Torque limiting method, electronic equipment and vehicle

Abstract

According to the torque limiting method, the electronic equipment and the vehicle, when the current slip rate is calculated, the navigation estimation vehicle speed and the wheel speed are introduced to correct the current detection vehicle speed, the accuracy of the current slip rate is guaranteed, then the accuracy of calculating the road adhesion coefficient is improved, and the torque limiting precision is improved. When the road adhesion coefficient is estimated, the recognition area of the current scanning image is corrected to improve the accuracy of road type recognition, so that the precision of estimating the road adhesion coefficient is improved, and the accuracy of torque limitation is ensured. When the limiting torque is determined, the road surface type confidence coefficient is introduced to reduce the difference between the target road surface adhesion coefficient and the true value, so that the precision of the limiting torque determined according to the target road surface adhesion coefficient is ensured, and the target road surface adhesion coefficient can be fully utilized when request limiting is carried out according to the limiting torque; and the wheels of the vehicle cannot slip while the dynamic property is ensured, so that the driving safety is ensured.

Description

Technical Field

[0001] The present application relates to the field of vehicle technology, and in particular to a torque limiting method, an electronic device and a vehicle. Background Art

[0002] Vehicles are developing towards electrification and intelligence. For vehicles with decoupled front and rear axles, both the front and rear axle motors can output greater torque. When driving at high torque, if the requested torque is too large, it may cause the vehicle wheels to slip, resulting in driving hazards. Summary of the invention

[0003] In view of this, the purpose of the present application is to propose a torque limiting method, an electronic device and a vehicle, which can ensure that the wheels do not slip when driving on different road surfaces through torque limiting, thereby improving driving safety.

[0004] Based on the above purpose, the present application provides a torque limiting method, comprising:

[0005] Determine a reference vehicle speed according to the navigation estimated vehicle speed, the current detected vehicle speed and the wheel speed of each wheel, determine a current slip rate according to the reference vehicle speed and the wheel linear speed of the driving wheel, and determine and calculate a road adhesion coefficient according to the current slip rate and a preset dynamic model;

[0006] Correcting the recognition area of ​​the current scanned image according to the reference vehicle speed and the current front wheel steering angle to obtain a road surface recognition image, and classifying the road surface recognition image to obtain an estimated road surface adhesion coefficient and a road surface type confidence;

[0007] A target road adhesion coefficient is determined according to the road type confidence, the calculated road adhesion coefficient and the estimated road adhesion coefficient, and a current limit torque is determined according to the target road adhesion coefficient, the front axle load and the rear axle load, and a request torque is limited and controlled according to the current limit torque.

[0008] Based on the same inventive concept, the present disclosure also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable by the processor, wherein the processor implements the method as described above when executing the computer program.

[0009] Based on the same inventive concept, the present disclosure also provides a vehicle, comprising the electronic device as described above.

[0010] As can be seen from the above, the torque limiting method, electronic device and vehicle provided by the present application can determine the reference vehicle speed according to the navigation estimated vehicle speed, the current detected vehicle speed and the wheel speed of each wheel, determine the current slip rate according to the reference vehicle speed and the wheel linear speed of the driving wheel, and determine the calculated road adhesion coefficient according to the current slip rate and the preset dynamic model. When calculating the current slip rate, the navigation estimated vehicle speed and the wheel speed are introduced to correct the current detected vehicle speed to ensure the accuracy of the current slip rate, thereby improving the accuracy of the calculated road adhesion coefficient and improving the accuracy of the torque limiting. According to the reference vehicle speed and the current front wheel turning angle, the recognition area of ​​the current scanned image is corrected to obtain a road recognition image, and the road recognition image is image-classified to obtain the estimated road adhesion coefficient and the road type confidence. When estimating the road adhesion coefficient, the accuracy of the road type recognition is improved by correcting the recognition area of ​​the current scanned image, thereby improving the accuracy of the estimated road adhesion coefficient and ensuring the accuracy of the torque limiting. The target road adhesion coefficient is determined according to the road type confidence, the calculated road adhesion coefficient and the estimated road adhesion coefficient, and the current limit torque is determined according to the target road adhesion coefficient, the front axle load and the rear axle load, and the requested torque is limited and controlled according to the current limit torque. When determining the limit torque, the road type confidence is introduced to narrow the gap between the target road adhesion coefficient and the true value to ensure the accuracy of the limit torque determined according to the target road adhesion coefficient, and then ensure that when the request limit is made according to the limit torque, the target road adhesion coefficient can be fully utilized, and the vehicle wheels will not slip while ensuring the power performance, and the driving safety is ensured. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] In order to more clearly illustrate the technical solutions in the present application or related technologies, the drawings required for use in the embodiments or related technical descriptions are briefly introduced below. Obviously, the drawings described below are only embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0012] Figure 1 This is a flow chart of the torque limiting method according to an embodiment of the present application;

[0013] Figure 2 A flow chart for determining a reference vehicle speed for an embodiment of the present application;

[0014] Figure 3 This is a flow chart of a road surface recognition image according to an embodiment of the present application;

[0015] Figure 4a This is a schematic diagram of the deviation identification area under the straight-line driving condition of an embodiment of the present application;

[0016] Figure 4bThis is a schematic diagram of the offset recognition area under the turning driving condition of the embodiment of the present application;

[0017] Figure 5 A flow chart for determining an estimated road surface adhesion coefficient and a road surface type confidence for an embodiment of the present application;

[0018] Figure 6 A flow chart for determining a target road adhesion coefficient for an embodiment of the present application;

[0019] Figure 7 A flow chart for determining the current limiting torque for an embodiment of the present application;

[0020] Figure 8 This is a flow chart of limiting the requested torque according to the current limited torque according to an embodiment of the present application;

[0021] Fig. 9 This is a schematic diagram of the structure of the torque limiting device according to an embodiment of the present application;

[0022] Fig.10 It is a schematic diagram of the structure of an electronic device according to an embodiment of the present application. DETAILED DESCRIPTION

[0023] In order to make the objectives, technical solutions and advantages of the present application more clearly understood, the present application is further described in detail below in combination with specific embodiments and with reference to the accompanying drawings.

[0024] It should be noted that, unless otherwise defined, the technical terms or scientific terms used in the embodiments of the present application should be the usual meanings understood by people with ordinary skills in the field to which the present application belongs. The "first", "second" and similar words used in the embodiments of the present application do not represent any order, quantity or importance, but are only used to distinguish different components. "Including" or "comprising" and similar words mean that the elements or objects appearing in front of the word cover the elements or objects listed after the word and their equivalents, without excluding other elements or objects. "Connect" or "connected" and similar words are not limited to physical or mechanical connections, but can include electrical connections, whether direct or indirect. "Up", "down", "left", "right" and the like are only used to indicate relative positional relationships. When the absolute position of the described object changes, the relative positional relationship may also change accordingly.

[0025] It should be understood herein that any number of elements in the drawings is for illustration rather than limitation, and any naming is only for distinction rather than having any limiting meaning.

[0026] Based on the description of the above background technology, the related technology also has the following situations:

[0027] Vehicles are developing towards electrification and intelligence. For vehicles with decoupled front and rear axles, the front and rear axle motors can both output large torques. When driving with large torque, such as when driving on off-road conditions, precise torque control is required to prevent the vehicle from slipping, so as to make full use of the adhesion coefficient of the road and enhance the vehicle's off-road capability and safety. If the requested torque value is large and exceeds the maximum torque allowed by the road adhesion coefficient, it may cause the vehicle wheels to slip, resulting in driving hazards.

[0028] In order to ensure that slippage occurs when torque is requested, the requested torque needs to be precisely controlled. The premise of precise torque control is the precise calculation of the reference vehicle speed and the road adhesion coefficient. The current method for calculating the reference vehicle speed of the vehicle relies on four wheel speeds, the vehicle's longitudinal acceleration, lateral acceleration, yaw acceleration, etc. When there are working conditions such as wheel spinning and flying up a slope, the reference vehicle speed is not calculated accurately, resulting in a large error in torque control, which is prone to slippage and causes driving hazards.

[0029] The calculation method of the road adhesion coefficient mainly relies on vehicle dynamics, and the vehicle dynamics model and the tire model are used to estimate the road adhesion coefficient. Since this method requires the use of more input parameters when estimating the road adhesion coefficient, such as slip rate, the calculation of the slip rate also requires the use of a reference vehicle speed. The reference vehicle speed has a large error due to wheel spinning, flying slopes and other working conditions, which will cause the error of the road adhesion coefficient to further increase, resulting in a large error in the estimation of the road adhesion coefficient. When performing torque control, the vehicle's torque cannot be accurately controlled due to the accuracy of the estimation of the vehicle state (represented by parameters such as the road adhesion coefficient and slip rate), which makes it easy for slipping to occur.

[0030] The torque limiting method, electronic device and vehicle provided in the embodiment of the present application introduce the navigation estimated vehicle speed and wheel speed to correct the current detected vehicle speed when calculating the current slip rate, thereby ensuring the accuracy of the current slip rate, thereby improving the accuracy of calculating the road adhesion coefficient, and improving the accuracy of the torque limiting. When estimating the road adhesion coefficient, the accuracy of the road type recognition is improved by correcting the recognition area of ​​the current scanned image, thereby improving the accuracy of the estimated road adhesion coefficient and ensuring the accuracy of the torque limiting. When determining the limiting torque, the road type confidence is introduced to narrow the gap between the target road adhesion coefficient and the true value, so as to ensure the accuracy of the limiting torque determined according to the target road adhesion coefficient, thereby ensuring that when requesting the limit according to the limiting torque, the target road adhesion coefficient can be fully utilized, and the wheels of the vehicle will not slip while ensuring the power, thereby ensuring the safety of driving.

[0031] The torque limiting method provided by the embodiments of the present application is described in detail below with reference to the accompanying drawings.

[0032] In some embodiments, Figure 1 As shown, a torque limiting method includes:

[0033] Step 101: Determine a reference vehicle speed based on the navigation estimated vehicle speed, the current detected vehicle speed and the wheel speed of each wheel, determine the current slip rate based on the reference vehicle speed and the wheel linear speed of the driving wheel, and calculate the road adhesion coefficient based on the current slip rate and a preset dynamic model.

[0034] In specific implementation, the proportion of the sliding component in the wheel movement is the slip rate. The slip rate is calculated as follows: slip rate = (wheel linear speed - reference vehicle speed) / wheel linear speed. Therefore, if you want to improve the calculation accuracy of the slip rate, you need to improve the data accuracy of the reference vehicle speed and the wheel linear speed. The wheel linear speed is determined by the wheel speed and the wheel radius. The wheel radius is a fixed value. Even if the wheel is worn, the change in the wheel radius is small before reaching the scrap standard, and will not affect the calculation of the wheel linear speed. The measurement technology of wheel speed is relatively mature, so the calculated value of the wheel linear speed is reliable and accurate. You only need to improve the accuracy of the reference vehicle speed to achieve the improvement of the slip rate accuracy.

[0035] First, it is necessary to determine whether there is wheel flywheel (i.e., the wheel is separated from the ground). The degree of separation between the wheel and the ground can be quantified by the mean square deviation of the wheel speeds of the four wheels:

[0036]

[0037] Among them, MSE stands for mean square error, which is the separation coefficient, indicating the degree of separation between the wheel and the ground; i represents the wheel speed (linear speed) of the th wheel, Indicates the average wheel speed.

[0038] After the user enters the destination in the navigation software, the navigation software will provide the user with multiple paths to choose from. After the user performs the selection operation, the path from the starting location to the destination selected by the user is the planned path. The planned path selected by the user can be determined by reading the navigation data. After the user selects the planned path, the navigation software will obtain the path information corresponding to the planned path. The path information includes the speed information of the planned path, congestion information, whether there is construction, etc. Among them, the speed information of the planned path is the navigation estimated vehicle speed V when the vehicle is traveling on the planned path. g (Generally the predicted value of average vehicle speed).

[0039] Then, the vehicle state information is determined according to the vehicle state sensor, and the current detected vehicle speed V is calculated based on the vehicle state information based on the vehicle dynamics model. d, and compare the current detected speed with the navigation estimated speed to obtain the speed error value representing the relative error: Then, the corresponding reference speed is determined according to the separation coefficient and the speed error value. The reference speed V C The determination process is as follows:

[0040] (1)0≤MSE<K1,

[0041] (2) K1≤MSE<K2, and u <k u When V C =avg(V g ,V d );

[0042] (3) K1≤MSE<K2, and u≥k u When V C =V g ;

[0043] (4)K2≤MSE, and u <k u When V C =f(V C ,V g );

[0044] (5) K2≤MSE, and u≥k u When V C =V g .

[0045] Wherein, K1 is the first coefficient threshold, K2 is the second coefficient threshold, and the first coefficient threshold is less than the second coefficient threshold, k2 represents the vehicle speed error threshold, avg(,) represents the calculated average value, f(V C ,V g ) represents the fitting function relationship between the reference vehicle speed and the navigation estimated vehicle speed.

[0046] Among them, considering that some scenes may not be covered by navigation signals, such as tunnel conditions, etc., resulting in the inability to obtain the navigation estimated vehicle speed, in this case, another V C =V d Therefore, the vehicle speed is corrected according to the navigation data. The navigation correction strategy will be enabled only when the signal strength of the navigation signal reaches a certain requirement (for example, greater than the preset signal strength threshold). When the navigation signal is abnormal, the navigation correction function is turned off and the vehicle speed is directly adjusted. C =V d .

[0047] Determine the corresponding reference speed V according to the current vehicle running state C Then, the current slip ratio is determined according to the reference vehicle speed and the wheel linear velocity of the driving wheel. Current slip ratio = (wheel linear velocity - reference vehicle speed VC ) / wheel linear speed, which makes it possible to correct the vehicle speed through navigation data and obtain a more accurate reference speed.

[0048] The road adhesion coefficient is the ratio of adhesion to wheel normal (perpendicular to the road) pressure. In rough calculation, it can be regarded as the static friction coefficient between the tire and the road. It is determined by the road surface and the tire. The larger this coefficient is, the greater the available adhesion is, and the less likely the car is to slip. The road adhesion coefficient determines the adhesion ability of the tire on different road surfaces. The value of the road adhesion coefficient is mainly determined by factors such as the material of the road, the condition of the road surface, the tire structure, tread pattern, material, and the speed of the vehicle. Generally speaking, the adhesion coefficient of dry and good asphalt or concrete roads is the largest, which can reach 0.7-0.8. The adhesion coefficient of icy and snowy roads is the smallest and is most likely to slip.

[0049] The braking force and driving force of the vehicle are both related to the road adhesion coefficient. When the wheels are in a semi-slip and semi-rolling state, the road adhesion coefficient can reach the maximum, that is, the braking force and driving force can reach a large value, and the stability of the vehicle is also good at this time. When the wheels are completely locked and there is no rolling, the ground adhesion decreases, the road adhesion coefficient decreases, and the lateral stability is zero, which is very likely to cause side slip and tail swing, which can easily cause accidents. Therefore, it is necessary to make full use of the road adhesion coefficient to output large torque without slipping.

[0050] Adhesion rate μ is the ratio of the longitudinal force of the tire to the vertical load. There is a certain relationship between adhesion rate μ and slip rate s. As the slip rate increases, adhesion first increases and then decreases. Generally, the maximum adhesion rate under a certain road surface is called the road adhesion coefficient, that is, the road adhesion coefficient is μ. max Generally, there will be μ in the slip ratio range of 0.1 to 0.3. max The road adhesion coefficient can be calculated based on the current slip rate and the preset dynamic model.

[0051] Alternatively, the calculation process of the road adhesion coefficient in the dynamic model can be simplified as follows:

[0052]

[0053] Among them, a x is the lateral acceleration, a y represents longitudinal acceleration, fac represents correction factor, and g represents gravitational acceleration.

[0054] Step 102: Correct the recognition area of ​​the current scanned image according to the reference vehicle speed and the current front wheel steering angle to obtain a road surface recognition image, and classify the road surface recognition image to obtain an estimated road surface adhesion coefficient and road surface type confidence.

[0055] In specific implementation, in machine vision and image processing, the area to be processed is outlined from the processed image in the form of a box, circle, ellipse, irregular polygon, etc., which is called a region of interest (ROI). In the field of image processing, a region of interest is an image area selected from an image, which is the focus of image analysis. The area is circled for further processing. Using the region of interest to circle the target to be read can reduce processing time and increase accuracy.

[0056] Therefore, the corresponding recognition area can be obtained by delineating the region of interest in the current scanned image. For example, the recognition area can be a rectangular fixed area of ​​3.5m*10m 3.5m in front of the vehicle. Since the recognition area is delineated in the scanned image when the vehicle is stationary, the real-time transmission of the scanned image may be delayed due to network delays during vehicle driving. Therefore, it is necessary to correct the error caused by network delays during driving to improve the accuracy of the road recognition image. The scanned image is a real-time image taken by the vehicle's front-view camera.

[0057] Image classification is performed using the collected images in front of the vehicle. Image classification can be performed using machine learning, such as support vector machines, decision trees and other machine learning models, or deep learning image classification methods, such as MobileNet, ResNet, etc. The embodiment of the present application uses a deep learning method for image classification, and uses the MobileNetV2 model to classify the road surface recognition image to obtain the road surface type and road surface type confidence α. Then, the corresponding estimated road surface adhesion coefficient is determined according to the road surface type, where different road surface types have corresponding road surface adhesion coefficient ranges, where the relationship between the road surface type and the road surface adhesion coefficient range is shown in Table 1:

[0058] Table 1 Relationship between road surface type and road surface adhesion coefficient range

[0059] Road surface type Road adhesion coefficient range Asphalt or concrete 0.8～1.2 Asphalt (wet) 0.6～0.85 Dirt Road 0.6～0.8 Sandy 0.4～0.6 Mud 0.4～0.5 grassland 0.3～0.4 Snow (snow tires) 0.3～0.4 Ice 0.1～0.25

[0060] The corresponding road adhesion coefficient range is determined according to the road type, and the maximum value in the road adhesion coefficient range is determined as the estimated road adhesion coefficient.

[0061] In deep learning, confidence usually refers to how sure the model is about its predictions. The model assigns a probability value to each category, which indicates how likely the model thinks the input data belongs to that category. Confidence is part of the model output and is usually obtained through a softmax function, Q function, or other probability function.

[0062] For example, in an image classification task, the model may need to classify the input image into the corresponding road surface type. For a specific input image, the MobileNetV2 model may output the following probabilities: Asphalt or Concrete = 0.70, Asphalt (Wet) = 0.25, Dirt Road = 0.05. The model has the highest classification confidence of 70% for the road surface type being asphalt or concrete. Therefore, the road surface type confidence indicates the degree of confidence of the model in the image classification result.

[0063] Determining the confidence level of a road surface type has several key functions:

[0064] 1. Decision basis: In practical applications, further decisions can be made based on the confidence of the model. For example, in an automated system, relevant actions are only performed when the model is sufficiently confident about a certain prediction result.

[0065] 2. Performance evaluation: By analyzing the model’s confidence in its predictions, we can better understand the model’s performance, including under what circumstances it is more or less confident, which can help diagnose model deficiencies and make improvements.

[0066] 3. Uncertainty management: In some applications, it is very important to understand the uncertainty of model predictions. When the model's confidence in the prediction is too low, it may indicate that human intervention or the use of other sources of information is needed to make the final decision, because the classification results obtained at this time are unreliable and may cause a significant impact on the subsequent calculation process.

[0067] Step 103: Determine a target road adhesion coefficient according to the road type confidence, the calculated road adhesion coefficient and the estimated road adhesion coefficient, determine a current limit torque according to the target road adhesion coefficient, the front axle load and the rear axle load, and perform limit control on the requested torque according to the current limit torque.

[0068] In specific implementation, the estimated road adhesion coefficient is represented as f1; the calculated road adhesion coefficient is represented as f2; then the relative coefficient error between the estimated road adhesion coefficient and the calculated road adhesion coefficient is Then the process of determining the target road adhesion coefficient f is:

[0069] (1) Road surface type confidence α>α1, u f <k f , target road adhesion coefficient f=f1.

[0070] (2) Road surface type confidence α>α1, u f ≥k f , target road adhesion coefficient

[0071] (3) Road surface type confidence α≤α1, f=f2.

[0072] Among them, α1 represents the confidence threshold, k f Relative error threshold.

[0073] According to the different road type confidence and relative coefficient errors, different values ​​of the target road adhesion coefficient are determined to ensure the accuracy of the target road adhesion coefficient under different conditions and the accuracy of the torque limit. Finally, the current limit torque that meets the current working conditions is determined by looking up the table according to the target road adhesion coefficient f, the front axle load m1 and the rear axle load m2, and the requested torque is limited to a range less than or equal to the current limit torque to ensure that the wheels will not slip due to excessive request torque, and to ensure power performance and safety while fully utilizing the target road adhesion coefficient.

[0074] In summary, the torque limiting method provided in the embodiment of the present application introduces the navigation estimated vehicle speed and the wheel speed to correct the current detected vehicle speed when calculating the current slip rate, thereby ensuring the accuracy of the current slip rate, thereby improving the accuracy of calculating the road adhesion coefficient, and improving the accuracy of the torque limiting. When estimating the road adhesion coefficient, the accuracy of the road type recognition is improved by correcting the recognition area of ​​the current scanned image, thereby improving the accuracy of the estimated road adhesion coefficient and ensuring the accuracy of the torque limiting. When determining the limiting torque, the road type confidence is introduced to narrow the gap between the target road adhesion coefficient and the true value, so as to ensure the accuracy of the limiting torque determined according to the target road adhesion coefficient, thereby ensuring that when requesting the limit according to the limiting torque, the target road adhesion coefficient can be fully utilized, and the wheels of the vehicle will not slip while ensuring the power, thereby ensuring the safety of driving.

[0075] In some embodiments, Figure 2 As shown, the reference vehicle speed is determined according to the navigation estimated vehicle speed, the current detected vehicle speed and the wheel speed of each wheel, including:

[0076] Step 201: Determine an average wheel speed according to the wheel speed of each wheel, and determine a separation coefficient according to the average wheel speed and the wheel speed.

[0077] In a specific implementation, if the wheel speed of the left front wheel is y1, if the wheel speed of the right front wheel is y2, if the wheel speed of the left rear wheel is y3, if the wheel speed of the right rear wheel is y4, then the average wheel speed

[0078] The separation coefficient is expressed by the mean square error of the wheel speeds, and the calculation process of the separation coefficient is:

[0079]

[0080] Among them, y i represents the wheel speed of the i-th wheel.

[0081] Step 202: Determine a vehicle speed error value based on the current detected vehicle speed and the navigation estimated vehicle speed.

[0082] In specific implementation, the speed error value is the relative error value of the current detected speed relative to the navigation estimated speed, and the speed error value is:

[0083]

[0084] In order to facilitate the subsequent determination and calculation process, the absolute value of the difference between the current detected vehicle speed and the navigation estimated vehicle speed is used to calculate the relative error value.

[0085] Step 203: Determine a reference vehicle speed from the average wheel speed, the navigation estimated vehicle speed and the current detected vehicle speed according to the vehicle speed error value and the separation coefficient.

[0086] In some embodiments, step 203 includes:

[0087] Step 2031: In response to the separation coefficient being less than a preset first coefficient threshold, determining the average wheel speed as a reference vehicle speed.

[0088] In specific implementation, if the separation coefficient is less than the preset first coefficient threshold value K1, the wheel speeds of the four wheels are similar, indicating that there is almost no wheel spin, vehicle flying over the slope (four wheels hanging in the air), and crossed axles. The credibility of the average wheel speed is high, and the average wheel speed is determined as the reference vehicle speed. That is, when 0≤MSE<K1 exists, let To ensure the accuracy of the reference speed.

[0089] Step 2032: In response to the vehicle speed error value being greater than or equal to a preset vehicle speed error threshold, and the separation coefficient being greater than or equal to a preset first coefficient threshold, determining the navigation estimated vehicle speed as a reference vehicle speed.

[0090] In specific implementation, when the speed error value is greater than or equal to the preset speed error threshold, that is, u≥k u When , it means that there is a large difference between the calculated value of the dynamic model and the estimated value predicted by the navigation data, indicating that there is unreliable data in the navigation estimated vehicle speed and the current detected vehicle speed. If the separation coefficient at this time is greater than or equal to the preset first coefficient threshold K1, it means that there is a certain difference between the wheel speeds of the four wheels, indicating that the vehicle may have wheel spinning, vehicle flying uphill (four wheels hanging in the air), crossed axles, etc. during driving, resulting in a large error between the current detected vehicle speed and the average wheel speed. The navigation estimated vehicle speed is more accurate than the current detected vehicle speed, so the more accurate navigation estimated vehicle speed is determined as the reference vehicle speed, that is, K1≤MSE, and u≥k u At any time, let V C =V g , to ensure the accuracy of the reference speed.

[0091] Step 2033: In response to the vehicle speed error value being less than a preset vehicle speed error threshold, and the separation coefficient being greater than or equal to a preset first coefficient threshold, and less than a preset second coefficient threshold, the average of the navigation estimated vehicle speed and the current detected vehicle speed is determined as the reference vehicle speed.

[0092] In specific implementation, the speed error value is less than the preset speed error threshold, that is, u <k u When , it indicates that there is a small difference between the calculated value of the dynamic model and the estimated value predicted by the navigation data, indicating that the navigation estimated vehicle speed and the current detected vehicle speed are both reliable data. If the separation coefficient is greater than or equal to the preset first coefficient threshold and less than the preset second coefficient threshold, that is, K1≤MSE<K2, it can be further verified that the probability of wheel spinning, vehicle flying uphill (four wheels hanging in the air), and crossed axles during driving is low, and the accuracy of the navigation estimated vehicle speed is similar to that of the current detected vehicle speed. Then, the average of the navigation estimated vehicle speed and the current detected vehicle speed is determined as the reference vehicle speed, that is, K1≤MSE<K2, and u <k u When V C =avg(V g ,V d ) to balance the error between the two and ensure the accuracy of the reference speed.

[0093] Step 2034: In response to the vehicle speed error value being less than a preset vehicle speed error threshold, and the separation coefficient being greater than or equal to a preset second coefficient threshold, a navigation corrected vehicle speed corresponding to the navigation estimated vehicle speed is determined according to preset navigation detection relationship data, and the navigation corrected vehicle speed is determined as the reference vehicle speed.

[0094] In specific implementation, the speed error value is less than the preset speed error threshold, that is, u <k u When , it means that there is a small difference between the calculated value of the dynamic model and the estimated value predicted by the navigation data, indicating that the navigation estimated vehicle speed and the current detected vehicle speed are both reliable data. If the separation coefficient at this time is greater than or equal to the preset second coefficient threshold, that is, K2≤MSE, it means that there is a high probability of wheel spinning, vehicle flying uphill (four wheels hanging in the air), and cross-axle during driving. The current detected vehicle speed and average wheel speed calculated according to the vehicle state parameters are not reliable. Because the navigation estimated vehicle speed is similar to the current detected vehicle speed, the credibility of the navigation estimated vehicle speed is also low. At this time, it is necessary to determine the navigation corrected vehicle speed corresponding to the navigation estimated vehicle speed according to the preset navigation detection relationship data, and determine the navigation corrected vehicle speed as the reference vehicle speed, that is, when K2≤MSE, and u <k u When V C =f(V C ,V g ), where f(V C,V g ) represents the fitting function relationship between the reference speed and the navigation estimated speed. At this time, the navigation estimated speed is taken as the input, and the corresponding output value is taken as the reference speed to realize the correction of the speed and ensure the accuracy of the reference speed.

[0095] In some embodiments, Figure 3 As shown, the recognition area of ​​the current scanned image is corrected according to the reference vehicle speed and the current front wheel turning angle to obtain a road surface recognition image, including:

[0096] Step 301: Determine the current network delay and the vertex pixel coordinates of the identification area.

[0097] When implementing it specifically, Figure 4a The fan-shaped area in the image represents the current scanned image. The recognition area when the vehicle is stationary is Figure 4a The area corresponding to the dotted box is a fixed area of ​​3.5m×10m, 3.5m in front of the vehicle, that is, Xmin=3.5m, Xmax=3.5+10=13.5m, Ymin=-1.75m, Ymin=1.75m (the distance value in the vehicle coordinate system in the actual space). At this time, the vertex pixel coordinates of the recognition area in the current scanned image are x_spd[i], i∈(1,2,3,4), indicating Figure 4a The pixel coordinates of the four vertices of the dashed box.

[0098] Step 302: Determine the longitudinal offset according to the reference vehicle speed and the current network delay.

[0099] In specific implementation, due to the network delay, the current scanned image is relatively lagging, so the recognition area needs to be offset forward (away from the vehicle direction) to ensure the advance estimation area of ​​the previous scanned image that is transmitted with a lag in the recognition area, so as to offset the offset caused by the network delay, and the calculation formula of the longitudinal offset Plex of the forward offset is:

[0100] Plex=V c ×(1000 / FPS+90)×0.034 / x

[0101] Among them, FPS is the camera frame rate of the vehicle's front-view camera, 90 represents the network delay, and 0.034 is the scale of the scanned image. When the vehicle is moving straight forward, Figure 4a As shown, the identification area is offset forward by Plex.

[0102] Step 303: Determine the lateral offset according to the vertex pixel coordinates and the current front wheel steering angle.

[0103] In specific implementation, if the vehicle is Figure 4bFor the turning driving condition shown in the figure, the lateral offset pts_l needs to be determined based on the vertex pixel coordinates and the current front wheel turning angle:

[0104]

[0105] Among them, v represents the front wheel turning angle, and L represents the vehicle wheelbase.

[0106] Step 304: Correct the position of the recognition area according to the longitudinal offset and the lateral offset to obtain a corrected recognition area, and select an image in the current scanned image according to the corrected recognition area to obtain a road surface recognition image.

[0107] In specific implementation, since the vehicle will move forward at the same time when turning, there will be both lateral and longitudinal offsets. Therefore, the recognition area in the stationary state needs to be corrected in two directions, that is, the longitudinal offset is offset forward while the lateral offset is offset in the turning direction. The corrected recognition area is as follows: Figure 4b As shown. The part selected by the corrected recognition area in the current scanned image is the road surface recognition image. By classifying and recognizing the road surface recognition image, the corresponding road surface type and road surface type confidence can be determined, providing data support for determining the estimated road surface adhesion coefficient.

[0108] In some embodiments, Figure 5 As shown, the road surface recognition image is classified to obtain the estimated road surface adhesion coefficient and road surface type confidence, including:

[0109] Step 501: performing image classification on the road surface recognition image to obtain the road surface type and road surface type confidence corresponding to the road surface recognition image.

[0110] In the specific implementation, the collected road surface recognition images are used for image classification. Image classification can be performed using machine learning, such as support vector machines, decision trees and other machine learning models, or deep learning image classification methods, such as MobileNet, ResNet, etc. The embodiment of the present application uses a deep learning method for image classification, and uses a trained MobileNetV2 model to classify the road surface recognition images to obtain the road surface type and road surface type confidence α. Among them, the MobileNetV2 model can be trained using a preset road surface library to obtain a trained MobileNetV2 model.

[0111] Step 502: Determine a search value corresponding to the road surface type according to a preset type coefficient relationship, and determine the search value as the estimated road surface adhesion coefficient.

[0112] In specific implementation, the type coefficient relationship may be a relationship table between road surface type and road surface adhesion coefficient range as shown in Table 1, or a relationship table between road surface type and road surface adhesion coefficient value. For example, when the type coefficient relationship is a relationship table between road surface type and road surface adhesion coefficient range as shown in Table 1,

[0113] For example, in an image classification task, the model may need to classify the input image into the corresponding road surface type. For a road surface recognition image, the MobileNetV2 model may output the following probabilities: asphalt or concrete = 0.70, asphalt (wet) = 0.25, dirt road = 0.05. The model has the highest classification confidence of 70% for the road surface type as asphalt or concrete. The corresponding road surface type is asphalt or concrete, the corresponding road surface adhesion coefficient range is 0.8 to 1.2, and the corresponding search value is the maximum value of the road surface adhesion coefficient range. The search value is 1.2, and the corresponding estimated road surface adhesion coefficient is 1.2, realizing a single estimate of the corresponding road surface adhesion coefficient.

[0114] In some embodiments, Figure 6 As shown, the target road adhesion coefficient is determined according to the road type confidence, the calculated road adhesion coefficient and the estimated road adhesion coefficient, including:

[0115] Step 601: In response to the road type confidence being less than a preset confidence threshold, the calculated road adhesion coefficient is determined as a target road adhesion coefficient.

[0116] In specific implementation, the estimated road adhesion coefficient is represented as f1; the calculated road adhesion coefficient is represented as f2; if the road type confidence is less than the preset confidence threshold, it means that the credibility of the estimated road adhesion coefficient is low. At this time, the calculated road adhesion coefficient is determined as the target road adhesion coefficient, that is, when the road type confidence α is less than α1, let f=f2 to ensure the accuracy of the target road adhesion coefficient.

[0117] Step 602: In response to the road type confidence being greater than or equal to a preset confidence threshold, determining a relative coefficient error based on the calculated road adhesion coefficient and the estimated road adhesion coefficient.

[0118] In specific implementation, if the road type confidence is greater than or equal to the preset confidence threshold, it means that the estimated road adhesion coefficient is highly reliable. At this time, the relative coefficient error is determined based on the calculated road adhesion coefficient and the estimated road adhesion coefficient. Used to represent the error of the calculated road adhesion coefficient f2 relative to the estimated road adhesion coefficient f1.

[0119] Step 603: In response to the relative coefficient error being less than a preset relative error threshold, the estimated road adhesion coefficient is determined as the target road adhesion coefficient.

[0120] In specific implementation, if the relative coefficient error is less than the preset relative error threshold k f , indicating that the calculated road adhesion coefficient f2 and the estimated road adhesion coefficient f1 are close in value. Since the road type confidence is relatively large at this time, the estimated road adhesion coefficient is determined as the target road adhesion coefficient. That is, the road type confidence α≥α1, u f <k f When f=f1, the target road adhesion coefficient is guaranteed to be accurate.

[0121] Step 604: In response to the relative coefficient error being greater than or equal to a preset relative error threshold, determining an average value of the calculated road adhesion coefficient and the estimated road adhesion coefficient as a target road adhesion coefficient.

[0122] In specific implementation, if the relative coefficient error is greater than or equal to the preset relative error threshold k f , indicating that the calculated road adhesion coefficient f2 and the estimated road adhesion coefficient f1 have a large difference. In this case, the calculated road adhesion coefficient is expressed as the average value of f2 and the estimated road adhesion coefficient f1. Determine the target road adhesion coefficient to balance the error and ensure the accuracy of the target road adhesion coefficient. That is, the road type confidence α≥α1, u f ≥k f season To ensure the accuracy of the target road adhesion coefficient.

[0123] In some embodiments, Figure 7 As shown, the current limit torque is determined according to the target road adhesion coefficient, the front axle load and the rear axle load, including:

[0124] Step 701: Determine a target coefficient torque relationship in a preset relationship database according to the front axle load and the rear axle load.

[0125] In specific implementation, there is a four-dimensional relationship between front axle load-rear axle load-target road adhesion coefficient-limiting torque in the preset relational database. Since the front axle load and the rear axle load can be monitored in real time, the target coefficient torque relationship is first determined in the preset relational database through the front axle load and the rear axle load, that is, the four-dimensional relationship is reduced to a two-dimensional target coefficient torque relationship. The target coefficient torque relationship is a two-dimensional relationship between the target road adhesion coefficient and the limiting torque.

[0126] Step 702: Determine a search torque corresponding to a target road adhesion coefficient according to the target coefficient torque relationship, and determine the search torque as a current limit torque.

[0127] In specific implementation, in the two-dimensional target coefficient torque relationship, the target road adhesion coefficient is the input value, and the search is performed based on the input value. The output search torque is the current limit torque, thereby limiting the requested torque, ensuring power while preventing wheel slippage and ensuring driving safety.

[0128] In some embodiments, Figure 8 As shown, the request torque is limited and controlled according to the current limited torque, including:

[0129] Step 801 : In response to the requested torque being less than or equal to the current torque limit, the drive motor is controlled to output according to the requested torque.

[0130] In specific implementation, if the requested torque is less than or equal to the current limit torque, it means that outputting with the requested torque will not cause wheel slippage. At this time, there is no safety risk. The main focus is on power, and the drive motor is controlled to output according to the requested torque to meet the user's request.

[0131] Step 802 : In response to the request torque being greater than the current torque limit, the drive motor is controlled to output according to the current torque limit.

[0132] During specific implementation, if the requested torque is greater than or equal to the current limit torque, it means that outputting with the requested torque will cause wheel slippage. At this time, there is a safety risk. With safety as the priority, the maximum torque that will not cause slippage - the current limit torque is used as the actual requested torque, and the drive motor is controlled to output according to the current limit torque, ensuring power while ensuring that the wheels will not slip, thereby ensuring driving safety.

[0133] It should be noted that the method of the embodiment of the present application can be performed by a single device, such as a computer or server. The method of this embodiment can also be applied to a distributed scenario and completed by multiple devices cooperating with each other. In the case of such a distributed scenario, one of the multiple devices can only perform one or more steps in the method of the embodiment of the present application, and the multiple devices will interact with each other to complete the described method.

[0134] It should be noted that the above describes some embodiments of the present application. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the above embodiments and still achieve the desired results. In addition, the processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0135] Based on the same inventive concept, corresponding to any of the above-mentioned embodiments and methods, the present application also provides a torque limiting device.

[0136] refer to Fig. 9 , the torque limiting device comprises:

[0137] The first coefficient determination module 10 is configured to: determine a reference vehicle speed according to the navigation estimated vehicle speed, the current detected vehicle speed and the wheel speed of each wheel, determine a current slip ratio according to the reference vehicle speed and the wheel linear speed of the driving wheel, and determine and calculate a road adhesion coefficient according to the current slip ratio and a preset dynamic model;

[0138] The second coefficient determination module 20 is configured to: modify the recognition area of ​​the current scanned image according to the reference vehicle speed and the current front wheel steering angle to obtain a road surface recognition image, and classify the road surface recognition image to obtain an estimated road surface adhesion coefficient and a road surface type confidence;

[0139] The torque limit control module 30 is configured to: determine the target road adhesion coefficient based on the road type confidence, the calculated road adhesion coefficient and the estimated road adhesion coefficient, determine the current limit torque based on the target road adhesion coefficient, the front axle load and the rear axle load, and limit the requested torque based on the current limit torque.

[0140] For the convenience of description, the above device is described in terms of functions divided into various modules. Of course, when implementing the present application, the functions of each module can be implemented in the same or multiple software and / or hardware.

[0141] The device of the above embodiment is used to implement the corresponding torque limiting method in any of the above embodiments, and has the beneficial effects of the corresponding method embodiment, which will not be described in detail here.

[0142] Based on the same inventive concept, corresponding to any of the above-mentioned embodiments and methods, the present application also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the torque limiting method described in any of the above embodiments is implemented.

[0143] Fig.10 A more specific schematic diagram of the hardware structure of an electronic device provided in this embodiment is shown, and the device may include: a processor 1010, a memory 1020, an input / output interface 1030, a communication interface 1040, and a bus 1050. The processor 1010, the memory 1020, the input / output interface 1030, and the communication interface 1040 are connected to each other through the bus 1050 in the device.

[0144] The processor 1010 can be implemented by a general-purpose CPU (Central Processing Unit), a microprocessor, an application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of this specification.

[0145] The memory 1020 may be implemented in the form of ROM (Read Only Memory), RAM (Random Access Memory), static storage device, dynamic storage device, etc. The memory 1020 may store an operating system and other application programs. When the technical solutions provided in the embodiments of this specification are implemented by software or firmware, the relevant program codes are stored in the memory 1020 and are called and executed by the processor 1010.

[0146] The input / output interface 1030 is used to connect the input / output module to realize information input and output. The input / output module can be configured in the device as a component (not shown in the figure), or it can be externally connected to the device to provide corresponding functions. The input device may include a keyboard, a mouse, a touch screen, a microphone, various sensors, etc., and the output device may include a display, a speaker, a vibrator, an indicator light, etc.

[0147] The communication interface 1040 is used to connect a communication module (not shown) to realize communication interaction between the device and other devices. The communication module can realize communication through a wired mode (such as USB, network cable, etc.) or a wireless mode (such as mobile network, WIFI, Bluetooth, etc.).

[0148] The bus 1050 includes a path that transmits information between the various components of the device (eg, the processor 1010, the memory 1020, the input / output interface 1030, and the communication interface 1040).

[0149] It should be noted that, although the above device only shows the processor 1010, the memory 1020, the input / output interface 1030, the communication interface 1040 and the bus 1050, in the specific implementation process, the device may also include other components necessary for normal operation. In addition, it can be understood by those skilled in the art that the above device may also only include the components necessary for implementing the embodiments of the present specification, and does not necessarily include all the components shown in the figure.

[0150] The electronic device of the above embodiment is used to implement the corresponding torque limiting method in any of the above embodiments, and has the beneficial effects of the corresponding method embodiment, which will not be described in detail here.

[0151] Based on the same inventive concept, corresponding to any of the above-mentioned embodiment methods, the present application also provides a non-transitory computer-readable storage medium, wherein the non-transitory computer-readable storage medium stores computer instructions, and the computer instructions are used to enable the computer to execute the torque limiting method described in any of the above embodiments.

[0152] The computer-readable medium of this embodiment includes permanent and non-permanent, removable and non-removable media, and information storage can be implemented by any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, read-only compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, tape disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device.

[0153] The computer instructions stored in the storage medium of the above embodiment are used to enable the computer to execute the torque limiting method described in any of the above embodiments, and have the beneficial effects of the corresponding method embodiments, which will not be repeated here.

[0154] Based on the same inventive concept, corresponding to any of the above-mentioned embodiments and methods, the present application also provides a vehicle, including the electronic device or torque limiting device of the above-mentioned embodiment, and the torque limiting method described in any of the above embodiments is executed through the electronic device or torque limiting device of the above-mentioned embodiment, and has the beneficial effects of the corresponding method embodiments, which will not be repeated here.

[0155] It is understandable that before using the technical solutions of each embodiment of the present disclosure, the type, scope of use, usage scenarios, etc. of the personal information involved will be informed to the user in an appropriate manner, and the user's authorization will be obtained.

[0156] For example, in response to receiving an active request from a user, a prompt message is sent to the user to clearly remind the user that the operation requested to be performed will require obtaining and using the user's personal information. Thus, the user can independently choose whether to provide personal information to software or hardware such as an electronic device, application, server, or storage medium that performs the operation of the technical solution of the present disclosure according to the prompt message.

[0157] As an optional but non-limiting implementation, in response to receiving the user's active request, the prompt information may be sent to the user in the form of a pop-up window, in which the prompt information may be presented in text form. In addition, the pop-up window may also carry a selection control for the user to choose "agree" or "disagree" to provide personal information to the electronic device.

[0158] It is understandable that the above notification and the process of obtaining user authorization are merely illustrative and do not constitute a limitation on the implementation of the present disclosure. Other methods that meet relevant laws and regulations may also be applied to the implementation of the present disclosure.

[0159] A person skilled in the art should understand that the discussion of any of the above embodiments is merely illustrative and is not intended to imply that the scope of the present application is limited to these examples. In line with the concept of the present application, the technical features in the above embodiments or different embodiments may be combined, the steps may be implemented in any order, and there are many other variations of the different aspects of the embodiments of the present application as described above, which are not provided in detail for the sake of simplicity.

[0160] In addition, to simplify the description and discussion, and in order not to make the embodiments of the present application difficult to understand, the known power supply / ground connection with the integrated circuit (IC) chip and other components may or may not be shown in the provided drawings. In addition, the device can be shown in the form of a block diagram to avoid making the embodiments of the present application difficult to understand, and this also takes into account the fact that the details of the implementation of these block diagram devices are highly dependent on the platform to be implemented in the embodiments of the present application (that is, these details should be fully within the scope of understanding of those skilled in the art). In the case of elaborating specific details (e.g., circuits) to describe exemplary embodiments of the present application, it is obvious to those skilled in the art that the embodiments of the present application can be implemented without these specific details or when these specific details are changed. Therefore, these descriptions should be considered to be illustrative rather than restrictive.

[0161] Although the present application has been described in conjunction with specific embodiments of the present application, many replacements, modifications and variations of these embodiments will be apparent to those skilled in the art from the foregoing description. For example, other memory architectures (e.g., dynamic RAM (DRAM)) may use the embodiments discussed.

[0162] The embodiments of the present application are intended to cover all such substitutions, modifications and variations that fall within the broad scope of the present application. Therefore, any omissions, modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the embodiments of the present application should be included in the protection scope of the present application.

Claims

1. A torque limiting method, characterized in that: include: Determine a reference vehicle speed according to the navigation estimated vehicle speed, the current detected vehicle speed and the wheel speed of each wheel, determine a current slip rate according to the reference vehicle speed and the wheel linear speed of the driving wheel, and determine and calculate a road adhesion coefficient according to the current slip rate and a preset dynamic model; Correcting the recognition area of ​​the current scanned image according to the reference vehicle speed and the current front wheel steering angle to obtain a road surface recognition image, and classifying the road surface recognition image to obtain an estimated road surface adhesion coefficient and a road surface type confidence; A target road adhesion coefficient is determined according to the road type confidence, the calculated road adhesion coefficient and the estimated road adhesion coefficient, and a current limit torque is determined according to the target road adhesion coefficient, the front axle load and the rear axle load, and a request torque is limited and controlled according to the current limit torque.

2. The torque limiting method according to claim 1, characterized in that: The step of determining the reference vehicle speed according to the navigation estimated vehicle speed, the current detected vehicle speed and the wheel speed of each wheel comprises: determining an average wheel speed based on the wheel speed of each wheel, and determining a separation factor based on the average wheel speed and the wheel speed; Determine a vehicle speed error value according to the current detected vehicle speed and the navigation estimated vehicle speed; The reference vehicle speed is determined from among the average wheel speed, the navigation estimated vehicle speed and the current detected vehicle speed according to the vehicle speed error value and the separation coefficient.

3. The torque limiting method according to claim 2, characterized in that: The step of determining the reference vehicle speed from the average wheel speed, the navigation estimated vehicle speed and the current detected vehicle speed according to the vehicle speed error value and the separation coefficient comprises: In response to the separation coefficient being less than a preset first coefficient threshold, determining the average wheel speed as the reference vehicle speed; In response to the vehicle speed error value being greater than or equal to a preset vehicle speed error threshold, and the separation coefficient being greater than or equal to a preset first coefficient threshold, determining the navigation estimated vehicle speed as the reference vehicle speed; In response to the vehicle speed error value being less than a preset vehicle speed error threshold, and the separation coefficient being greater than or equal to a preset first coefficient threshold, and less than a preset second coefficient threshold, determining an average value of the navigation estimated vehicle speed and the current detected vehicle speed as the reference vehicle speed; In response to the vehicle speed error value being less than a preset vehicle speed error threshold and the separation coefficient being greater than or equal to a preset second coefficient threshold, a navigation corrected vehicle speed corresponding to the navigation estimated vehicle speed is determined according to preset navigation detection relationship data, and the navigation corrected vehicle speed is determined as the reference vehicle speed.

4. The torque limiting method according to claim 1, characterized in that: The step of correcting the recognition area of ​​the current scanned image according to the reference vehicle speed and the current front wheel turning angle to obtain a road surface recognition image includes: Determining the current network delay and the vertex pixel coordinates of the identified area; determining a longitudinal offset according to the reference vehicle speed and the current network delay; Determine a lateral offset according to the vertex pixel coordinates and the current front wheel turning angle; The position of the recognition area is corrected according to the longitudinal offset and the lateral offset to obtain a corrected recognition area, and an image is selected in the current scanned image according to the corrected recognition area to obtain the road surface recognition image.

5. The torque limiting method according to claim 1, characterized in that: The performing image classification on the road surface recognition image to obtain an estimated road surface adhesion coefficient and a road surface type confidence level includes: Performing image classification on the road surface recognition image to obtain a road surface type corresponding to the road surface recognition image and a confidence level of the road surface type; A retrieval value corresponding to the road surface type is determined according to a preset type coefficient relationship, and the retrieval value is determined as the estimated road surface adhesion coefficient.

6. The torque limiting method according to claim 1, characterized in that: The determining of the target road surface adhesion coefficient according to the road surface type confidence, the calculated road surface adhesion coefficient and the estimated road surface adhesion coefficient comprises: In response to the road type confidence being less than a preset confidence threshold, determining the calculated road adhesion coefficient as the target road adhesion coefficient; In response to the road type confidence being greater than or equal to a preset confidence threshold, determining a relative coefficient error based on the calculated road adhesion coefficient and the estimated road adhesion coefficient; In response to the relative coefficient error being less than a preset relative error threshold, determining the estimated road surface adhesion coefficient as the target road surface adhesion coefficient; In response to the relative coefficient error being greater than or equal to a preset relative error threshold, an average value of the calculated road adhesion coefficient and the estimated road adhesion coefficient is determined as the target road adhesion coefficient.

7. The torque limiting method according to claim 1, characterized in that: The determining the current limit torque according to the target road adhesion coefficient, the front axle load and the rear axle load comprises: Determining a target coefficient torque relationship in a preset relationship database according to the front axle load and the rear axle load; A search torque corresponding to the target road surface adhesion coefficient is determined according to the target coefficient torque relationship, and the search torque is determined as the current limit torque.

8. The torque limiting method according to claim 1, characterized in that: The limiting control of the requested torque according to the current limited torque includes: In response to the requested torque being less than or equal to the current limit torque, controlling the drive motor to output according to the requested torque; In response to the request torque being greater than the current limit torque, the drive motor is controlled to output according to the current limit torque.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that: When the processor executes the program, the method according to any one of claims 1 to 8 is implemented.

10. A vehicle, characterized in that: Comprising the electronic device as claimed in claim 9.

Images