is determined using the extended Kalman filter algorithm.

7. The method according to claim 1, characterized in that, Based on the steady-state information, the second steering information of the vehicle is determined, including: Obtain a preset third steering angle model; wherein the preset third steering angle model represents the functional relationship between steady-state information and front wheel steering angle, and the steady-state information includes at least one of yaw rate, longitudinal speed of the vehicle, and characteristic vehicle speed; Based on the steady-state information and the preset third steering angle model, the second steering information of the vehicle is determined using a preset recursive least squares method.

8. The method according to claim 7, characterized in that, The preset third turning angle model is characterized as follows: Among them, w z The yaw rate is represented by L, the wheelbase of the vehicle is represented by v. x Characterizing longitudinal velocity, v cx Characteristic vehicle speed, δ f It represents the front wheel steering angle.

9. The method according to any one of claims 1-8, characterized in that, Based on the first steering information and the second steering information, the front wheel steering angle information of the vehicle at the current moment is determined, including: Based on a preset low-pass filter, first target information is filtered out from the first steering information; wherein, the first target information represents a signal in the first steering information that is less than a preset first frequency threshold. Based on a preset high-pass filter, second target information is filtered out from the second steering information; wherein, the second target information represents a signal in the second steering information that is greater than a preset second frequency threshold; Based on the first target information and the second target information, the front wheel steering angle information of the vehicle at the current moment is determined.

10. A device for determining the steering angle of a vehicle's front wheels, characterized in that, include: An information acquisition unit is used to acquire the vehicle's dynamic information and steady-state information at the current moment; wherein, the dynamic information represents the vehicle's driving and steering conditions, and the steady-state information represents the vehicle's steady-state yaw conditions; A steering determination unit is configured to determine first steering information of the vehicle based on the dynamic information, and to determine second steering information of the vehicle based on the steady-state information; wherein both the first steering information and the second steering information characterize the estimated front wheel steering angle of the vehicle; Angle determination unit is used to determine the front wheel angle information of the vehicle at the current moment based on the first steering information and the second steering information.

11. An electronic device, characterized in that, include: Memory, processor; The memory stores computer-executed instructions; The processor executes computer execution instructions stored in the memory, causing the processor to perform the method as described in any one of claims 1-9.

12. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-executable instructions, which, when executed by a processor, are used to implement the method as described in any one of claims 1-9.

13. A computer program product, characterized in that, Includes a computer program that, when executed by a processor, implements the method described in any one of claims 1-9.

Images