Zero deviation determination method and device of steering system and storage medium

Abstract

The invention relates to the field of vehicle steering systems, and discloses a zero deviation determination method and device for a steering system and a storage medium, and the method comprises the steps: obtaining a direction turning angle, a lane center line coefficient, a yaw velocity and a vehicle speed; according to the direction turning angle, the lane center line coefficient, the yaw velocity, the vehicle speed and a preset self-learning condition, a self-learning flag bit corresponding to zero deviation is determined; and in response to the fact that the self-learning flag bit is true, determining a target zero deviation according to the lane center line coefficient, the direction rotation angle, the yaw velocity, a historical zero deviation, a historical minimum cost value and a preset cost function. By means of the technical scheme, real-time estimation of the zero deviation is achieved, and the flexibility and effectiveness of zero deviation learning are improved.

Description

Technical Field

[0001] The present invention relates to the field of vehicle steering systems, and particularly to a method, device, and storage medium for determining the zero position deviation of a steering system. Background Art

[0002] An electric power steering system is an actuator for the lateral control of intelligent driving. Its zero position is affected by factors such as four-wheel alignment, tire pressure, and the self-calibration performance of the steering system itself, resulting in a certain deviation. This deviation will cause problems such as inaccurate lateral control and performance degradation.

[0003] In order to eliminate the influence brought by the zero position deviation of the steering system, it is necessary to estimate and compensate the zero position deviation. Currently, there are mainly two methods. One is to rely on the self-calibration function of the steering system itself. However, due to the lack of perception information, it is impossible to accurately judge whether the vehicle is in a straight driving state, and it is sensitive to the initial position of the steering wheel when the vehicle is powered on, resulting in unstable and inaccurate zero position correction performance. The other is to use the intelligent driving system to judge when the vehicle is parallel to the lane line and record the direction angle as the zero position deviation. However, the evaluation of the parallel state is difficult, which will introduce poor data into the estimation of the zero position deviation, resulting in inaccurate estimation of the zero position deviation.

[0004] In view of this, the present invention is specifically proposed. Summary of the Invention

[0005] In order to solve the above technical problems, the present invention provides a method, device, and storage medium for determining the zero position deviation of a steering system, realizing real-time estimation of the zero position deviation, and improving the flexibility and effectiveness of zero position deviation learning.

[0006] An embodiment of the present invention provides a method for determining the zero position deviation of a steering system, the method comprising:

[0007] Obtain the direction angle, lane center line coefficient, yaw rate, and vehicle speed;

[0008] Determine a self-learning flag bit corresponding to the zero position deviation according to the direction angle, the lane center line coefficient, the yaw rate, the vehicle speed, and a preset self-learning condition;

[0009] In response to the self-learning flag bit being true, determine the target zero position deviation according to the lane center line coefficient, the direction angle, the yaw rate, the historical zero position deviation, the historical minimum cost value, and a preset cost function.

[0010] An embodiment of the present invention provides an electronic device, the electronic device comprising:

[0011] A processor and a memory;

[0012] The processor is configured to execute the steps of the zero - position deviation determination method for the steering system according to any one of the embodiments by calling the program or instructions stored in the memory.

[0013] An embodiment of the present invention provides a computer - readable storage medium storing a program or instructions, which cause a computer to execute the steps of the zero - position deviation determination method for the steering system according to any one of the embodiments.

[0014] The embodiments of the present invention have the following technical effects:

[0015] By obtaining the direction angle, lane center - line coefficient, yaw rate, and vehicle speed, and determining the self - learning flag bit corresponding to the zero - position deviation according to the direction angle, lane center - line coefficient, yaw rate, vehicle speed, and a preset self - learning condition, so as to accurately determine when to enter the self - learning of the zero - position deviation. Furthermore, in response to the self - learning flag bit being true, the target zero - position deviation is determined according to the lane center - line coefficient, direction angle, yaw rate, historical zero - position deviation, historical minimum cost value, and a preset cost function, so as to evaluate and iterate the zero - position deviation, ensuring the superiority of the self - learning data and the convergence of the performance, and achieving the effect of real - time estimation of the zero - position deviation of the steering system using the perception information and the information of the steering system. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the following will briefly introduce the drawings required for the description of the specific embodiments or the prior art. Obviously, the drawings in the following description are some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0017] Figure 1 is a flowchart of a zero - position deviation determination method for a steering system provided by an embodiment of the present invention;

[0018] Figure 2 is a flowchart of another zero - position deviation determination method for a steering system provided by an embodiment of the present invention;

[0019] Figure 3 is a schematic structural diagram of a zero - position deviation self - learning system provided by an embodiment of the present invention;

[0020] Figure 4 is a schematic structural diagram of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0021] To make the objectives, technical solutions, and advantages of the present invention clearer, the technical solutions of the present invention will be described clearly and completely below. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts fall within the scope of protection of the present invention.

[0022] The zero-position deviation determination method for a steering system provided by an embodiment of the present invention is mainly applicable to the situation of real-time estimation of the zero-position deviation of the steering system. The zero-position deviation determination method for a steering system provided by an embodiment of the present invention can be executed by an electronic device.

[0023] Figure 1 is a flowchart of a zero-position deviation determination method for a steering system provided by an embodiment of the present invention. Refer to Figure 1 , and the zero-position deviation determination method for the steering system specifically includes:

[0024] S110. Obtain the direction angle, lane centerline coefficient, yaw rate, and vehicle speed.

[0025] Among them, in this example, the steering system refers to an Electric Power Steering (EPS), specifically a power steering system that relies on a motor to provide auxiliary torque. The direction angle is the steering angle in the steering system. The lane centerline coefficient is the coefficient of each order in the lane centerline expression. The yaw rate is the rotational speed of the vehicle around its vertical axis (i.e., the centerline of the vehicle). The vehicle speed is the current driving speed of the vehicle.

[0026] Specifically, based on modules and devices such as sensors and the steering system, the current direction angle, lane centerline coefficient, yaw rate, and vehicle speed of the vehicle can be obtained.

[0027] The lane centerline expression is:

[0028] y = c 0 + c 1 × x + c 2 × x 2 + c 3 × x 3

[0029] where x and y are the horizontal axis coordinate and vertical axis coordinate in the vehicle coordinate system of the vehicle, respectively, c 0 is the zero-order coefficient in the lane centerline coefficient, c 1 is the first-order coefficient in the lane centerline coefficient, c 2 is the second-order coefficient in the lane centerline coefficient, c 3 is the third-order coefficient in the lane centerline coefficient.

[0030] Based on the above examples, before obtaining the direction rotation angle, lane center line coefficient, yaw rate, and vehicle speed, since the signals often have large fluctuations, in order to reduce the fluctuations, filtering processing can be performed to improve the availability of the signals. Specifically, it can be:

[0031] Obtain the initial rotation angle, initial center line coefficient, initial angular velocity, and initial speed;

[0032] Perform first-order smoothing filtering on the initial rotation angle, initial center line coefficient, initial angular velocity, and initial speed respectively to obtain the direction rotation angle, lane center line coefficient, yaw rate, and vehicle speed.

[0033] Among them, the initial rotation angle, initial center line coefficient, initial angular velocity, and initial speed are the initial input data obtained through various module devices such as sensors or steering systems.

[0034] Specifically, based on module devices such as sensors and steering systems, the initial rotation angle, initial center line coefficient, initial angular velocity, and initial speed with fluctuating changes can be obtained. Perform first-order smoothing filtering on the input data such as the initial rotation angle, initial center line coefficient, initial angular velocity, and initial speed respectively to obtain the output data, that is, the direction rotation angle corresponding to the initial rotation angle, the lane center line coefficient corresponding to the initial center line coefficient, the yaw rate corresponding to the initial angular velocity, and the vehicle speed corresponding to the initial speed.

[0035] Exemplarily, the first-order filtering formula is as follows:

[0036] out t = λ × int t +(1 - λ) × out t-1

[0037] Among them, out t is the output data at the current moment, int t is the input data at the current moment, out t-1 is the output data at the previous moment of the current moment, and λ is the filtering coefficient. It can be understood that the filtering coefficients corresponding to different types of data can be different.

[0038] S120. Determine the self-learning flag bit corresponding to the zero position deviation according to the direction rotation angle, lane center line coefficient, yaw rate, vehicle speed, and preset self-learning conditions.

[0039] Among them, the preset self-learning condition is a condition used to determine whether to enter the zero-position deviation self-learning, and it can be a preset condition corresponding to the direction angle, the lane center line coefficient, the yaw angular velocity, and the vehicle speed respectively. The self-learning flag bit is a flag bit used to identify whether to enter self-learning. If it is true, it indicates that the zero-position deviation self-learning is entered. If it is false, it indicates that the zero-position deviation self-learning is not entered.

[0040] Specifically, it is respectively determined whether the direction angle meets the preset condition corresponding to the direction angle in the preset self-learning condition, whether the lane center line coefficient meets the preset condition corresponding to the lane center line coefficient in the preset self-learning condition, whether the yaw angular velocity meets the preset condition corresponding to the yaw angular velocity in the preset self-learning condition, and whether the vehicle speed meets the preset condition corresponding to the vehicle speed in the preset self-learning condition. If all are met, it can be determined that the self-learning flag bit corresponding to the zero-position deviation is true. If at least one is not met, it can be determined that the self-learning flag bit corresponding to the zero-position deviation is false.

[0041] Based on the above example, the self-learning flag bit corresponding to the zero-position deviation can be determined by the following method according to the direction angle, the lane center line coefficient, the yaw angular velocity, the vehicle speed, and the preset self-learning condition:

[0042] When the lane center line availability is available, the first-order coefficient in the lane center line coefficient is used as the center line included angle, and twice the second-order coefficient in the lane center line coefficient is used as the lane center line curvature;

[0043] If the absolute value of the center line included angle, the lane center line curvature, the absolute value of the direction angle, the absolute value of the yaw angular velocity, and the vehicle speed all meet the corresponding preset thresholds respectively, it is determined that the self-learning flag bit corresponding to the zero-position deviation is true;

[0044] If at least one of the absolute value of the center line included angle, the lane center line curvature, the absolute value of the direction angle, the absolute value of the yaw angular velocity, and the vehicle speed does not meet the corresponding preset threshold, it is determined that the self-learning flag bit corresponding to the zero-position deviation is false.

[0045] Among them, the lane center line availability is an identifier used to evaluate the reliability of the lane center line expression, and it can be determined according to the confidence level of the lane center line expression. The center line included angle is the included angle between the vehicle and the lane center line. The lane center line curvature refers to the degree of bending of the lane center line at a certain point. The preset threshold is the threshold corresponding to each type of data in the preset self-learning condition, and it can include a preset included angle threshold, a preset curvature threshold, a preset rotation angle threshold, a preset angular velocity threshold, and a speed threshold.

[0046] Specifically, subsequent self-learning and re-learning operations are only performed when the lane centerline availability is available. Therefore, when the lane centerline availability is available, the first-order coefficient in the lane centerline coefficient can be used to estimate the centerline angle, and this first-order coefficient is used as the centerline angle. The second-order coefficient in the lane centerline coefficient can also be used to estimate the lane centerline curvature, and twice this second-order coefficient is used as the lane centerline curvature. If the absolute value of the centerline angle is less than the preset angle threshold in the preset threshold, the lane centerline curvature is less than the preset curvature threshold in the preset threshold, the absolute value of the direction angle is less than the preset direction angle threshold in the preset threshold, the absolute value of the yaw rate is less than the preset angular velocity threshold in the preset threshold, and the vehicle speed is less than the speed threshold in the preset threshold, it means that the conditions of the preset threshold are met, that is, the preset self-learning conditions are met. Therefore, it is determined that the self-learning flag bit corresponding to the zero position deviation is true. If at least one of the centerline angle, lane centerline curvature, absolute value of the direction angle, absolute value of the yaw rate, and vehicle speed does not meet the corresponding preset threshold, it means that the preset self-learning conditions are not met. Therefore, it can be determined that the self-learning flag bit corresponding to the zero position deviation is false.

[0047] Exemplarily, if the vehicle simultaneously meets the following conditions (preset self-learning conditions) and continues for a certain time threshold, the self-learning flag bit can be set to true: the lane centerline is available, that is, enable = true; the absolute value of the angle between the vehicle and the centerline of the lane heading < the angle threshold. Generally, the angle between the vehicle and the centerline of the lane is small, so the first-order coefficient c in the lane centerline coefficient can be used to 1 estimate as heading; the absolute value of the lane centerline curvature curv < the curvature threshold, and twice the second-order coefficient in the lane centerline coefficient, that is, 2c 2 can be estimated as curv; the absolute value of the direction angle of the steering system |θ| < the direction angle threshold; the absolute value of the yaw rate of the vehicle |yawrate| < the angular velocity threshold; the vehicle speed v < the speed threshold.

[0048] S130. In response to the self-learning flag bit being true, the target zero position deviation is determined according to the lane centerline coefficient, direction angle, yaw rate, historical zero position deviation, historical minimum cost value, and preset cost function.

[0049] Among them, the historical zero position deviation is the zero position deviation value determined in the previous cycle, and the historical minimum cost value is the cost value corresponding to the historical zero position deviation. The preset cost function is a function established in advance for calculating risk losses.

[0050] Specifically, if the self-learning flag bit is true, self-learning of the zero position deviation can be performed. The lane centerline coefficient, direction angle, and yaw rate can be substituted into a preset cost function to determine the current zero position deviation and the current cost value. Combining the historical zero position deviation and the historical minimum cost value, it can be determined whether to enter re-learning. If re-learning is not entered, the current zero position deviation is directly compared with the historical zero position deviation, and the current cost value is compared with the historical minimum cost value. The current zero position deviation or the historical zero position deviation is used as the target zero position deviation. Moreover, the target zero position deviation is the historical zero position deviation corresponding to the determination of the target zero position deviation in the next cycle, and the current cost value corresponding to the target zero position deviation is the historical minimum cost value corresponding to the determination of the target zero position deviation in the next cycle. If re-learning is not entered, the current zero position deviation is used as the target zero position deviation, and the historical zero position deviation and the historical minimum cost value are updated with the current zero position deviation and the current cost value.

[0051] Based on the above example, after determining the target zero position deviation according to the lane centerline coefficient, direction angle, yaw rate, historical zero position deviation, historical minimum cost value, and preset cost function, the target zero position deviation can also be used in combination with the target angle required for lateral control to perform lateral control of the vehicle. Specifically, it can be:

[0052] Obtain the target angle corresponding to the steering system, and determine the control angle according to the target angle and the target zero position deviation;

[0053] Perform lateral control of the vehicle according to the control angle.

[0054] Among them, the target angle corresponding to the steering system is the angle value calculated in the lateral control module for output to the steering system. The control angle is the angle value used by the steering system for lateral control of the vehicle.

[0055] Specifically, the lateral control module can calculate the target angle corresponding to the steering system, output the control angle by superimposing the target angle on the target zero position deviation, and input the control angle to the steering system to perform lateral control of the vehicle.

[0056] The present invention has the following technical effects: By obtaining the direction angle, lane centerline coefficient, yaw rate, and vehicle speed, and determining the self-learning flag bit corresponding to the zero position deviation according to the direction angle, lane centerline coefficient, yaw rate, vehicle speed, and preset self-learning conditions, it can accurately determine when to enter self-learning of the zero position deviation. Furthermore, in response to the self-learning flag bit being true, the target zero position deviation is determined according to the lane centerline coefficient, direction angle, yaw rate, historical zero position deviation, historical minimum cost value, and preset cost function to evaluate and iterate the zero position deviation, ensuring the superiority of the self-learning data and the convergence of the performance, and achieving the effect of real-time estimation of the zero position deviation of the steering system using perception information and information of the steering system.

[0057] The above embodiments describe the process of determining the zero - position deviation using the self - learning method when the self - learning flag bit is true. In this embodiment, it is also possible to further describe the method of determining whether to enter re - learning and the specific re - learning process after entering self - learning, so as to improve the accuracy and flexibility of zero - position deviation learning. For example Figure 2 as shown. Figure 2 FIG. is a flowchart of another method for determining the zero - position deviation of a steering system provided by an embodiment of the present invention. Among them, the explanations of the same or corresponding terms as those in the above embodiments will not be repeated here. For example Figure 2 as shown, the method may specifically include the following steps:

[0058] S210. Obtain the direction angle, lane center line coefficient, yaw rate, and vehicle speed.

[0059] S220. Determine the self - learning flag bit corresponding to the zero - position deviation according to the direction angle, lane center line coefficient, yaw rate, vehicle speed, and preset self - learning conditions.

[0060] S230. In response to the self - learning flag bit being true, determine the current zero - position deviation and the current cost value according to the lane center line coefficient, direction angle, yaw rate, and preset cost function.

[0061] Among them, the current zero - position deviation is the direction angle input in the current cycle. The current cost value is the value obtained by calculating the preset cost function in the current cycle.

[0062] Specifically, when the self - learning flag bit is true, substitute the lane center line coefficient, direction angle, and yaw rate into the preset cost function to obtain the current cost value, and use the direction angle as the current zero - position deviation.

[0063] Based on the above example, the following method can be used to determine the current zero - position deviation and the current cost value according to the lane center line coefficient, direction angle, yaw rate, and preset cost function:

[0064] Determine the current cost value through the following formula:

[0065] f = |c 1 |×η 1 +2×|c 2 |×η 2 +|yawrate|×η 3 +|θ|×η 4

[0066] Among them, f is the current cost value, c 1 is the first - order coefficient in the lane center line coefficient, η 1is the first coefficient, c 2 is the second-order coefficient in the lane centerline coefficient, η 2 is the second coefficient, yawrate is the yaw rate, η 3 is the third coefficient, θ is the steering angle, η 4 is the fourth coefficient;

[0067] Take the steering angle as the current zero position deviation.

[0068] S240. Determine the relearning flag bit based on the current zero position deviation, the current cost value, the historical zero position deviation, and the historical minimum cost value, and judge whether the relearning flag bit is true. If it is true, execute S250; if it is false, execute S260.

[0069] Among them, the relearning flag bit is a flag bit used to identify whether to enter relearning. If it is true, it indicates entering the relearning of the zero position deviation; if it is false, it indicates not entering the relearning of the zero position deviation.

[0070] Specifically, respectively judge whether the difference between the current zero position deviation and the historical zero position deviation, the current cost value, and the historical minimum cost value all meet the preset relearning conditions. If they meet, determine that the relearning flag bit is true; otherwise, determine that the relearning flag bit is false. Furthermore, judge whether the relearning flag bit is true to further determine whether to use the relearning method to determine the target zero position deviation or continue to use the self-learning method to determine the target zero position deviation.

[0071] Based on the above example, the relearning flag bit can be determined according to the current zero position deviation, the current cost value, the historical zero position deviation, and the historical minimum cost value in the following way:

[0072] In response to the difference between the current zero position deviation and the historical zero position deviation being greater than the preset zero position deviation threshold, the current cost value being less than the preset first cost threshold, and the historical minimum cost value being less than the preset second cost threshold, determine that the relearning flag bit is true;

[0073] In response to the difference between the current zero position deviation and the historical zero position deviation being less than or equal to the preset zero position deviation threshold, determine that the relearning flag bit is false;

[0074] In response to the current cost value being greater than or equal to the preset first cost threshold, determine that the relearning flag bit is false;

[0075] In response to the historical minimum cost value being greater than or equal to the preset second cost threshold, determine that the relearning flag bit is false.

[0076] Among them, the preset zero position deviation threshold, the preset first cost threshold, and the preset second cost threshold are preset thresholds for determining whether to enter relearning.

[0077] Specifically, if the difference between the current zero - position deviation and the historical zero - position deviation is greater than the preset zero - position deviation threshold, the current cost value is less than the preset first cost threshold, and the historical minimum cost value is less than the preset second cost threshold, it indicates that the preset first cost threshold is met, and the re - learning flag bit can be determined to be true. If at least one of the following conditions is satisfied: the difference between the current zero - position deviation and the historical zero - position deviation is less than or equal to the preset zero - position deviation threshold, the current cost value is greater than or equal to the preset first cost threshold, and the historical minimum cost value is greater than or equal to the preset second cost threshold, it indicates that the preset first cost threshold is not met, and the re - learning flag bit can be determined to be false.

[0078] Exemplarily, the self - calibration of the steering system itself runs through the entire power - on cycle. The steering system may be contaminated by bad data, resulting in performance degradation. Therefore, the self - learning of the steering system needs to be carried out in a timely manner to correct it. When the following conditions (preset re - learning conditions) are simultaneously met and continue for a certain period of time, the preset re - learning condition satisfaction flag bit can be set to true. After detecting the rising edge of the re - learning condition satisfaction flag bit, the re - learning flag bit is set to true: the zero - position deviation (current zero - position deviation) α of the newly learned steering system new and the zero - position deviation (historical zero - position deviation) α of the already learned steering system best The difference > the preset zero - position deviation threshold; the cost value (current cost value) cost of the newly learned steering system new <the preset first cost threshold; the cost value (historical minimum cost value) cost of the already learned steering system min < the preset second cost threshold.

[0079] S250. Take the current zero - position deviation as the target zero - position deviation, and update the historical zero - position deviation and the historical minimum cost value according to the current zero - position deviation and the current cost value.

[0080] Specifically, take the current zero - position deviation as the target zero - position deviation, take the current zero - position deviation as the new historical zero - position deviation, and take the current cost value as the new historical minimum cost value.

[0081] S260. Determine the target zero - position deviation according to the historical zero - position deviation, the historical minimum cost value, the current zero - position deviation, and the current cost value.

[0082] Specifically, compare the magnitudes of the current cost value and the historical minimum cost value, and take the zero - position deviation corresponding to the smaller cost value, that is, the historical zero - position deviation or the current zero - position deviation, as the target zero - position deviation.

[0083] Based on the above example, the target zero - position deviation can be determined in the following way according to the historical zero - position deviation, the historical minimum cost value, the current zero - position deviation, and the current cost value:

[0084] In response to the current cost value being less than the historical minimum cost value, the current zero position deviation is used as the target zero position deviation.

[0085] In response to the current cost value being greater than or equal to the historical minimum cost value, the historical zero position deviation is used as the target zero position deviation.

[0086] Specifically, if the current cost value is less than the historical minimum cost value, it indicates that the current cost value is better. Therefore, the current zero position deviation corresponding to the current cost value is used as the target zero position deviation. If the current cost value is greater than or equal to the historical minimum cost value, it indicates that the historical minimum cost value is better. Therefore, the original historical zero position deviation is still retained as the target zero position deviation.

[0087] It can be understood that there are two iteration methods for the zero position deviation of the steering system: The first is normal self - learning: when the current cost value cost new is less than the historical minimum cost value cost min , the zero position deviation of the steering system starts to iterate: α best =α new , cost min =cost new , where α best is the target zero position deviation and also the historical zero position deviation in the next cycle. The second is re - learning in self - learning: when the re - learning flag is true, α best =α new , cost min =cost new .

[0088] Figure 3 FIG. is a schematic structural diagram of a zero position deviation self - learning system provided by an embodiment of the present invention. The zero position deviation self - learning system includes: a signal receiving module, a zero position self - learning module of the steering system, and a lateral control module.

[0089] Among them, the signal receiving module is used to receive the direction angle, the lane center line coefficient, the yaw rate, and the vehicle speed. The zero-position self-learning module of the steering system is used to estimate the zero position of the steering system, and mainly consists of four units, namely the signal processing unit, the self-learning flag processing unit, the re-learning flag processing unit, and the zero-position deviation iteration unit. The signal processing unit is used to perform first-order smoothing filtering on the received input signal. The self-learning flag processing unit is used to judge whether the preset self-learning condition is met and determine the self-learning flag bit. The re-learning flag processing unit is used to judge whether the preset re-learning condition is met and determine the re-learning flag bit. The zero-position deviation iteration unit, in order to ensure the convergence of the zero-position self-learning of the steering system, uses the cost function method to iteratively estimate the zero-position deviation. The lateral control module is used to calculate the target angle corresponding to the steering system through lateral control, superimpose the target zero-position deviation to obtain the control angle, and output the control angle to the steering system for lateral control.

[0090] The present invention has the following technical effects: by responding to the self-learning flag bit being true, the current zero-position deviation and the current cost value are determined according to the lane center line coefficient, the direction angle, the yaw rate, and the preset cost function. According to the current zero-position deviation, the current cost value, the historical zero-position deviation, and the historical minimum cost value, the re-learning flag bit is determined. In response to the re-learning flag bit being true, the current zero-position deviation is used as the target zero-position deviation, and the historical zero-position deviation and the historical minimum cost value are updated according to the current zero-position deviation and the current cost value. In response to the re-learning flag bit being false, the target zero-position deviation is determined according to the historical zero-position deviation, the historical minimum cost value, the current zero-position deviation, and the current cost value, realizing the evaluation and iteration of the zero-position deviation using the evaluation function, ensuring the superiority and performance convergence of the zero-position deviation self-learning, and re-entering the self-learning state when the zero-position deviation increases, ensuring the flexibility of the zero-position deviation self-learning.

[0091] Figure 4 It is a schematic structural diagram of an electronic device provided by an embodiment of the present invention. As Figure 4 shown, the electronic device 400 includes one or more processors 401 and a memory 402.

[0092] The processor 401 may be a central processing unit (CPU) or other form of processing unit with data processing capabilities and / or instruction execution capabilities, and may control other components in the electronic device 400 to perform desired functions.

[0093] The memory 402 may include one or more computer program products, and the computer program products may include various forms of computer-readable storage media, such as volatile memory and / or non-volatile memory. The volatile memory may include, for example, random access memory (RAM) and / or cache memory, etc. The non-volatile memory may include, for example, read-only memory (ROM), hard disk, flash memory, etc. One or more computer program instructions may be stored on the computer-readable storage media, and the processor 401 may run the program instructions to implement the zero-position deviation determination method of the steering system according to any embodiment of the present invention described above and / or other desired functions. Various contents such as initial external parameters, thresholds, etc. may also be stored in the computer-readable storage media.

[0094] In one example, the electronic device 400 may further include: an input device 403 and an output device 404, and these components are interconnected through a bus system and / or other forms of connection mechanisms (not shown). The input device 403 may include, for example, a keyboard, a mouse, etc. The output device 404 may output various information to the outside, including warning prompt information, braking force, etc. The output device 404 may include, for example, a display, a speaker, a printer, and a communication network and its connected remote output devices, etc.

[0095] Of course, for simplicity, Figure 4 only some of the components related to the present invention in the electronic device 400 are shown, and components such as buses, input / output interfaces, etc. are omitted. In addition, according to specific application scenarios, the electronic device 400 may further include any other appropriate components.

[0096] In addition to the above methods and devices, an embodiment of the present invention may also be a computer program product, which includes computer program instructions, and when the computer program instructions are run by a processor, the processor is caused to execute the steps of the zero-position deviation determination method of the steering system provided by any embodiment of the present invention.

[0097] The computer program product may be written in any combination of one or more programming languages to write program code for performing the operations of the embodiments of the present invention. The programming languages include object-oriented programming languages, such as Java, C++, etc., and also include conventional procedural programming languages, such as the "C" language or similar programming languages. The program code may be executed entirely on the user computing device, partially on the user device, executed as an independent software package, partially on the user computing device and partially on a remote computing device, or entirely on a remote computing device or server.

[0098] In addition, an embodiment of the present invention may also be a computer-readable storage medium storing computer program instructions, which, when run by a processor, cause the processor to execute the steps of the zero position deviation determination method of the steering system provided in any embodiment of the present invention.

[0099] The computer-readable storage medium may employ any combination of one or more readable media. The readable media may be a readable signal medium or a readable storage medium. The readable storage medium may, for example, include but is not limited to an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples (a non-exhaustive list) of the readable storage medium include: an electrical connection with one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0100] It should be noted that the terms used in the present invention are only for describing specific embodiments and do not limit the scope of the present application. As shown in the specification of the present invention, unless the context clearly indicates an exception, words such as "a", "an", "one", and / or "the" are not specifically singular and may also include the plural. The term "comprising", "including", or any other variant thereof is intended to cover a non-exclusive inclusion, such that a process, method, or device including a series of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, or device. Without further limitation, an element defined by the statement "including one..." does not exclude the presence of additional identical elements in the process, method, or device including the element.

[0101] It should also be noted that the orientation or positional relationship indicated by terms such as "center", "upper", "lower", "left", "right", "vertical", "horizontal", "inner", "outer", etc. is based on the orientation or positional relationship shown in the drawings, and is only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and thus should not be construed as a limitation of the present invention. Unless otherwise clearly specified and limited, terms such as "mounted", "connected", "coupled", etc. should be understood in a broad sense. For example, it may be a fixed connection, a detachable connection, or an integral connection; it may be a mechanical connection or an electrical connection; it may be directly connected or indirectly connected through an intermediate medium, and it may be the internal communication of two elements. For those of ordinary skill in the art, the specific meanings of the above terms in the present invention can be understood in specific cases.

[0102] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements on some or all of the technical features; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the technical solutions of the embodiments of the present invention.

Claims

1. A method for determining a zero deviation of a steering system, characterized in that: include: Obtain the direction angle, lane centerline coefficient, yaw rate and vehicle speed; Determine a self-learning flag corresponding to a zero position deviation according to the direction angle, the lane centerline coefficient, the yaw angular velocity, the vehicle speed, and a preset self-learning condition; In response to the self-learning flag being true, a target zero position deviation is determined according to the lane centerline coefficient, the direction angle, the yaw angular velocity, the historical zero position deviation, the historical minimum cost value and a preset cost function.

2. The method according to claim 1, characterized in that: The determining of the target zero position deviation according to the lane centerline coefficient, the direction angle, the yaw angular velocity, the historical zero position deviation, the historical minimum cost value and the preset cost function includes: Determine a current zero position deviation and a current cost value according to the lane centerline coefficient, the direction angle, the yaw angular velocity and the preset cost function; Determine a relearning flag according to the current zero-bit deviation, the current cost value, the historical zero-bit deviation and the historical minimum cost value; In response to the relearning flag being true, taking the current zero-bit deviation as a target zero-bit deviation, and updating the historical zero-bit deviation and the historical minimum cost value according to the current zero-bit deviation and the current cost value; In response to the relearning flag being false, a target zero bit deviation is determined according to the historical zero bit deviation, the historical minimum cost value, the current zero bit deviation, and the current cost value.

3. The method according to claim 2, characterized in that The determining a target zero deviation according to the historical zero deviation, the historical minimum cost value, the current zero deviation and the current cost value includes: In response to the current cost value being less than the historical minimum cost value, taking the current zero position deviation as a target zero position deviation; In response to the current cost value being greater than or equal to the historical minimum cost value, the historical zero-position deviation is used as the target zero-position deviation.

4. The method according to claim 2, characterized in that: The determining of the relearning flag according to the current zero-bit deviation, the current cost value, the historical zero-bit deviation and the historical minimum cost value includes: In response to the difference between the current zero-bit deviation and the historical zero-bit deviation being greater than a preset zero-bit deviation threshold, the current cost value being less than a preset first cost threshold, and the historical minimum cost value being less than a preset second cost threshold, determining that the relearning flag is true; In response to a difference between the current zero-bit deviation and the historical zero-bit deviation being less than or equal to the preset zero-bit deviation threshold, determining that the relearning flag is false; In response to the current cost value being greater than or equal to the preset first cost threshold, determining that the relearning flag is false; In response to the historical minimum cost value being greater than or equal to the preset second cost threshold, determining that the relearning flag is false.

5. The method according to claim 2, characterized in that: The determining of the current zero position deviation and the current cost value according to the lane centerline coefficient, the direction angle, the yaw angular velocity and the preset cost function includes: The current cost is determined by the following formula: f=|c1|×η1+2×|c2|×η2+|yawrate|×η3+|θ|×η4 Wherein, f is the current cost value, c1 is the first-order coefficient in the lane centerline coefficient, η1 is the first coefficient, c2 is the second-order coefficient in the lane centerline coefficient, η2 is the second coefficient, yawrate is the yaw rate, η3 is the third coefficient, θ is the direction angle, and η4 is the fourth coefficient; The direction angle is used as the current zero position deviation.

6. The method according to claim 1, characterized in that The determining, according to the direction angle, the lane centerline coefficient, the yaw angular velocity, the vehicle speed and a preset self-learning condition, a self-learning flag corresponding to the zero position deviation includes: In the case where the lane centerline availability is available, the first-order coefficient in the lane centerline coefficient is used as the centerline angle, and twice the second-order coefficient in the lane centerline coefficient is used as the lane centerline curvature; If the centerline angle, the lane centerline curvature, the absolute value of the direction angle, the absolute value of the yaw angular velocity, and the vehicle speed all meet corresponding preset thresholds, then the self-learning flag corresponding to the zero deviation is determined to be true; If at least one of the centerline angle, the lane centerline curvature, the absolute value of the direction angle, the absolute value of the yaw angular velocity and the vehicle speed does not meet the corresponding preset threshold, it is determined that the self-learning flag corresponding to the zero deviation is false.

7. The method according to claim 1, characterized in that After determining the target zero position deviation according to the lane centerline coefficient, the direction angle, the yaw angular velocity, the historical zero position deviation, the historical minimum cost value and the preset cost function, the method further includes: Obtaining a target angle corresponding to the steering system, and determining a control angle according to the target angle and the target zero position deviation; The vehicle is laterally controlled according to the control angle.

8. The method according to claim 1, characterized in that Before acquiring the direction angle, lane centerline coefficient, yaw rate and vehicle speed, the method further includes: Get the initial rotation angle, initial centerline coefficient, initial angular velocity and initial velocity; The initial turning angle, the initial centerline coefficient, the initial angular velocity and the initial velocity are respectively subjected to first-order smoothing filtering to obtain a direction turning angle, a lane centerline coefficient, a yaw angular velocity and a vehicle speed.

9. An electronic device, characterized in that: The electronic device comprises: Processor and memory; The processor is used to execute the steps of the method for determining the zero position deviation of the steering system as described in any one of claims 1 to 8 by calling the program or instruction stored in the memory.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a program or an instruction, and the program or the instruction enables a computer to execute the steps of the method for determining the zero deviation of a steering system according to any one of claims 1 to 8.

Images