Method and system for evaluating road surface conditions, computer program product

Abstract

The embodiment of the invention provides a method for evaluating the condition of a road surface. The method comprises the following steps: collecting vibration information (S1) of noise generated when a tire passes through the road surface; road surface condition information about a road surface on which the tire travels is evaluated based on the acquired vibration information, where the road surface condition information includes a road surface friction coefficient, a road surface flatness, and a road surface resistance (S2). The present application also relates to a system for evaluating a road surface condition and a computer program product. According to the method and the device, the vibration information of the noise generated when the tire passes through the road surface is subjected to frequency domain analysis of different frequency bands by virtue of a deep learning model, and different frequency characteristics of various road surface types in different frequency bands are fully utilized to evaluate the road surface type and the confidence coefficient thereof; and road surface condition information such as a road surface friction coefficient, road surface flatness and road surface resistance is evaluated based on the evaluated road surface type and the confidence thereof, so that a foundation is laid for reliable vehicle control.

Description

Technical Field

[0001] The present application relates to the field of vehicle data processing, and in particular to a method for evaluating road conditions, a system for evaluating road conditions, and a computer program product for at least assisting in implementing the steps of the method described in the present application. Background Art

[0002] With the development of vehicle technology, road condition information plays an important role in controlling the vehicle's assisted driving functions and / or autonomous driving functions. Road conditions are affected by a variety of factors, including road material, road texture, road wetness, road snow cover, and / or road icing conditions. In the prior art, various types of on-board sensors—such as on-board microphones, on-board cameras, speed sensors, and / or steering angle sensors—are typically used to collect a variety of information to analyze the road conditions on which the tires are traveling. However, this data processing method not only consumes a large amount of computing power, but also lacks the accuracy and timeliness to meet the high-precision and low-latency response requirements of vehicle control.

[0003] Therefore, how to obtain road condition information accurately, in real time and with low technical overhead has become a technical problem that needs to be solved. Summary of the Invention

[0004] The object of the present application is to provide a method for evaluating road conditions, a system for evaluating road conditions, and a computer program product to at least partially solve the problems in the prior art.

[0005] According to a first aspect of the present application, a method for assessing road conditions is provided, which may include:

[0006] - Step S1: collecting vibration information about the noise generated by the tires passing over the road; and

[0007] - Step S2: Evaluating road condition information about the road surface on which the tire travels based on the collected vibration information, wherein the road condition information includes road friction coefficient, road roughness, and road resistance.

[0008] The core concept of this application is to perform frequency domain analysis on the vibration information of the noise generated by the tires passing over the road, for example with the help of a deep learning model, and make full use of the different frequency characteristics of various road types in different frequency bands to evaluate the road type and its confidence level, and then evaluate road condition information such as road friction coefficient, road surface flatness and road surface resistance based on the evaluated road type and its confidence level. At the same time, the information collected by other sensors can be fully utilized to integrate and verify the credibility of the evaluated road condition information, further improving the accuracy of road condition information and laying the foundation for reliable vehicle control.

[0009] According to a second aspect of the present application, a system for evaluating road conditions is provided, wherein the system may include the following components:

[0010] - a vibration information collection unit configured to collect vibration information about noise generated by the tires driving over a road surface; and

[0011] - A control unit for carrying out the method according to the present application.

[0012] According to a third aspect of the present application, a computer program product, such as a computer-readable program carrier, is provided, comprising computer program instructions, which, when executed by a processor, at least assist in implementing the steps of the method described in the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] The present application will be described in more detail below with reference to the accompanying drawings, so that the principles, features and advantages of the present application can be better understood. The accompanying drawings include:

[0014] Figure 1 A flowchart showing a method for evaluating road conditions according to an exemplary embodiment of the present application is shown;

[0015] Figure 2 A flowchart showing a method for evaluating road conditions according to another exemplary embodiment of the present application is shown;

[0016] Figure 3 A flowchart showing a method for evaluating road conditions according to another exemplary embodiment of the present application is shown;

[0017] Figure 4 A flowchart showing a method for evaluating road conditions according to another exemplary embodiment of the present application is shown;

[0018] Figure 5 A flowchart showing a method for evaluating road conditions according to another exemplary embodiment of the present application is shown;

[0019] Figure 6 A flowchart showing a method for evaluating road conditions according to another exemplary embodiment of the present application is shown;

[0020] Figure 7 A flowchart showing a method for evaluating road conditions according to another exemplary embodiment of the present application is shown;

[0021] Figure 8 A flowchart showing a method for evaluating road conditions according to another exemplary embodiment of the present application is shown;

[0022] Figure 9 A flowchart showing a method for evaluating road conditions according to another exemplary embodiment of the present application is shown;

[0023] Figure 10 A flowchart showing a method for evaluating road conditions according to another exemplary embodiment of the present application; and

[0024] Figure 11 A schematic block diagram of a system for evaluating road conditions according to an exemplary embodiment of the present application is shown. DETAILED DESCRIPTION

[0025] In order to make the technical problems, technical solutions and beneficial technical effects to be solved by this application more clearly understood, this application will be further described in detail below with reference to the accompanying drawings and multiple exemplary embodiments. It should be understood that the specific embodiments described herein are only used to explain this application and are not used to limit the scope of protection of this application.

[0026] Figure 1 A flowchart of a method for evaluating road conditions according to an exemplary embodiment of the present application is shown. The following exemplary embodiments describe the method according to the present application in more detail.

[0027] like Figure 1 As shown, the method may include steps S1 and S2. In step S1, vibration information regarding the noise generated by the tires as they pass over the road surface may be collected. When a vehicle is traveling at a speed, for example, less than 80 km / h, the tires generate significant noise, particularly structure-borne noise. This noise is generated by the transmission of vibrations from the vehicle's solid components to the vehicle's excited vibrators. A vibration information collection unit 11, positioned at the vehicle's front axle, can be used to collect vibration information regarding the structure-borne noise generated by the tires, particularly the front tires, as the vehicle travels. A vibration information collection unit 11 may be positioned near the left front tire and one near the right front tire. The vibration information collection unit 11 may be configured as a road noise sensor, configured to collect triaxial vibration signals regarding the structure-borne noise generated by the tires as they pass over the road surface—including an X-axis vibration signal along the vehicle's forward direction, a Y-axis vibration signal along the vehicle's lateral motion, and a Z-axis vibration signal along the vehicle's vertical direction. The road noise sensor may be integrated with the wheel speed sensor 16, thereby saving installation space and sharing data transmission channels. The vibration information acquisition unit 11 can also be configured as a pressure sensor, which is used to collect two-axis vibration signals about the structure-borne noise generated by the tire passing over the road surface, including an X-axis vibration signal along the vehicle's forward direction and a Y-axis vibration signal along the vehicle's lateral movement direction.

[0028] In step S2, road condition information about the road surface the tire is traveling over can be evaluated based on the collected vibration information, wherein the road condition information particularly includes the road friction coefficient, road surface smoothness, and road surface resistance. In the context of this application, the road friction coefficient represents the ratio of the friction force between the tire and the road surface to the vertical pressure when the tire is traveling over the road surface. The road friction coefficient is affected not only by the type of road surface material, including sand, gravel, rock, grass, snow, ice, asphalt, epoxy resin, tile, concrete, metal, or rubber (used to construct speed bumps), but also by the road surface morphology, including the hardness of the road surface, the wetness of the road surface, the amount of snow on the road surface, and / or the icy condition of the road surface. The road surface smoothness represents the vertical deviation of the road surface from an ideal plane. The lower the road surface smoothness, the greater the vibration generated by the vehicle traveling over the road surface. This vibration can cause driving bumps, affecting driving stability and passenger comfort. Road resistance refers to the force exerted by the road surface on the tire surface to hinder the vehicle's forward motion. This force is generated by the interaction between road bumps and depressions and the tire surface, hindering the vehicle's motion. Therefore, road resistance significantly impacts a vehicle's braking distance, handling stability, and other aspects. Road resistance is influenced not only by the type of road surface material, including sand, gravel, rock, grass, snow, ice, asphalt, epoxy resin, tile, concrete, metal, or rubber (used in speed bumps), but also by the surface morphology, including its hardness, wetness, snow cover, and / or icy conditions.

[0029] Next, combine Figure 2 The flowchart of the method for evaluating road conditions according to another exemplary embodiment of the present application details step S2. Figure 2 As shown, the step S2 may include steps S21 to S23. In step S21, the collected vibration signal is converted into a multi-axis vibration signal based on the vehicle body coordinate system in combination with the installation position information of the vibration information collection unit 11. During the vehicle driving process, the original vibration signal collected by the vibration information collection unit 11 installed near the left front tire and the original vibration signal collected by the vibration information collection unit 11 installed near the right front tire are as follows. Figure 11The signals are transmitted to the cockpit domain controller 121 via the car audio bus (A2B), as indicated by the arrow in the figure. Signal analysis is then performed in the cockpit domain controller 121. Since the raw vibration signals collected by the two vibration information acquisition units 11 are based on different sensor coordinate systems, they are uniformly converted to the vehicle body coordinate system to facilitate subsequent signal processing and vehicle control. Thus, the three-axis vibration signal collected by the road noise sensor can be converted into a three-axis vibration signal based on the vehicle body coordinate system, while the two-axis vibration signal collected by the pressure sensor is converted into a two-axis vibration signal based on the vehicle body coordinate system.

[0030] In step S22, the multi-axis vibration signal can be converted into a frequency domain signal and then segmented into multiple frequency bands, where the frequency bands are divided based on the road surface material type. A fast Fourier transform (FFT) is performed on the multi-axis vibration signal in the cockpit domain controller 121 to convert the original time domain signal into a frequency domain signal. Taking into account that the vibration signals generated by tires passing over different road materials will exhibit different vibration characteristics in different frequency bands, the frequency domain signals can be divided into multiple frequency bands based on the road material type, for example, including the following frequency bands: a low-frequency band of 20Hz to 500Hz, for example, when a tire passes over an asphalt road, it will produce violent low-frequency vibrations in this low-frequency band; a medium-frequency band of 500Hz to 2kHz, when a tire passes over a road covered with ice or snow, it will produce wide-band vibrations diffused in this medium-frequency band, while when a tire passes over an asphalt road, it will produce clear periodic peaks in this medium-frequency band; a high-frequency band of 2Hz-10kHz, when a tire passes over an ice-covered road, it will produce high-frequency peaks in this high-frequency band due to slight slippage and ice cracks, while when a tire passes over an asphalt road, it will produce continuous vibrations with different harmonics in this high-frequency band, and so on.

[0031] After completing the division of the frequency bands, step S23 can be continued in the cockpit domain controller 121. In step S23, the road surface type of the road surface on which the tire has traveled can be determined based on the frequency domain signals of the multiple frequency bands, wherein the road surface type is classified based on the road surface friction coefficient, the road surface flatness, and the road surface resistance. In order to simplify the classification of road surface types, different flatness levels can be set for road surface flatness, such as low, medium, and high, and different resistance levels can be set for road surface resistance, such as large, small, and medium. At the same time, a fixed value or value range of the road surface friction coefficient can be assigned to each road surface type through multiple tests. Thus, for example, the classification results of exemplary road surface types according to the present application can be obtained as shown in Table 1:

[0032]

[0033]

[0034] Table 1: Classification results of exemplary road surface types according to the present application

[0035] In particular, deep learning models can be used to assess the road surface type of the tire's road surface. These models may include, for example, convolutional neural networks, recurrent neural networks, multi-layer perceptrons, long short-term memory networks, and / or large language models based on self-attention mechanisms. Because actual road conditions are complex and differ from those of the test road surface, the deep learning model can determine the probability that the current road surface condition belongs to one or more road surface types based on frequency domain signals in multiple frequency bands. The deep learning model's assessment results thus include possible road surface types for the tire's road surface and confidence information associated with each road surface type. This confidence information is used to characterize the reliability of the road surface type assessment result and is typically expressed as a percentage of the probability that the actual road surface condition is the assessed road surface type.

[0036] After the cockpit domain controller 121 completes the evaluation of the road surface type and its confidence level, the evaluated road surface type and its confidence level information may be transmitted to the braking domain controller 122 via, for example, a CAN bus, and the following steps may be executed in the braking domain controller 122 .

[0037] like Figure 3 The flowchart of a method for evaluating road conditions according to another exemplary embodiment of the present application is shown. Step S2 may further include step S24. In step S24, the estimated road friction coefficient, road surface roughness, and road surface resistance may be determined based on the assessed road surface type and confidence information associated with the assessed road surface type. For example, in vehicle operating conditions requiring low-latency response, if the highest confidence level among the assessed road surface types exceeds a preset confidence threshold, the road friction coefficient, road surface roughness, and road surface resistance corresponding to the road surface type with the highest confidence level may be used as the assessed road condition information. For example, when the requirements for delayed response are not high, the weighted average of the road friction coefficient corresponding to each road surface type and the confidence information assigned to the corresponding road surface type can be calculated to obtain the average road friction coefficient as the evaluated road surface friction coefficient; the weighted average of the road surface flatness corresponding to each road surface type and the confidence information assigned to the corresponding road surface type can be calculated to obtain the average road surface flatness as the evaluated road surface flatness; the weighted average of the road surface resistance corresponding to each road surface type and the confidence information assigned to the corresponding road surface type can be calculated to obtain the average road surface resistance as the evaluated road surface resistance.

[0038] like Figure 4The flowchart of a method for evaluating road conditions according to another exemplary embodiment of the present application is shown, wherein step S2 may further include step S25. In step S25, collected vertical acceleration information is additionally introduced as an influencing factor for evaluating road surface roughness, and the assessed road surface roughness may be subjected to a credibility check based on the vertical acceleration information. Here, the vehicle's vertical acceleration information in a direction perpendicular to the road surface may be collected by the peripheral suspension sensor 14, which can reflect the degree of bumpiness of the road surface as the vehicle travels over it. Based on the vertical acceleration information, the road surface roughness level of the road surface as the vehicle travels over it may be determined, and the credibility check of the assessed road surface roughness may be performed using the determined level. If the road surface roughness level determined based on the vertical acceleration information is consistent with the assessed road surface roughness level, the assessed road surface roughness is credible and may be used in subsequent vehicle control processes.

[0039] like Figure 5 The workflow diagram of a method for evaluating road conditions according to another exemplary embodiment of the present application is shown, wherein step S2 may further include step S26. In step S26, the collected steering rack force is additionally introduced as an influencing factor for evaluating the road friction coefficient. The evaluated road friction coefficient—i.e., the road friction coefficient evaluated based on the road surface type and its confidence information—can be adjusted based on the steering rack force. Here, the current detection sensor 13 can detect the motor current and calculate the vehicle's steering rack force based on the motor current. The steering rack force is the force transmitted to the steering wheel through components such as the steering rod, which is used to push the steering wheel to produce a certain deflection angle, thereby achieving vehicle steering. This steering rack force is transmitted to the braking domain controller 122 via, for example, a CAN bus. Braking domain controller 122 then calculates the road friction coefficient based on the steering rack force. Based on the current vehicle operating conditions, a first weight is assigned to the calculated road friction coefficient and a second weight is assigned to the estimated road friction coefficient. For example, during a cornering situation, the first weight can be increased and the second weight can be decreased. This weighted average of the calculated road friction coefficient and its first weight and the estimated road friction coefficient and its second weight is then taken to adjust the estimated road friction coefficient. By additionally incorporating the collected steering rack force as an influencing factor in evaluating the road friction coefficient, the accuracy and reliability of the road friction coefficient evaluation results are further improved.

[0040] like Figure 6The flowchart of the method for evaluating road conditions according to another exemplary embodiment of the present application is shown, wherein step S2 may further include steps S27 and S28. In step S27, the road friction coefficient of the road surface on which the tire is traveling may be calculated based on the collected yaw rate information, lateral acceleration information, longitudinal acceleration information, wheel speed information, and steering angle information. During vehicle travel, the vehicle's yaw rate information, lateral acceleration information (i.e., acceleration in the vehicle's lateral direction of motion), and longitudinal acceleration information (i.e., acceleration in the vehicle's forward direction) may be collected by the inertial sensor 15, the vehicle's wheel speed information may be collected by the wheel speed sensor 16, and the vehicle's steering angle information may be collected by the steering angle sensor 17. When the vehicle is turning, the theoretical lateral acceleration of the vehicle can be calculated based on the vehicle's steering angle information, yaw angular velocity information and wheel speed information. The actual lateral acceleration of the vehicle can be determined based on the collected lateral acceleration information and longitudinal acceleration information. The vehicle's slip rate can be calculated based on the theoretical lateral acceleration and the actual lateral acceleration, and the road friction coefficient of the road surface over which the tires are traveling can be calculated based on the calculated slip rate.

[0041] In step S28, a fused road friction coefficient can be determined based on the calculated and estimated road friction coefficients. In particular, under conditions of vehicle acceleration or deceleration, the calculated road friction coefficient is closer to the actual road friction coefficient. Under conditions of constant vehicle speed, the road friction coefficient estimated based on the road surface type and its confidence level is closer to the actual road friction coefficient. Therefore, if the vehicle's acceleration or deceleration is greater than or equal to a preset threshold, the calculated road friction coefficient can be used as the fused road friction coefficient. If both the vehicle's acceleration and deceleration are less than the preset threshold, and the deviation between the calculated road friction coefficient and the evaluated road friction coefficient is less than the preset deviation threshold—this means that the credibility test result of the evaluated road friction coefficient using the calculated road friction coefficient is positive—then the evaluated road friction coefficient of the current road section can be used as the fused road friction coefficient. If both the vehicle's acceleration and deceleration are less than the preset threshold, and the deviation between the calculated road friction coefficient and the evaluated road friction coefficient is greater than or equal to the preset deviation threshold—this means that the credibility test result of the evaluated road friction coefficient using the calculated road friction coefficient is negative, the evaluated road friction coefficient of the current road section is unreliable. Considering that the vehicle is currently traveling at a near-constant speed, the evaluated road friction coefficient of the previous road section can be used as the fused road friction coefficient. In this way, not only is the credibility test of the evaluated road friction coefficient achieved, but a road friction coefficient that is closer to the actual road conditions can also be selected based on the vehicle's operating conditions.

[0042] According to the embodiments of the present application, by performing frequency domain analysis on the vibration information of the noise generated by the tires passing over the road surface, for example, with the help of a deep learning model, the different frequency characteristics of various road types in different frequency bands are fully utilized to evaluate the road surface type and its confidence level, and then the road surface condition information such as the road surface friction coefficient, road surface flatness and road surface resistance is evaluated based on the evaluated road surface type and its confidence level. At the same time, the information collected by other sensors can be fully utilized to fuse and verify the credibility of the evaluated road surface condition information, further improving the accuracy of the road surface condition information and laying the foundation for reliable vehicle control.

[0043] Figure 7 The following is a flowchart of a method for evaluating road conditions according to another exemplary embodiment of the present application. Figure 6 The differences between the embodiments shown in FIG and FIG are omitted, and the same steps are not described again for the sake of brevity.

[0044] like Figure 7 As shown, the method may further include step S3. The braking domain controller 122 may transmit the fused road friction coefficient to the driving assistance domain controller 123, for example, via a CAN bus, and step S3 may be executed in the driving assistance domain controller 123. In step S3, the fused road friction coefficient may be introduced as an additional control factor to participate in the control of the vehicle's driving assistance system, wherein the driving assistance system may include, for example, an intelligent turning assistance system, and / or an electric power steering system, and / or an emergency avoidance system, and / or an adaptive cruise control system, and / or a lane keeping assist system.

[0045] For example, when the vehicle's intelligent turning assist system detects the driver's steering intention based on vehicle signals, it can calculate the expected braking force or expected driving force to be applied to the wheel based at least on the fused road friction coefficient, and apply the calculated expected braking force or expected driving force to the corresponding wheel, thereby generating a yaw that is beneficial to the driver's desired steering direction and reducing the turning radius.

[0046] For another example, when the vehicle's electric power steering system detects that the driver is turning the steering wheel, it can calculate the power required for the steering system based at least on the integrated road friction coefficient, and apply the calculated power to the steering system, thereby reducing the driver's manual operating burden.

[0047] For example, when a vehicle's emergency avoidance system detects the risk of collision with an obstacle, pedestrian, or other vehicle in front of the vehicle, it can formulate an emergency avoidance plan based on vehicle state parameters and surrounding environment information - including the integrated road friction coefficient - including the avoidance direction, speed change, required steering angle and braking force, etc., and control the vehicle to complete the corresponding steering process and / or braking process.

[0048] For another example, during operation of the vehicle's adaptive cruise control system, the vehicle's speed can be controlled based on vehicle state parameters and surrounding environment information, including the fused road friction coefficient, to maintain a safe distance from the vehicle ahead.

[0049] For another example, when the vehicle's lane keeping assist system detects that the vehicle has a tendency to deviate from the lane, it can calculate the expected steering force to be provided to the steering system based at least on the fused road friction coefficient to guide the vehicle to adjust its driving direction.

[0050] Figure 8 The following is a flowchart of a method for evaluating road conditions according to another exemplary embodiment of the present application. Figure 6 The differences between the embodiments shown in FIG and FIG are omitted, and the same steps are not described again for the sake of brevity.

[0051] like Figure 8 As shown, the method may further include step S4. In step S4, the braking domain controller 122 may send the fused road friction coefficient and corresponding road segment location information to the first cloud server 2 of the vehicle supplier and / or the second cloud server 3 of the map supplier. The first cloud server 2 of the vehicle supplier and / or the second cloud server 3 of the map supplier may integrate and store the received fused road friction coefficient based on the road segment location information, and when other vehicles travel to the same road segment location and issue a data request, the fused road friction coefficient corresponding to the road segment location may be sent to the other vehicles, allowing the other vehicles to also utilize the received fused road friction coefficient to participate in the control of the driving assistance system.

[0052] Figure 9 The following is a flowchart of a method for evaluating road conditions according to another exemplary embodiment of the present application. Figure 6 The differences between the embodiments shown in FIG and FIG are omitted, and the same steps are not described again for the sake of brevity.

[0053] like Figure 9As shown, the method may further include step S5. The braking domain controller 122 may send the fused road friction coefficient to the suspension domain controller 124, for example, via the CAN bus, and execute step S5 in the suspension domain controller 124. In step S5, the suspension of the vehicle may be controlled based on the assessed road surface roughness. For example, when the vehicle is traveling over a road section with low road surface roughness, such as a hard sand road, a snowy road, or an icy road, especially when the road surface roughness level determined based on the collected vertical acceleration information is consistent with the assessed road surface roughness level, the vehicle suspension may be controlled based on at least the assessed road surface roughness, thereby reducing the degree of bumpiness of the vehicle when traveling over the road surface and improving the driving smoothness and ride comfort of the vehicle.

[0054] Figure 10 The following is a flowchart of a method for evaluating road conditions according to another exemplary embodiment of the present application. Figure 6 The differences between the embodiments shown in FIG and FIG are omitted, and the same steps are not described again for the sake of brevity.

[0055] like Figure 10 As shown, the method may further include step S6. The braking domain controller 122 may send the fused road friction coefficient to the cockpit domain controller 121, for example, via the CAN bus, and execute step S6 in the cockpit domain controller 121. In step S6, the driving mode switching of the vehicle, and / or the cockpit alarm function, and / or the vehicle rescue function may be controlled based on the evaluated road resistance. For example, when the vehicle is driving through a road section with a high road resistance level, such as a rocky road surface, the driving mode of the vehicle may be switched to an off-road mode based on the evaluated road resistance. For another example, when the vehicle is driving through a road section with a high road resistance level, such as a dry gravel road surface, a wet gravel road surface, or a soft sand road surface, the cockpit alarm function may be turned on to prompt the driver to drive carefully. For example, when the vehicle is stuck in the sand, the vehicle rescue function may be turned on to send a rescue request message to the rescue agency in a timely manner.

[0056] In addition, it should be noted that the step numbers described herein do not necessarily represent a chronological order, but are merely a reference mark. The order can be changed according to specific circumstances as long as the technical purpose of this application can be achieved.

[0057] Figure 11 A schematic block diagram of a system 10 for evaluating road conditions according to an exemplary embodiment of the present application is shown.

[0058] like Figure 11 As shown, the system 1 may include the following components:

[0059] - a vibration information acquisition unit 11, which is configured to collect vibration information about noise generated by the tires passing over the road surface, wherein the vibration information acquisition unit 11 may include a road noise sensor for collecting three-axis vibration signals about structure-borne noise generated by the tires passing over the road surface, and / or a pressure sensor for collecting two-axis vibration signals about structure-borne noise generated by the tires passing over the road surface, wherein the vibration information acquisition unit 11 is, for example, arranged at the front axle of the vehicle, and in particular, one vibration information acquisition unit 11 is arranged near the left front tire and one near the right front tire; and

[0060] - A control unit for executing the method according to the present application, wherein the control unit is configured as a domain controller, wherein the domain controller includes, for example, a cockpit domain controller 121, and / or a brake domain controller 122, and / or a driving assistance domain controller 123, and / or a suspension domain controller 124, etc.

[0061] Optionally, the system 1 may further include a current detection sensor 13 configured to measure the motor current and calculate the steering rack force of the vehicle based on the measured motor current.

[0062] Optionally, the system 1 may further include a peripheral suspension sensor 14 configured to collect vertical acceleration information of the vehicle.

[0063] Optionally, the system 1 may further include an inertial sensor 15 configured to collect yaw rate information, lateral acceleration information, and longitudinal acceleration information of the vehicle.

[0064] Optionally, the system 1 may further include a wheel speed sensor 16 configured to collect wheel speed information of the vehicle.

[0065] Optionally, the system 1 may further include a steering angle sensor 17 configured to collect steering angle information of the vehicle.

[0066] It should be understood that, in this document, the expressions "first", "second", "third", etc. are used for descriptive purposes only and should not be understood as indicating or implying relative importance, nor should they be understood as implicitly indicating the quantity of the indicated technical features.

[0067] If an embodiment includes an "and / or" relationship between a first feature and a second feature, it should be interpreted as follows: according to one embodiment, the embodiment has both the first feature and the second feature, and according to another embodiment, the embodiment has either only the first feature or only the second feature.

[0068] Although specific embodiments have been described above, these embodiments are not intended to limit the scope of the present disclosure, even when only a single embodiment is described with respect to specific features. The feature examples provided in the present disclosure are intended to be illustrative and not limiting, unless otherwise stated. In specific implementations, multiple features may be combined with each other, depending on actual needs, where technically feasible. Various substitutions, changes, and modifications may be contemplated without departing from the spirit and scope of the present application.

Claims

1. A method for evaluating road conditions, the method comprising: Step S1: collecting vibration information about the noise generated by the tire passing over the road; as well as Step S2: evaluating road condition information about the road the tire travels on based on the collected vibration information, wherein the road condition information includes road friction coefficient, road roughness, and road resistance.

2. The method according to claim 1, wherein The step S2 comprises: Step S21: converting the collected vibration signal into a multi-axis vibration signal based on the vehicle body coordinate system in combination with the installation position information of the vibration information collection unit (11); Step S22: converting the multi-axis vibration signal into a frequency domain signal, and dividing the frequency domain signal into frequency domain signals of multiple frequency bands, wherein the frequency bands are divided based on road material types; and Step S23: Determine the road surface type of the road surface on which the tire travels based on the frequency domain signals of the multiple frequency bands, wherein the road surface type is classified based on the road surface friction coefficient, the road surface flatness, and the road surface resistance.

3. The method according to claim 2, wherein: Based on the frequency domain signals of the multiple frequency bands, for example, a deep learning model is used to evaluate the road surface type of the road surface traveled by the tire and the confidence information assigned to the evaluated road surface type, wherein the deep learning model includes, for example, a convolutional neural network, a recurrent neural network, a multi-layer perceptron, a long short-term memory network and / or a large language model based on a self-attention mechanism; and / or The step S2 further includes a step S24 of determining an estimated road surface friction coefficient, road surface roughness, and road surface resistance based on the estimated road surface type and confidence information assigned to the estimated road surface type, wherein: Using the road friction coefficient, road roughness, and road resistance corresponding to the road type with the highest confidence as the evaluated road condition information, wherein the highest confidence is greater than a preset confidence threshold, and / or Calculate the weighted average of the road friction coefficient corresponding to each road surface type and the confidence information assigned to the corresponding road surface type to obtain the average road friction coefficient as the evaluated road surface friction coefficient, and / or calculate the weighted average of the road surface flatness corresponding to each road surface type and the confidence information assigned to the corresponding road surface type to obtain the average road surface flatness as the evaluated road surface flatness, and / or calculate the weighted average of the road surface resistance corresponding to each road surface type and the confidence information assigned to the corresponding road surface type to obtain the average road surface resistance as the evaluated road surface resistance.

4. The method according to claim 3, wherein: The step S2 further includes: Step S25: additionally introducing the collected vertical acceleration information as an influencing factor for evaluating the road surface smoothness, and performing a credibility check on the evaluated road surface smoothness based on the vertical acceleration information; and / or Step S26 : additionally introducing the acquired steering rack force as an influencing factor for estimating the road surface friction coefficient, and adjusting the estimated road surface friction coefficient based on the steering rack force.

5. The method according to claim 3, wherein The step S2 further includes: Step S27: Calculating the road friction coefficient of the road the tire is traveling on based on the collected yaw rate information, lateral acceleration information, longitudinal acceleration information, wheel speed information, and steering angle information; and Step S28: Determine a fused road friction coefficient based on the calculated road friction coefficient and the estimated road friction coefficient, wherein: If the acceleration or deceleration of the vehicle is greater than or equal to a preset threshold, the calculated road friction coefficient is used as the fused road friction coefficient, and / or If the acceleration and deceleration of the vehicle are both less than a preset threshold, and the deviation between the calculated road friction coefficient and the estimated road friction coefficient is less than a preset deviation threshold, the estimated road friction coefficient of the current road section is used as the fused road friction coefficient, and / or If the acceleration and deceleration of the vehicle are both less than the preset threshold, and the deviation between the calculated road friction coefficient and the evaluated road friction coefficient is greater than or equal to the preset deviation threshold, the evaluated road friction coefficient of the previous road section is used as the fused road friction coefficient.

6. The method according to claim 5, wherein: The method further comprises: Step S3: Introducing the fused road friction coefficient as an additional control factor to participate in the control of the vehicle's driving assistance system, wherein the driving assistance system includes, for example, an intelligent takeover assistance system, and / or an electric power steering system, and / or an emergency avoidance system, and / or an adaptive cruise control system, and / or a lane keeping assistance system; and / or Step S4: sending the fused road friction coefficient and corresponding road segment location information to the first cloud server (2) of the vehicle supplier and / or the second cloud server (3) of the map supplier; and / or Step S5: controlling the vehicle's suspension based on the assessed road surface roughness; and / or Step S6: Controlling a driving mode switch of the vehicle, and / or a cockpit warning function, and / or a vehicle rescue function based on the estimated road resistance.

7. A system (1) for evaluating road conditions, wherein: The system (1) comprises the following components: a vibration information collecting unit (11) configured to collect vibration information about noise generated by the tires running over a road surface; and A control unit for executing the method according to any one of claims 1 to 6.

8. The system (1) according to claim 7, wherein The control unit is configured as a domain controller, wherein the domain controller includes, for example, a cockpit domain controller (121), and / or a brake domain controller (122), and / or a driver assistance domain controller (123), and / or a suspension domain controller (124); and / or The vibration information acquisition unit (11) includes a road noise sensor for acquiring a three-axis vibration signal of structure-borne noise generated by the tire passing over the road surface, and / or a pressure sensor for acquiring a two-axis vibration signal of structure-borne noise generated by the tire passing over the road surface, wherein the vibration information acquisition unit (11) is, for example, arranged at the front axle of the vehicle, and in particular, one vibration information acquisition unit (11) is arranged at a position close to the left front tire and one at a position close to the right front tire.

9. System (1) according to claim 7 or 8, wherein The system (1) further comprises: a current detection sensor (13) configured to measure a motor current and calculate a steering rack force of the vehicle based on the measured motor current; and / or A peripheral suspension sensor (14) configured to collect vertical acceleration information of the vehicle; and / or an inertial sensor (15) configured to collect yaw rate information, lateral acceleration information, and longitudinal acceleration information of the vehicle; and / or A wheel speed sensor (16) configured to collect wheel speed information of the vehicle; and / or A steering angle sensor (17) is configured to collect steering angle information of the vehicle. 10 . A computer program product, such as a computer-readable program carrier, comprising computer program instructions which, when executed by a processor, at least assist in implementing the steps of the method according to claim 1 .

Images