Methods, devices, vehicle-mounted equipment, storage media, and program products for determining the road surface adhesion coefficient.

Abstract

This application relates to a method, apparatus, vehicle-mounted device, storage medium, and program product for determining the road surface adhesion coefficient. The method obtains an empirical estimation model corresponding to the type of road surface the vehicle is traveling on, and a real-time estimation model corresponding to a preset time period of vehicle travel on the road surface. Based on the real-time estimation model and the empirical estimation model, the road surface adhesion coefficient corresponding to the road surface is determined. The empirical estimation model characterizes the correspondence between the utilization adhesion coefficient and slip ratio determined by experimental data; the real-time estimation model characterizes the correspondence between the utilization adhesion coefficient and slip ratio determined by the vehicle's dynamic performance. This method, by combining the empirical estimation model and the real-time estimation model to estimate the road surface adhesion coefficient of the vehicle's travel surface, considers not only the road surface type but also the real-time dynamic performance of the vehicle, thus improving the accuracy of the road surface adhesion coefficient estimation.

Description

Technical Field

[0001] This application relates to the field of vehicle control technology, and in particular to a method, apparatus, vehicle-mounted equipment, storage medium, and program product for determining the road surface adhesion coefficient. Background Technology

[0002] With the rapid development of vehicle intelligent control technology, the requirements for vehicle handling, braking, and safety performance are becoming increasingly stringent. These performance characteristics are closely related to the tire's grip on the road surface during driving. Related technologies typically use the vehicle's tire-road grip to optimize various vehicle performance parameters. While the coefficient of friction (COP) reflects this grip, current technologies cannot directly measure it; they only estimate it based on the vehicle's tire dynamics model when the vehicle is skidding.

[0003] However, the above-mentioned method for estimating the road surface adhesion coefficient has the problem of inaccuracy. Summary of the Invention

[0004] Therefore, it is necessary to provide a method, apparatus, vehicle-mounted equipment, storage medium, and program product for determining the road surface adhesion coefficient that can improve the accuracy of road surface adhesion coefficient estimation, in order to address the above-mentioned technical problems.

[0005] In a first aspect, this application provides a method for determining the road surface adhesion coefficient, including:

[0006] An empirical estimation model corresponding to the type of road surface in which the vehicle is driving is obtained; the empirical estimation model is used to characterize the correspondence between the adhesion coefficient and the slip ratio determined by experimental data.

[0007] Obtain a real-time estimation model corresponding to a preset time period during which the vehicle travels on the road surface; the real-time estimation model is used to characterize the correspondence between the adhesion coefficient and the slip ratio determined by the vehicle's dynamic performance.

[0008] The real-time estimation model and the empirical estimation model are fused to determine the target estimation model, and the road surface adhesion coefficient corresponding to the driving road surface is determined based on the target estimation model.

[0009] In some embodiments, fusing the real-time estimation model and the empirical estimation model to determine the target estimation model includes:

[0010] An empirical estimation model corresponding to the low slip ratio interval is extracted from the empirical estimation model and used as the first intermediate empirical estimation model; the low slip ratio interval is consistent with the slip ratio interval in which multiple slip ratios are located in the real-time estimation model;

[0011] The real-time estimation model and the first intermediate empirical estimation model are fused to determine the target estimation model.

[0012] In some embodiments, fusing the real-time estimation model and the first intermediate empirical estimation model to determine the target estimation model includes:

[0013] Based on the real-time estimation model and the first intermediate empirical estimation model, determine the first correction parameter;

[0014] The adhesion coefficients of multiple slip ratios in the first intermediate empirical estimation model are corrected according to the first correction parameter to obtain the corrected adhesion coefficients.

[0015] The target estimation model is constructed based on the modified multiple adhesion coefficients.

[0016] In some embodiments, constructing the target estimation model based on the modified plurality of adhesion coefficients includes:

[0017] Based on the modified multiple low slip rate estimation models using the adhesion coefficient, the low slip rate interval is constructed accordingly.

[0018] The target estimation model is determined based on the low slip ratio estimation model and the empirical estimation model.

[0019] In some embodiments, determining the target estimation model based on the low slip ratio estimation model and the empirical estimation model includes:

[0020] The empirical estimation model corresponding to the high slip ratio interval is extracted from the empirical estimation model as the second intermediate empirical estimation model; the high slip ratio interval is the slip ratio region other than the low slip ratio interval;

[0021] The second intermediate empirical estimation model is modified to obtain the third intermediate empirical estimation model;

[0022] The target estimation model is constructed based on the third intermediate empirical estimation model and the low slip ratio estimation model.

[0023] In some embodiments, the step of modifying the second intermediate empirical estimation model to obtain a third intermediate empirical estimation model includes:

[0024] The second correction parameter is determined based on the first intermediate empirical estimation model and the low slip ratio estimation model;

[0025] The second intermediate empirical estimation model is modified according to the second modification parameter to obtain the third intermediate empirical estimation model.

[0026] In some embodiments, determining the first correction parameter based on the real-time estimation model and the first intermediate empirical estimation model includes:

[0027] Determine the first mean of the adhesion coefficients for all slip ratios in the first intermediate empirical estimation model, and the second mean of the adhesion coefficients for all slip ratios in the real-time estimation model;

[0028] The first correction parameter is determined based on the first mean and the second mean.

[0029] In some embodiments, the method further includes:

[0030] Obtain the initial road adhesion coefficient corresponding to the type of the driving road surface;

[0031] Determining the road surface adhesion coefficient corresponding to the driving surface based on the target estimation model includes:

[0032] Based on the target estimation model and the initial road surface adhesion coefficient, the road surface adhesion coefficient corresponding to the driving road surface is determined.

[0033] In some embodiments, determining the road surface adhesion coefficient corresponding to the driving road surface based on the target estimation model and the initial road surface adhesion coefficient includes:

[0034] The maximum utilization adhesion coefficient in the target estimation model is used as the intermediate road surface adhesion coefficient.

[0035] The road surface adhesion coefficient corresponding to the driving road surface is obtained by performing a weighted summation operation on the intermediate road surface adhesion coefficient and the initial road surface adhesion coefficient.

[0036] In some embodiments, obtaining the initial road adhesion coefficient corresponding to the type of the driving road surface includes:

[0037] Based on the type of road surface, look up the corresponding adhesion coefficient range from the vehicle slip adhesion coefficient reference table;

[0038] The initial road surface adhesion coefficient is obtained by processing all adhesion coefficients included in the adhesion coefficient range.

[0039] In some embodiments, the method further includes:

[0040] Acquire images of the road surface on the driving surface;

[0041] The road surface image is input into a preset road surface recognition network for recognition, and the type of the driving road surface is output.

[0042] In some embodiments, obtaining the real-time estimation model corresponding to the vehicle's travel time on the road surface for a preset period of time includes:

[0043] The longitudinal force and vertical force of the tires of the vehicle are obtained during a preset time period when the vehicle is traveling on the road surface.

[0044] The real-time estimation model is constructed based on the longitudinal and vertical forces of the vehicle's tires.

[0045] Secondly, this application also provides a device for determining the road surface adhesion coefficient, comprising:

[0046] The first acquisition module is used to acquire an empirical estimation model corresponding to the type of road surface where the vehicle is driving; the empirical estimation model is used to characterize the correspondence between the adhesion coefficient and the slip ratio determined by experimental data.

[0047] The second acquisition module is used to acquire a real-time estimation model corresponding to a preset time period during which the vehicle travels on the road surface; the real-time estimation model is used to characterize the correspondence between the adhesion coefficient and the slip ratio determined by the dynamic performance of the vehicle.

[0048] The fusion module is used to fuse the real-time estimation model and the empirical estimation model to determine the target estimation model, and to determine the road surface adhesion coefficient corresponding to the driving road surface based on the target estimation model.

[0049] Thirdly, this application also provides an on-board device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the method for determining the road adhesion coefficient described in the first aspect above.

[0050] Fourthly, this application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the method for determining the road surface adhesion coefficient described in the first aspect above.

[0051] Fifthly, this application also provides a computer program product, including a computer program that, when executed by a processor, implements the method for determining the road surface adhesion coefficient described in the first aspect.

[0052] The aforementioned method, apparatus, vehicle-mounted equipment, storage medium, and program product for determining the road surface adhesion coefficient (LPC) acquire an empirical estimation model corresponding to the type of road surface the vehicle is traveling on, and a real-time estimation model corresponding to a preset time period of vehicle travel on the road surface. Based on the real-time and empirical estimation models, the LPC corresponding to the driving road surface is determined. The empirical estimation model characterizes the relationship between the LPC and slip ratio determined by experimental data; the real-time estimation model characterizes the relationship between the LPC and slip ratio determined by the vehicle's dynamic performance. In this method, since the empirical estimation model can characterize the LPC for various road surface types, and the real-time estimation model can characterize the LPC under the vehicle's real-time dynamic state, the method combines these two models to estimate the LPC of the driving road surface. This approach considers not only the road surface type but also the vehicle's real-time dynamic performance, thus improving the accuracy of LPC estimation. Attached Figure Description

[0053] To more clearly illustrate the technical solutions in the embodiments of this application or related technologies, the drawings used in the description of the embodiments of this application or related technologies will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0054] Figure 1 This is a diagram illustrating the application environment of the method for determining the road surface adhesion coefficient in the embodiments of this application.

[0055] Figure 2 This is one of the flowcharts illustrating the method for determining the road surface adhesion coefficient in the embodiments of this application;

[0056] Figure 2A This is a schematic diagram of the hyperparameter list in an embodiment of this application;

[0057] Figure 2B Experience in the embodiments of this application A schematic diagram of the curve;

[0058] Figure 3 This is the second flowchart illustrating the method for determining the road surface adhesion coefficient in this application.

[0059] Figure 3A Examples of embodiments in this application One of the schematic diagrams of the curve;

[0060] Figure 4 This is the third flowchart illustrating the method for determining the road surface adhesion coefficient in this application.

[0061] Figure 4A Examples of embodiments in this application The second schematic diagram of the curve;

[0062] Figure 5 This is the fourth flowchart illustrating the method for determining the road surface adhesion coefficient in the embodiments of this application;

[0063] Figure 6 This is the fifth flowchart illustrating the method for determining the road surface adhesion coefficient in the embodiments of this application;

[0064] Figure 7 This is the sixth flowchart illustrating the method for determining the road surface adhesion coefficient in this application.

[0065] Figure 8 This is the seventh flowchart illustrating the method for determining the road surface adhesion coefficient in this application.

[0066] Figure 9 This is a reference list of adhesion coefficients in the embodiments of this application;

[0067] Figure 10 This is the eighth flowchart illustrating the method for determining the road surface adhesion coefficient in this application.

[0068] Figure 11 This is the ninth flowchart illustrating the method for determining the road surface adhesion coefficient in the embodiments of this application;

[0069] Figure 12 This is the tenth flowchart illustrating the method for determining the road surface adhesion coefficient in the embodiments of this application;

[0070] Figure 13 This is eleventh of the flowcharts illustrating the method for determining the road surface adhesion coefficient in the embodiments of this application;

[0071] Figure 14 This is the twelfth flowchart illustrating the method for determining the road surface adhesion coefficient in the embodiments of this application;

[0072] Figure 15 This is a structural block diagram of the device for determining the road surface adhesion coefficient in the embodiments of this application;

[0073] Figure 16 This is an internal structure diagram of the vehicle-mounted device in one embodiment. Detailed Implementation

[0074] To facilitate understanding of this application, a more complete description will be provided below with reference to the accompanying drawings. Preferred embodiments of this application are shown in the drawings. However, this application can be implemented in many different forms and is not limited to the embodiments described herein. Rather, these embodiments are provided to provide a thorough and complete understanding of the disclosure of this application.

[0075] It should be understood that although the terms “first,” “second,” etc., may be used herein to describe various elements, this does not indicate any order, quantity, or importance, but is merely used to distinguish different components. These terms are used only to distinguish one element from another. For example, without departing from the scope of this application, a first element may be referred to as a second element, and similarly, a second element may be referred to as a first element. Words such as “comprising” or “including” mean that the element or object preceding the word covers the element or object listed after the word and its equivalents, without excluding other elements or objects.

[0076] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein in the specification of this application is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. The term "and / or" as used herein includes any and all combinations of one or more of the associated listed items.

[0077] In related technologies, the coefficient of friction (coefficient of adhesion) is a physical quantity describing the magnitude of friction between a vehicle's tires and the road surface, usually denoted by μ. It reflects the vehicle's grip on the road surface during driving. The coefficient of friction directly affects a vehicle's handling, braking performance, and safety. The level of the coefficient of friction depends on factors such as road surface materials, humidity, temperature, contaminants (e.g., oil, water, snow), and tire material and tread pattern. Generally, vehicle braking systems (such as anti-lock braking systems (ABS) and electronic brake-force distribution (EBD) rely on the coefficient of friction to optimize braking performance and prevent wheel lock-up or slippage. Furthermore, autonomous vehicles also adjust their driving strategies (such as speed and steering angle) based on different coefficients of friction to ensure safety. In summary, accurately estimating the road surface adhesion coefficient during vehicle operation is crucial for optimizing the vehicle's handling, braking, and safety performance. However, in related technologies, on the one hand, the sensors on the vehicle cannot directly measure the tire-road adhesion coefficient; on the other hand, the road surface adhesion coefficient can be obtained by querying the U-curve of the existing empirical tire model, but this method is no longer able to accurately estimate the road surface adhesion coefficient under the current conditions of new energy vehicles and their varying power performance.

[0078] In view of this, embodiments of this application propose a method, apparatus, vehicle-mounted equipment, storage medium, and program product for determining the road surface adhesion coefficient, which can accurately estimate the road surface adhesion coefficient of the road surface on which the vehicle is currently traveling.

[0079] It should be noted that the beneficial effects or technical problems solved by the embodiments of this application are not limited to this one, but may also be other implicit or related problems. For details, please refer to the description of the embodiments below.

[0080] The method for determining the road surface adhesion coefficient provided in this application embodiment can be applied to, for example, Figure 1 The application environment is shown. The measuring device 102 is installed on the vehicle 104. The measuring device 102 can acquire sensing data from various types of sensors on the vehicle 104 and analyze and process various performance parameters of the vehicle 104 based on the sensing data. In this embodiment, the measuring device 102 can estimate the road surface adhesion coefficient of the road surface on which the vehicle 104 is traveling, so as to determine the road surface adhesion coefficient of the road surface on which the vehicle 104 is traveling in real time. The measuring device 102 can be, but is not limited to, various personal computers, laptops, smartphones, tablets, IoT devices, and portable wearable devices. IoT devices can be smart speakers, smart TVs, smart air conditioners, smart in-vehicle devices, projection devices, etc. Portable wearable devices can be smartwatches, smart bracelets, head-mounted devices, etc. Head-mounted devices can be virtual reality (VR) devices, augmented reality (AR) devices, smart glasses, etc.

[0081] Those skilled in the art will understand that Figure 1 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the measuring device to which the present application is applied. A specific measuring device may include more or fewer components than those shown in the figure, or may combine certain components, or may have different component arrangements.

[0082] In some exemplary embodiments, such as Figure 2 As shown, a method for determining the road surface adhesion coefficient is provided, and this method is applied to... Figure 1 Taking the measuring device in the middle as an example, the following steps are included:

[0083] S201, Obtain the empirical estimation model corresponding to the type of road surface where the vehicle is traveling.

[0084] Among them, the empirical estimation model is used to characterize the correspondence between the coefficient of adhesion and the slip ratio determined by experimental data. For example, the empirical estimation model can be an empirical model of the coefficient of adhesion versus slip ratio derived from the Burckhardt tire model. Curve, the experience The curve can be obtained from a large amount of experimental data. The empirical estimation model can be obtained using the following relationship (1):

[0085] (1);

[0086] In the above relation, Indicates slip ratio, This indicates the use of the adhesion coefficient. This represents hyperparameters. It is related to the road surface type; that is, different road surface types correspond to different hyperparameters. Available from Figure 2A Obtain from the list of standard hyperparameters shown.

[0087] The types of driving surfaces include dry asphalt roads, wet asphalt roads, dry cobblestone roads, wet cobblestone roads, dry cement roads, snow roads, and ice roads. The correspondence between driving surface types and hyperparameters can be pre-stored in the vehicle's database or a cloud database. This correspondence can be stored in a tabular format, a curve-based representation, or other methods for easy retrieval later.

[0088] In this embodiment of the application, an optional implementation of obtaining the empirical estimation model includes: the initial empirical estimation model can be pre-stored in the vehicle's database or a cloud database. When the measuring device on the vehicle needs to estimate the road adhesion coefficient of the road surface where the vehicle is traveling, the measuring device can obtain the initial empirical estimation model from the vehicle's database, or communicate with the cloud server and obtain the initial empirical estimation model from the cloud database (Note: the initial empirical estimation model here is an empirical estimation model without specific hyperparameters assigned). Then, the measuring device can identify the type of the road surface where the vehicle is traveling, determine the type of the road surface, and obtain the corresponding hyperparameters from the database or cloud database according to the type of the road surface. Finally, the hyperparameters can be substituted into the obtained initial empirical estimation model to obtain the final empirical estimation model corresponding to the type of road surface.

[0089] Optionally, the above method for obtaining hyperparameters includes: the measuring device can obtain the hyperparameters corresponding to the type of driving road surface by querying a list of standard hyperparameters pre-stored in a database or cloud database, wherein the list of standard hyperparameters (for example, see...) Figure 2A The list shown records the correspondence between different pavement types and hyperparameters. For example, it lists the correspondence between dry asphalt pavement, wet asphalt pavement, dry cobblestone pavement, wet cobblestone pavement, dry cement pavement, snow pavement, ice pavement, and their respective hyperparameters. The standard hyperparameter list also records the values ​​of the hyperparameters corresponding to different pavement types for easy reference later. It should be noted that... Figure 2A The road surface types and hyperparameters recorded are merely illustrative examples and are not intended to limit the types and hyperparameters.

[0090] Alternatively, another way to obtain the empirical estimation model includes: when the measuring device on the vehicle needs to estimate the road adhesion coefficient of the road surface where the vehicle is traveling, the measuring device can first identify the type of road surface where the vehicle is traveling, determine the type of road surface, and then obtain the empirical model from a database or cloud database. A list of curves, and from that experience Extracting experience from the curve list corresponding to the type of road surface. The curve, and finally the extracted experience The curve serves as an empirical estimation model corresponding to the type of road surface the vehicle is traveling on. For example, see... Figure 2B The experience shown The diagram illustrates the curves, including empirical data corresponding to different road surface types. Curves, and each experience The curve includes the relationship between the adhesion coefficient and the slip ratio. It should be noted that... Figure 2B The empirical curves for various road surface types recorded are merely illustrative examples and not empirical data on road surface types. Curve constraints.

[0091] S202, Obtain the real-time estimation model corresponding to the preset time period of vehicle driving on the road surface.

[0092] The real-time estimation model is used to characterize the relationship between the coefficient of adhesion and the slip ratio, determined by the vehicle's dynamic performance. For example, the real-time estimation model can be a model that utilizes vehicle dynamics to determine the coefficient of adhesion versus slip ratio. Curve, therefore The curve can utilize the correlation between the adhesion coefficient and the slip ratio, where the slip ratio includes the slip ratio at each moment within a preset time period when the vehicle is traveling on the road surface. The preset time period can be determined according to actual measurement needs; for example, the preset time period can include different time periods such as 15 seconds, 30 seconds, and 1 minute.

[0093] In this embodiment, when the measuring device on the vehicle needs to estimate the road surface adhesion coefficient of the driving surface where the vehicle is located, the measuring device can obtain an adhesion coefficient calculation model for calculating the utilization adhesion coefficient and a slip ratio calculation model for estimating the slip ratio between the tires and the ground on the driving surface where the vehicle is currently driving. Then, the measuring device can acquire the perception data of various types of sensors on the vehicle in real time within a preset time period, and substitute these perception data into the slip ratio calculation model and the adhesion coefficient calculation model respectively to calculate the slip ratio and the utilization adhesion coefficient, so as to obtain the slip ratio between the tires and the ground and the utilization adhesion coefficient of the vehicle driving on the current driving surface within the preset time period. Finally, based on the calculated slip ratio and the utilization adhesion coefficient, and the corresponding relationship between the calculated utilization adhesion coefficient and the slip ratio, a real-time estimation model corresponding to the vehicle driving on the driving surface for a preset time period is obtained. The real-time estimation model obtained here is used to estimate the utilization adhesion coefficient of the vehicle driving on the driving surface for a preset time period.

[0094] S203, determine the road adhesion coefficient corresponding to the driving road surface based on the real-time estimation model and the empirical estimation model.

[0095] The road surface adhesion coefficient refers to the friction coefficient between the tire and the road surface, which is the ratio of the adhesion force to the wheel's normal (perpendicular to the road surface) pressure. The target estimation model is used to estimate the friction coefficient between the vehicle's tires and the road surface, i.e., the road surface adhesion coefficient, during a preset time period of driving on the road surface. The target estimation model can be a modified empirical estimation model or a modified real-time estimation model. The target estimation model utilizes the correspondence between the adhesion coefficient and the slip ratio.

[0096] In this embodiment, when the measuring device obtains the real-time estimation model and the empirical estimation model based on the aforementioned steps, it can first obtain the slip ratio between the vehicle tires and the ground during a preset time period of vehicle travel on the road surface, and substitute these slip ratios into the real-time estimation model to calculate the real-time utilization adhesion coefficient of the road surface during the preset time period of vehicle travel on the road surface; then, it obtains the experimental utilization adhesion coefficient of the road surface based on the empirical estimation model; finally, it analyzes and processes the real-time utilization adhesion coefficient and the experimental utilization adhesion coefficient to obtain the road surface adhesion coefficient of the road surface; the above analysis and processing method may include: optionally, the measuring device may first determine the intermediate value of the real-time utilization adhesion coefficient and the experimental utilization adhesion coefficient, and then obtain the road surface adhesion coefficient of the road surface based on the intermediate value; optionally, the measuring device may use the real-time utilization adhesion coefficient to correct the experimental utilization adhesion coefficient, and then obtain the road surface adhesion coefficient of the road surface based on the corrected utilization adhesion coefficient; optionally, the measuring device may also use the experimental utilization adhesion coefficient to correct the real-time utilization adhesion coefficient, and then obtain the road surface adhesion coefficient of the road surface based on the corrected utilization adhesion coefficient.

[0097] The method for determining the road surface adhesion coefficient described in the above embodiments obtains an empirical estimation model corresponding to the type of road surface where the vehicle is traveling, and a real-time estimation model corresponding to the vehicle's travel time on the road surface for a preset period of time. Based on the real-time estimation model and the empirical estimation model, the road surface adhesion coefficient corresponding to the road surface is determined. The empirical estimation model characterizes the relationship between the utilization adhesion coefficient and the slip ratio determined by experimental data; the real-time estimation model characterizes the relationship between the utilization adhesion coefficient and the slip ratio determined by the vehicle's dynamic performance. In this method, since the empirical estimation model can characterize the utilization adhesion coefficient for various road surface types, and the real-time estimation model can characterize the utilization adhesion coefficient under the vehicle's real-time dynamic state, the method combines the empirical and real-time estimation models to estimate the road surface adhesion coefficient of the vehicle's travel surface. This approach considers not only the road surface type but also the vehicle's real-time dynamic performance, thus improving the accuracy of the road surface adhesion coefficient estimation. Furthermore, in practical applications, vehicles are rarely in a slipping state under normal driving conditions, and their slip ratio is very small. Therefore, the real-time estimation model determined by the vehicle's dynamic performance cannot obtain the slip ratio peak or is difficult to obtain the slip ratio peak, resulting in the inability to accurately determine the road adhesion coefficient of the vehicle's current driving surface using the slip ratio peak. However, the real-time estimation model can represent the objective situation of the vehicle's wheels and the road surface in real time to a certain extent. Therefore, the embodiments of this application determine the road adhesion coefficient by fusing the real-time estimation model and the empirical estimation model, which can overcome the problem of not being able to accurately determine the road adhesion coefficient of the vehicle's current driving surface using the slip ratio peak, and can realize the real-time determination of the vehicle's road adhesion coefficient.

[0098] In some exemplary embodiments, a method for determining the road surface adhesion coefficient based on the above-described real-time estimation model and empirical estimation model is provided, such as... Figure 3 As shown, this implementation method includes:

[0099] S301, fuses the real-time estimation model and the empirical estimation model to determine the target estimation model.

[0100] In this embodiment of the application, when the measuring device acquires a real-time estimation model and an empirical estimation model, one optional fusion method is to use the real-time estimation model to modify the empirical estimation model and use the modified empirical estimation model as the target estimation model; another optional fusion method is to use the empirical estimation model to modify the real-time estimation model and use the modified real-time estimation model as the target estimation model. For example, see... Figure 3A The model diagram shown is as follows: L1 corresponds to the empirical estimation model; L2 corresponds to the real-time estimation model; and L3 corresponds to the target estimation model.

[0101] S302, determine the road surface adhesion coefficient corresponding to the driving road surface based on the target estimation model.

[0102] In this embodiment of the application, when the measuring device obtains the target estimation model based on the aforementioned steps, it can first obtain the slip ratio between the vehicle tires and the ground during a preset time period when the vehicle is driving on the road surface, and substitute these slip ratios into the target estimation model to calculate the utilization adhesion coefficient of the road surface during the preset time period when the vehicle is driving on the road surface. Then, it can select the utilization adhesion coefficient corresponding to the vehicle in the slipping state from the utilization adhesion coefficients within the preset time period, or select the utilization adhesion coefficient of the slip ratio peak point as the road surface adhesion coefficient corresponding to the road surface.

[0103] The method for determining the road adhesion coefficient described in the above embodiments can simultaneously consider the road type on which the vehicle is traveling and the real-time dynamic performance of the vehicle to estimate the road adhesion coefficient because the empirical estimation model can characterize the utilization adhesion coefficient of various road types and the real-time estimation model can characterize the utilization adhesion coefficient under the real-time dynamic state of the vehicle. Therefore, the target estimation model obtained by fusing the real-time estimation model and the empirical estimation model can improve the estimation accuracy of the road adhesion coefficient.

[0104] In some exemplary embodiments, a method for fusing two models is provided, namely, an implementation of "fusing the real-time estimation model and the empirical estimation model to determine the target estimation model" in S301 above, such as... Figure 4 As shown, this implementation method includes:

[0105] S401, extract the empirical estimation model corresponding to the low slip rate interval from the empirical estimation model as the first intermediate empirical estimation model.

[0106] The low slip ratio interval is consistent with the slip ratio interval in the real-time estimation model. The first intermediate empirical estimation model is used to characterize the correspondence between the adhesion coefficient and the slip ratio determined by experimental data, and includes the correspondence between all slip ratios and the adhesion coefficient in the low slip ratio interval; the first intermediate empirical estimation model is a part of the empirical estimation model, which can also be obtained from the above relationship (1). The difference between it and the empirical estimation model is that the slip ratio is taken as data in the low slip ratio interval.

[0107] In this embodiment of the application, when the measuring device obtains the empirical estimation model, it can first determine the low slip ratio range based on the data of multiple slip ratios included in the real-time estimation model, then extract the utilization adhesion coefficient corresponding to the low slip ratio range from the empirical estimation model, and finally construct the first intermediate empirical estimation model based on the correspondence between the slip ratio included in the low slip ratio range and the above-extracted utilization adhesion coefficient.

[0108] S402, fuse the real-time estimation model and the first intermediate empirical estimation model to determine the target estimation model.

[0109] Both the real-time estimation model and the first intermediate empirical estimation model include the utilization adhesion coefficient corresponding to the low slip ratio zone. The difference between the two is that the real-time estimation model determines the utilization adhesion coefficient corresponding to the low slip ratio based on the vehicle's dynamic performance, while the first intermediate empirical estimation model determines the utilization adhesion coefficient corresponding to the low slip ratio based on experimental data.

[0110] In this embodiment of the application, when the measuring device acquires the real-time estimation model and the first intermediate empirical estimation model, one possible fusion method is to use the real-time estimation model to modify the first intermediate empirical estimation model and use the modified first intermediate empirical estimation model as the target estimation model; another possible fusion method is to use the first intermediate empirical estimation model to modify the real-time estimation model and use the modified real-time estimation model as the target estimation model. For example, see... Figure 4A The model diagram shown illustrates that L11 corresponds to the empirical estimation model and the first intermediate empirical estimation model for the low slip ratio range; L1 corresponds to the empirical estimation model; L2 corresponds to the real-time estimation model; L3 corresponds to the target estimation model; and the slip ratio range [0, 0.2] is the low slip ratio range. It should be noted that... Figure 4A The low slip ratio range in the text is merely an example and is not a definition or limitation of low slip ratio.

[0111] The method for determining the road surface adhesion coefficient described in the above embodiments, since the vehicle's driving state is generally a low slip state, the real-time estimation model can characterize the adhesion coefficient under the vehicle's actual dynamic state. The corresponding first intermediate empirical estimation model for the low slip rate range can also reflect the adhesion coefficient corresponding to the actual road surface type. Therefore, the above method can improve the estimation accuracy of the road surface adhesion coefficient by fusing the real-time estimation model and the first intermediate empirical estimation model to obtain the target estimation model.

[0112] In some exemplary embodiments, a specific method for fusing two models is provided, namely, an implementation of "fusing the real-time estimation model and the first intermediate empirical estimation model to determine the target estimation model" in S402 above, such as... Figure 5 As shown, this implementation method includes:

[0113] S501, determine the first correction parameter based on the real-time estimation model and the first intermediate empirical estimation model.

[0114] Wherein, the first correction parameter represents the correction amount of the adhesion coefficient. The first correction parameter can be a single parameter, which is used to correct multiple adhesion coefficients in the first intermediate empirical estimation model. Optionally, the first correction parameter can also include multiple first correction parameters, and these multiple first correction parameters correspond to multiple adhesion coefficients in the real-time estimation model or to multiple adhesion coefficients in the first intermediate empirical estimation model. Based on this, the multiple first correction parameters are used to correct each corresponding adhesion coefficient in the first intermediate empirical estimation model.

[0115] In this embodiment, the measuring device can obtain the adhesion coefficients corresponding to each slip ratio from the first intermediate empirical estimation model as the experimental adhesion coefficients; and obtain the adhesion coefficients corresponding to each slip ratio from the real-time estimation model as the real-time adhesion coefficients. Then, the real-time adhesion coefficients and the experimental adhesion coefficients are analyzed and processed to obtain a first correction parameter. Optionally, the measuring device can determine the intermediate values ​​of each real-time adhesion coefficient and the corresponding experimental adhesion coefficient as the first correction parameter, thereby obtaining multiple first correction parameters. Optionally, the measuring device can also first determine the intermediate values ​​of each real-time adhesion coefficient and the corresponding experimental adhesion coefficient, i.e., obtain multiple intermediate values, then perform averaging on the multiple intermediate values, and use the intermediate average obtained after averaging as the first correction parameter, thereby obtaining one first correction parameter.

[0116] Optionally, the method for determining the first correction parameter includes: determining a first mean of the coefficient of adhesion for all slip ratios in the first intermediate empirical estimation model, and determining a second mean of the coefficient of adhesion for all slip ratios in the real-time estimation model, and then determining the value of the first correction parameter based on the first mean and the second mean.

[0117] In this embodiment, when the measuring device needs to determine the first correction parameter, it can first extract all the adhesion coefficients from the first intermediate empirical estimation model, and then calculate the first mean of all the adhesion coefficients; then it can extract all the adhesion coefficients from the real-time estimation model, and then calculate the second mean of all the adhesion coefficients. The difference between the first mean and the second mean is then calculated, and the calculated difference is used as the value of the first correction parameter.

[0118] S502, the adhesion coefficients of multiple slip ratios in the first intermediate empirical estimation model are corrected according to the first correction parameter to obtain the corrected adhesion coefficients.

[0119] In this embodiment, when the first correction parameter is a single parameter, the measuring device can use the first correction parameter to correct the adhesion coefficients of multiple slip ratios in the first intermediate empirical estimation model. For example, the first correction parameter can be superimposed on the adhesion coefficient of each slip ratio to obtain the corrected adhesion coefficients. When the first correction parameter includes multiple correction parameters, the measuring device can use the multiple first correction parameters to correct the adhesion coefficients of multiple slip ratios in the first intermediate empirical estimation model respectively. For example, the multiple first correction parameters can be superimposed on the adhesion coefficient of each corresponding slip ratio to obtain the corrected adhesion coefficients. It should be noted that the multiple first correction parameters and the aforementioned multiple adhesion coefficients have a one-to-one correspondence.

[0120] Optionally, when the first correction parameter is determined by the first mean and the second mean in the above embodiments, when the measuring device performs step S502, it can specifically correct each of the adhesion coefficients in the first intermediate empirical estimation model according to the following relationship (2):

[0121] (2);

[0122] in, This indicates the modified utilization of the adhesion coefficient. This indicates the use of adhesion coefficients to represent the slip ratios in the first intermediate empirical estimation model. This represents the first mean. This represents the second mean. In practical applications, when the measuring device obtains the first mean and the second mean, it can compare the first mean and the second mean. If the first mean is greater than the second mean, the first term in the above relation (2) can be used to revise the utilization adhesion coefficient in the first intermediate empirical estimation model to obtain the corrected utilization adhesion coefficient; if the first mean is less than the second mean, the second term in the above relation (2) can be used to revise the utilization adhesion coefficient in the first intermediate empirical estimation model to obtain the corrected utilization adhesion coefficient. Here, it should be noted that when the first mean is equal to the second mean, the first or second term can be used to revise the utilization adhesion coefficient in the first intermediate empirical estimation model to obtain the corrected utilization adhesion coefficient.

[0123] S503, constructs a target estimation model based on the modified multiple adhesion coefficients.

[0124] In this embodiment, when the measuring device obtains multiple corrected adhesion coefficients based on the aforementioned steps, one approach is that the measuring device can construct a target estimation model based on the correspondence between the multiple adhesion coefficients and their corresponding slip ratios; another approach is that the measuring device can perform curve fitting on the multiple adhesion coefficients and their corresponding slip ratios to obtain the fitted empirical value. The curve, and the fitted experience The curve serves as the target estimation model.

[0125] The method for determining the road surface adhesion coefficient described in the above embodiments realizes the method of correcting the first intermediate empirical estimation model using a real-time estimation model, and the target estimation model obtained based on the correction parameters determined by the two models can accurately estimate the road surface adhesion coefficient.

[0126] In some exemplary embodiments, a method is provided for constructing a target estimation model using multiple adhesion coefficients, such as... Figure 6 As shown, the method includes:

[0127] S601, based on the modified low slip ratio estimation model corresponding to the low slip ratio range constructed using multiple adhesion coefficients.

[0128] Among them, the low slip ratio estimation model is used to characterize the correspondence between all slip ratios and multiple adhesion coefficients within the low slip ratio range.

[0129] In this embodiment, when the measuring device obtains multiple corrected adhesion coefficients based on the aforementioned steps, one approach is that the measuring device can construct a low slip ratio estimation model based on the correspondence between the multiple adhesion coefficients and all slip ratios within the corresponding low slip ratio range; another approach is that the measuring device can perform curve fitting on the multiple adhesion coefficients and all slip ratios within the low slip ratio range to obtain the fitted empirical model. The curve, and the fitted experience The curve serves as a low slip rate estimation model. For example, a low slip rate estimation model can be found here. Figure 4A The L33 curve corresponds to the low slip ratio estimation model.

[0130] S602, Determine the target estimation model based on the low slip ratio estimation model and the empirical estimation model.

[0131] The empirical estimation models include models corresponding to low slip ratio ranges and models corresponding to high slip ratio ranges. For example, see... Figure 4A The L11 curve corresponds to the empirical estimation model for the low slip ratio range, and the L12 curve corresponds to the empirical estimation model for the high slip ratio range.

[0132] In this embodiment of the application, when the measuring device obtains a low slip ratio estimation model and an empirical estimation model, one approach is to modify the empirical estimation model and combine the modified empirical estimation model with the low slip ratio estimation model to determine the target estimation model. Another approach is to predict the high slip ratio estimation model by analyzing the adhesion coefficient corresponding to the high slip ratio range in the empirical estimation model, and then combine the high slip ratio estimation model with the low slip ratio estimation model to determine the target estimation model.

[0133] The method for determining the road adhesion coefficient described in the above embodiments fully considers that vehicles are generally in a low slip ratio driving state. Therefore, when determining the target estimation model for estimating the road adhesion coefficient, a low slip ratio estimation model is first constructed, and then the target estimation model is determined by combining the low slip ratio estimation model with an empirical model that includes all slip ratio ranges. This can improve the accuracy of the target estimation model for estimating the road adhesion coefficient.

[0134] In some exemplary embodiments, another specific method for fusing the two models is provided, namely, an implementation of "determining the target estimation model based on the low slip ratio estimation model and the empirical estimation model" in S602 above, such as... Figure 7 As shown, this implementation method includes:

[0135] S701, extract the empirical estimation model corresponding to the high slip rate interval from the empirical estimation model as the second intermediate empirical estimation model.

[0136] The high slip ratio range refers to the slip ratio range outside the low slip ratio range. The second intermediate empirical estimation model is used to characterize the correspondence between the adhesion coefficient and the slip ratio determined by experimental data, and includes the correspondence between all slip ratios and the adhesion coefficient within the high slip ratio range. The second intermediate empirical estimation model is part of the empirical estimation model, and it can also be obtained from the above relationship (1). The difference between it and the empirical estimation model is that the slip ratio is taken from data within the high slip ratio range.

[0137] In this embodiment of the application, when the measuring device obtains the empirical estimation model, it can first determine the low slip ratio range based on the multiple slip ratio data included in the real-time estimation model, and then determine the high slip ratio range based on the slip ratio range and the low slip ratio range included in the empirical estimation model. Then, it can extract the adhesion coefficient corresponding to the high slip ratio range, and finally construct the second intermediate empirical estimation model based on the correspondence between the slip ratio included in the high slip ratio range and the above-extracted adhesion coefficient.

[0138] S702, the second intermediate empirical estimation model is modified to obtain the third intermediate empirical estimation model.

[0139] In this embodiment, the measuring device can first extract multiple slip ratios corresponding to various slip ratios within the high slip ratio range from the second intermediate empirical estimation model, then correct the extracted multiple slip ratios to obtain multiple corrected slip ratios, and finally construct a third intermediate empirical estimation model based on the correspondence between the multiple corrected slip ratios and the aforementioned multiple slip ratios. For example, see [link to relevant documentation]. Figure 4A The L34 curve corresponds to the third intermediate empirical estimation model. It should be noted that the method for correcting the extracted adhesion coefficients can be to perform curve fitting on the multiple adhesion coefficients to generate the corresponding empirical model. Curve, and then that experience The curve is translated so that the translated experience The curve can be compared with the empirical model corresponding to the low slip ratio estimation model. Curve matching, for example, see Figure 4A The schematic diagram shows that curve L11 is the first intermediate empirical estimation model, curve L12 is the second intermediate empirical estimation model, and curve L33 is the low slip ratio estimation model. The curve L12 is moved downward in the vertical direction to form curve L34, which corresponds to the third intermediate empirical estimation model. The curve L34 can be connected to the curve L33, that is, it matches the curve L33.

[0140] S703, construct the target estimation model based on the third intermediate empirical estimation model and the low slip ratio estimation model.

[0141] In this embodiment, when the measuring device obtains a low slip ratio estimation model and a third intermediate empirical estimation model, one method for constructing a target estimation model is as follows: since the low slip ratio estimation model includes the correspondence between all slip ratios and the utilization adhesion coefficient within the low slip ratio range, and the third intermediate empirical estimation model includes the correspondence between all slip ratios and the utilization adhesion coefficient within the high slip ratio range, the measuring device can construct a target estimation model based on the above two relationships. Another method for constructing a target estimation model is to extract the utilization adhesion coefficients corresponding to all slip ratios within the low slip ratio range from the low slip ratio estimation model, and extract the utilization adhesion coefficients corresponding to all slip ratios within the high slip ratio range from the third intermediate empirical estimation model. Then, the measuring device can perform curve fitting on the utilization adhesion coefficients and slip ratios of all slip ratios within the above two ranges to obtain the target estimation model.

[0142] In some exemplary embodiments, a method for revising a second intermediate empirical estimation model is provided, such as... Figure 8 As shown, the method includes:

[0143] S801, determine the second correction parameter based on the first intermediate empirical estimation model and the low slip ratio estimation model.

[0144] The second correction parameter represents the amount of correction applied to the adhesion coefficient. The second correction parameter can be a single parameter, which is used to correct multiple adhesion coefficients in the second intermediate empirical estimation model. Optionally, the second correction parameter can also include multiple second correction parameters, which correspond to multiple adhesion coefficients in the second intermediate empirical estimation model or to multiple adhesion coefficients in the low slip ratio estimation model. In this case, the multiple second correction parameters are used to correct each adhesion coefficient in the second intermediate empirical estimation model.

[0145] In this embodiment, the measuring device can obtain the adhesion coefficients corresponding to each slip ratio from the first intermediate empirical estimation model as the first reference adhesion coefficients; and obtain the adhesion coefficients corresponding to each slip ratio from the low slip ratio estimation model as the second reference adhesion coefficients. Then, the first and second reference adhesion coefficients are analyzed and processed to obtain a second correction parameter. Optionally, the measuring device can determine the intermediate values ​​of each first reference adhesion coefficient and the corresponding second reference adhesion coefficient as the second correction parameter, thereby obtaining multiple second correction parameters. Optionally, the measuring device can also first determine the intermediate values ​​of each first reference adhesion coefficient and the corresponding second reference adhesion coefficient, i.e., obtain multiple intermediate values, then perform averaging on the multiple intermediate values, and use the intermediate average obtained after averaging as the second correction parameter, thereby obtaining one second correction parameter.

[0146] S802, the second intermediate empirical estimation model is modified according to the second correction parameter to obtain the third intermediate empirical estimation model.

[0147] In this embodiment, when the second correction parameter is a single parameter, the measuring device can use the second correction parameter to correct the adhesion coefficients of multiple slip ratios in the second intermediate empirical estimation model. For example, the value of the second correction parameter can be superimposed on the adhesion coefficient of each slip ratio to obtain corrected adhesion coefficients. When the second correction parameter includes multiple correction parameters, the measuring device can use the multiple second correction parameters to correct the adhesion coefficients of multiple slip ratios in the second intermediate empirical estimation model respectively. For example, the values ​​of the multiple second correction parameters can be superimposed on the adhesion coefficient of each corresponding slip ratio to obtain corrected adhesion coefficients. Finally, a third intermediate empirical estimation model is constructed based on the corrected adhesion coefficients and the corresponding slip ratios, or the corrected adhesion coefficients and the corresponding slip ratios are fitted, and the generated model is... The curve serves as the third intermediate empirical estimation model; it should be noted that there is a one-to-one correspondence between the multiple second correction parameters and the aforementioned adhesion coefficients. For example, see... Figure 4A The schematic diagram shows that, based on the first intermediate empirical estimation model (curve L11) and the low slip ratio estimation model (curve L33), the second correction parameter is determined, and then the second intermediate empirical estimation model (curve L12) is corrected based on the second correction parameter to obtain the third intermediate empirical estimation model (curve L34).

[0148] In some exemplary embodiments, this application can also estimate the road surface adhesion coefficient of the road surface where the vehicle is traveling by referring to the initial road surface adhesion coefficient obtained from the national standard. Therefore, the above... Figures 3-8The method in any embodiment further includes: obtaining an initial road adhesion coefficient corresponding to the type of driving road surface; correspondingly, the measuring device performs... Figure 3 In the embodiment, step S302, "determine the road surface adhesion coefficient corresponding to the driving road surface according to the target estimation model", specifically involves the following steps: determining the road surface adhesion coefficient corresponding to the driving road surface based on the target estimation model and the initial road surface adhesion coefficient.

[0149] The initial road surface adhesion coefficient can be macroscopically represented as the road surface adhesion coefficient under the current driving surface where the vehicle is located.

[0150] In this embodiment, after identifying the road surface type of the vehicle's driving surface, the measuring device can obtain the initial road surface adhesion coefficient corresponding to the road surface type from a database or cloud database. Optionally, the measuring device can also determine the road surface adhesion coefficient corresponding to the type of road surface the vehicle is driving surface based on a pre-stored mapping relationship between road surface adhesion coefficients and road surface types, and use the determined road surface adhesion coefficient as the initial road surface adhesion coefficient. The mapping relationship between the road surface adhesion coefficients and road surface types can be recorded in a table, and this table can be pre-stored in a database or cloud database. When it is necessary to determine the initial road surface adhesion coefficient, the table can be directly retrieved from the database or cloud database. For example, see... Figure 9 The table shown records the mapping relationship between road surface adhesion coefficient and road surface type. It should be noted that this table is only an example and does not constitute a limitation on the above method.

[0151] In this embodiment of the application, when the measuring device obtains the target estimation model and the initial road surface adhesion coefficient, it can first use the target estimation model to estimate the road surface adhesion coefficient of the vehicle's driving road surface, obtain the estimated intermediate road surface adhesion coefficient, and then analyze and process the intermediate road surface adhesion coefficient and the initial road surface adhesion coefficient to obtain the road surface adhesion coefficient corresponding to the driving road surface. It should be noted that when analyzing and processing the intermediate road surface adhesion coefficient and the initial road surface adhesion coefficient, one approach is for the measuring device to calculate the average of the intermediate and initial road surface adhesion coefficients and use the calculated average as the road surface adhesion coefficient corresponding to the driving surface. Another approach is for the measuring device to first compare the initial and intermediate road surface adhesion coefficients. If the difference between the initial and intermediate road surface adhesion coefficients is large, the average of the initial and intermediate road surface adhesion coefficients is used as the road surface adhesion coefficient corresponding to the final driving surface. If the difference between the initial and intermediate road surface adhesion coefficients is small, the intermediate road surface adhesion coefficient can be directly used as the road surface adhesion coefficient corresponding to the final driving surface, or the initial road surface adhesion coefficient can be used as the road surface adhesion coefficient corresponding to the final driving surface, or the initial road surface adhesion coefficient can be used to adjust the intermediate road surface adhesion coefficient, and the adjusted intermediate road surface adhesion coefficient can be used as the road surface adhesion coefficient corresponding to the final driving surface. It should be noted that the above determination of whether the difference between two coefficients is a large or small difference can be based on whether the difference is greater than a preset value. If the difference is greater than the preset value, the difference is determined to be relatively large; if the difference is not greater than the preset value, the difference is determined to be small. The preset value can be determined according to the actual judgment requirements.

[0152] In some exemplary embodiments, this application also provides a method for determining the road surface adhesion coefficient corresponding to the driving road surface based on the target estimation model and the initial road surface adhesion coefficient, such as... Figure 10 As shown, the method includes:

[0153] S1001, the maximum utilization adhesion coefficient in the target estimation model is used as the intermediate road surface adhesion coefficient.

[0154] In this embodiment, when the measuring device acquires the target estimation model and the initial road surface adhesion coefficient, the maximum utilization adhesion coefficient in the target estimation model can be used as the intermediate road surface adhesion coefficient. Optionally, if the target estimation model corresponds to a curve, the method for determining the maximum utilization adhesion coefficient in the target estimation model can be to perform a first-order derivative on the curve corresponding to the target estimation model, and determine the utilization adhesion coefficient obtained by the first-order derivative being zero as the intermediate road surface adhesion coefficient. Here, it is explained that the above-mentioned first-order derivative essentially determines the peak value of the curve corresponding to the target estimation model. That is to say, the utilization adhesion coefficient corresponding to the peak value of the curve is the intermediate road surface adhesion coefficient, which is also the utilization adhesion coefficient corresponding to the slip ratio of the vehicle in the "slipping" state, that is, the road surface adhesion coefficient of the driving surface is obtained.

[0155] S1002, perform a weighted summation of the intermediate road surface adhesion coefficient and the initial road surface adhesion coefficient to obtain the road surface adhesion coefficient corresponding to the driving road surface.

[0156] In this embodiment of the application, when the measuring device obtains the intermediate road surface adhesion coefficient and the initial road surface adhesion coefficient based on the aforementioned steps, it can assign corresponding weights to the intermediate road surface adhesion coefficient and the initial road surface adhesion coefficient, and then perform a weighted summation operation on the intermediate road surface adhesion coefficient and the initial road surface adhesion coefficient based on their respective assigned weights to obtain the road surface adhesion coefficient corresponding to the driving road surface; for example, the measuring device can use the following relationship (3) to perform a weighted summation operation on the intermediate road surface adhesion coefficient and the initial road surface adhesion coefficient:

[0157] (3);

[0158] in, This represents the road surface adhesion coefficient corresponding to the driving surface. Indicates the adhesion coefficient of the intermediate road surface; Indicates the initial road surface adhesion coefficient; The weight of the adhesion coefficient of the intermediate road surface; This represents the weight of the initial road surface adhesion coefficient. In practical applications, and It can be determined based on a large number of actual measurements, for example, here. and They can be set to 0.5 respectively.

[0159] In some exemplary embodiments, this application also provides a method for obtaining the initial road surface adhesion coefficient corresponding to the type of driving road surface, such as... Figure 11 As shown, the method includes:

[0160] S1101, based on the type of road surface, look up the corresponding adhesion coefficient range in the vehicle slip adhesion coefficient reference table.

[0161] The vehicle slip adhesion coefficient reference table includes the correspondence between road surface types and road surface adhesion coefficients; optionally, the vehicle slip adhesion coefficient reference table may include road surface adhesion coefficients corresponding to various road surface types, for example, see [link to relevant documentation]. Figure 9 The table shown is a reference table for vehicle slip adhesion coefficients. This reference table can be pre-stored in the vehicle's database or a cloud database for easy retrieval and use.

[0162] In this embodiment of the application, after the measuring device identifies the road surface type of the driving road where the vehicle is located, it can first obtain the above-mentioned vehicle slip adhesion coefficient reference table from the database or cloud database, and then query the vehicle slip adhesion coefficient reference table based on the road surface type to extract the adhesion coefficient interval corresponding to the type of driving road surface. The adhesion coefficient interval includes at least two adhesion coefficients.

[0163] S1102 processes all adhesion coefficients within the adhesion coefficient range to obtain the initial road surface adhesion coefficient.

[0164] In this embodiment of the application, when the measuring device obtains all adhesion coefficients contained within the adhesion coefficient range, one way to process all adhesion coefficients is to perform an average calculation on all adhesion coefficients and determine the average adhesion coefficient obtained after the calculation as the initial road surface adhesion coefficient; another way to process all adhesion coefficients is to first randomly select a number of adhesion coefficients from all adhesion coefficients, perform an average calculation on the number of adhesion coefficients, and determine the average adhesion coefficient obtained after the calculation as the initial road surface adhesion coefficient; yet another way to process all adhesion coefficients is to select the adhesion coefficients at the boundary of the adhesion coefficient range from all adhesion coefficients, i.e., two adhesion coefficients, then perform an average calculation on these two adhesion coefficients, and determine the average adhesion coefficient obtained after the calculation as the initial road surface adhesion coefficient. For example, if the adhesion coefficient range is [a, b], then (a+b) / 2 is used as the initial road surface adhesion coefficient.

[0165] In some exemplary embodiments, this application also provides a method for identifying road surface types, such as... Figure 12 As shown, the method includes:

[0166] S1201, collects road surface images of the driving surface.

[0167] In this embodiment of the application, an image acquisition device, such as a camera or a dashcam, is installed on the vehicle, and the image acquisition device is connected to the measuring device. When the measuring device needs to identify the road surface type, the vehicle can first start the image acquisition device and use the image acquisition device to acquire the road surface image of the road surface on which the vehicle is driving. Then the measuring device can obtain the road surface image from the image acquisition device.

[0168] S1202, input the road surface image into the preset road surface recognition network for recognition, and output the type of the driving road surface.

[0169] The pre-defined road surface recognition network can be a neural network model, and it can be a network pre-trained based on a set of road surface image samples. The pre-defined road surface recognition network is used to identify the type of road surface in the image. It can include a backbone network (such as a vision transformer VIT), fully connected layers, and classification layers. The advantage of the pre-defined road surface recognition network lies in introducing a self-attention mechanism to capture the global dependencies between all blocks in the image, achieving global modeling capabilities. This significantly improves image feature extraction capabilities compared to traditional CNN networks. Furthermore, the network structure simplifies input processing and allows the model to retain spatial information through positional encoding.

[0170] In this embodiment, when the measuring device acquires a road surface image, it can directly input the image into a preset road surface recognition network for road surface type identification. This preset road surface recognition network can output the type of road surface the vehicle is traveling on. It should be noted that the preset road surface recognition network can be pre-trained and pre-stored in the vehicle's database or a cloud database. When the preset road surface recognition network is needed, it can be directly retrieved from the database or cloud database. Optionally, during normal driving, the vehicle can collect road surface images and use these images as training image samples to train the initial road surface recognition network, resulting in a trained preset road surface recognition network that can accurately identify the type of road surface the vehicle is traveling on. Once the preset road surface recognition network is trained, it can be stored in the vehicle's database or a cloud database. When the measuring device needs to use the preset road surface recognition network, it can retrieve it from the database or cloud database. Furthermore, the vehicle can also perform time-interval training and updates on the stored preset road surface recognition network based on real-time acquired road surface images, ensuring that the stored preset road surface recognition network can always accurately identify the type of road surface the vehicle is traveling on.

[0171] In some exemplary embodiments, this application also provides a method for constructing a real-time estimation model based on vehicle dynamics, such as... Figure 13 As shown, the method includes:

[0172] S1301, obtain the longitudinal force and vertical force of the tires of the vehicle during a preset time period of driving on the road surface.

[0173] This application relates to a method for determining the longitudinal force of a vehicle's tires, which can be obtained using the following relationship (4):

[0174] (4);

[0175] in, This indicates the longitudinal force of the tire; This represents the moment of inertia of the vehicle's wheels. This indicates the angular acceleration of the vehicle's tires; This indicates the wheel-end torque of the tire; The effective radius of the tire is represented by the formula (4). In practical applications, when the measuring device needs to obtain the longitudinal force of the tire, it can obtain some of the physical parameters in the above formula (4) from various types of sensors on the vehicle (e.g., tire angular acceleration, tire wheel end torque), or obtain some of the physical parameters in the above formula (4) from the vehicle information (e.g., tire effective radius), or calculate the tire torque and tire effective radius using the vehicle's engine or motor. Then, these physical parameters are substituted into the above formula (4) for calculation to obtain the longitudinal force of the vehicle's tire. The above method realizes the calculation of wheel angular acceleration by differentiating the known moment of inertia of the tire and the measured wheel angular velocity, and combined with the tire torque and tire effective radius calculated by the engine or motor, the real-time longitudinal force Fx of the tire can be obtained using the above formula (4).

[0176] This application also relates to a method for determining the vertical force of a vehicle's tires, which can be obtained using the following relationships (5) and (6):

[0177] (5);

[0178] (6);

[0179] in, Indicates the overall vehicle weight; Indicates unsprung mass; This indicates the distance from the center of gravity to the front axle; Indicates the distance from the center of mass to the rear axle Indicates wheelbase; Indicates wheel track; Indicates the height of the center of mass; This indicates the vehicle's longitudinal acceleration; Indicates the lateral acceleration of the vehicle; , , , This indicates the longitudinal force on the four wheels of the vehicle; Indicates the angular velocity of the wheel; V represents the tire radius; V represents the vehicle's actual speed; and s represents the tire slip ratio.

[0180] S1302, a real-time estimation model is constructed based on the longitudinal and vertical forces of the vehicle's tires.

[0181] In practical applications, the vehicle can calculate the vertical force Fy of the vehicle's tires based on the above relationship (5) and several required physical parameters, and calculate the longitudinal force Fx of the vehicle's tires based on the above relationship (4) and several required physical parameters. Then, the vehicle's real-time utilization adhesion coefficient can be calculated based on the following relationship (7) according to the vertical force Fy and the longitudinal force Fx, and the vehicle's road slip ratio can be calculated based on the above relationship (6). Finally, a real-time estimation model can be constructed based on the calculated vehicle slip ratio and the real-time utilization adhesion coefficient.

[0182] (7);

[0183] in, Fx represents the vehicle's real-time coefficient of adhesion; Fy represents the longitudinal force of the vehicle's tires; Fx represents the vertical force of the vehicle's tires.

[0184] The method described in this application calculates a real-time estimation model of the vehicle by solving the vehicle's dynamic performance. This model can be used to estimate the vehicle's real-time slip ratio using the adhesion coefficient. To a certain extent, it estimates the objective conditions of the road surface where the vehicle is located. This can help correct the empirical estimation model and thus obtain a more accurate road adhesion coefficient.

[0185] In summary, based on all the above embodiments, this application also provides a method for determining the road surface adhesion coefficient, such as... Figure 14 As shown, the method includes:

[0186] S1401 controls the image acquisition device on the vehicle to acquire road surface images of the road surface.

[0187] S1402, input the road surface image into the preset road surface recognition network for recognition, and output the type of the driving road surface.

[0188] S1403, obtain the initial road adhesion coefficient corresponding to the type of driving road surface.

[0189] S1404, obtain the empirical estimation model corresponding to the type of road surface where the vehicle is driving, and extract the empirical estimation model corresponding to the low slip ratio range from the empirical estimation model as the first intermediate empirical estimation model.

[0190] The low slip ratio range is consistent with the slip ratio range in the real-time estimation model.

[0191] S1405, Obtain the real-time estimation model corresponding to the preset time period of vehicle driving on the road surface.

[0192] S1406, Determine the first correction parameter based on the real-time estimation model and the first intermediate empirical estimation model.

[0193] S1407, The adhesion coefficients of multiple slip ratios in the first intermediate empirical estimation model are corrected according to the first correction parameter to obtain the corrected adhesion coefficients.

[0194] S1408, based on the modified low slip ratio estimation model corresponding to the low slip ratio range constructed using the adhesion coefficient.

[0195] S1409, extract the empirical estimation model corresponding to the high slip rate interval from the empirical estimation model as the second intermediate empirical estimation model.

[0196] Among them, the high slip ratio range is the slip ratio region outside the low slip ratio range;

[0197] S1410, Determine the second correction parameter based on the first intermediate empirical estimation model and the low slip ratio estimation model;

[0198] S1411, The second intermediate empirical estimation model is modified according to the second correction parameter to obtain the third intermediate empirical estimation model.

[0199] S1412, construct the target estimation model based on the third intermediate empirical estimation model and the low slip rate estimation model.

[0200] The methods described in each of the above steps have been explained above. For details, please refer to the above explanations, which will not be repeated here.

[0201] The method for determining the road surface adhesion coefficient described in the above embodiments can obtain a preliminary reference adhesion coefficient by recognizing the road surface type where the vehicle is located through image recognition, which helps in vehicle control operations such as control and anti-skid driving. Furthermore, by integrating traditional empirical parameters and real-time vehicle dynamics, it solves the problem of estimating the road surface adhesion coefficient of actual vehicles under non-skid conditions, as well as the problem of road surface adhesion coefficients that sensors cannot detect. This application also has the potential for application in the estimation of adhesion coefficients in the fields of vehicle handling, braking performance, and safety.

[0202] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.

[0203] Based on the same inventive concept, this application also provides a device for determining the road surface adhesion coefficient to implement the method for determining the road surface adhesion coefficient described above. The solution provided by this device is similar to the solution described in the above method. Therefore, the specific limitations of one or more embodiments of the device for determining the road surface adhesion coefficient provided below can be found in the limitations of the method for determining the road surface adhesion coefficient described above, and will not be repeated here.

[0204] In some exemplary embodiments, such as Figure 15 As shown, a device for determining the road surface adhesion coefficient is provided, comprising:

[0205] The first acquisition module 151 is used to acquire an empirical estimation model corresponding to the type of road surface where the vehicle is traveling; the empirical estimation model is used to characterize the correspondence between the adhesion coefficient and the slip ratio determined by experimental data.

[0206] The second acquisition module 152 is used to acquire a real-time estimation model corresponding to a preset time period of driving on the road surface; the real-time estimation model is used to characterize the correspondence between the adhesion coefficient and the slip ratio determined by the dynamic performance of the vehicle.

[0207] The determination module 153 is used to fuse the real-time estimation model and the empirical estimation model to determine the target estimation model, and determine the road surface adhesion coefficient corresponding to the driving road surface based on the target estimation model.

[0208] In some exemplary embodiments, the above-mentioned fusion module includes:

[0209] An extraction unit is used to extract from the empirical estimation model the empirical estimation model corresponding to the low slip rate interval as the first intermediate empirical estimation model; the low slip rate interval is consistent with the slip rate interval where multiple slip rates are located in the real-time estimation model;

[0210] The fusion unit is used to fuse the real-time estimation model and the first intermediate empirical estimation model to determine the target estimation model.

[0211] In some exemplary embodiments, the fusion unit includes:

[0212] A subunit is defined to determine a first correction parameter based on the real-time estimation model and the first intermediate empirical estimation model.

[0213] The correction subunit is used to correct the multiple slip ratios of the first intermediate empirical estimation model based on the first correction parameter, so as to obtain the corrected multiple slip ratios.

[0214] Construct sub-units for building the target estimation model based on the modified multiple adhesion coefficients.

[0215] In some exemplary embodiments, the above-described construction subunit is specifically used to construct a low slip rate estimation model corresponding to the low slip rate interval based on the modified multiple adhesion coefficients; and to determine the target estimation model based on the low slip rate estimation model and the empirical estimation model.

[0216] In some exemplary embodiments, when the above-mentioned construction subunit performs the step of determining the target estimation model based on the low slip ratio estimation model and the empirical estimation model, it is specifically used to extract the empirical estimation model corresponding to the high slip ratio interval from the empirical estimation model as a second intermediate empirical estimation model; modify the second intermediate empirical estimation model to obtain a third intermediate empirical estimation model; and construct the target estimation model based on the third intermediate empirical estimation model and the low slip ratio estimation model; wherein the high slip ratio interval is the slip ratio region outside the low slip ratio interval.

[0217] In some exemplary embodiments, when the first construction subunit performs the step of correcting the second intermediate empirical estimation model to obtain a third intermediate empirical estimation model, it is specifically used to determine a second correction parameter based on the first intermediate empirical estimation model and the low slip ratio estimation model; and to correct the second intermediate empirical estimation model based on the second correction parameter to obtain the third intermediate empirical estimation model.

[0218] In some exemplary embodiments, the aforementioned determining subunit is specifically used to determine a first mean of the slip ratios using the adhesion coefficients in the first intermediate empirical estimation model, and a second mean of the slip ratios using the adhesion coefficients in the real-time estimation model; and to determine the first correction parameter based on the first mean and the second mean.

[0219] In some exemplary embodiments, the above-described device for determining the road surface adhesion coefficient further includes:

[0220] The third acquisition module is used to acquire the initial road adhesion coefficient corresponding to the type of the driving road surface;

[0221] Correspondingly, the aforementioned determining module is specifically used to determine the road surface adhesion coefficient corresponding to the driving road surface based on the target estimation model and the initial road surface adhesion coefficient.

[0222] In some exemplary embodiments, the above-described determining module includes:

[0223] A determining unit is used to take the maximum utilization adhesion coefficient in the target estimation model as the intermediate road surface adhesion coefficient.

[0224] The calculation unit is used to perform a weighted summation calculation on the intermediate road surface adhesion coefficient and the initial road surface adhesion coefficient to obtain the road surface adhesion coefficient corresponding to the driving road surface.

[0225] In some exemplary embodiments, the third acquisition module described above includes:

[0226] The query unit is used to query the corresponding adhesion coefficient range from the vehicle slip adhesion coefficient reference table according to the type of the driving road surface;

[0227] The processing unit is used to process all adhesion coefficients included in the adhesion coefficient range to obtain the initial road surface adhesion coefficient.

[0228] In some exemplary embodiments, the above-described device for determining the road surface adhesion coefficient further includes:

[0229] The acquisition module is used to acquire images of the road surface of the driving road.

[0230] The recognition module is used to input the road surface image into a preset road surface recognition network for recognition and output the type of the driving road surface.

[0231] In some exemplary embodiments, the second acquisition module described above includes:

[0232] The acquisition unit is used to acquire the longitudinal force and vertical force of the tires of the vehicle during a preset time period of driving on the road surface.

[0233] The construction unit is used to construct the real-time estimation model based on the longitudinal and vertical forces of the tires of the vehicle.

[0234] Each module in the aforementioned device for determining the road surface adhesion coefficient can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device, or stored in the memory of a computer device as software, so that the processor can call and execute the corresponding operations of each module.

[0235] In one exemplary embodiment, an in-vehicle device is provided, which may be a terminal, and its internal structure diagram may be as follows. Figure 16 As shown, the vehicle-mounted device includes a processor, memory, input / output interface, communication interface, display unit, and input device. The processor, memory, and input / output interface are connected via a system bus, and the communication interface, display unit, and input device are also connected to the system bus via the input / output interface. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The input / output interface is used for exchanging information between the processor and external devices. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, mobile cellular networks, Near Field Communication (NFC), or other technologies. When the computer program is executed by the processor, it implements a method for determining the road surface adhesion coefficient. The display unit is used to form a visually visible image and can be a display screen, projection device, or virtual reality imaging device. The display screen can be an LCD screen or an e-ink screen. The input device of the vehicle-mounted equipment can be a touch layer covering the display screen, or buttons, trackballs, or touchpads set on the housing of the vehicle-mounted equipment, or external keyboards, touchpads, or mice, etc.

[0236] Those skilled in the art will understand that Figure 16 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0237] In some exemplary embodiments, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to perform the following steps:

[0238] An empirical estimation model corresponding to the type of road surface in which the vehicle is driving is obtained; the empirical estimation model is used to characterize the correspondence between the adhesion coefficient and the slip ratio determined by experimental data.

[0239] Obtain a real-time estimation model corresponding to a preset time period during which the vehicle travels on the road surface; the real-time estimation model is used to characterize the correspondence between the adhesion coefficient and the slip ratio determined by the vehicle's dynamic performance.

[0240] The real-time estimation model and the empirical estimation model are fused to determine the target estimation model, and the road surface adhesion coefficient corresponding to the driving road surface is determined based on the target estimation model.

[0241] In some exemplary embodiments, the processor, when executing a computer program, also performs the following steps:

[0242] An empirical estimation model corresponding to the low slip ratio interval is extracted from the empirical estimation model and used as the first intermediate empirical estimation model; the low slip ratio interval is consistent with the slip ratio interval in which multiple slip ratios are located in the real-time estimation model;

[0243] The real-time estimation model and the first intermediate empirical estimation model are fused to determine the target estimation model.

[0244] In some exemplary embodiments, the processor, when executing a computer program, also performs the following steps:

[0245] Based on the real-time estimation model and the first intermediate empirical estimation model, determine the first correction parameter;

[0246] The adhesion coefficients of multiple slip ratios in the first intermediate empirical estimation model are corrected according to the first correction parameter to obtain the corrected adhesion coefficients.

[0247] The target estimation model is constructed based on the modified multiple adhesion coefficients.

[0248] In some exemplary embodiments, the processor, when executing a computer program, also performs the following steps:

[0249] Based on the modified multiple low slip rate estimation models using the adhesion coefficient, the low slip rate interval is constructed accordingly.

[0250] The target estimation model is determined based on the low slip ratio estimation model and the empirical estimation model.

[0251] In some exemplary embodiments, the processor, when executing a computer program, also performs the following steps:

[0252] The empirical estimation model corresponding to the high slip ratio interval is extracted from the empirical estimation model as the second intermediate empirical estimation model; the high slip ratio interval is the slip ratio region other than the low slip ratio interval;

[0253] The second intermediate empirical estimation model is modified to obtain the third intermediate empirical estimation model;

[0254] The target estimation model is constructed based on the third intermediate empirical estimation model and the low slip ratio estimation model.

[0255] In some exemplary embodiments, the processor, when executing a computer program, also performs the following steps:

[0256] The second correction parameter is determined based on the first intermediate empirical estimation model and the low slip ratio estimation model;

[0257] The second intermediate empirical estimation model is modified according to the second modification parameter to obtain the third intermediate empirical estimation model.

[0258] In some exemplary embodiments, the processor, when executing a computer program, also performs the following steps:

[0259] Determine the first mean of the adhesion coefficients for all slip ratios in the first intermediate empirical estimation model, and the second mean of the adhesion coefficients for all slip ratios in the real-time estimation model;

[0260] The first correction parameter is determined based on the first mean and the second mean.

[0261] In some exemplary embodiments, the processor, when executing a computer program, also performs the following steps:

[0262] Obtain the initial road adhesion coefficient corresponding to the type of the driving road surface;

[0263] Determining the road surface adhesion coefficient corresponding to the driving surface based on the target estimation model includes:

[0264] Based on the target estimation model and the initial road surface adhesion coefficient, the road surface adhesion coefficient corresponding to the driving road surface is determined.

[0265] In some exemplary embodiments, the processor, when executing a computer program, also performs the following steps:

[0266] The maximum utilization adhesion coefficient in the target estimation model is used as the intermediate road surface adhesion coefficient.

[0267] The road surface adhesion coefficient corresponding to the driving road surface is obtained by performing a weighted summation operation on the intermediate road surface adhesion coefficient and the initial road surface adhesion coefficient.

[0268] In some exemplary embodiments, the processor, when executing a computer program, also performs the following steps:

[0269] Based on the type of road surface, look up the corresponding adhesion coefficient range from the vehicle slip adhesion coefficient reference table;

[0270] The initial road surface adhesion coefficient is obtained by processing all adhesion coefficients included in the adhesion coefficient range.

[0271] In some exemplary embodiments, the processor, when executing a computer program, also performs the following steps:

[0272] Acquire images of the road surface on the driving surface;

[0273] The road surface image is input into a preset road surface recognition network for recognition, and the type of the driving road surface is output.

[0274] In some exemplary embodiments, the processor, when executing a computer program, also performs the following steps:

[0275] The longitudinal force and vertical force of the tires of the vehicle are obtained during a preset time period when the vehicle is traveling on the road surface.

[0276] The real-time estimation model is constructed based on the longitudinal and vertical forces of the vehicle's tires.

[0277] In some exemplary embodiments, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, performs the following steps:

[0278] An empirical estimation model corresponding to the type of road surface in which the vehicle is driving is obtained; the empirical estimation model is used to characterize the correspondence between the adhesion coefficient and the slip ratio determined by experimental data.

[0279] Obtain a real-time estimation model corresponding to a preset time period during which the vehicle travels on the road surface; the real-time estimation model is used to characterize the correspondence between the adhesion coefficient and the slip ratio determined by the vehicle's dynamic performance.

[0280] The real-time estimation model and the empirical estimation model are fused to determine the target estimation model, and the road surface adhesion coefficient corresponding to the driving road surface is determined based on the target estimation model.

[0281] In some exemplary embodiments, when the computer program is executed by the processor, it further performs the following steps:

[0282] An empirical estimation model corresponding to the low slip ratio interval is extracted from the empirical estimation model and used as the first intermediate empirical estimation model; the low slip ratio interval is consistent with the slip ratio interval in which multiple slip ratios are located in the real-time estimation model;

[0283] The real-time estimation model and the first intermediate empirical estimation model are fused to determine the target estimation model.

[0284] In some exemplary embodiments, when the computer program is executed by the processor, it further performs the following steps:

[0285] Based on the real-time estimation model and the first intermediate empirical estimation model, determine the first correction parameter;

[0286] The adhesion coefficients of multiple slip ratios in the first intermediate empirical estimation model are corrected according to the first correction parameter to obtain the corrected adhesion coefficients.

[0287] The target estimation model is constructed based on the modified multiple adhesion coefficients.

[0288] In some exemplary embodiments, when the computer program is executed by the processor, it further performs the following steps:

[0289] Based on the modified multiple low slip rate estimation models using the adhesion coefficient, the low slip rate interval is constructed accordingly.

[0290] The target estimation model is determined based on the low slip ratio estimation model and the empirical estimation model.

[0291] In some exemplary embodiments, when the computer program is executed by the processor, it further performs the following steps:

[0292] The empirical estimation model corresponding to the high slip ratio interval is extracted from the empirical estimation model as the second intermediate empirical estimation model; the high slip ratio interval is the slip ratio region other than the low slip ratio interval;

[0293] The second intermediate empirical estimation model is modified to obtain the third intermediate empirical estimation model;

[0294] The target estimation model is constructed based on the third intermediate empirical estimation model and the low slip ratio estimation model.

[0295] In some exemplary embodiments, when the computer program is executed by the processor, it further performs the following steps:

[0296] The second correction parameter is determined based on the first intermediate empirical estimation model and the low slip ratio estimation model;

[0297] The second intermediate empirical estimation model is modified according to the second modification parameter to obtain the third intermediate empirical estimation model.

[0298] In some exemplary embodiments, when the computer program is executed by the processor, it further performs the following steps:

[0299] Determine the first mean of the adhesion coefficients for all slip ratios in the first intermediate empirical estimation model, and the second mean of the adhesion coefficients for all slip ratios in the real-time estimation model;

[0300] The first correction parameter is determined based on the first mean and the second mean.

[0301] In some exemplary embodiments, when the computer program is executed by the processor, it further performs the following steps:

[0302] Obtain the initial road adhesion coefficient corresponding to the type of the driving road surface;

[0303] Based on the target estimation model and the initial road surface adhesion coefficient, the road surface adhesion coefficient corresponding to the driving road surface is determined.

[0304] In some exemplary embodiments, when the computer program is executed by the processor, it further performs the following steps:

[0305] The maximum utilization adhesion coefficient in the target estimation model is used as the intermediate road surface adhesion coefficient.

[0306] The road surface adhesion coefficient corresponding to the driving road surface is obtained by performing a weighted summation operation on the intermediate road surface adhesion coefficient and the initial road surface adhesion coefficient.

[0307] In some exemplary embodiments, when the computer program is executed by the processor, it further performs the following steps:

[0308] Based on the type of road surface, look up the corresponding adhesion coefficient range from the vehicle slip adhesion coefficient reference table;

[0309] The initial road surface adhesion coefficient is obtained by processing all adhesion coefficients included in the adhesion coefficient range.

[0310] In some exemplary embodiments, when the computer program is executed by the processor, it further performs the following steps:

[0311] Acquire images of the road surface on the driving surface;

[0312] The road surface image is input into a preset road surface recognition network for recognition, and the type of the driving road surface is output.

[0313] In some exemplary embodiments, when the computer program is executed by the processor, it further performs the following steps:

[0314] The longitudinal force and vertical force of the tires of the vehicle are obtained during a preset time period when the vehicle is traveling on the road surface.

[0315] The real-time estimation model is constructed based on the longitudinal and vertical forces of the vehicle's tires.

[0316] In some exemplary embodiments, a computer program product is provided, including a computer program that, when executed by a processor, performs the following steps:

[0317] An empirical estimation model corresponding to the type of road surface in which the vehicle is driving is obtained; the empirical estimation model is used to characterize the correspondence between the adhesion coefficient and the slip ratio determined by experimental data.

[0318] Obtain a real-time estimation model corresponding to a preset time period during which the vehicle travels on the road surface; the real-time estimation model is used to characterize the correspondence between the adhesion coefficient and the slip ratio determined by the vehicle's dynamic performance.

[0319] The real-time estimation model and the empirical estimation model are fused to determine the target estimation model, and the road surface adhesion coefficient corresponding to the driving road surface is determined based on the target estimation model.

[0320] In some exemplary embodiments, when the computer program is executed by the processor, it further performs the following steps:

[0321] An empirical estimation model corresponding to the low slip ratio interval is extracted from the empirical estimation model and used as the first intermediate empirical estimation model; the low slip ratio interval is consistent with the slip ratio interval in which multiple slip ratios are located in the real-time estimation model;

[0322] The real-time estimation model and the first intermediate empirical estimation model are fused to determine the target estimation model.

[0323] In some exemplary embodiments, when the computer program is executed by the processor, it further performs the following steps:

[0324] Based on the real-time estimation model and the first intermediate empirical estimation model, determine the first correction parameter;

[0325] The adhesion coefficients of multiple slip ratios in the first intermediate empirical estimation model are corrected according to the first correction parameter to obtain the corrected adhesion coefficients.

[0326] The target estimation model is constructed based on the modified multiple adhesion coefficients.

[0327] In some exemplary embodiments, when the computer program is executed by the processor, it further performs the following steps:

[0328] Based on the modified multiple low slip rate estimation models using the adhesion coefficient, the low slip rate interval is constructed accordingly.

[0329] The target estimation model is determined based on the low slip ratio estimation model and the empirical estimation model.

[0330] In some exemplary embodiments, when the computer program is executed by the processor, it further performs the following steps:

[0331] The empirical estimation model corresponding to the high slip ratio interval is extracted from the empirical estimation model as the second intermediate empirical estimation model; the high slip ratio interval is the slip ratio region other than the low slip ratio interval;

[0332] The second intermediate empirical estimation model is modified to obtain the third intermediate empirical estimation model;

[0333] The target estimation model is constructed based on the third intermediate empirical estimation model and the low slip ratio estimation model.

[0334] In some exemplary embodiments, when the computer program is executed by the processor, it further performs the following steps:

[0335] The second correction parameter is determined based on the first intermediate empirical estimation model and the low slip ratio estimation model;

[0336] The second intermediate empirical estimation model is modified according to the second modification parameter to obtain the third intermediate empirical estimation model.

[0337] In some exemplary embodiments, when the computer program is executed by the processor, it further performs the following steps:

[0338] Determine the first mean of the adhesion coefficients for all slip ratios in the first intermediate empirical estimation model, and the second mean of the adhesion coefficients for all slip ratios in the real-time estimation model;

[0339] The first correction parameter is determined based on the first mean and the second mean.

[0340] In some exemplary embodiments, when the computer program is executed by the processor, it further performs the following steps:

[0341] Obtain the initial road adhesion coefficient corresponding to the type of the driving road surface;

[0342] Determining the road surface adhesion coefficient corresponding to the driving surface based on the target estimation model includes:

[0343] Based on the target estimation model and the initial road surface adhesion coefficient, the road surface adhesion coefficient corresponding to the driving road surface is determined.

[0344] In some exemplary embodiments, when the computer program is executed by the processor, it further performs the following steps:

[0345] The maximum utilization adhesion coefficient in the target estimation model is used as the intermediate road surface adhesion coefficient.

[0346] The road surface adhesion coefficient corresponding to the driving road surface is obtained by performing a weighted summation operation on the intermediate road surface adhesion coefficient and the initial road surface adhesion coefficient.

[0347] In some exemplary embodiments, when the computer program is executed by the processor, it further performs the following steps:

[0348] Based on the type of road surface, look up the corresponding adhesion coefficient range from the vehicle slip adhesion coefficient reference table;

[0349] The initial road surface adhesion coefficient is obtained by processing all adhesion coefficients included in the adhesion coefficient range.

[0350] In some exemplary embodiments, when the computer program is executed by the processor, it further performs the following steps:

[0351] Acquire images of the road surface on the driving surface;

[0352] The road surface image is input into a preset road surface recognition network for recognition, and the type of the driving road surface is output.

[0353] In some exemplary embodiments, when the computer program is executed by the processor, it further performs the following steps:

[0354] The longitudinal force and vertical force of the tires of the vehicle are obtained during a preset time period when the vehicle is traveling on the road surface.

[0355] The real-time estimation model is constructed based on the longitudinal and vertical forces of the vehicle's tires.

[0356] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, artificial intelligence (AI) processors, etc., and are not limited to these.

[0357] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0358] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A method for determining the road surface adhesion coefficient, characterized in that, The method includes: An empirical estimation model corresponding to the type of road surface in which the vehicle is driving is obtained; the empirical estimation model is used to characterize the correspondence between the adhesion coefficient and the slip ratio determined by experimental data. Obtain a real-time estimation model corresponding to a preset time period during which the vehicle travels on the road surface; the real-time estimation model is used to characterize the correspondence between the adhesion coefficient and the slip ratio determined by the vehicle's dynamic performance. The road surface adhesion coefficient corresponding to the driving surface is determined based on the real-time estimation model and the empirical estimation model. The step of determining the road surface adhesion coefficient corresponding to the driving surface based on the real-time estimation model and the empirical estimation model includes: An empirical estimation model corresponding to the low slip ratio interval is extracted from the empirical estimation model and used as the first intermediate empirical estimation model; the low slip ratio interval is consistent with the slip ratio interval in which multiple slip ratios are located in the real-time estimation model; The real-time estimation model and the first intermediate empirical estimation model are fused to determine the target estimation model; The road surface adhesion coefficient corresponding to the driving road surface is determined based on the target estimation model. The step of fusing the real-time estimation model and the first intermediate empirical estimation model to determine the target estimation model includes: Based on the real-time estimation model and the first intermediate empirical estimation model, determine the first correction parameter; The adhesion coefficients of multiple slip ratios in the first intermediate empirical estimation model are corrected according to the first correction parameter to obtain the corrected adhesion coefficients. The target estimation model is constructed based on the modified multiple adhesion coefficients.

2. The method according to claim 1, characterized in that, The step of constructing the target estimation model based on the modified multiple adhesion coefficients includes: Based on the modified multiple low slip rate estimation models using the adhesion coefficient, the low slip rate interval is constructed accordingly. The empirical estimation model corresponding to the high slip ratio range is extracted from the empirical estimation model as the second intermediate empirical estimation model; the high slip ratio range is the slip ratio region other than the low slip ratio range; The second correction parameter is determined based on the first intermediate empirical estimation model and the low slip ratio estimation model; The second intermediate empirical estimation model is modified according to the second modification parameter to obtain the third intermediate empirical estimation model; The target estimation model is constructed based on the third intermediate empirical estimation model and the low slip ratio estimation model.

3. The method according to claim 1, characterized in that, The step of determining the first correction parameter based on the real-time estimation model and the first intermediate empirical estimation model includes: Determine the first mean of the adhesion coefficients for all slip ratios in the first intermediate empirical estimation model, and the second mean of the adhesion coefficients for all slip ratios in the real-time estimation model; The first correction parameter is determined based on the first mean and the second mean.

4. The method according to any one of claims 1-3, characterized in that, The method further includes: Obtain the initial road adhesion coefficient corresponding to the type of the driving road surface; Determining the road surface adhesion coefficient corresponding to the driving surface based on the target estimation model includes: The maximum utilization adhesion coefficient in the target estimation model is used as the intermediate road surface adhesion coefficient. The road surface adhesion coefficient corresponding to the driving road surface is obtained by performing a weighted summation operation on the intermediate road surface adhesion coefficient and the initial road surface adhesion coefficient.

5. A device for determining the road surface adhesion coefficient, characterized in that, The device includes: The first acquisition module is used to acquire an empirical estimation model corresponding to the type of road surface where the vehicle is driving; the empirical estimation model is used to characterize the correspondence between the adhesion coefficient and the slip ratio determined by experimental data. The second acquisition module is used to acquire a real-time estimation model corresponding to a preset time period during which the vehicle travels on the road surface; the real-time estimation model is used to characterize the correspondence between the adhesion coefficient and the slip ratio determined by the dynamic performance of the vehicle. The determination module is used to fuse the real-time estimation model and the empirical estimation model to determine the target estimation model, and determine the road surface adhesion coefficient corresponding to the driving road surface based on the target estimation model; Specifically, the determination module is used for: An empirical estimation model corresponding to the low slip ratio interval is extracted from the empirical estimation model and used as the first intermediate empirical estimation model; the low slip ratio interval is consistent with the slip ratio interval in which multiple slip ratios are located in the real-time estimation model; The real-time estimation model and the first intermediate empirical estimation model are fused to determine the target estimation model; The road surface adhesion coefficient corresponding to the driving road surface is determined based on the target estimation model. Specifically, the determination module is used for: Based on the real-time estimation model and the first intermediate empirical estimation model, determine the first correction parameter; The adhesion coefficients of multiple slip ratios in the first intermediate empirical estimation model are corrected according to the first correction parameter to obtain the corrected adhesion coefficients. The target estimation model is constructed based on the modified multiple adhesion coefficients.

6. An in-vehicle device, comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 4.

7. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 4.

8. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 4.

Images