Vehicle road surface anti-slip control method, device and system

Abstract

This application provides a vehicle road surface anti-skid control method, device, and system. The method is applied to a vehicle motor controller and includes: receiving, in real time, the road surface type identification result sent by the on-board environmental perception sensor during vehicle operation; searching for the target optimal drive torque MAP corresponding to the road surface type identification result based on a pre-built road surface-torque MAP database; the road surface-torque MAP database stores the optimal drive torque MAPs corresponding to various road surface types; and controlling the torque of the drive motor according to the found target optimal drive torque MAP. This application changes the anti-skid control logic from "responding after slippage" to "pre-setting after identification," fundamentally preventing slippage by sensing the road surface in advance and calling the preset optimal drive strategy.

Description

Technical Field

[0001] This application relates to the field of new energy vehicle technology, and in particular to a method, device and system for vehicle road surface anti-skid control. Background Technology

[0002] With the rapid development of new energy vehicles and their increasing market share, the safety requirements for electric vehicles are also becoming increasingly stringent, especially the precise control of torque in electric drive systems. Currently, the mainstream protection methods on the market are ABS and TCS. Traditional ABS / TCS rely on wheel speed sensors to detect wheel speed differences before triggering the mechanical braking system. This hydraulic build-up process has a delay of tens to hundreds of milliseconds, which may not be enough to prevent slippage on low-traction surfaces (such as ice) or during sudden high torque demands (rapid acceleration). Furthermore, the intervention of mechanical braking may produce shocks and jerks, affecting ride comfort. Also, abrupt braking and torque reduction may excessively suppress power, resulting in sluggish acceleration. When the drive wheels of an electric vehicle are running on low-traction surfaces (such as ice or snow), due to the fast torque response and high output torque of the motor, wheel slippage is highly likely. This not only leads to sluggish acceleration and wasted energy but is also a significant factor threatening driving safety.

[0003] Existing anti-slip methods for motor controllers generally only take measures to reduce torque or brake after the drive wheel has already slipped. This reactive approach has problems such as control lag and limited ability to cope with complex road conditions. Summary of the Invention

[0004] The purpose of this application is to provide a vehicle road surface anti-skid control method, device and system that changes the control logic from "responding after skidding" to "pre-setting after identification", thereby fundamentally preventing skidding by sensing the road surface in advance and calling the preset optimal driving strategy.

[0005] In a first aspect, this application provides a vehicle road surface anti-skid control method, which is applied to a vehicle motor controller. The method includes: receiving in real time the road surface type identification result sent by the on-board environmental perception sensor during vehicle operation; searching for the target optimal driving torque MAP corresponding to the road surface type identification result based on a pre-built road surface-torque MAP database; the road surface-torque MAP database stores the optimal driving torque MAP corresponding to various road surface types; and performing torque control on the drive motor according to the found target optimal driving torque MAP.

[0006] Furthermore, the aforementioned vehicle-mounted environmental perception sensor is a vehicle-mounted camera; the road surface type recognition result includes: the road surface type identified by the vehicle-mounted camera within a specified range in front of the vehicle through a built-in road surface type recognition model; wherein, the road surface type recognition model includes: an image classification model or a semantic segmentation model trained based on deep learning.

[0007] Furthermore, the above road surface type identification results include at least one road surface type; the road surface type is one of the following: dry asphalt road surface, wet asphalt road surface, snow-covered road surface, icy road surface, gravel road surface, mud road surface, block road surface, and cement concrete road surface.

[0008] Furthermore, the above-mentioned steps for torque control of the drive motor based on the found target optimal drive torque MAP include: if multiple road surface types are identified, the target optimal drive torque MAP corresponding to the target road surface is called in advance based on the predicted wheel trajectory, vehicle navigation path or driver steering intention, so as to perform torque control of the drive motor based on the target optimal drive torque MAP after entering the target road surface.

[0009] Furthermore, the aforementioned target optimal drive torque MAP stores the correspondence between accelerator pedal opening, motor speed, and motor drive torque. The steps of torque control of the drive motor based on the target optimal drive torque MAP include: obtaining the vehicle's current accelerator pedal opening and current motor speed; finding the motor drive torque that best matches the accelerator pedal opening and current motor speed from the target optimal drive torque MAP; and controlling the drive motor to work based on the best-matching motor drive torque.

[0010] Furthermore, the above method also includes: monitoring the real-time slip ratio of the drive wheels through wheel speed sensors; when the real-time slip ratio exceeds a safety threshold, prioritizing the activation of rapid torque reduction control based on slip ratio.

[0011] Furthermore, the construction process of the aforementioned road surface-torque MAP database is as follows: For each specified road surface type, the following steps are performed: Drive tests are conducted on a pre-arranged road surface of the specified road surface type under different operating conditions using test vehicles; Motor torque output curves under different operating conditions are collected during the drive test; Operating conditions include: accelerator pedal opening and motor speed; The motor torque output curve can maximize the use of ground adhesion while ensuring smooth vehicle start-up and acceleration; Based on the motor torque output curves under different operating conditions, a two-dimensional MAP map is plotted with accelerator pedal opening and motor speed as inputs and optimal limiting torque as output, and stored in the road surface-torque MAP database.

[0012] Secondly, this application also provides a vehicle road surface anti-skid control device, which is applied to a vehicle motor controller. The device includes: a road surface type receiving module, used to receive in real time the road surface type identification result sent by the vehicle environment perception sensor during vehicle operation; a torque lookup module, used to look up the target optimal driving torque MAP corresponding to the road surface type identification result based on a pre-built road surface-torque MAP database; the road surface-torque MAP database stores the optimal driving torque MAP corresponding to various road surface types; and a motor torque control module, used to control the torque of the drive motor according to the found target optimal driving torque MAP.

[0013] Thirdly, this application also provides a vehicle road surface anti-skid control system, the system comprising: an on-board environmental perception sensor and a vehicle motor controller connected in communication; the on-board environmental perception sensor is used to acquire the road surface type identification result in front of the vehicle; the vehicle motor controller is used to execute the method described in the first aspect.

[0014] Fourthly, this application also provides a computer-readable storage medium storing computer-executable instructions, which, when invoked and executed by a processor, cause the processor to implement the method described in the first aspect above.

[0015] The vehicle road surface anti-skid control method, device, and system provided in this application first receive the road surface type identification results sent by the on-board environmental perception sensor in real time during vehicle operation; then, based on a pre-built road surface-torque MAP database, it searches for the target optimal drive torque MAP corresponding to the road surface type identification result; this road surface-torque MAP database stores the optimal drive torque MAPs corresponding to various road surface types; finally, it controls the torque of the drive motor according to the found target optimal drive torque MAP. This method changes the anti-skid control logic from "responding after slippage" to "pre-setting after identification," fundamentally preventing slippage by sensing the road surface in advance and calling the preset optimal drive strategy. Attached Figure Description

[0016] To more clearly illustrate the technical solutions in the specific embodiments of this application or the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this application. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0017] Figure 1 A flowchart of a vehicle road surface anti-skid control method provided in this application embodiment; Figure 2This is a schematic diagram of the overall process of a vehicle road surface anti-skid control method provided in an embodiment of this application; Figure 3 This application provides a schematic diagram of a predictive MAP invocation. Figure 4 A structural block diagram of a vehicle road surface anti-skid control device provided in an embodiment of this application; Figure 5 This is a schematic diagram of a vehicle road surface anti-skid control system provided in an embodiment of this application. Detailed Implementation

[0018] The technical solutions of this application will be clearly and completely described below with reference to the embodiments. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0019] Existing anti-slip methods for motor controllers, whether rule-based slip ratio control (such as PID control) or model-based complex algorithm control, are essentially "responsive." That is, the system only takes torque reduction or braking measures after detecting that the drive wheels have slipped (manifested as a sudden change in wheel speed and an increase in slip ratio). This "remedial" approach has inherent flaws: ① Control lag: There is inevitably a time delay from the occurrence of slippage to its detection, and then to the execution of torque adjustment. Although the electric motor responds faster than the hydraulic system, even a brief delay can lead to vehicle dynamic instability on roads with extremely low traction.

[0020] ② The contradiction between smoothness and power: In order to prevent slippage, the control strategy tends to be conservative, which may excessively suppress torque, resulting in soft acceleration and failure to make full use of the maximum adhesion provided by the road surface, affecting the driving experience and vehicle performance.

[0021] ③Limited ability to cope with complex road conditions: When the vehicle is driving on a road surface with drastic changes in the coefficient of friction (such as suddenly driving from ice to dry ground), the responsive control may cause the vehicle to vibrate due to frequent and drastic torque adjustments.

[0022] Therefore, existing technologies lack a predictive anti-skid control scheme that can adjust the drive strategy in advance before slippage occurs, thus achieving "prevention before the problem occurs".

[0023] Based on this, embodiments of this application provide a vehicle road surface anti-skid control method, device, and system, which transforms the control logic from "responding after skidding" to "presetting after identification." By sensing the road surface in advance and invoking a preset optimal driving strategy, skidding is fundamentally prevented. To facilitate understanding of this embodiment, a detailed description of the vehicle road surface anti-skid control method disclosed in this application embodiment will be provided first.

[0024] Figure 1 A flowchart of a vehicle road surface anti-skid control method provided in this application embodiment is shown. The method is applied to a vehicle motor controller and specifically includes the following steps: Step S102: During vehicle operation, receive the road surface type identification results sent by the on-board environmental perception sensor in real time. The aforementioned vehicle-mounted environmental perception sensor can be a vehicle-mounted camera. During vehicle operation, the camera captures real-time images of the road surface ahead and identifies the road type in the images using a preset algorithm. The road type identification algorithm can include various implementations, which are not specifically limited here.

[0025] The road surface type recognition results include: the road surface type identified by the vehicle camera within a specified range in front of the vehicle through the built-in road surface type recognition model; wherein, the road surface type recognition model includes: an image classification model or a semantic segmentation model trained based on deep learning.

[0026] The road surface type identification results mentioned above can include one or more of the following: dry asphalt, wet asphalt, snow, ice, gravel, and mud road surface.

[0027] Step S104: Based on the pre-built road surface-torque MAP database, find the target optimal driving torque MAP corresponding to the road surface type identification result; The road surface-torque MAP (Mapping Table) database stores the optimal driving torque MAPs corresponding to various road surface types. These MAPs contain the optimal correspondence between motor driving torque, accelerator pedal opening, and motor speed. Essentially, the optimal driving torque MAP is a data table.

[0028] Based on the road surface type identification results received in the previous step, the corresponding target optimal driving torque MAP can be found in the road surface-torque MAP database. The road surface type identification results include one or more road surface types; the road surface type is one of the following: dry asphalt pavement, wet asphalt pavement, snow-covered pavement, icy pavement, gravel pavement, mud pavement, block pavement, or cement concrete pavement. For multiple road surface types, searches can be performed separately in the road surface-torque MAP database, ultimately determining the target optimal driving torque MAP for each road surface type.

[0029] Step S106: Perform torque control on the drive motor based on the found target optimal drive torque MAP.

[0030] The target optimal drive torque MAP stores the optimal correspondence between motor drive torque, accelerator pedal opening, and motor speed. Therefore, based on the current motor speed and current accelerator pedal opening, the optimal motor drive torque can be determined, enabling the drive motor to perform optimal torque control.

[0031] The vehicle road surface anti-skid control method provided in this application pre-establishes an optimal drive torque MAP database for different typical road surfaces through motor calibration; uses an on-board vision sensor to identify the road surface type in front of the vehicle in real time; and, based on the identification result, retrieves the optimal drive torque MAP that matches it from the database in advance before the drive wheels enter the road surface, and hands it over to the motor controller to control the torque of the drive motor.

[0032] This application also provides a vehicle road surface anti-skid control method, which is implemented based on the previous embodiment. This embodiment focuses on describing the pre-calibration and MAP storage process, as well as the online anti-skid process of the actual vehicle.

[0033] See Figure 2 The overall flowchart shown illustrates the two main stages: offline calibration and online control.

[0034] Phase 1: Calibration and MAP storage procedure: For various typical road surfaces, the motor drive characteristics are calibrated to generate an optimal drive torque map (MAP) for anti-skid control corresponding to each road surface. This MAP is then constructed into a road surface-torque map database and stored in the vehicle motor controller. Typical road surfaces include, but are not limited to, dry asphalt roads, wet asphalt roads, snow-covered roads, icy roads, gravel roads, mud roads, block roads, and cement concrete roads. The construction process of the aforementioned road surface-torque MAP database is as follows: For each specified road surface type, perform the following steps: (1) Drive tests were conducted on test vehicles under different working conditions on pre-arranged road surfaces of specified road types; (2) Collect motor torque output curves under different working conditions during the drive test; the working conditions include: accelerator pedal opening and motor speed; the motor torque output curve can make the maximum use of ground adhesion and ensure smooth vehicle start and acceleration. (3) Based on the motor torque output curves under different working conditions, draw a two-dimensional MAP management table with the accelerator pedal opening and motor speed as inputs and the optimal motor drive torque as output, and store it in the road surface-torque MAP database.

[0035] In practice, during the vehicle development phase, extensive experiments can be conducted to calibrate the drive motor on various typical road surfaces (such as dry asphalt, wet asphalt, compacted snow, ice, and gravel roads). The goal of calibration is to find the motor torque output curve that, under the given road surface conditions, maximizes the use of ground adhesion (i.e., the drive wheels are near the optimal slip ratio) while ensuring smooth vehicle start-up and acceleration. These curves are then created as a two-dimensional map (MAP) with accelerator pedal opening and motor speed as inputs and the optimal limiting torque as the output. This MAP is stored as a complete "road surface-torque MAP" database in the vehicle's motor controller or relevant domain controller.

[0036] Specifically, this can be done by: setting up various typical road surfaces at the test site; equipping test vehicles with data acquisition systems; and conducting drive tests under multiple conditions (different pedal openings and speeds) on each type of road surface by professional drivers or robots. Collecting torque, pedal pressure, and speed data for each test when the vehicle does not slip and achieves optimal acceleration performance; and generating an optimal anti-slip torque map (MAP) for that type of road surface through data processing and optimization algorithms. The MAPs for all road surfaces are then compiled and burned into the motor controller of the production vehicle. Simultaneously, collecting a large amount of image data from various road surfaces is used to train a high-precision road surface recognition deep learning model, which is then integrated into the vehicle's vision processing unit, such as an onboard camera.

[0037] Phase Two: Online Control Phase 1. Environmental perception: During vehicle operation, the forward-facing camera captures real-time images of the road ahead.

[0038] 2. Road surface recognition: The image is analyzed in real time using a pre-trained deep learning model (such as a convolutional neural network CNN) to identify the road surface type (e.g., "wet asphalt road" or "compacted snow").

[0039] 3. Predictive Decision-Making: Based on the identification results, the motor controller immediately retrieves the optimal drive torque MAP corresponding to this type of road surface from the pre-stored MAP database, such as... Figure 3 The diagram illustrating predictive MAP recall demonstrates how the controller recalls the ice surface torque MAP in advance after the camera detects the ice surface. If the camera detects different road surfaces in different lanes ahead, the controller can also combine the navigation path or the driver's steering intention to prepare the corresponding MAP in advance for the road surface the drive wheels are about to enter.

[0040] Specifically, for each identified road surface type, the target optimal drive torque MAP corresponding to that road surface type is retrieved from the road surface-torque MAP database. If multiple road surface types are identified, the target optimal drive torque MAP corresponding to the target road surface is retrieved in advance based on the predicted wheel trajectory, vehicle navigation path, or driver steering intention, so that torque control of the drive motor can be performed according to the target optimal drive torque MAP after entering the target road surface.

[0041] The aforementioned target optimal drive torque MAP stores the correspondence between accelerator pedal opening, motor speed, and motor drive torque. By obtaining the vehicle's current accelerator pedal opening and current motor speed, the motor drive torque that best matches the accelerator pedal opening and current motor speed can be found in the target optimal drive torque MAP. Then, the drive motor can be controlled to work based on the best matching motor drive torque.

[0042] 4. Forward-looking control: The motor controller no longer uses the default torque MAP suitable for good road surfaces, but switches to an anti-slip torque MAP "tailor-made" for the current road surface. When the driver presses the accelerator pedal, the controller queries this dedicated MAP based on the current accelerator pedal opening and the current motor speed, and outputs a torque value that is limited within a safe range and best suited for the current road surface. In this way, even if the driver presses the accelerator pedal deeply, the torque output by the motor will be automatically limited to a level that will not cause serious slippage.

[0043] As a further improvement to this embodiment, the motor controller also includes a safety redundancy mechanism. This means that the traditional wheel speed sensor and slip ratio calculation module are retained. When predictive control fails to completely prevent slippage due to certain reasons (such as road surface recognition errors or sudden local anomalies), this redundant system will immediately intervene, ensuring vehicle safety through rapid torque intervention.

[0044] Specifically, the real-time slip ratio of the drive wheels is monitored by wheel speed sensors; when the real-time slip ratio exceeds the safety threshold, the slip ratio-based rapid torque reduction control is activated first, complementing the predictive control.

[0045] The vehicle road surface anti-skid control method provided in this application fundamentally changes the control logic, that is, it changes from passive response to active prevention, eliminating the main cause of skidding (excessive driving torque) before it occurs, thereby bringing the following beneficial effects: 1. Extreme smoothness: By avoiding slippage and subsequent correction processes, the vehicle's start-up and acceleration are incredibly smooth and linear, greatly improving the driving experience.

[0046] 2. Maximize the use of adhesion: The pre-calibrated MAP is the maximum safe torque that can be used on this road surface, so that the vehicle can obtain the best possible acceleration performance on low-adhesion roads, which is better than conservative responsive control.

[0047] 3. Improved energy efficiency: It avoids energy waste caused by slippage and extends the driving range.

[0048] 4. Achieve adaptive driving: The vehicle can "release the accelerator in advance" or "gently apply the accelerator" according to road conditions, just like an experienced driver, achieving a preliminary level of driving intelligence.

[0049] Based on the above method embodiments, this application also provides a vehicle road surface anti-skid control device, which is applied to a vehicle motor controller. See [link to relevant documentation]. Figure 4 As shown, the device includes: a road surface type receiving module 42, used to receive the road surface type identification results sent by the vehicle environment perception sensor in real time during vehicle operation; a torque lookup module 44, used to look up the target optimal driving torque MAP corresponding to the road surface type identification result based on a pre-built road surface-torque MAP database; the road surface-torque MAP database stores the optimal driving torque MAPs corresponding to various road surface types; and a motor torque control module 46, used to control the torque of the drive motor according to the found target optimal driving torque MAP.

[0050] Furthermore, the aforementioned vehicle-mounted environmental perception sensor is a vehicle-mounted camera; the road surface type recognition result includes: the road surface type identified by the vehicle-mounted camera within a specified range in front of the vehicle through a built-in road surface type recognition model; wherein, the road surface type recognition model includes: an image classification model or a semantic segmentation model trained based on deep learning.

[0051] Furthermore, the above road surface type identification results include at least one road surface type; the road surface type is one of the following: dry asphalt road surface, wet asphalt road surface, snow-covered road surface, icy road surface, gravel road surface, mud road surface, block road surface, and cement concrete road surface.

[0052] Furthermore, the aforementioned motor torque control module 46 is used to, if multiple road surface types are identified, pre-call the target optimal drive torque MAP corresponding to the target road surface to be entered based on the predicted wheel trajectory, vehicle navigation path, or driver steering intention, so as to perform torque control on the drive motor control based on the target optimal drive torque MAP after entering the target road surface.

[0053] Furthermore, the aforementioned target optimal drive torque MAP stores the correspondence between accelerator pedal opening, motor speed, and motor drive torque; the motor torque control module 46 is used to obtain the vehicle's current accelerator pedal opening and current motor speed; from the target optimal drive torque MAP, it finds the motor drive torque that best matches the accelerator pedal opening and current motor speed; and controls the drive motor to work according to the best-matched motor drive torque.

[0054] Furthermore, the aforementioned device also includes a redundant control module for monitoring the real-time slip ratio of the drive wheels via wheel speed sensors; when the real-time slip ratio exceeds a safety threshold, it prioritizes initiating rapid torque reduction control based on the slip ratio.

[0055] Furthermore, the aforementioned device also includes a MAP construction module for performing the following road-torque MAP database construction process: For each specified road surface type, the following steps are performed: driving tests are conducted on a pre-arranged road surface of the specified road surface type under different operating conditions using a test vehicle; during the driving test, motor torque output curves under different operating conditions are collected; operating conditions include: accelerator pedal opening and motor speed; the motor torque output curve can maximize the use of ground adhesion while ensuring smooth vehicle start-up and acceleration; based on the motor torque output curves under different operating conditions, a two-dimensional MAP map is drawn with accelerator pedal opening and motor speed as inputs and optimal limiting torque as output, and stored in the road-torque MAP database.

[0056] The device provided in this application embodiment has the same implementation principle and technical effect as the aforementioned method embodiment. For the sake of brevity, any parts of the device embodiment not mentioned can be referred to the corresponding content in the aforementioned method embodiment.

[0057] Based on the above method embodiments, this application also provides a vehicle road surface anti-skid control system, see [link to relevant documentation]. Figure 5 As shown, the system includes: an on-board environmental perception sensor 52 and a vehicle motor controller 54 connected in communication; the on-board environmental perception sensor 52 is used to acquire the road surface type recognition result in front of the vehicle; the vehicle motor controller 54 is used to execute the method described in the above method embodiment.

[0058] The system provided in this application embodiment has the same implementation principle and technical effects as the aforementioned method embodiment. For the sake of brevity, any parts not mentioned in the system embodiment can be referred to the corresponding content in the aforementioned method embodiment.

[0059] The computer program products of the methods, apparatus, and electronic devices provided in the embodiments of this application include a computer-readable storage medium storing program code. The instructions included in the program code can be used to execute the methods described in the preceding method embodiments. For specific implementations, please refer to the method embodiments, which will not be repeated here.

[0060] Unless otherwise specifically stated, the relative steps, numerical expressions, and values ​​of the components and steps described in these embodiments do not limit the scope of this application.

[0061] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a processor-executable, non-volatile, computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0062] In the description of this application, it should be noted that the terms "center," "upper," "lower," "left," "right," "vertical," "horizontal," "inner," and "outer," etc., indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. They are used only for the convenience of describing this application and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limitations on this application. Furthermore, the terms "first," "second," and "third" are used for descriptive purposes only and should not be construed as indicating or implying relative importance.

[0063] Finally, it should be noted that the above-described embodiments are merely specific implementations of this application, used to illustrate the technical solutions of this application, and not to limit them. The protection scope of this application is not limited thereto. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that any person skilled in the art can still modify or easily conceive of changes to the technical solutions described in the foregoing embodiments, or make equivalent substitutions for some of the technical features, within the technical scope disclosed in this application. Such modifications, changes, or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application, and should all be covered within the protection scope of this application. Therefore, the protection scope of this application should be determined by the protection scope of the claims.

Claims

1. A method for controlling vehicle road surface anti-skid, characterized in that, The method is applied to a vehicle motor controller, and the method includes: During vehicle operation, the vehicle receives real-time road surface type identification results from the on-board environmental perception sensor. Based on a pre-built road surface-torque MAP database, the target optimal driving torque MAP corresponding to the road surface type identification result is found; the road surface-torque MAP database stores the optimal driving torque MAPs corresponding to various road surface types. The drive motor is torque controlled based on the found target optimal drive torque MAP.

2. The method according to claim 1, characterized in that, The vehicle-mounted environmental perception sensor is a vehicle-mounted camera; the road surface type recognition result includes: the road surface type of the road surface within a specified range in front of the vehicle, identified by the vehicle-mounted camera through a built-in road surface type recognition model; wherein, the road surface type recognition model includes: an image classification model or a semantic segmentation model trained based on deep learning.

3. The method according to claim 1, characterized in that, The road surface type identification result includes at least one road surface type; the road surface type is one of the following: dry asphalt road surface, wet asphalt road surface, snow-covered road surface, icy road surface, gravel road surface, mud road surface, block road surface, and cement concrete road surface.

4. The method according to claim 1, characterized in that, The steps for torque control of the drive motor based on the found target optimal drive torque MAP include: If multiple road surface types are identified, the target optimal drive torque MAP corresponding to the target road surface is called in advance based on the predicted wheel trajectory, vehicle navigation path, or driver steering intention, so that the drive motor can be controlled according to the target optimal drive torque MAP after entering the target road surface.

5. The method according to claim 4, characterized in that, The target optimal driving torque MAP stores the correspondence between accelerator pedal opening, motor speed and motor driving torque; The steps of torque control of the drive motor based on the target optimal drive torque MAP include: Obtain the vehicle's current accelerator pedal opening and current motor speed; From the target optimal drive torque MAP, find the motor drive torque that best matches the accelerator pedal opening and the current motor speed; The drive motor is controlled to operate based on the most suitable motor drive torque.

6. The method according to claim 1, characterized in that, The method further includes: The real-time slip rate of the drive wheels is monitored by wheel speed sensors; When the real-time slip ratio exceeds the safety threshold, the slip ratio-based rapid torque reduction control is initiated first.

7. The method according to claim 1, characterized in that, The process of constructing the road surface-torque MAP database is as follows: For each specified road surface type, perform the following steps: The test vehicle was driven under different operating conditions on a pre-arranged road surface of the specified road type. The motor torque output curves under different operating conditions are collected during the drive test; the operating conditions include: accelerator pedal opening and motor speed; the motor torque output curves can maximize the use of ground adhesion and ensure smooth vehicle start and acceleration. Based on the motor torque output curves under different operating conditions, a two-dimensional MAP is plotted with accelerator pedal opening and motor speed as inputs and optimal limiting torque as output, and stored in the road surface-torque MAP database.

8. A vehicle road surface anti-skid control device, characterized in that, The device is used in a vehicle motor controller, and the device includes: The road surface type receiving module is used to receive the road surface type identification results sent by the on-board environmental perception sensor in real time during vehicle operation. The torque lookup module is used to look up the target optimal driving torque MAP corresponding to the road surface type identification result based on a pre-built road surface-torque MAP database; the road surface-torque MAP database stores the optimal driving torque MAPs corresponding to various road surface types. The motor torque control module is used to control the torque of the drive motor based on the target optimal drive torque MAP found.

9. A vehicle road surface anti-skid control system, characterized in that, The system includes: an on-board environmental perception sensor and a vehicle motor controller connected in communication; the on-board environmental perception sensor is used to acquire the road surface type recognition result in front of the vehicle; the vehicle motor controller is used to execute the method as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-executable instructions that, when invoked and executed by a processor, cause the processor to perform the method according to any one of claims 1 to 7.

Images