Multi-mode switching servo motor control system

Abstract

The invention discloses a multi-mode switching servo motor control system, and the system comprises a first obtaining module which is used for obtaining an operation environment image and vehicle attribute information when a vehicle moves; the first determination module is used for predicting an operation mode when the vehicle moves based on the operation environment image; the second determination module is used for determining a wheel steering angle reference value in the vehicle running process according to the prediction result and the vehicle attribute information; the second acquisition module is used for acquiring a real-time numerical value of a wheel steering angle in the vehicle running process; the calculation module is used for comparing the real-time numerical value of the wheel steering angle in the running process of the vehicle with the reference value of the wheel steering angle in the running process of the vehicle; the third determination module is used for determining a multi-mode switching control strategy of the servo motor according to the comparison result; the control module is used for controlling vehicle movement based on the servo motor multi-mode switching control strategy; multi-mode switching enables the servo motor to steer more flexibly in a narrow space.

Description

Technical Field

[0001] The invention relates to the field of automobile industry, and in particular to a multi-mode switching servo motor control system. Background Art

[0002] With the continuous development of science and technology, servo motors play an increasingly important role in industrial production. In the automotive manufacturing industry, they can achieve high-precision position control and motion control, which is of key significance for improving the efficiency, quality and automation of automobile production.

[0003] In the prior art, intelligent mobile robot vehicles always shake during movement, especially when running in sharp turns or narrow corridors in industrial scenarios. When facing steering conditions in narrow spaces, there will be problems such as low flexibility and poor stability. Therefore, a multi-mode switching servo motor control system is urgently needed to solve the above problems. Summary of the invention

[0004] The present invention aims to solve at least one of the technical problems in the above-mentioned technology to a certain extent. To this end, the purpose of the present invention is to propose a servo motor control system with multi-mode asynchronous switching, which can make the servo motor more flexible in steering in a narrow space and improve stability.

[0005] To achieve the above object, an embodiment of the present invention proposes a multi-mode switching servo motor control system, comprising:

[0006] The first acquisition module is used to acquire the operating environment image and vehicle attribute information when the vehicle is moving;

[0007] A first determination module, used to predict the operation mode of the vehicle when it moves based on the operation environment image;

[0008] A second determination module is used to determine a wheel steering angle reference value during vehicle operation according to the prediction result and vehicle attribute information;

[0009] The second acquisition module is used to obtain the real-time value of the wheel steering angle during the operation of the vehicle;

[0010] A calculation module, used for comparing the real-time value of the wheel steering angle during the operation of the vehicle with a reference value of the wheel steering angle during the operation of the vehicle;

[0011] A third determination module is used to determine the servo motor multi-mode switching control strategy according to the comparison result;

[0012] A control module is used to control the movement of the vehicle based on the servo motor multi-mode switching control strategy.

[0013] Preferably, the first determining module includes:

[0014] A denoising submodule, used to denoise the operating environment image to obtain a denoised operating environment image;

[0015] The first determination submodule is used to input the noise-reduced operating environment image into a pre-trained vehicle operation path planning model for identification, and determine the ideal path information of the vehicle movement; the ideal path information of the vehicle movement is input into a pre-trained operation mode judgment model for prediction, and obtain the time series of the operation mode switching when the vehicle moves.

[0016] Preferably, the method for constructing a vehicle operation path planning model includes:

[0017] Obtain vehicle operation path planning training set;

[0018] Inputting the vehicle operation path planning training set into the neural network model for iterative training to obtain an initial vehicle operation path planning model;

[0019] Get the vehicle operation path planning test set;

[0020] The initial vehicle operation path planning model is tested based on the vehicle operation path planning test set, and when the test result is qualified, a trained vehicle operation path planning model is obtained.

[0021] Preferably, the noise reduction submodule includes:

[0022] The first screening unit is used to:

[0023] Take any running environment image as the image to be processed;

[0024] Gray-scale the image to be processed to obtain a first target image;

[0025] Obtaining the grayscale value of each pixel in the first target image;

[0026] Randomly select a pixel point in the first target image as the target pixel point;

[0027] Determine the target area with the target pixel as the center and the preset distance as the radius;

[0028] Respectively obtain grayscale differences between a target pixel point in the target area and other pixel points in the target area except the target pixel point, and obtain a plurality of grayscale differences;

[0029] Sum the absolute values ​​of several grayscale differences and take the average to obtain the grayscale difference value corresponding to the target pixel;

[0030] Traverse all pixels in the first target image to obtain the grayscale difference value corresponding to each pixel;

[0031] Determine the discreteness value corresponding to each pixel based on the grayscale difference value corresponding to each pixel;

[0032] Compare the discreteness value corresponding to each pixel with a preset discreteness threshold, and delete the corresponding pixel when the discreteness value is greater than or equal to the preset discreteness threshold to obtain a second target image;

[0033] The second screening unit is used for:

[0034] Determine a noise evaluation value corresponding to each pixel point in the second target image based on a discreteness value corresponding to each pixel point in the second target image;

[0035] Compare the noise evaluation value with a preset noise evaluation threshold, and take the pixel points corresponding to when the noise evaluation value is greater than or equal to the preset noise evaluation threshold as the pixel points to be denoised; traverse all the pixel points in the second target image to obtain a plurality of pixel points to be denoised;

[0036] The denoising unit is used to denoise the plurality of pixels to be denoised based on a preset filter to obtain a denoised second target image; and traverse all operating environment images to obtain a denoised operating environment image.

[0037] Preferably, the second screening unit is used to determine the noise evaluation value corresponding to each pixel point in the second target image based on the discreteness value corresponding to each pixel point in the second target image, including:

[0038]

[0039] Among them, Z t represents the noise evaluation value corresponding to the t-th pixel in the second target image; t represents the discreteness value corresponding to the t-th pixel in the second target image; represents the mean value of the discreteness of the pixels in the second target image; Q represents the total number of pixels in the second target image; P a Indicates the discreteness value corresponding to the a-th pixel in the second target image.

[0040] Preferably, the method for determining the discreteness value corresponding to each pixel point based on the grayscale difference value corresponding to each pixel point includes:

[0041]

[0042] Among them, L i Represents the discrete value corresponding to the i-th pixel; R i Represents the gray value corresponding to the i-th pixel; Represents the grayscale mean of the pixels in the first target image; represents the grayscale difference value corresponding to the i-th pixel; T i Represents the gradient value corresponding to the i-th pixel; represents the gradient mean of the pixel points in the first target image; Represents the mean of the grayscale difference values ​​of the pixels in the first target image.

[0043] Preferably, the second determining module includes:

[0044] The first computing submodule is used for:

[0045] Calculating a wheel steering angle reference value during vehicle operation in the single Ackerman mode at each time point in the time series based on the vehicle attribute information and a first preset algorithm to obtain a first wheel steering angle reference value;

[0046] The second computing submodule is used for:

[0047] Calculating a wheel steering angle reference value during vehicle operation in the dual-Ackerman mode at each time point in the time series based on the vehicle attribute information and a second preset algorithm to obtain a second wheel steering angle reference value;

[0048] The second determining submodule is used to use the first wheel steering angle reference value and the second wheel steering angle reference value as wheel steering angle reference values ​​during vehicle operation.

[0049] Preferably, the first preset algorithm includes:

[0050]

[0051] Among them, D1, i represents the first wheel steering angle reference value in the single Ackerman mode at the i-th time point during vehicle operation; l f Indicates the distance between the center of gravity of the vehicle and the front wheel; l r Indicates the distance between the vehicle's center of gravity and the rear wheels; R o，i Represents the turning radius corresponding to the i-th time point.

[0052] Preferably, the third determination module includes:

[0053] Comparison submodule, used to:

[0054] Calculate the difference between the real-time value of the wheel steering angle corresponding to each time point in the time series and the single Ackerman mode wheel steering angle reference value corresponding to each time point to obtain a first difference;

[0055] Calculate the difference between the real-time value of the wheel steering angle corresponding to each time point in the time series and the reference value of the wheel steering angle in the double Ackerman mode corresponding to each time point to obtain a second difference;

[0056] Comparing the absolute value of the first difference with the absolute value of the second difference;

[0057] The operation mode corresponding to the minimum absolute value is used as the target operation mode corresponding to each time point;

[0058] The third determination submodule is used to use the target operating mode corresponding to each time point as the servo motor multi-mode switching control strategy.

[0059] Preferably, it also includes:

[0060] The delay estimation module is used to calculate the delay in the servo motor multi-mode switching process before controlling the vehicle movement based on the servo motor multi-mode switching control strategy, obtain the delay time corresponding to each time point of the servo motor multi-mode switching; and correct the time series based on the delay time.

[0061] The present invention discloses a servo motor control system with multi-mode switching. By acquiring operating environment images and vehicle attribute information, the system can better adapt to different driving scenarios and vehicle states and achieve more precise control. The operating mode is predicted based on the image, and the wheel steering angle reference value is determined in combination with the vehicle attributes, and then the control strategy is determined by comparing with the real-time value, which can improve the accuracy and real-time performance of the control. Accurate wheel steering control helps to ensure the driving safety of the vehicle in various situations and reduce potential risks. Multi-mode switching allows the servo motor to flexibly adjust the working mode according to actual needs, thereby optimizing the overall performance and efficiency of the vehicle.

[0062] Other features and advantages of the present invention will be described in the following description, and partly become apparent from the description, or understood by practicing the present invention. The purpose and other advantages of the present invention can be realized and obtained by the structures particularly pointed out in the written description and the accompanying drawings.

[0063] The technical solution of the present invention is further described in detail below through the accompanying drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0064] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0065] Figure 1 is a block diagram of a multi-mode switching servo motor control system according to an embodiment of the present invention;

[0066] Figure 2 is a block diagram of a first determination module according to an embodiment of the present invention;

[0067] Figure 3 is a block diagram of a noise reduction submodule according to an embodiment of the present invention. DETAILED DESCRIPTION

[0068] The preferred embodiments of the present invention are described below in conjunction with the accompanying drawings. It should be understood that the preferred embodiments described herein are only used to illustrate and explain the present invention, and are not used to limit the present invention.

[0069] Example 1

[0070] like Figure 1 As shown, a multi-mode switching servo motor control system is characterized by comprising:

[0071] The first acquisition module is used to acquire the operating environment image and vehicle attribute information when the vehicle is moving;

[0072] A first determination module, used to predict the operation mode of the vehicle when it moves based on the operation environment image;

[0073] A second determination module is used to determine a wheel steering angle reference value during vehicle operation according to the prediction result and vehicle attribute information;

[0074] The second acquisition module is used to obtain the real-time value of the wheel steering angle during the operation of the vehicle;

[0075] A calculation module, used for comparing the real-time value of the wheel steering angle during the operation of the vehicle with a reference value of the wheel steering angle during the operation of the vehicle;

[0076] A third determination module is used to determine the servo motor multi-mode switching control strategy according to the comparison result;

[0077] A control module is used to control the movement of the vehicle based on the servo motor multi-mode switching control strategy.

[0078] In this embodiment, the method of obtaining the operating environment image includes but is not limited to a vehicle-mounted camera and a surround-view camera system; the operating environment image includes but is not limited to road surface flatness, the presence or absence of obstacles, lane lines, curves, uphill and downhill slopes, other vehicles, pedestrians, and buildings.

[0079] In this embodiment, the vehicle attribute information includes the weight of the vehicle, the running speed of the vehicle, and the stiffness coefficient of the wheels.

[0080] In this embodiment, the operation modes of the vehicle during movement include but are not limited to a single Ackerman mode and a double Ackerman mode.

[0081] In this embodiment, the prediction result includes the time points at which the operation mode needs to be switched when the vehicle moves, thereby obtaining a time sequence of the operation mode switching.

[0082] The beneficial effects of the above technical solution are: by acquiring the operating environment image and vehicle attribute information, the system can better adapt to different driving scenarios and vehicle conditions and achieve more precise control; the operating mode is predicted based on the image, and the wheel steering angle reference value is determined in combination with the vehicle attributes, and then compared with the real-time value to determine the control strategy, which can improve the accuracy and real-time performance of the control; accurate wheel steering control helps to ensure the driving safety of the vehicle in various situations and reduce potential risks; multi-mode switching allows the servo motor to flexibly adjust the working mode according to actual needs, thereby optimizing the overall performance and efficiency of the vehicle.

[0083] Example 2

[0084] like Figure 2 As shown, the first determination module includes:

[0085] A denoising submodule, used to denoise the operating environment image to obtain a denoised operating environment image;

[0086] The first determination submodule is used to input the noise-reduced operating environment image into a pre-trained vehicle operation path planning model for identification, and determine the ideal path information of the vehicle movement; the ideal path information of the vehicle movement is input into a pre-trained operation mode judgment model for prediction, and obtain the time series of the operation mode switching when the vehicle moves.

[0087] In this embodiment, the method for constructing the operation mode judgment model includes:

[0088] Obtaining a vehicle operation mode judgment training set;

[0089] Inputting the vehicle operation mode judgment training set into a neural network model for iterative training to obtain an initial operation mode judgment model;

[0090] Obtain a vehicle operation mode judgment test set;

[0091] The initial operation mode judgment model is tested based on the vehicle operation mode judgment test set, and when the test result is qualified, a trained operation mode judgment model is obtained.

[0092] The beneficial effects of the above technical solution are: the noise reduction sub-module is used to perform noise reduction processing on the operating environment image, thereby improving the quality and clarity of the image and providing a more accurate data basis for subsequent recognition and analysis; the pre-trained vehicle operation path planning model is used to determine the ideal path information for vehicle movement, which helps to achieve more reasonable and efficient path planning and improve the safety and efficiency of vehicle driving; the ideal path information is input into the operation mode judgment model to predict the time series of operation mode switching, which can enable the vehicle to prepare in advance and achieve smoother and smoother operation mode switching, thereby improving the driving experience and the performance of the vehicle.

[0093] Example 3

[0094] The method for constructing a vehicle operation path planning model includes:

[0095] Obtain vehicle operation path planning training set;

[0096] Inputting the vehicle operation path planning training set into the neural network model for iterative training to obtain an initial vehicle operation path planning model;

[0097] Get the vehicle operation path planning test set;

[0098] The initial vehicle operation path planning model is tested based on the vehicle operation path planning test set, and when the test result is qualified, a trained vehicle operation path planning model is obtained.

[0099] The beneficial effects of the above technical solution are: by obtaining a special training set for model training, it is ensured that the model can learn the characteristics and rules related to vehicle operation path planning; by using the neural network model for iterative training, it can automatically extract and learn complex patterns and relationships, and improve the accuracy and adaptability of the model; and then testing with the test set can verify the performance of the model on new data to ensure its reliability and generalization ability; the final trained vehicle operation path planning model can provide the vehicle with more accurate and reasonable operation path planning, thereby improving the efficiency and safety of vehicle operation.

[0100] Example 4

[0101] Noise reduction submodule, including:

[0102] The first screening unit is used to:

[0103] Take any running environment image as the image to be processed;

[0104] Gray-scale the image to be processed to obtain a first target image;

[0105] Obtaining the grayscale value of each pixel in the first target image;

[0106] Randomly select a pixel point in the first target image as the target pixel point;

[0107] Determine the target area with the target pixel as the center and the preset distance as the radius;

[0108] Respectively obtain grayscale differences between a target pixel point in the target area and other pixel points in the target area except the target pixel point, and obtain a plurality of grayscale differences;

[0109] Sum the absolute values ​​of several grayscale differences and take the average to obtain the grayscale difference value corresponding to the target pixel;

[0110] Traverse all pixels in the first target image to obtain the grayscale difference value corresponding to each pixel;

[0111] Determine the discreteness value corresponding to each pixel based on the grayscale difference value corresponding to each pixel;

[0112] Compare the discreteness value corresponding to each pixel with a preset discreteness threshold, and delete the corresponding pixel when the discreteness value is greater than or equal to the preset discreteness threshold to obtain a second target image;

[0113] The second screening unit is used for:

[0114] Determine a noise evaluation value corresponding to each pixel point in the second target image based on a discreteness value corresponding to each pixel point in the second target image;

[0115] Compare the noise evaluation value with a preset noise evaluation threshold, and take the pixel points corresponding to when the noise evaluation value is greater than or equal to the preset noise evaluation threshold as the pixel points to be denoised; traverse all the pixel points in the second target image to obtain a plurality of pixel points to be denoised;

[0116] The denoising unit is used to denoise the plurality of pixels to be denoised based on a preset filter to obtain a denoised second target image; and traverse all operating environment images to obtain a denoised operating environment image.

[0117] In this embodiment, first, the first screening unit starts working. The image is grayed to obtain the first target image. Then the gray value of each pixel is obtained. For example, a pixel is selected as the target pixel, and a target area is determined with it as the center and a preset distance (such as 3 pixels) as the radius. The gray difference between the target pixel and other pixels in the area is calculated to obtain a number of gray difference values ​​(such as the difference with the surrounding 8 pixels). The absolute values ​​of these differences are summed and averaged to obtain the gray difference value corresponding to the target pixel. The entire first target image is traversed to obtain the gray difference value of each pixel. The discreteness value is determined based on these gray difference values, and those pixels whose discreteness values ​​are greater than or equal to the preset discreteness threshold are deleted to obtain the second target image; then, based on the second screening unit, the noise evaluation value is determined based on the discreteness value of each pixel in the second target image. Assuming that the noise evaluation value of some pixels is greater than or equal to the preset noise evaluation threshold, these pixels are marked as pixels to be denoised. After traversing all the pixels, several pixels to be denoised are obtained; finally, the denoising unit processes these pixels to be denoised using a preset filter to remove noise and obtain a denoised second target image. This process is repeated to process all the operating environment images, and finally all denoised operating environment images are obtained.

[0118] The beneficial effects of the above technical solution are: through grayscale processing and calculation of the grayscale difference value of pixel points, pixels that are greatly different from the surrounding areas can be effectively identified and deleted, thereby preliminarily reducing abnormal interference in the image and improving the stability of image quality; possible noise pixels are further screened out based on the discreteness value, thereby improving the accuracy of noise point judgment and making subsequent noise reduction more targeted; using a preset filter to process the determined pixels to be denoised can accurately reduce the impact of noise, making the final operating environment image clearer and more accurate, and providing a more reliable data basis for subsequent image-based analysis and processing.

[0119] Example 5

[0120] The second screening unit is used to determine the noise evaluation value corresponding to each pixel point in the second target image based on the discreteness value corresponding to each pixel point in the second target image, including:

[0121]

[0122] Among them, Z t represents the noise evaluation value corresponding to the t-th pixel in the second target image; t represents the discreteness value corresponding to the t-th pixel in the second target image; represents the mean value of the discreteness of the pixels in the second target image; Q represents the total number of pixels in the second target image; P aIndicates the discreteness value corresponding to the a-th pixel in the second target image.

[0123] The beneficial effects of the above technical solution are: by considering the relationship between the discrete value of each pixel point and the overall discrete mean value and factors such as the total number of pixels, the noise evaluation is made more scientific and reasonable; it can more accurately identify pixels with a higher possibility of noise, providing a reliable basis for subsequent targeted noise reduction processing, and helping to improve the accuracy and effect of noise reduction.

[0124] Example 6

[0125] The method for determining a discreteness value corresponding to each pixel point based on a grayscale difference value corresponding to each pixel point includes:

[0126]

[0127] Among them, L i Represents the discrete value corresponding to the i-th pixel; R i Represents the gray value corresponding to the i-th pixel; Represents the grayscale mean of the pixels in the first target image; represents the grayscale difference value corresponding to the i-th pixel; T i Represents the gradient value corresponding to the i-th pixel; represents the gradient mean of the pixel points in the first target image; Represents the mean of the grayscale difference values ​​of the pixels in the first target image.

[0128] The beneficial effects of the above technical solution are: by comprehensively considering multiple factors such as the grayscale value, grayscale mean, grayscale difference value, gradient value and corresponding mean of the pixel point, the discreteness value is calculated more comprehensively and accurately, thereby improving the scientificity and reliability of the discreteness calculation; this complex calculation method helps to distinguish the characteristics of different pixel points more finely, thereby performing subsequent image processing and analysis more accurately; the consideration of factors such as grayscale and gradient can better adapt to the characteristics of different types of images, thereby improving the applicability and effectiveness of the method in various scenarios.

[0129] Example 7

[0130] The second determination module includes:

[0131] The first computing submodule is used for:

[0132] Calculating a wheel steering angle reference value during vehicle operation in the single Ackerman mode at each time point in the time series based on the vehicle attribute information and a first preset algorithm to obtain a first wheel steering angle reference value;

[0133] The second computing submodule is used for:

[0134] Calculating a wheel steering angle reference value during vehicle operation in the dual-Ackerman mode at each time point in the time series based on the vehicle attribute information and a second preset algorithm to obtain a second wheel steering angle reference value;

[0135] The second determining submodule is used to use the first wheel steering angle reference value and the second wheel steering angle reference value as wheel steering angle reference values ​​during vehicle operation.

[0136] In this embodiment, the second preset algorithm includes:

[0137]

[0138] Among them, D2, i represents the reference value of the second wheel steering angle in the dual Ackerman mode at the i-th time point during vehicle operation; l f Indicates the distance between the center of gravity of the vehicle and the front wheel; l r Indicates the distance between the vehicle's center of gravity and the rear wheels; R o，i represents the turning radius corresponding to the i-th time point; m represents the weight of the vehicle; V i represents the vehicle running speed corresponding to the i-th time point; k f Indicates the stiffness coefficient of the front wheel; k r Represents the stiffness coefficient of the rear wheel.

[0139] The beneficial effects of the above technical solution are: by performing calculations based on the first preset algorithm and the second preset algorithm respectively, the steering requirements of vehicle operation in different scenarios can be handled more flexibly, thereby improving the adaptability of vehicle control; while considering the single Ackerman mode and the double Ackerman mode, more options and references are provided for determining the steering angle during vehicle operation, which helps to optimize the vehicle's driving performance and stability.

[0140] Example 8

[0141] The first preset algorithm includes:

[0142]

[0143] Among them, D1, i represents the first wheel steering angle reference value in the single Ackerman mode at the i-th time point during vehicle operation; l f Indicates the distance between the center of gravity of the vehicle and the front wheel; l r Indicates the distance between the vehicle's center of gravity and the rear wheels; R o，i Represents the turning radius corresponding to the i-th time point.

[0144] The beneficial effect of the above technical solution is that by considering key parameters such as the distance between the vehicle's center of gravity and the front and rear wheels and the turning radius, the wheel steering angle at a specific time point can be calculated more accurately, which helps to accurately control the vehicle's steering and improve the vehicle's handling performance.

[0145] Example 9

[0146] The third determination module includes:

[0147] Comparison submodule, used to:

[0148] Calculate the difference between the real-time value of the wheel steering angle corresponding to each time point in the time series and the single Ackerman mode wheel steering angle reference value corresponding to each time point to obtain a first difference;

[0149] Calculate the difference between the real-time value of the wheel steering angle corresponding to each time point in the time series and the reference value of the wheel steering angle in the double Ackerman mode corresponding to each time point to obtain a second difference;

[0150] Comparing the absolute value of the first difference with the absolute value of the second difference;

[0151] The operation mode corresponding to the minimum absolute value is used as the target operation mode corresponding to each time point;

[0152] The third determination submodule is used to use the target operating mode corresponding to each time point as the servo motor multi-mode switching control strategy.

[0153] In this embodiment, the servo motor multi-mode switching control strategy is the target operating mode corresponding to each time point.

[0154] The beneficial effects of the above technical solution are: by comparing the absolute value of the difference to determine the target operating mode, the operating mode that best suits the current situation can be selected more accurately to achieve more optimized control; the operating mode can be dynamically switched according to real-time conditions, which improves the adaptability and flexibility of the system to better cope with different driving scenarios and needs; the servo motor multi-mode switching control strategy determined in this way helps to improve the accuracy and stability of vehicle steering control; it helps to achieve more energy-saving and efficient vehicle operation, so that the vehicle can work in the optimal mode under different conditions.

[0155] Example 10

[0156] Also includes:

[0157] The delay estimation module is used to calculate the delay in the servo motor multi-mode switching process before controlling the vehicle movement based on the servo motor multi-mode switching control strategy, obtain the delay time corresponding to each time point of the servo motor multi-mode switching; and correct the time series based on the delay time.

[0158] In this embodiment, the delay in the multi-mode switching process of the servo motor is mainly considered that a large amount of real-time data interaction may easily cause poor communication, resulting in interaction delays and data loss, and ultimately causing delays in the multi-mode switching process.

[0159] In this embodiment, delay estimation is performed based on a delay calculation method during data transmission.

[0160] The beneficial effects of the above technical solution are: taking into account the delay in the switching process and performing calculations and corrections, it can improve the accuracy and real-time performance of the control and avoid control deviations caused by delays; making vehicle movement control more precise and reliable and reducing the uncertainty and potential risks caused by delays; and helping to optimize the performance of the entire control system and ensure a smooth transition and good operating state of the vehicle when switching between different modes.

[0161] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. A multi-mode switching servo motor control system, characterized in that: include: The first acquisition module is used to acquire the operating environment image and vehicle attribute information when the vehicle is moving; A first determination module, used to predict the operation mode of the vehicle when it moves based on the operation environment image; A second determination module is used to determine a wheel steering angle reference value during vehicle operation according to the prediction result and vehicle attribute information; The second acquisition module is used to obtain the real-time value of the wheel steering angle during the operation of the vehicle; A calculation module, used for comparing the real-time value of the wheel steering angle during the operation of the vehicle with a reference value of the wheel steering angle during the operation of the vehicle; A third determination module is used to determine the servo motor multi-mode switching control strategy according to the comparison result; A control module is used to control the movement of the vehicle based on the servo motor multi-mode switching control strategy.

2. The multi-mode switching servo motor control system according to claim 1, characterized in that: The first determination module includes: A denoising submodule, used to denoise the operating environment image to obtain a denoised operating environment image; The first determination submodule is used to input the noise-reduced operating environment image into a pre-trained vehicle operation path planning model for identification, and determine the ideal path information of the vehicle movement; the ideal path information of the vehicle movement is input into a pre-trained operation mode judgment model for prediction, and obtain the time series of the operation mode switching when the vehicle moves.

3. The multi-mode switching servo motor control system according to claim 2, characterized in that: The method for constructing a vehicle operation path planning model includes: Obtain vehicle operation path planning training set; Inputting the vehicle operation path planning training set into the neural network model for iterative training to obtain an initial vehicle operation path planning model; Get the vehicle operation path planning test set; The initial vehicle operation path planning model is tested based on the vehicle operation path planning test set, and when the test result is qualified, a trained vehicle operation path planning model is obtained.

4. The multi-mode switching servo motor control system according to claim 2, characterized in that: Noise reduction submodule, including: The first screening unit is used to: Take any running environment image as the image to be processed; Gray-scale the image to be processed to obtain a first target image; Obtaining the grayscale value of each pixel in the first target image; Randomly select a pixel point in the first target image as the target pixel point; Determine the target area with the target pixel as the center and the preset distance as the radius; Respectively obtain grayscale differences between a target pixel point in the target area and other pixel points in the target area except the target pixel point, and obtain a plurality of grayscale differences; Sum the absolute values ​​of several grayscale differences and take the average to obtain the grayscale difference value corresponding to the target pixel; Traverse all pixels in the first target image to obtain the grayscale difference value corresponding to each pixel; Determine the discreteness value corresponding to each pixel based on the grayscale difference value corresponding to each pixel; Compare the discreteness value corresponding to each pixel with a preset discreteness threshold, and delete the corresponding pixel when the discreteness value is greater than or equal to the preset discreteness threshold to obtain a second target image; The second screening unit is used for: Determine a noise evaluation value corresponding to each pixel point in the second target image based on a discreteness value corresponding to each pixel point in the second target image; Compare the noise evaluation value with a preset noise evaluation threshold, and take the pixel points corresponding to when the noise evaluation value is greater than or equal to the preset noise evaluation threshold as the pixel points to be denoised; traverse all the pixel points in the second target image to obtain a plurality of pixel points to be denoised; The denoising unit is used to denoise the plurality of pixels to be denoised based on a preset filter to obtain a denoised second target image; and traverse all operating environment images to obtain a denoised operating environment image.

5. The multi-mode switching servo motor control system according to claim 4, characterized in that: The second screening unit is used to determine the noise evaluation value corresponding to each pixel point in the second target image based on the discreteness value corresponding to each pixel point in the second target image, including: Among them, Z t represents the noise evaluation value corresponding to the t-th pixel in the second target image; t represents the discreteness value corresponding to the t-th pixel in the second target image; represents the mean value of the discreteness of the pixels in the second target image; Q represents the total number of pixels in the second target image; P a Indicates the discreteness value corresponding to the a-th pixel in the second target image.

6. The multi-mode switching servo motor control system according to claim 4, characterized in that: The method for determining a discreteness value corresponding to each pixel point based on a grayscale difference value corresponding to each pixel point includes: Among them, L i Represents the discrete value corresponding to the i-th pixel; R i Represents the gray value corresponding to the i-th pixel; Represents the grayscale mean of the pixels in the first target image; represents the grayscale difference value corresponding to the i-th pixel; T i Represents the gradient value corresponding to the i-th pixel; represents the gradient mean of the pixel points in the first target image; Represents the mean of the grayscale difference values ​​of the pixels in the first target image.

7. The multi-mode switching servo motor control system according to claim 2, characterized in that: The second determination module includes: The first computing submodule is used for: Calculating a wheel steering angle reference value during vehicle operation in the single Ackerman mode at each time point in the time series based on the vehicle attribute information and a first preset algorithm to obtain a first wheel steering angle reference value; The second computing submodule is used for: Calculating a wheel steering angle reference value during vehicle operation in the dual-Ackerman mode at each time point in the time series based on the vehicle attribute information and a second preset algorithm to obtain a second wheel steering angle reference value; The second determining submodule is used to use the first wheel steering angle reference value and the second wheel steering angle reference value as wheel steering angle reference values ​​during vehicle operation.

8. The multi-mode switching servo motor control system according to claim 7, characterized in that: The first preset algorithm includes: Among them, D1, i represents the first wheel steering angle reference value in the single Ackerman mode at the i-th time point during vehicle operation; l f Indicates the distance between the center of gravity of the vehicle and the front wheel; l r Indicates the distance between the vehicle's center of gravity and the rear wheels; R o，i Represents the turning radius corresponding to the i-th time point.

9. The multi-mode switching servo motor control system according to claim 8, characterized in that: The third determination module includes: Comparison submodule, used to: Calculate the difference between the real-time value of the wheel steering angle corresponding to each time point in the time series and the single Ackerman mode wheel steering angle reference value corresponding to each time point to obtain a first difference; Calculate the difference between the real-time value of the wheel steering angle corresponding to each time point in the time series and the reference value of the wheel steering angle in the double Ackerman mode corresponding to each time point to obtain a second difference; Comparing the absolute value of the first difference with the absolute value of the second difference; The operation mode corresponding to the minimum absolute value is used as the target operation mode corresponding to each time point; The third determination submodule is used to use the target operating mode corresponding to each time point as the servo motor multi-mode switching control strategy.

10. The multi-mode switching servo motor control system according to claim 2, characterized in that: Also includes: A delay estimation module is used to calculate the delay in the servo motor multi-mode switching process before controlling the vehicle movement based on the servo motor multi-mode switching control strategy, and obtain the delay time corresponding to each time point of the servo motor multi-mode switching; The time series is corrected based on the delay time.

Images