Steering engine zero parameter online identification method, device and equipment and storage medium
By using the least squares method and gradient descent method to identify the zero position parameters of the steering machine in a straight-line driving state, the problems of large identification errors and high calculation complexity in the prior art are solved, and an efficient steering machine is realized Deviation parameter identification.
Patent Information
- Application Number
- CN202411200440.1
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-29
- Publication Date
- 2024-12-06
- Estimated Expiration
- 2044-08-29
AI Technical Summary
In the prior art, the identification of zero-position parameters of the steering machine has problems such as large errors, high computational complexity, and high requirements for computing resources and training data, especially in complex environments, which are difficult to achieve accurate identification.
By obtaining lateral error observation data when the target vehicle is in a straight-line driving state, the loss function is constructed using the least squares method and solving it through the gradient descent method to generate the target steering machine deviation value to realize the online identification of the zero position parameters of the steering machine.
The identification accuracy of steering machine deviation parameters is improved, the calculation complexity and requirements for computing resources are reduced, and the rapid and reliable online identification is achieved.
Smart Images

Figure CN119086113A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of automobile intelligent driving technology, and in particular to a method, device, equipment and storage medium for online identification of zero-position parameters of a steering gear. Background Art
[0002] The identification of steering gear zero position parameters (i.e. steering gear deviation parameters) is an important means to improve the system positioning accuracy, stability, control performance and adapt to different working environments. Therefore, it is very critical to accurately identify steering gear deviation parameters in the field of intelligent driving control.
[0003] In related technologies, steering machine deviation parameters are often identified through offline manual methods or long short-term memory networks. However, offline manual identification has the problem of large errors; and although the long short-term memory network can improve the identification accuracy of the steering machine deviation parameters, it introduces a gating mechanism and a long-term memory mechanism, so it requires more parameters and calculations, resulting in a high computational complexity problem; and the long short-term memory network usually requires a large number of iterations and calculations to evaluate individual fitness, which requires high computing resources, especially when solving complex problems, which may require more time and computing power; in addition, the long short-term memory network has more parameters that need to be trained, so more training data is needed to avoid overfitting, and if the training data is insufficient, the long short-term memory network may face the problem of insufficient generalization ability. Summary of the invention
[0004] The present application provides a method, device, equipment and storage medium for online identification of steering gear zero position parameters, which can effectively improve the identification accuracy of steering gear deviation parameters while reducing the computational complexity and the requirements for computing resources and training data volume.
[0005] In a first aspect, an embodiment of the present application provides a method for online identification of zero position parameters of a steering gear, the method comprising:
[0006] When it is detected that the target vehicle is in a straight-line driving state, lateral error observation data is obtained;
[0007] An initial loss function constructed based on a least square method is updated according to the lateral error observation data to generate a target loss function, wherein the target loss function includes a steering gear deviation function;
[0008] The target loss function is solved by the gradient descent method to obtain the target steering gear deviation value, so as to realize the identification of the steering gear zero position parameter.
[0009] In combination with the first aspect, in one implementation, the objective loss function is:
[0010] L(θ)=∑(Ef(θ)) 2
[0011] Wherein, L(θ) represents the target loss function, E represents the lateral error observation data, θ represents the steering gear deviation parameter, and f(θ) represents the steering gear deviation function, which is used to characterize the lateral error prediction value.
[0012] In combination with the first aspect, in one implementation, solving the target loss function by a gradient descent method to obtain a target steering machine deviation value includes:
[0013] The target loss function is solved by a gradient descent method to obtain an initial steering machine deviation value;
[0014] Inputting the initial steering gear deviation value into a preset lateral error tracking model for simulation to output a target steering angle;
[0015] When the target turning angle is within a preset turning angle threshold range, the initial steering gear deviation value is used as the target steering gear deviation value.
[0016] In combination with the first aspect, in one implementation, before the step of acquiring lateral error observation data when the target vehicle is detected to be in a straight-line driving state, the method further includes:
[0017] Obtain curvature feedforward information of the target vehicle's location;
[0018] Determining a target curvature value of a target vehicle's position according to the curvature feedforward information;
[0019] When the target curvature value is less than or equal to a preset curvature threshold, it is determined that the target vehicle is in a straight-line driving state.
[0020] In a second aspect, an embodiment of the present application provides a device for online identification of zero position parameters of a steering gear, the device for online identification of zero position parameters of a steering gear comprising:
[0021] A data acquisition module, which is used to acquire lateral error observation data when it is detected that the target vehicle is in a straight-line driving state;
[0022] A function updating module, which is used to update the initial loss function constructed based on the least square method according to the lateral error observation data to generate a target loss function, wherein the target loss function includes a steering gear deviation function;
[0023] The parameter identification module is used to solve the target loss function by gradient descent method to obtain the target steering gear deviation value so as to realize the identification of the steering gear zero position parameter.
[0024] In conjunction with the second aspect, in one implementation, the objective loss function is:
[0025] L(θ)=Σ(Ef(θ)) 2
[0026] Wherein, L(θ) represents the target loss function, E represents the lateral error observation data, θ represents the steering gear deviation parameter, and f(θ) represents the steering gear deviation function, which is used to characterize the lateral error prediction value.
[0027] In conjunction with the second aspect, in one implementation, the parameter identification module is specifically used to:
[0028] The target loss function is solved by a gradient descent method to obtain an initial steering machine deviation value;
[0029] Inputting the initial steering gear deviation value into a preset lateral error tracking model for simulation to output a target steering angle;
[0030] When the target turning angle is within a preset turning angle threshold range, the initial steering gear deviation value is used as the target steering gear deviation value.
[0031] In combination with the second aspect, in one implementation, the steering gear zero position parameter online identification device further includes a state recognition module, which is used to:
[0032] Obtain curvature feedforward information of the target vehicle's location;
[0033] Determining a target curvature value of a target vehicle's position according to the curvature feedforward information;
[0034] When the target curvature value is less than or equal to a preset curvature threshold, it is determined that the target vehicle is in a straight-line driving state.
[0035] In the third aspect, an embodiment of the present application provides a steering gear zero position parameter online identification device, the steering gear zero position parameter online identification device comprising a processor, a memory, and a steering gear zero position parameter online identification program stored in the memory and executable by the processor, wherein when the steering gear zero position parameter online identification program is executed by the processor, the steps of the steering gear zero position parameter online identification method as described above are implemented.
[0036] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, on which a steering gear zero position parameter online identification program is stored, wherein when the steering gear zero position parameter online identification program is executed by a processor, the steps of the steering gear zero position parameter online identification method as described above are implemented.
[0037] The beneficial effects brought by the technical solution provided in the embodiments of the present application include:
[0038] The initial loss function including the steering gear deviation function constructed based on the least squares method is updated by the corresponding lateral error observation data when the target vehicle is in a straight-line driving state to generate a target loss function, and then the target loss function is solved by the gradient descent method to obtain the target steering gear deviation value to realize the identification of the steering gear zero position parameters. The present application can realize fast and reliable online identification of steering gear deviation parameters by using the least squares method, without the need for more parameters and calculations, which not only effectively improves the identification accuracy, but also reduces the computational complexity and the requirements for computing resources and training data volume. BRIEF DESCRIPTION OF THE DRAWINGS
[0039] Figure 1 This is a flow chart of an embodiment of a method for online identification of zero position parameters of a steering gear of the present application;
[0040] Figure 2 For this application Figure 1 Detailed flow chart of step S30;
[0041] Figure 3 This is a functional module diagram of an embodiment of the online identification device for zero position parameters of a steering gear of the present application;
[0042] Figure 4 This is a schematic diagram of the hardware structure of the steering gear zero position parameter online identification device involved in the embodiment of the present application. DETAILED DESCRIPTION
[0043] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.
[0044] The embodiment of the present application provides a method for online identification of steering gear zero position parameters, which can effectively improve the identification accuracy of steering gear deviation parameters while reducing the computational complexity and the requirements for computing resources and the amount of training data.
[0045] To achieve the above objectives, the overall idea of this application is as follows:
[0046] Step S10: when it is detected that the target vehicle is in a straight-line driving state, obtaining lateral error observation data;
[0047] Step S20: updating the initial loss function constructed based on the least square method according to the lateral error observation data to generate a target loss function, wherein the target loss function includes a steering gear deviation function;
[0048] Step S30: Solving the target loss function by gradient descent method to obtain the target steering gear deviation value to identify the steering gear zero position parameter.
[0049] In order to make the objectives, technical solutions and advantages of the present application clearer, the implementation methods of the present application will be further described in detail below with reference to the accompanying drawings.
[0050] In a first aspect, an embodiment of the present application provides a method for online identification of zero-position parameters of a steering gear.
[0051] In one embodiment, referring to Figure 1 , Figure 1 This is a flow chart of an embodiment of the method for online identification of zero position parameters of a steering gear of the present application. Figure 1 As shown, the online identification method of the steering gear zero position parameters includes:
[0052] Step S10: When it is detected that the target vehicle is in a straight-line driving state, lateral error observation data is obtained.
[0053] Exemplarily, it can be understood that the lateral error refers to the vertical distance between the center of gravity of the vehicle and the center line of the lane (or the target trajectory), and the steering gear deviation can be identified through the lateral error. In this embodiment, the steering gear deviation parameters will be identified only when the target vehicle is located in a straight-line driving section. Therefore, when it is detected that the target vehicle is not in a straight-line driving state, the steering gear deviation parameters will not be identified; and if it is detected that the target vehicle is in a straight-line driving state, the lateral error observation data can be obtained through the vehicle controller, and the lateral error observation data can be cleaned to improve the data quality. It should be noted that data cleaning includes but is not limited to missing value processing, outlier processing and deduplication, and the specific implementation method and principle of data cleaning are common knowledge in the field, so for the sake of brevity of description, it is not limited here.
[0054] Furthermore, in one embodiment, before the step of acquiring lateral error observation data when the target vehicle is detected to be in a straight-line driving state, the method further includes:
[0055] Obtain curvature feedforward information of the target vehicle's location;
[0056] Determining a target curvature value of a target vehicle's position according to the curvature feedforward information;
[0057] When the target curvature value is less than or equal to a preset curvature threshold, it is determined that the target vehicle is in a straight-line driving state.
[0058] Exemplarily, it should be understood that curvature feedforward refers to using the curvature information of the reference path as the input of the feedforward control in the control system to adjust the output of the controller in advance, so as to better cope with the upcoming path change. In this embodiment, the curvature feedforward information of the position of the target vehicle can be obtained through the vehicle controller, so as to determine the target curvature value of the position of the target vehicle based on the relationship between the curvature feedforward C and the curvature c: C = K × c, where K is a proportional parameter, and its specific value setting can be determined according to actual needs, and is not limited here; then, the target vehicle is determined to be located in a straight driving section by the size relationship between the target curvature value and the curvature threshold. If the target curvature value is less than the curvature threshold, it means that the target vehicle is located in a straight driving section, and the target vehicle is determined to be in a straight driving state; and if the target curvature value is greater than the curvature threshold, it means that the target vehicle is located in a non-straight driving section, and the target vehicle is determined to be not in a straight driving state. It should be noted that the specific value setting of the curvature threshold can be determined according to actual needs, and is not limited here.
[0059] Step S20: updating the initial loss function constructed based on the least square method according to the lateral error observation data to generate a target loss function, wherein the target loss function includes a steering gear deviation function; wherein the target loss function is:
[0060] L(θ)=Σ(Ef(θ)) 2
[0061] Wherein, L(θ) represents the target loss function, E represents the lateral error observation data, θ represents the steering gear deviation parameter, and f(θ) represents the steering gear deviation function, which is used to characterize the lateral error prediction value.
[0062] Exemplarily, in this embodiment, the online identification of the steering gear deviation parameter will be achieved by using the least squares method, that is, the sum of squares of the preferred residual is used as the loss function. Specifically, the relationship model between the steering gear deviation parameter θ and the lateral error can be expressed in the form of y=f(θ), where y represents the lateral error prediction value, f is a function of the steering gear deviation parameter θ, that is, f(θ) is the steering gear deviation function, and the lateral error prediction value can be obtained through the f(θ) function; it should be noted that the goal of this embodiment is to find the optimal parameter estimation value θ so that the sum of squares of the residuals between the lateral error observation data and the lateral error prediction value is minimized. It should be understood that the residual ∈ in this embodiment can be defined as the difference between the lateral error observation data E and the lateral error prediction value y, that is, ∈=Ef(θ), then the loss function is:
[0063] L(θ)=∑∈ 2 =∑(Ef(θ)) 2
[0064] Therefore, after obtaining the lateral error observation data E, the lateral error observation data E is substituted into the L(θ) loss function to update the loss function, and then the target loss function L(θ) = ∑(Ef(θ)) is obtained. 2 .
[0065] Step S30: Solving the target loss function by gradient descent method to obtain the target steering gear deviation value to identify the steering gear zero position parameter.
[0066] For example, in this embodiment, after obtaining the target loss function, it is necessary to minimize the loss function to obtain the steering gear deviation value, thereby realizing the identification of the steering gear zero position parameter. Specifically, the target loss function is derived with respect to the steering gear deviation parameter θ and the derivative of the target loss function is set to zero, that is, Then, the above equation is solved by the gradient descent method to obtain the optimal steering gear deviation parameter θ. It should be noted that the method and principle of how to determine the optimal parameter by the gradient descent method is common knowledge in the art, so for the sake of brevity, it will not be repeated here. The gradient descent method includes but is not limited to the stochastic gradient descent method and batch gradient descent.
[0067] It should be understood that, after fitting the lateral error E and the steering gear deviation r in this embodiment, the relationship between the two can be obtained as follows:
[0068] E=k×r
[0069] Among them, k represents the proportional coefficient, and its specific value setting can be determined according to actual needs and is not limited here; it can be seen that the steering gear deviation parameter θ=k×r can be determined through the above relationship. Therefore, after calculating the steering gear deviation parameter θ, the target steering gear deviation value can be calculated according to θ=k×r, thereby realizing fast, accurate and reliable online identification of the steering gear deviation parameter, so as to effectively improve the response performance, stability and robustness of the system.
[0070] It can be seen that when the least square method is used to identify the steering gear deviation parameters, the present embodiment does not need to introduce a gating mechanism and a long-term memory mechanism, that is, no more parameters and calculations are required, and a large number of iterations and calculations for evaluating individual fitness are not required, so the requirements for computing resources can be reduced; in addition, there are no more parameters that need to be trained, that is, no more training data is required to avoid overfitting. Therefore, the present embodiment not only effectively improves the identification accuracy, but also reduces the computational complexity and the requirements for computing resources and the amount of training data.
[0071] Further, see Figure 2As shown, the target loss function is solved by the gradient descent method to obtain the target steering machine deviation value, including:
[0072] Step S301: solving the target loss function by gradient descent method to obtain an initial steering gear deviation value;
[0073] Step S302: inputting the initial steering gear deviation value into a preset lateral error tracking model for simulation to output a target steering angle;
[0074] Step S303: When the target turning angle is within a preset turning angle threshold range, the initial steering gear deviation value is used as a target steering gear deviation value.
[0075] Exemplarily, in this embodiment, after solving the target loss function by the gradient descent method to obtain the initial steering gear deviation value, the steering gear deviation identification result (i.e., the initial steering gear deviation value) is brought into the lateral error tracking model for simulation to output the simulation result (i.e., the target angle), and the target angle can be the front wheel angle or the steering wheel angle (i.e., the steering gear angle), which is not limited here; then the simulation result is judged to determine whether the influence of the zero position on the control algorithm is weakened, that is, if the target angle is within the preset angle threshold range, it means that the influence of the zero position on the control algorithm is weakened, then the calculation of the steering gear deviation value is stopped, and the initial steering gear deviation value is substituted as the target steering gear deviation value into the existing lateral control algorithm for automatic driving control. It should be noted that the specific structure and working principle of the lateral error tracking model are common knowledge in the art, so for the sake of brevity of description, it will not be repeated here; and the specific value limit of the angle threshold range can be determined according to actual needs, which is not limited here.
[0076] If the target steering angle is outside the steering angle threshold range, it means that the influence of the zero position on the control algorithm has not been weakened. At this time, the optimal steering gear deviation parameter θ needs to be solved again until the optimal steering gear deviation value corresponding to the solved optimal steering gear deviation parameter θ is substituted into the lateral error tracking model, and the output steering angle is within the steering angle threshold range. Then the optimal steering gear deviation value is substituted as the target steering gear deviation value into the existing lateral control algorithm to perform automatic driving control.
[0077] In summary, this embodiment provides an efficient parameter identification algorithm, that is, using the least squares method to perform real-time calculations of the steering gear zero position parameters to achieve fast and reliable parameter estimation, thereby obtaining high-precision identification results and strong anti-interference ability, and reducing the computational complexity and shortening the time required for parameter identification through reasonable algorithm design and optimization; at the same time, the data used in this embodiment can be easily obtained from the vehicle, thereby ensuring its feasibility and practicality in the real-time control system. It can be seen that the online identification method for the steering gear zero position parameters provided in this embodiment can perform real-time identification of the steering gear deviation parameters in the vehicle lateral control algorithm, and can be applied to parameter adjustment under the condition of intelligent driving of the vehicle; among them, when applying the online identification method for the steering gear zero position parameters provided in this embodiment, the characteristics and requirements of the actual system can be considered to ensure that the proposed parameter identification method can operate effectively in various actual environments and application scenarios, and meet the requirements of the actual control system.
[0078] In a second aspect, an embodiment of the present application also provides a device for online identification of zero-position parameters of a steering gear.
[0079] In one embodiment, referring to Figure 3 , Figure 3 This is a functional module diagram of an embodiment of the steering gear zero position parameter online identification device of the present application. Figure 3 As shown, the steering gear zero position parameter online identification device includes:
[0080] A data acquisition module, which is used to acquire lateral error observation data when it is detected that the target vehicle is in a straight-line driving state;
[0081] A function updating module, which is used to update the initial loss function constructed based on the least square method according to the lateral error observation data to generate a target loss function, wherein the target loss function includes a steering gear deviation function;
[0082] The parameter identification module is used to solve the target loss function by gradient descent method to obtain the target steering gear deviation value so as to realize the identification of the steering gear zero position parameter.
[0083] Furthermore, in one embodiment, the objective loss function is:
[0084] L(θ)=∑(Ef(θ)) 2
[0085] Wherein, L(θ) represents the target loss function, E represents the lateral error observation data, θ represents the steering gear deviation parameter, and f(θ) represents the steering gear deviation function, which is used to characterize the lateral error prediction value.
[0086] Furthermore, in one embodiment, the parameter identification module is specifically used for:
[0087] The target loss function is solved by a gradient descent method to obtain an initial steering machine deviation value;
[0088] Inputting the initial steering gear deviation value into a preset lateral error tracking model for simulation to output a target steering angle;
[0089] When the target turning angle is within a preset turning angle threshold range, the initial steering gear deviation value is used as the target steering gear deviation value.
[0090] Furthermore, in one embodiment, the steering gear zero position parameter online identification device further includes a state recognition module, which is used to:
[0091] Obtain curvature feedforward information of the target vehicle's location;
[0092] Determining a target curvature value of a target vehicle's position according to the curvature feedforward information;
[0093] When the target curvature value is less than or equal to a preset curvature threshold, it is determined that the target vehicle is in a straight-line driving state.
[0094] Among them, the functional implementation of each module in the above-mentioned steering gear zero position parameter online identification device corresponds to the various steps in the above-mentioned steering gear zero position parameter online identification method embodiment, and its functions and implementation processes are no longer repeated here one by one.
[0095] In a third aspect, an embodiment of the present application provides a steering gear zero position parameter online identification device, which may be a personal computer (PC), a laptop computer, a server, or other device with data processing capabilities.
[0096] Reference Figure 4 , Figure 4 The hardware structure diagram of the steering gear zero position parameter online identification device involved in the embodiment of the present application is shown in FIG. In the embodiment of the present application, the steering gear zero position parameter online identification device may include a processor, a memory, a communication interface and a communication bus.
[0097] The communication bus may be of any type and is used to interconnect the processor, the memory, and the communication interface.
[0098] The communication interface includes input / output (I / O) interface, physical interface and logical interface, etc., which are used to realize the interconnection of devices inside the steering gear zero position parameter online identification device, and the interface used to realize the interconnection of the steering gear zero position parameter online identification device with other devices (such as other computing devices or user devices). The physical interface can be an Ethernet interface, an optical fiber interface, an ATM interface, etc.; the user device can be a display, a keyboard, etc.
[0099] The memory can be various types of storage media, such as random access memory (RAM), read-only memory (ROM), non-volatile RAM (NVRAM), flash memory, optical storage, hard disk, programmable ROM (PROM), erasable PROM (EPROM), electrically erasable PROM (EEPROM), etc.
[0100] The processor may be a general-purpose processor, and the general-purpose processor may call the steering gear zero position parameter online identification program stored in the memory, and execute the steering gear zero position parameter online identification method provided by the embodiment of the present application. For example, the general-purpose processor may be a central processing unit (CPU). Among them, the method executed when the steering gear zero position parameter online identification program is called may refer to the various embodiments of the steering gear zero position parameter online identification method of the present application, which will not be repeated here.
[0101] Those skilled in the art will understand that Figure 4 The hardware structure shown in the figure does not constitute a limitation on the present application, and may include more or less components than shown in the figure, or combine certain components, or arrange the components differently.
[0102] In a fourth aspect, an embodiment of the present application also provides a computer-readable storage medium.
[0103] The readable storage medium of the present application stores a steering gear zero position parameter online identification program, wherein when the steering gear zero position parameter online identification program is executed by a processor, the steps of the steering gear zero position parameter online identification method as described above are implemented.
[0104] Among them, the method implemented when the steering gear zero position parameter online identification program is executed can refer to the various embodiments of the steering gear zero position parameter online identification method of the present application, and will not be repeated here.
[0105] It should be noted that the serial numbers of the above-mentioned embodiments of the present application are only for description and do not represent the advantages or disadvantages of the embodiments.
[0106] The terms "including" and "having" and any variations thereof in the specification and claims of this application and the above-mentioned drawings are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not limited to the listed steps or units, but optionally includes steps or units that are not listed, or optionally includes other steps or units inherent to these processes, methods, products or devices. The terms "first", "second" and "third" are used to distinguish different objects, etc., and do not represent a sequence, nor do they limit "first", "second" and "third" to different types.
[0107] In the description of the embodiments of the present application, "exemplary", "for example" or "for example" are used to indicate examples, illustrations or descriptions. Any embodiment or design described as "exemplary", "for example" or "for example" in the embodiments of the present application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "exemplary", "for example" or "for example" is intended to present related concepts in a specific way.
[0108] In the description of the embodiments of the present application, unless otherwise specified, “ / ” means or, for example, A / B can mean A or B; the “and / or” in the text is merely a description of the association relationship of associated objects, indicating that three relationships may exist, for example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone. In addition, in the description of the embodiments of the present application, “multiple” refers to two or more than two.
[0109] In some processes described in the embodiments of the present application, multiple operations or steps that appear in a specific order are included, but it should be understood that these operations or steps may not be executed in the order in which they appear in the embodiments of the present application or in parallel, and the sequence number of the operation is only used to distinguish the different operations, and the sequence number itself does not represent any execution order. In addition, these processes may include more or fewer operations, and these operations or steps may be executed in sequence or in parallel, and these operations or steps may be combined.
[0110] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application is essentially or the part that contributes to the prior art can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, disk, CD) as described above, and includes a number of instructions for a terminal device to execute the methods described in each embodiment of the present application.
[0111] The above are only preferred embodiments of the present application, and are not intended to limit the patent scope of the present application. Any equivalent structure or equivalent process transformation made using the contents of the present application specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present application.
Claims
1. A method for online identification of zero position parameters of a steering gear, characterized in that: The steering gear zero position parameter online identification method comprises: When it is detected that the target vehicle is in a straight-line driving state, lateral error observation data is obtained; An initial loss function constructed based on a least square method is updated according to the lateral error observation data to generate a target loss function, wherein the target loss function includes a steering gear deviation function; The target loss function is solved by the gradient descent method to obtain the target steering gear deviation value, so as to realize the identification of the steering gear zero position parameter.
2. The method for online identification of zero position parameters of a steering gear according to claim 1, characterized in that: The objective loss function is: L(θ)=Σ(Ef(θ)) 2 Wherein, L(θ) represents the target loss function, E represents the lateral error observation data, θ represents the steering gear deviation parameter, and f(θ) represents the steering gear deviation function, which is used to characterize the lateral error prediction value.
3. The method for online identification of zero position parameters of a steering gear according to claim 1, characterized in that: The target loss function is solved by the gradient descent method to obtain the target steering machine deviation value, including: The target loss function is solved by a gradient descent method to obtain an initial steering machine deviation value; Inputting the initial steering gear deviation value into a preset lateral error tracking model for simulation to output a target steering angle; When the target turning angle is within a preset turning angle threshold range, the initial steering gear deviation value is used as the target steering gear deviation value.
4. The method for online identification of zero position parameters of a steering gear according to claim 1, characterized in that: Before the step of acquiring lateral error observation data when the target vehicle is detected to be in a straight-line driving state, the method further includes: Obtain curvature feedforward information of the target vehicle's location; Determining a target curvature value of a target vehicle's position according to the curvature feedforward information; When the target curvature value is less than or equal to a preset curvature threshold, it is determined that the target vehicle is in a straight-line driving state.
5. A device for online identification of zero position parameters of a steering gear, characterized in that: The steering gear zero position parameter online identification device comprises: A data acquisition module, which is used to acquire lateral error observation data when it is detected that the target vehicle is in a straight-line driving state; A function updating module, which is used to update the initial loss function constructed based on the least square method according to the lateral error observation data to generate a target loss function, wherein the target loss function includes a steering gear deviation function; The parameter identification module is used to solve the target loss function by gradient descent method to obtain the target steering gear deviation value so as to realize the identification of the steering gear zero position parameter.
6. The device for online identification of zero position parameters of a steering gear according to claim 5, characterized in that: The objective loss function is: L(θ)=∑(Ef(θ)) 2 Wherein, L(θ) represents the target loss function, E represents the lateral error observation data, θ represents the steering gear deviation parameter, and f(θ) represents the steering gear deviation function, which is used to characterize the lateral error prediction value.
7. The device for online identification of zero position parameters of a steering gear according to claim 5, characterized in that: The parameter identification module is specifically used for: The target loss function is solved by a gradient descent method to obtain an initial steering machine deviation value; Inputting the initial steering gear deviation value into a preset lateral error tracking model for simulation to output a target steering angle; When the target turning angle is within a preset turning angle threshold range, the initial steering gear deviation value is used as the target steering gear deviation value.
8. The device for online identification of zero position parameters of a steering gear according to claim 5, characterized in that: The steering gear zero position parameter online identification device also includes a state recognition module, which is used for: Obtain curvature feedforward information of the target vehicle's location; Determining a target curvature value of a target vehicle's position according to the curvature feedforward information; When the target curvature value is less than or equal to a preset curvature threshold, it is determined that the target vehicle is in a straight-line driving state.
9. A steering gear zero position parameter online identification device, characterized in that: The steering gear zero position parameter online identification device comprises a processor, a memory, and a steering gear zero position parameter online identification program stored in the memory and executable by the processor, wherein when the steering gear zero position parameter online identification program is executed by the processor, the steps of the steering gear zero position parameter online identification method as described in any one of claims 1 to 4 are implemented.
10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a steering gear zero position parameter online identification program, wherein when the steering gear zero position parameter online identification program is executed by the processor, the steps of the steering gear zero position parameter online identification method as described in any one of claims 1 to 4 are implemented.
Citation Information
Patent Citations
Question and answer system test method and device, computer equipment and storage medium
CN111124898A
Zero deviation dynamic calibration method and device, electronic equipment and storage medium
CN113581289A
Model training method and device based on knowledge distillation, equipment and storage medium
CN115062769A
Related device of model training method
CN117436540A
System and method for vehicle steering control
US20160107682A1
