Road surface recognition method and device, medium and vehicle

Abstract

The invention provides a road surface recognition method, electronic equipment, a medium and a vehicle. The road surface recognition method is applied to a multi-motor driven vehicle and comprises the following steps: acquiring a wheel speed signal of a wheel directly driven by each motor; obtaining frequency domain characteristics of each wheel speed signal; and obtaining a road surface identification result based on the frequency domain feature of each wheel speed signal and a pre-established road surface discrimination rule. Through the identification method, different types of pavements can be accurately identified.

Description

Technical Field

[0001] The present application relates to the field of vehicles, and more specifically to a road surface recognition method, device, medium and vehicle. Background Art

[0002] In related technologies, the current road adhesion coefficient μ is calculated by collecting the driving torque, wheel speed and yaw, roll, pitch and other angle signals from the inertial measurement unit (IMU) using a dynamic model, and the current road type is determined by the road adhesion coefficient range. However, the difficulty in determining the road type by the road adhesion coefficient μ value is that the range of different road adhesion coefficient μ values ​​overlaps greatly. For example, the road adhesion coefficient μ values ​​for snow, mud, sand and other roads all fluctuate within the range of 0.2-0.5, so it is difficult to accurately distinguish different road surfaces based only on the adhesion coefficient μ value. Summary of the invention

[0003] The present application is proposed in view of the above problems. The present application provides a road surface recognition method, device, medium and vehicle, which can accurately recognize different types of road surfaces.

[0004] According to a first aspect of the present application, a road surface recognition method is provided, which is applied to a multi-motor driven vehicle, and the road surface recognition method comprises:

[0005] Obtain wheel speed signals of wheels directly driven by each motor;

[0006] Obtaining frequency domain characteristics of each wheel speed signal;

[0007] A road surface recognition result is obtained based on the frequency domain characteristics of each wheel speed signal and a pre-established road surface recognition rule.

[0008] In one embodiment of the present application, the road surface recognition method further includes:

[0009] Acquiring dynamic parameters of the multi-motor driven vehicle;

[0010] Calculating the adhesion coefficient of the road surface based on the dynamic parameters;

[0011] The validity of the road surface recognition result is determined based on the adhesion coefficient.

[0012] In one embodiment of the present application, determining the validity of the road surface recognition result based on the adhesion coefficient includes:

[0013] Determining an adhesion coefficient value interval corresponding to the identified road surface according to the road surface recognition result;

[0014] When the adhesion coefficient falls within the adhesion coefficient value interval, determining that the road surface recognition result is valid;

[0015] When the adhesion coefficient does not fall within the adhesion coefficient value interval, it is determined that the road surface recognition result is invalid, and the road surface recognition is performed after the wheel speed signal of each wheel directly driven by the motor is re-acquired.

[0016] In one embodiment of the present application, obtaining the frequency domain feature of each wheel speed signal includes:

[0017] Performing time-frequency transformation on each of the wheel speed signals to obtain a frequency domain wheel speed signal of each wheel;

[0018] removing the acceleration signal from the frequency domain wheel speed signal;

[0019] Feature extraction is performed on each of the frequency domain wheel speed signals to obtain frequency domain features of each of the wheel speed signals.

[0020] In one embodiment of the present application, feature extraction is performed on each of the frequency domain wheel speed signals, including:

[0021] extracting a vibration peak from each of the frequency domain wheel speed signals;

[0022] Determine the peak frequency of each vibration peak and the number of vibration peaks contained in each of the frequency domain wheel speed signals

[0023] The number of the vibration peaks contained in each of the frequency-domain wheel speed signals and the peak frequency of each of the vibration peaks are used as frequency-domain features of each of the wheel speed signals.

[0024] In one embodiment of the present application, based on the frequency domain characteristics of each wheel speed signal and a pre-established road surface identification rule, a road surface identification result is obtained, including:

[0025] When the number of vibration peaks contained in each of the frequency-domain wheel speed signals is less than or equal to 2, and at least one peak frequency falls within a first preset interval, it is determined that the road surface is muddy;

[0026] When the number of vibration peaks contained in each of the frequency domain wheel speed signals is less than or equal to 3, and at least two peak frequencies fall into the second preset interval and the fourth preset interval respectively, it is determined that the road surface is a sandy grass;

[0027] When the number of vibration peaks contained in each of the frequency-domain wheel speed signals is greater than or equal to 5, and at least three peak frequencies fall into the second preset interval, the third preset interval, and the fourth preset interval respectively, it is determined that the road surface is sandy.

[0028] In one embodiment of the present application, before performing time-frequency transformation on each of the wheel speed signals, the road surface recognition method further includes:

[0029] Data preprocessing is performed on each of the wheel speed signals.

[0030] In one embodiment of the present application, the method of data preprocessing includes:

[0031] Abnormal values ​​and missing values ​​in the wheel speed signal are deleted or replaced.

[0032] In one embodiment of the present application, the wheel speed signal is segmented according to a preset time length.

[0033] According to a second aspect of the present application, an electronic device is provided, comprising a memory and a processor, wherein the memory stores a computer program executed by the processor, and when the computer program is executed by the processor, the device equipped with the processor executes the above-mentioned road surface recognition method.

[0034] According to a third aspect of the present application, a storage medium is provided, on which a computer program is stored. The computer program runs on a computer, and when the computer program is running, the computer executes the above-mentioned road surface recognition method.

[0035] According to a fourth aspect of the present application, a vehicle is provided, comprising the above-mentioned electronic device or the above-mentioned storage medium.

[0036] The road surface recognition method of the present application obtains the frequency domain characteristics of the wheel speed signal, and then performs road surface recognition based on the frequency domain characteristics of each wheel speed signal and pre-established road surface recognition rules, so as to accurately identify different types of road surfaces. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] The above and other purposes, features and advantages of the present invention will become more apparent by describing the embodiments of the present invention in more detail in conjunction with the accompanying drawings. The accompanying drawings are used to provide a further understanding of the embodiments of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings, the same reference numerals generally represent the same components or steps.

[0038] Figure 1 is a schematic block diagram of an electronic device used in the road surface recognition method according to an embodiment of the present invention;

[0039] Figure 2 is a schematic flow chart of a road surface recognition method according to an embodiment of the present application;

[0040] Figure 3is a wheel speed signal diagram on sand according to an embodiment of the present application;

[0041] Figure 4 is a wheel speed signal diagram of a sandy grassland according to an embodiment of the present application;

[0042] Figure 5 is a wheel speed signal diagram for muddy ground according to an embodiment of the present application;

[0043] Figure 6 is a flow chart of road surface identification according to an embodiment of the present application;

[0044] Figure 7 is a schematic flow chart of a road surface recognition method according to another embodiment of the present application;

[0045] Figure 8 is a schematic structural diagram of a vehicle according to an embodiment of the present application;

[0046] Fig. 9 is a schematic structural diagram of a vehicle according to another embodiment of the present application. DETAILED DESCRIPTION

[0047] In order to make the purpose, technical scheme and advantages of the present invention more obvious, the exemplary embodiments according to the present invention will be described in detail with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments of the present invention, and it should be understood that the present invention is not limited to the exemplary embodiments described herein. Based on the embodiments of the present invention described in the present invention, all other embodiments obtained by those skilled in the art without creative work should fall within the protection scope of the present invention.

[0048] In order to solve the problem that the existing road surface recognition method is difficult to accurately distinguish different road surfaces based on the adhesion coefficient μ value, the present application proposes a road surface recognition method, electronic equipment, medium and vehicle, which can effectively identify different types of road surfaces, which are described in detail below.

[0049] First, refer to Figure 1 An exemplary control device 100 for implementing an embodiment of the method of the present invention is described below.

[0050] like Figure 1 As shown, the control device 100 includes a processor 110, a memory 120, and a communication interface 130. The processor 110, the memory 120, and the communication interface 130 can be interconnected and communicated via a communication bus 140 and / or other forms of connection mechanisms (not shown).

[0051] It should be noted that Figure 1The components and structures of the control device 100 shown are merely exemplary and non-limiting. The control device may also have other components and structures as required.

[0052] Optionally, the communication interface 130 may also include a transmitter and / or a receiver.

[0053] The processor 110 can be a microcontroller unit (MCU), a central processing unit (CPU), a digital signal processor (DSP), a single-chip microcomputer and an embedded device, or other forms of processing units with data processing capabilities and / or instruction execution capabilities, and can control other components in the autonomous driving vehicle system to perform desired functions.

[0054] The memory 120 may be a computer-readable storage medium in various forms, such as a volatile memory and / or a non-volatile memory. The volatile memory may include, for example, a random access memory (RAM), a cache memory, a synchronous dynamic random access memory (SDRAM), etc. The non-volatile memory may include, for example, a read-only memory (ROM), a hard disk, a flash memory, etc. One or more computer program instructions may also be stored on the computer-readable storage medium, and the memory 120 may run the program instructions to implement the road surface recognition method in the embodiment of the present invention described below.

[0055] Next, refer to Figure 2 To describe the road surface recognition method according to an embodiment of the present application.

[0056] like Figure 2 As shown, the present application provides a road surface recognition method, which is applied to a multi-motor driven vehicle, comprising:

[0057] Get the wheel speed signal of each wheel directly driven by the motor.

[0058] The wheel speed signal is a wheel speed signal collected in real time by a wheel speed sensor during vehicle driving. Specifically, the wheel speed sensor can be a magnetoelectric wheel speed sensor or a Hall wheel speed sensor. In this application, the wheel speed signal can be obtained from the wheel speed sensor, or from the vehicle control unit (VCU) or domain controller, such as from an autonomous driving domain controller or a power domain controller. This application does not specifically limit the method for obtaining the wheel speed signal.

[0059] The road surface recognition method in the present application is applied to multi-motor driven vehicles, such as dual-motor driven, triple-motor driven and quad-motor driven vehicles. The wheel speed signal should be the wheel speed signal of the wheel directly driven by the motor. Therefore, the wheel speed signal to be obtained should be the wheel speed signal collected simultaneously from the wheels directly driven by each motor.

[0060] The frequency domain characteristics of each wheel speed signal are obtained.

[0061] Specifically, the method for obtaining the frequency domain features of each wheel speed signal includes performing time-frequency transformation on the wheel speed signal and then extracting the features of the frequency domain signal.

[0062] The road surface recognition result is obtained based on the frequency domain characteristics of each wheel speed signal and the pre-established road surface recognition rules.

[0063] Here, the road surface discrimination rule is determined after statistically analyzing the frequency characteristics of the wheel speed signal under different road surface conditions, and specifically includes a discrimination rule based on the number of vibration peaks, or a discrimination rule based on the frequency of the vibration peaks, and may also include a discrimination rule based on the number and frequency of the vibration peaks. Here, the vibration peak refers to the peak of the frequency domain signal curve after the time domain signal is converted into the frequency domain signal.

[0064] For example, the discrimination rule based on the number of vibration peaks can be to determine the type of road surface according to the number of vibration peaks, and different numbers of vibration peaks correspond to different road surfaces. For another example, the discrimination rule based on the frequency of vibration peaks can be to determine the type of road surface according to the frequency value corresponding to each vibration peak in the frequency domain signal.

[0065] The road surface recognition method of the present application transforms the wheel speed signal into a frequency domain signal through time-frequency transformation, extracts the frequency domain signal features to identify the road surface, thereby accurately extracting the features of the wheel speed signal under the influence of different road surfaces, and then based on the features, can accurately identify different types of road surfaces.

[0066] According to one embodiment of the present application, obtaining the frequency domain features of each wheel speed signal includes:

[0067] Perform time-frequency transformation on each wheel speed signal to obtain the frequency domain wheel speed signal of each wheel;

[0068] Remove the acceleration signal from the frequency domain wheel speed signal;

[0069] Feature extraction is performed on each frequency domain wheel speed signal to obtain the frequency domain features of each wheel speed signal.

[0070] In the present application, the time-frequency transformation method may be Fourier transformation or fast Fourier transformation. Through the time-frequency transformation, the wheel speed signal in the time domain may be transformed into a wheel speed signal in the frequency domain.

[0071] For example, by reading the wheel speed signals of a four-motor chassis and performing Fourier transform on the four-wheel speed signals, vibration curve information representing different road surfaces can be extracted.

[0072] The method for removing the acceleration signal from the frequency domain wheel speed signal may adopt the frequency domain signal filtering method. Specifically, a high-pass filter is used to filter out the low-frequency signal in the frequency domain wheel speed signal, thereby obtaining the frequency domain wheel speed signal of the wheel in uniform motion.

[0073] In the present application, the frequency domain feature may be the number of vibration peaks in the frequency domain wheel speed signal, or the frequency of the vibration peaks, or a combination of the two.

[0074] When the frequency domain feature is the number of vibration peaks in the frequency domain wheel speed signal, the road surface discrimination rule should be a discrimination rule based on the number of vibration peaks; when the frequency domain feature is the frequency of vibration peaks in the frequency domain wheel speed signal, the road surface discrimination rule should be a discrimination rule based on the frequency of vibration peaks.

[0075] By performing time-frequency transformation on the wheel speed signal, the wheel speed signals under the influence of different road surfaces can be distinguished; and then the frequency domain features can be extracted to effectively extract the features of the wheel speed signal under the influence of different road surfaces.

[0076] According to an embodiment of the present application, feature extraction is performed on each frequency domain wheel speed signal, including:

[0077] Extract vibration peaks from each frequency domain wheel speed signal;

[0078] determining the peak frequency of each vibration peak and the number of vibration peaks contained in each frequency domain wheel speed signal;

[0079] The number of vibration peaks contained in each frequency domain wheel speed signal and the peak frequency of each vibration peak are used as the frequency domain features of each wheel speed signal.

[0080] Here, the peak frequency refers to the frequency value of the abscissa corresponding to the vibration peak.

[0081] The following combination Figure 3-5 The feature extraction of wheel speed signals on muddy ground, sandy grass ground and sandy ground according to an embodiment of the present application is described.

[0082] Figure 3 is a wheel speed signal diagram on sand according to an embodiment of the present application, Figure 3(a) is the time domain wheel speed signal of the left front wheel, (c) is the time domain wheel speed signal of the right rear wheel, including the original wheel speed signal before processing and the wheel speed signal after processing to eliminate acceleration; (b) is the frequency domain wheel speed signal of the left front wheel obtained by Fourier transforming the wheel speed signal after eliminating acceleration, (d) is the frequency domain wheel speed signal of the right rear wheel obtained by Fourier transforming the wheel speed signal after eliminating acceleration. The arrows in the figure point to vibration peaks. From (b) and (d), it can be seen that the frequency domain signal of the sand includes 7 prominent vibration peaks, and the frequencies of the vibration peaks include 1.67, 5.44, and 11.24.

[0083] Figure 4 is a wheel speed signal diagram of a sandy grassland according to an embodiment of the present application, Figure 4 (a) is the time domain wheel speed signal of the left front wheel, (c) is the time domain wheel speed signal of the right rear wheel, (b) is the frequency domain wheel speed signal of the left front wheel obtained after Fourier transform, and (d) is the frequency domain wheel speed signal of the right rear wheel obtained after Fourier transform. From (b) and (d), it can be seen that the frequency domain signal of the sandy grassland includes three prominent vibration peaks, and the frequencies of the vibration peaks are 1.86, 12.23, and 38.75 respectively.

[0084] Figure 5 is a wheel speed signal diagram for muddy ground according to an embodiment of the present application, Figure 5 (a) is the time domain wheel speed signal of the left front wheel, (c) is the time domain wheel speed signal of the right rear wheel, (b) is the frequency domain wheel speed signal of the left front wheel obtained after Fourier transform, and (d) is the frequency domain wheel speed signal of the right rear wheel obtained after Fourier transform. It can be seen from (b) and (d) that the frequency domain signal of the mud includes a prominent vibration peak with a frequency of 0.432.

[0085] It should be noted that Figure 3-5 Only the time domain and frequency domain wheel speed signals of the left front wheel and the right rear wheel are shown as examples, and the time domain and frequency domain wheel speed signals of the wheels directly driven by other motors are basically the same as those of the left front wheel and the right rear wheel. When the four wheels of the vehicle are traveling on the same road surface, the wheel speed signals of different wheels will not differ greatly due to the different positions of the wheels, and after processing the wheel speed signals of different wheels using the feature extraction method of the present application, a consistent curve can be obtained, that is, the frequency domain features of the wheel speed signals are the same, so the curve can be used as a characteristic curve of the wheel speed signal, and the characteristic peaks reflected in the curve can be used to distinguish the road surface.

[0086] According to an embodiment of the present application, based on the frequency domain characteristics of each wheel speed signal and a pre-established road surface identification rule, a road surface identification result is obtained, including:

[0087] When the number of vibration peaks contained in each frequency domain wheel speed signal is less than or equal to 2, and at least one peak frequency falls into the first preset interval, it is determined that the road surface is muddy, that is, the road surface recognition result is muddy. Specifically, the first preset interval is (0.4, 0.5);

[0088] When the number of vibration peaks contained in each frequency domain wheel speed signal is less than or equal to 3, and at least two peak frequencies fall into the second preset interval and the fourth preset interval respectively, the road surface is determined to be sandy grassland, that is, the road surface recognition result is sandy grassland. Specifically, the second preset interval is (1.7, 2.0), and the fourth preset interval is (11, 13);

[0089] When the number of vibration peaks contained in each frequency domain wheel speed signal is greater than or equal to 5, and at least three peak frequencies fall into the second preset interval, the third preset interval, and the fourth preset interval respectively, the road type is determined to be sandy, that is, the road recognition result is sandy. Specifically, the third preset interval is (4, 6).

[0090] It should be noted that at least one peak frequency falls within each preset interval.

[0091] For example, when the number of vibration peaks included in each frequency-domain wheel speed signal is greater than or equal to 5, the peak frequencies of at least 3 vibration peaks fall into the second preset interval, the third preset interval, and the fourth preset interval respectively.

[0092] For each wheel directly driven by a motor, the frequency domain characteristics of its wheel speed signal should be the same. Therefore, when the frequency domain characteristics of the wheel speed signal of each wheel directly driven by a motor are the same, the road surface can be identified. When the frequency domain characteristics of the wheel speed signal of each wheel directly driven by a motor are different, the wheel speed signal of each wheel should be re-collected for road surface identification.

[0093] After observing and sorting out a large number of wheel speed signals on sandy grassland, sandy land, and muddy land, it is found that under different road conditions, wheel speed signals will show different frequency domain characteristics. Therefore, before road surface recognition, the road surface discrimination rules are obtained by counting these characteristics. The specific statistical method can adopt the existing method, which will not be elaborated here.

[0094] It should be noted that the road surface recognition method of the present application can also be used to recognize various other road surfaces, such as flooded roads, snowy roads, snowy areas, grass, etc. The present application does not specifically limit the types of road surfaces.

[0095] See below Figure 6 To illustrate the road surface recognition process according to an embodiment of the present application.

[0096] In this embodiment, the vehicle is a four-motor driven vehicle, so the acquired wheel speed signals are wheel speed signals of the four wheels.

[0097] First, filter the original wheel speed signal curves of the four wheels to obtain the wheel speed signals in the frequency domain, also called wheel speed vibration signals, which are T1 wheel speed vibration signal, T2 wheel speed vibration signal, T3 wheel speed vibration signal, and T4 wheel speed vibration signal. Perform Fourier transform on the vibration signal to obtain the characteristic vibration frequencies of the four wheels on different road surfaces: T1 characteristic vibration frequency, T2 characteristic vibration frequency, T3 characteristic vibration frequency, and T4 characteristic vibration frequency. Classify and analyze the vibration frequencies of the four wheels to determine the interval to which the vibration frequencies belong, so that the road surface can be identified according to the road surface discrimination rules, such as grass, sand, mud, etc.

[0098] It should be noted that when the wheel speed signals of the four wheels are judged and the road surfaces are judged to be the same, the judged road surface is used as the road surface recognition result; when the wheel speed signals of the four wheels are judged and the road surfaces are judged to be different, the wheel speed signals can be collected again for road surface recognition.

[0099] Road surface recognition based on road surface discrimination rules not only has a simple algorithm and is easy to implement, but also has a high road surface recognition accuracy.

[0100] According to one embodiment of the present application, the road surface recognition method further includes:

[0101] Obtain dynamic parameters of multi-motor driven vehicles;

[0102] Calculate the adhesion coefficient of the road surface based on the dynamic parameters;

[0103] The validity of the road surface recognition results is determined based on the adhesion coefficient.

[0104] Here, the dynamic parameters of the vehicle include but are not limited to driving torque, wheel speed, roll angle and pitch angle of the vehicle. The adhesion coefficient μ of the road surface is the ratio of adhesion to wheel normal pressure, which can be calculated using the dynamic model in the existing method and will not be elaborated in this application.

[0105] In a specific implementation, the adhesion coefficient of the road surface is calculated by a dynamic calculation module of the vehicle, and the validity of the road surface recognition result is determined based on the adhesion coefficient, including:

[0106] Determine the adhesion coefficient value interval corresponding to the identified road surface according to the road surface recognition result;

[0107] When the adhesion coefficient falls within the adhesion coefficient value range, it is determined that the road surface recognition result is valid;

[0108] When the adhesion coefficient does not fall within the adhesion coefficient value interval, it is determined that the road surface recognition result is invalid, and the road surface recognition is performed after the wheel speed signal of each wheel directly driven by the motor is re-acquired.

[0109] The following combination Figure 7 The process of determining the validity of the road surface recognition result based on the adhesion coefficient in a specific implementation is specifically described, and the process includes:

[0110] Collect wheel speed signals of the four wheels in a four-motor drive vehicle.

[0111] Obtain the dynamic parameters of the four-motor drive vehicle.

[0112] The road adhesion coefficient is calculated based on the dynamic parameters.

[0113] Get the wheel speed signal of each wheel.

[0114] The four wheel speed signals are filtered respectively and then time-frequency transformed to obtain the frequency domain wheel speed signal.

[0115] The frequency domain features of each wheel speed signal are extracted, and the road surface recognition result is obtained based on the frequency domain features and road surface recognition rules.

[0116] The adhesion coefficient value range corresponding to the identified road surface is determined according to the road surface recognition result. For example, the adhesion coefficient value range of sand is 0.2-0.5.

[0117] When the adhesion coefficient falls within the adhesion coefficient value range, the road surface recognition result is determined to be valid and output. Specifically, the valid road surface recognition result can be output to the vehicle's control system, such as the anti-lock braking system. When the adhesion coefficient does not fall within the adhesion coefficient value range, the road surface recognition result is determined to be invalid, and the wheel speed signals of the four wheels in the four-motor drive vehicle are re-collected for road surface recognition until a valid road surface recognition result is obtained.

[0118] In another specific implementation, the road type can also be determined by the road adhesion coefficient μ value. When the range overlap of different road adhesion coefficient μ values ​​is large, such as the road adhesion coefficient μ values ​​of snow, mud, sand, etc. all fluctuate within the range of 0.2-0.5, multiple types can be obtained when the current road type is determined by the road adhesion coefficient size range; the road surface determined based on the frequency domain characteristics can further determine the final road type, thereby obtaining the final road recognition result.

[0119] The final road surface recognition results can be used for vehicle control in various systems such as vehicle dynamic control system, vehicle electronic stability program, anti-lock braking system, etc., to improve the control accuracy and stability.

[0120] Through the method of this embodiment, the effectiveness of the road surface recognition result is further judged by the road surface adhesion coefficient μ value, which can not only improve the accuracy of the road surface recognition result, but also be applied to the dynamic road surface recognition system to perform road surface recognition on different road surfaces with highly overlapping adhesion coefficient μ value ranges, thereby improving the dynamic road surface recognition accuracy and effectively solving the problem that the vehicle dynamic road surface recognition module is difficult to judge different road surfaces with the same road surface adhesion coefficient.

[0121] According to an embodiment of the present application, before performing time-frequency transformation on each wheel speed signal, the road surface recognition method further includes: performing data preprocessing on each wheel speed signal.

[0122] Specifically, the data preprocessing method includes: deleting or replacing abnormal values ​​and missing values ​​in the wheel speed signal.

[0123] In addition, the wheel speed signal in the time domain can be denoised by using the rolling average method.

[0124] The rolling mean is the average of the previous observation windows, where a window is a sequence of values ​​from the time series data. The mean is calculated for each ordered window. This can greatly help minimize noise in time series data.

[0125] An embodiment of the present application also provides an electronic device, which includes a memory and a processor, wherein the memory stores a computer program executed by the processor, and when the computer program is executed by the processor, the device equipped with the processor executes the road surface recognition method described in any of the above embodiments.

[0126] An embodiment of the present application further provides a storage medium, on which a computer program is stored. The computer program runs on a computer, and when the computer program is running, the computer executes the road surface recognition method as described in any of the above embodiments.

[0127] An embodiment of the present application also provides a vehicle, comprising the above-mentioned electronic device or the above-mentioned storage medium. Figure 8 A vehicle according to an embodiment of the present application is exemplarily shown, and the vehicle includes an electronic device. Fig. 9 A vehicle according to another embodiment of the present application is exemplarily shown, the vehicle including a storage medium.

[0128] Although example embodiments have been described herein with reference to the accompanying drawings, it should be understood that the above example embodiments are merely exemplary and are not intended to limit the scope of the present invention thereto. Various changes and modifications may be made therein by one of ordinary skill in the art without departing from the scope and spirit of the present invention. All such changes and modifications are intended to be included within the scope of the present invention as required by the appended claims.

[0129] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0130] In the several embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic, for example, the division of the units is only a logical function division, and there may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another device, or some features can be ignored or not executed.

[0131] In the description provided herein, a large number of specific details are described. However, it is understood that embodiments of the present invention can be practiced without these specific details. In some instances, well-known methods, structures and techniques are not shown in detail so as not to obscure the understanding of this description.

[0132] Similarly, it should be understood that in order to streamline the present invention and help understand one or more of the various inventive aspects, in the description of the exemplary embodiments of the present invention, the various features of the present invention are sometimes grouped together into a single embodiment, figure, or description thereof. However, the method of the present invention should not be interpreted as reflecting the following intention: the claimed invention requires more features than the features explicitly stated in each claim. More specifically, as reflected in the corresponding claims, the inventive point is that the corresponding technical problem can be solved with less than all the features of a single disclosed embodiment. Therefore, the claims following the specific embodiment are hereby expressly incorporated into the specific embodiment, wherein each claim itself serves as a separate embodiment of the present invention.

[0133] It will be understood by those skilled in the art that, except for mutually exclusive features, all features disclosed in this specification (including the accompanying claims, abstracts and drawings) and all processes or units of any method or device disclosed in this specification may be combined in any combination. Unless otherwise expressly stated, each feature disclosed in this specification (including the accompanying claims, abstracts and drawings) may be replaced by an alternative feature that provides the same, equivalent or similar purpose.

[0134] In addition, those skilled in the art will appreciate that, although some embodiments described herein include certain features included in other embodiments but not other features, the combination of features of different embodiments is meant to be within the scope of the present invention and form different embodiments. For example, in the claims, any one of the claimed embodiments may be used in any combination.

[0135] The various component embodiments of the present invention may be implemented in hardware, or in software modules running on one or more processors, or in a combination thereof. It should be understood by those skilled in the art that a microprocessor or digital signal processor (DSP) may be used in practice to implement some or all of the functions of some modules in the article analysis device according to an embodiment of the present invention. The present invention may also be implemented as a device program (e.g., a computer program and a computer program product) for executing part or all of the methods described herein. Such a program implementing the present invention may be stored on a computer-readable medium, or may be in the form of one or more signals. Such a signal may be downloaded from an Internet website, or provided on a carrier signal, or provided in any other form.

[0136] It should be noted that the above embodiments illustrate the present invention rather than limit it, and that those skilled in the art may devise alternative embodiments without departing from the scope of the appended claims. In the claims, any reference symbol between brackets shall not be construed as a limitation on the claims. The word "comprising" does not exclude the presence of elements or steps not listed in the claims. The word "one" or "an" preceding an element does not exclude the presence of a plurality of such elements. The present invention may be implemented by means of hardware comprising a number of different elements and by means of a suitably programmed computer. In a unit claim enumerating a number of devices, several of these devices may be embodied by the same hardware item. The use of the words first, second, and third, etc., does not indicate any order. These words may be interpreted as names.

[0137] The above is only a specific embodiment of the present invention or an explanation of a specific embodiment, and the protection scope of the present invention is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. The protection scope of the present invention shall be based on the protection scope of the claims.

Claims

1. A road surface recognition method, characterized in that: Applied to a multi-motor driven vehicle, the road surface recognition method comprises: Obtain wheel speed signals of wheels directly driven by each motor; Obtaining frequency domain characteristics of each wheel speed signal; A road surface recognition result is obtained based on the frequency domain characteristics of each wheel speed signal and a pre-established road surface recognition rule.

2. The road surface recognition method as claimed in claim 1, characterized in that: The road surface recognition method further comprises: Acquiring dynamic parameters of the multi-motor driven vehicle; Calculating the adhesion coefficient of the road surface based on the dynamic parameters; The validity of the road surface recognition result is determined based on the adhesion coefficient.

3. The road surface recognition method as claimed in claim 2, characterized in that: Determining the validity of the road surface recognition result based on the adhesion coefficient includes: Determining an adhesion coefficient value interval corresponding to the identified road surface according to the road surface recognition result; When the adhesion coefficient falls within the adhesion coefficient value interval, determining that the road surface recognition result is valid; When the adhesion coefficient does not fall within the adhesion coefficient value interval, it is determined that the road surface recognition result is invalid, and the road surface recognition is performed after the wheel speed signal of each wheel directly driven by the motor is re-acquired.

4. The road surface recognition method as claimed in claim 1, characterized in that: Obtaining the frequency domain characteristics of each wheel speed signal, including: Performing time-frequency transformation on each of the wheel speed signals to obtain a frequency domain wheel speed signal of each wheel; removing the acceleration signal from the frequency domain wheel speed signal; Feature extraction is performed on each of the frequency domain wheel speed signals to obtain frequency domain features of each of the wheel speed signals.

5. The road surface recognition method according to claim 4, characterized in that: Performing feature extraction on each of the frequency domain wheel speed signals respectively includes: extracting a vibration peak from each of the frequency domain wheel speed signals; determining a peak frequency of each vibration peak and a number of vibration peaks contained in each of the frequency domain wheel speed signals; The number of the vibration peaks contained in each of the frequency-domain wheel speed signals and the peak frequency of each of the vibration peaks are used as frequency-domain features of each of the wheel speed signals.

6. The road surface recognition method according to claim 4, characterized in that: Based on the frequency domain characteristics of each wheel speed signal and the pre-established road surface identification rules, a road surface identification result is obtained, including: When the number of vibration peaks contained in each of the frequency-domain wheel speed signals is less than or equal to 2, and at least one peak frequency falls within a first preset interval, it is determined that the road surface is muddy; When the number of vibration peaks contained in each of the frequency domain wheel speed signals is less than or equal to 3, and at least two peak frequencies fall into the second preset interval and the fourth preset interval respectively, it is determined that the road surface is a sandy grass; When the number of vibration peaks contained in each of the frequency-domain wheel speed signals is greater than or equal to 5, and at least three peak frequencies fall into the second preset interval, the third preset interval, and the fourth preset interval respectively, it is determined that the road surface is sandy.

7. The road surface recognition method according to any one of claims 4 to 6, characterized in that: Before performing time-frequency transformation on each of the wheel speed signals, the road surface recognition method further includes: Data preprocessing is performed on each of the wheel speed signals.

8. The road surface recognition method according to claim 7, characterized in that: The data preprocessing method comprises: Abnormal values ​​and missing values ​​in the wheel speed signal are deleted or replaced.

9. An electronic device, characterized in that: The electronic device includes a memory and a processor, wherein the memory stores a computer program executed by the processor, and when the computer program is executed by the processor, the device equipped with the processor executes the road surface recognition method as described in any one of claims 1 to 8.

10. A storage medium, characterized in that: The storage medium stores a computer program, which runs on a computer. When the computer program is running, the computer executes the road surface recognition method according to any one of claims 1 to 8.

11. A vehicle, characterized in that: Includes the electronic device according to claim 9 or the storage medium according to claim 10.

Images