A control system and method for intelligent lawn mower forward speed and mowing motor speed

Abstract

The present invention discloses a control system and method for the forward speed and mowing motor speed of an intelligent lawn mower. First, the video obtained by the camera of the intelligent lawn mower is spliced ​​to obtain a mowing area picture, and the average height of the grass is calculated by the convex lens imaging principle. The density of the mowing area is obtained by preprocessing, threshold segmentation, binarization and corrosion processing, which is used as the input of the fuzzy control system. After fuzzification, fuzzy reasoning and precision, the appropriate forward speed and mowing motor speed of the intelligent lawn mower are obtained. The present invention uses a fuzzy control algorithm to simulate the human thinking mode, intelligently control the forward speed and mowing motor speed of the lawn mower, improve the working efficiency of the intelligent lawn mower, select the appropriate forward speed and mowing motor speed of the intelligent lawn mower according to different scenes, so as to achieve the purpose of no remaining weeds after the intelligent lawn mower mows once, prevent the blade from being blocked and missed mowing, and maximize the mowing efficiency.

Description

Technical Field

[0001] The invention belongs to the field of intelligent control of lawn mowers, and in particular relates to a control system and a method for intelligent regulation of lawn mowers. Background Art

[0002] With the development of the economy and the need to reduce people's labor intensity, smart lawn mower robots, as a type of outdoor mobile robot, play a vital role in weed trimming and garden mowing. With more and more weeds growing in urban greening, agricultural garden construction, ridges, mountains and forests, the lawn trimming tasks in various venues are becoming increasingly heavy. The traditional hand-pushed gasoline lawn mower weeding method is inefficient, labor-intensive and pollutes the environment. In order to reduce labor costs and improve work efficiency, smart lawn mowers came into being. Smart lawn mowers have a vast market and are developing rapidly. With the emergence of new technologies and new production methods, smart lawn mowers have greatly reduced labor intensity. As the working scenes of smart lawn mowers become more and more complex, how to control the forward speed of smart lawn mowers and the speed of mowing motors has become an important issue.

[0003] When evaluating the quality of smart lawn mowers, mowing efficiency and re-mowing rate have always been very important indicators. Existing smart lawn mowers are generally used in fixed occasions, which greatly limits the versatility of smart lawn mowers. In order to enable smart lawn mowers to work on both standard lawns and orchards with complex weeding environments, the forward speed and mowing motor speed control of smart lawn mowers become particularly important. When the smart lawn mower works in a scene with low weed density, the smart lawn mower needs to speed up the forward speed to improve work efficiency and reduce battery energy consumption without missing any weeds. When the smart lawn mower works in a scene with high weed density and high weed height, the smart lawn mower needs to reduce the forward speed and the speed of the mowing motor, which can improve the stability of the smart lawn mower's forward process and avoid the smart lawn mower from missing any weeds and the mowing motor from getting stuck, damaging the mowing motor, and resulting in low mowing quality.

[0004] In the prior art, the forward speed and the speed of the mowing motor of the mower are mostly controlled manually. The operator can select the most appropriate forward speed and the speed of the mowing motor based on experience to achieve the goal of leaving no weeds after the mower mows once. However, this method cannot achieve intelligent control of the forward speed and the speed of the mowing motor of the smart mower. Summary of the invention

[0005] The purpose of the present invention is to provide a control system and method for the forward speed and mowing motor speed of an intelligent lawn mower, which are used for the intelligent control of the forward speed and mowing motor speed of the intelligent lawn mower. A fuzzy control algorithm is used to simulate the human thinking mode, and the forward speed and mowing motor speed can be intelligently adjusted according to the current working conditions, thereby improving the working efficiency of the intelligent lawn mower.

[0006] To achieve the above purpose, the technical solution adopted by the present invention is:

[0007] A method for controlling the forward speed of an intelligent lawn mower and the speed of a lawn mowing motor comprises the following steps:

[0008] S1, the video of the mowing area taken by the camera of the smart mower is stitched to form a picture of the mowing area;

[0009] S2, calculating the average height H of weeds in the mowing area by the convex lens imaging principle;

[0010] S3, the mowing area image is preprocessed, threshold segmented, binarized and eroded to obtain the density S of the mowing area;

[0011] S4, the average height of weeds H and the density of mowing area S are used as fuzzy variables and input into the fuzzy controller;

[0012] S5, fuzzify the fuzzy variables, converting the precise quantity into the fuzzy quantity;

[0013] S6, inputting the fuzzy quantity of the average height of the weeds and the fuzzy quantity of the density of the mowing area into the fuzzy logic decision module, and the fuzzy quantity of the forward speed of the intelligent lawn mower and the speed of the mowing motor are used as the output of the fuzzy logic decision module, and the fuzzy quantity of the forward speed of the intelligent lawn mower and the speed of the mowing motor are obtained through fuzzy reasoning;

[0014] S7. Convert the fuzzy quantities of the forward speed of the intelligent lawn mower and the speed of the lawn mowing motor into precise quantities as the output of the fuzzy controller.

[0015] Preferably, in step S1, the images are first registered to achieve correct stitching and obtain the actual mowing area.

[0016] Preferably, the forward speed of the intelligent lawn mower and the speed of the mowing motor are controlled by simulating human thinking, the average height of the weeds and the density of the mowing area are used as the input of the fuzzy controller, and the forward speed of the intelligent lawn mower and the speed of the mowing motor are used as the output of the fuzzy controller.

[0017] Preferably, the fuzzy controller has a rule base and a knowledge base, the rule base stores control rules, and the knowledge base stores membership functions; the control rules can be obtained by expert experience, observation, fuzzy model-based methods and self-organization methods.

[0018] Preferably, before performing fuzzy reasoning, it is first necessary to determine the fuzzy quantity of the fuzzy variable and its corresponding membership function, and establish fuzzy control rules based on expert experience.

[0019] Preferably, the method has four fuzzy variables with their own membership functions; the fuzzy quantities of the fuzzy variables specifically include:

[0020] Average height blur of weeds includes very low, low, medium, high, and very high;

[0021] The density fuzzy amount of the mowing area includes sparse, medium, and dense;

[0022] The fuzzy amount of the forward speed of the smart lawn mower includes large, medium, and small;

[0023] The mowing motor speed fuzzy quantity includes fast and slow.

[0024] Preferably, in step S6, the fuzzy reasoning method of the fuzzy logic decision module in the fuzzy controller of the intelligent lawn mower is the Mamdani reasoning method.

[0025] An intelligent lawn mower forward speed and mowing motor speed control system, including hardware including a camera, a controller, an actuator, and a power supply;

[0026] The controller includes a visual processing algorithm, a fuzzy control algorithm, a kinematic analysis algorithm, and a PID control algorithm for controlling the motor speed;

[0027] The camera is connected to the controller, and the collected image of the mowing area is sent to the controller, and the average height and density of the grass are obtained through the visual processing algorithm in the controller;

[0028] The average height of the grass and the density of the grass are used as inputs of the fuzzy control algorithm, and the forward speed of the intelligent lawn mower and the speed of the mowing motor are obtained through the fuzzy control algorithm;

[0029] The forward speed of the smart lawn mower and the speed of the mowing motor are sent to the kinematic model analysis algorithm, the forward speed of the lawn mower is converted into the speed of the driving motor of the smart lawn mower, and the forward motor and the speed of the mowing motor of the smart lawn mower are controlled by the PID control algorithm to achieve precise adjustment of the forward speed of the smart lawn mower and the speed of the mowing motor;

[0030] The actuator is divided into two parts, namely, a motor drive module and a DC motor with an encoder. The controller sends a PWM signal, and the motor drive module converts the PWM signal into a voltage signal and sends it to the DC motor with an encoder. The DC motor with an encoder is the travel drive motor and mowing motor of the intelligent lawn mower. The encoder serves as a detection unit to feed back the speed of the travel drive motor of the intelligent lawn mower to the PID control algorithm.

[0031] Beneficial effects:

[0032] The present invention proposes a vision-based control method, which is more intelligent than other control methods. It can realize intelligent matching of the forward speed of the smart lawn mower and the speed of the mowing motor to achieve the best speed ratio to cope with the changing mowing environments such as mountains, forests, orchards, etc., and select the appropriate forward speed of the smart lawn mower and the speed of the mowing motor according to different scenes to prevent blade blockage and missed mowing, thereby maximizing mowing efficiency.

[0033] When an ordinary smart lawn mower enters a dense lawn, the mowing motor will stop working directly due to excessive load or blocked blades, resulting in incomplete mowing. The fuzzy control method provided by the present invention can adjust the speed of the mowing motor to obtain a larger torque and has better adaptive ability.

[0034] The fuzzy control method provided by the present invention is a control method obtained based on expert experience. This method simulates the thinking mode of a skilled worker operating a lawn mower, and is a specific application of intelligent control in a lawn mower. It greatly improves the intelligence of the intelligent lawn mower, enables the intelligent lawn mower to have a human way of thinking, and has better adaptive ability, so as to achieve the effect of mowing cleanly in one go without re-mowing.

[0035] The present invention can increase the mowing area in the same time and reduce power energy consumption. When the grass is sparse, the intelligent lawn mower can speed up the forward speed and shorten the mowing time. When the grass is dense, the intelligent lawn mower can slow down the forward speed and reduce the weed missed mowing rate, thereby saving energy and improving work efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0037] Figure 1 It is a flow chart of the fuzzy control method of the present invention;

[0038] Figure 2 is a structural diagram of the intelligent lawn mower system of the present invention;

[0039] Figure 3 is a graph showing the change in forward speed of the intelligent lawn mower with weed height under different densities of the present invention;

[0040] Figure 4 is a graph showing the change in the speed of the mowing motor with the height of the weeds at different densities of the present invention;

[0041] Figure 5is a graph showing the change in forward speed of the intelligent lawn mower with weed density at different mowing heights of the present invention;

[0042] Figure 6 This is a graph showing how the speed of the mowing motor changes with the density of weeds at different mowing heights according to the present invention. DETAILED DESCRIPTION

[0043] The following specific examples are given to further clearly, completely and in detail illustrate the technical solution of the present invention. This example is the best example based on the technical solution of the present invention, but the protection scope of the present invention is not limited to the following examples.

[0044] The specific implementation is as follows:

[0045] A method for controlling the forward speed of an intelligent lawn mower and the speed of a lawn mowing motor comprises the following steps:

[0046] S1, decomposing the mowing area video obtained by the camera of the smart lawn mower during the movement into pictures, and forming a mowing area picture by image stitching;

[0047] S2. The average height H of weeds can be obtained from the mowing area image through the convex lens imaging principle. The average height H of weeds is used as the first input of the fuzzy control system.

[0048] S3, the mowing area image, after preprocessing, threshold segmentation, binarization and corrosion processing, the mowing area density S is obtained, and the mowing area density S is used as the second input of the fuzzy control system;

[0049] S4, taking the average height H of weeds and the density S of mowing area as fuzzy variables and inputting them into the fuzzy controller;

[0050] S5, the fuzzy variables are the average height of weeds H and the density of mowing area S. The fuzzy variables are precise quantities and are converted into fuzzy quantities according to certain grammatical rules;

[0051] The fuzzy values ​​of the average height of weeds H are very low, low, medium, high, and very high. The fuzzy values ​​of the density of mowing area S are sparse, medium, and dense. These fuzzy values ​​have their own membership functions.

[0052] There are two output variables of the fuzzy control system of the intelligent lawn mower, namely the forward speed of the intelligent lawn mower and the speed of the mowing motor. The fuzzy quantity of the forward speed of the intelligent lawn mower has three types: large, medium and small, and the fuzzy quantity of the mowing motor speed has two types: fast and slow. These fuzzy quantities have their own membership functions.

[0053] S6. The fuzzy quantity of the average height of weeds and the fuzzy quantity of the density of the mowing area are input into the fuzzy logic decision module composed of fuzzy control rules established by expert experience. The fuzzy quantity of the forward speed of the intelligent lawn mower is obtained through fuzzy reasoning. Then, the membership function of the fuzzy quantity of the forward speed of the intelligent lawn mower is used to obtain the precise values ​​of the forward speed of the intelligent lawn mower and the speed of the mowing motor through the centroid method. The precise values ​​of the forward speed of the intelligent lawn mower and the speed of the mowing motor are used as the output of the fuzzy controller.

[0054] According to the above method, the forward speed of the smart lawn mower and the speed of the mowing motor are intelligently regulated.

[0055] Based on the above method, the intelligent lawn mower forward speed and mowing motor speed control system is designed. The system workflow is as follows:

[0056] First, the mowing area video is obtained by the camera of the smart mower, and a series of mowing area pictures with overlapping parts are obtained. These pictures cannot fully represent the whole mowing area, and the whole mowing area picture needs to be obtained after image stitching.

[0057] The full picture of the mowing area is sent to the controller. The average height and density of the grass obtained by the visual processing algorithm are used as the input of the fuzzy control algorithm. The forward speed of the smart mower and the speed of the mowing motor obtained by the fuzzy control algorithm are used as the input of the kinematic model analysis algorithm. The kinematic model analysis algorithm converts the forward speed of the smart mower into the speed of the smart mower drive motor. The PID control algorithm is used to control the rotation of the smart mower drive motor and the mowing motor, and accurately adjust the speed of the smart mower drive motor and the mowing motor.

[0058] The visual processing algorithm inputs a picture of the entire mowing area and outputs the average height of weeds in the mowing area and the density of the mowing area.

[0059] Another embodiment of the present invention:

[0060] The forward speed control method of the smart lawn mower and the speed control method of the lawn mower motor in the present invention will be further described in detail below in conjunction with the smart lawn mower and the accompanying drawings, but the implementation methods of the present invention are not limited to the smart lawn mower.

[0061] The present invention also includes an intelligent lawn mower, which includes a cutting table and the control system of the present invention. The control method of the present invention is implemented by the lawn mower.

[0062] Figure 1 is the flow chart of fuzzy control method, Figure 2This is the structure diagram of the intelligent lawn mower system. The camera first obtains the video of the mowing area. The video is a series of pictures with overlapping parts. The mowing area of ​​all pictures is spliced ​​according to the edges. The mowing area area is much larger than the actual mowing area area. Therefore, the pictures are first registered to achieve correct splicing and obtain the actual mowing area area. Image registration is to first find the same part of the two pictures, and then overlap them based on the same part. The mowing area picture obtained after image registration is used as the input of the visual processing algorithm.

[0063] The visual processing algorithm has two parts. Step 1 and step 2 obtain the average height of grass weeds and the density of grass weeds respectively:

[0064] Step 1: According to the imaging principle of convex lens, the size of weed image is related to the distance between weed and camera. The closer weed is to camera, the larger the image of base plate. Conversely, the farther weed is from camera, the smaller the image of base plate. Set up a ruler at the center of the far end of the camera sampling area. Take this ruler as the zero point. The horizontal distance from the ruler to the camera lens is L, and the actual distance from the actual position of weed to the ruler position is a. i , the imaging height translated to the ruler position is h i , the imaging height at the actual position is h. According to the principle of similar triangles, we can get:

[0065]

[0066] H is the actual height of the weeds, H i is the imaging height, h i is the actual height at the scale, and the actual height of the weeds can be obtained from the formula;

[0067] However, since not all weeds are on the center line between the camera lens and the ruler, the height of weeds that deviate from the center line needs to be corrected. Let a i is the vertical distance between the weeds and the ruler, b i is the vertical distance between the weeds and the center line, c i is the distance between the weeds and the camera lens. The revised weed height can be obtained according to the formula:

[0068]

[0069] The camera lens is at a certain angle to the mowing area, so the camera shooting angle needs to be corrected. The actual height of the weeds after the final correction can be obtained from the following equation:

[0070]

[0071] Step 2: From the color principle of the image, we can know that the lawn mower area image can be divided into the RGB color system, and the weed density in the mowing area is calculated by setting the color threshold. Since the lawn mower camera works in the wild environment, in order to solve the image vignetting caused by insufficient light in some shooting areas, the image must first be corrected for vignetting. When the smart lawn mower is walking on a bumpy road, the camera will shake and cause the captured image to be deformed. The image needs to be geometrically corrected. In order to solve the problem of image distortion in the camera, the image needs to be corrected for the response curve. After these three steps of preprocessing, an image that restores the real scene to the greatest extent can be obtained, providing a basis for further estimating the weed density;

[0072] The linear color system value L is obtained by the following formula:

[0073]

[0074] Among them, r, gb are RGB pixel values, ranging from 0 to 255 integers, and θ is a constant;

[0075] The optimal threshold after image segmentation is obtained by the OTSU algorithm:

[0076] T=Max[w0×(u0-u) 2 +w1×(u1-u) 2 ]

[0077] Among them, w0 is the ratio of the background image of the preprocessed mowing area, u0 is the grayscale mean of the background image of the preprocessed mowing area image, w1 is the ratio of the foreground image of the preprocessed mowing area, u1 is the grayscale mean of the foreground image of the preprocessed mowing area image, and u is the mean of the entire image of the preprocessed mowing area image.

[0078] According to the threshold range of weeds and the linear color system value L, the type of the current pixel is determined, binarization and corrosion processing are performed, and finally the density of weeds in the mowing area is calculated.

[0079] Step 3: By Figure 2 It can be seen that the average height of weeds obtained in step 1 and the density obtained in step 2 are two inputs of the fuzzy control algorithm. The fuzzy controller in this example is a two-input and two-output fuzzy controller. The fuzzy variables include the average height of weeds, the density of weeds, the forward speed of the smart mower, and the speed of the mowing motor.

[0080] The domain of the average height of weeds is [0-70], the domain of weed density is [0-100], the domain of the forward speed of the smart mower is [0-8], and the domain of the mowing motor speed is [0-4800], and their proportional factors are all set to 1;

[0081] To fuzzify fuzzy variables, commonly used fuzzification functions include single point fuzzification, triangular function and Gaussian function. In this example, all fuzzy variables are fuzzified using triangular functions;

[0082] The fuzzy quantities of the average height of weeds after fuzzification are very low, low, medium, high, and very high. The fuzzy quantities of the density of the mowing area are sparse, medium, and dense. The fuzzy quantities of the forward speed of the smart mower are large, medium, and small. The fuzzy quantities of the speed of the mowing motor are fast and slow. These fuzzy quantities have their own membership functions and are stored in the knowledge base.

[0083] Step 4: The fuzzy controller also has a rule base. The knowledge base stores membership functions and the rule base stores control rules. The control rules can be obtained by expert experience, observation, fuzzy model-based methods and self-organization methods. This example uses the observation method, and the control rules are completed by control experts and skilled operators.

[0084] The control rules of this example are shown in Table 1 below:

[0085] Table 1

[0086]

[0087] like Figure 1 As shown, the weed height H and weed density S are input, the knowledge base provides the membership function, the rule base provides the control rules, and after the inference engine reasoning, the fuzzy value V of the forward speed of the intelligent lawn mower and the fuzzy value N of the speed of the lawn mower motor are obtained.

[0088] Commonly used fuzzy reasoning methods of inference engines include Zadeh reasoning method and Mamdani method.

[0089] The method used in this example is the Mamdani reasoning method, which is as follows:

[0090] A→B=A×B=A T ∧B

[0091] Among them, A is the input fuzzy set and B is the output fuzzy set.

[0092] Step 5: The fuzzy quantity V of the forward speed of the smart lawn mower and the fuzzy quantity N of the speed of the lawn mower motor obtained in step 4 are refined to convert the fuzzy quantity into the precise quantity. The methods include the maximum membership function method, the centroid method and the weighted average method. This example uses the centroid method. The formula is as follows:

[0093]

[0094] Step 6: The precise values ​​of the forward speed of the smart lawn mower and the speed of the mowing motor obtained by the fuzzy control algorithm are analyzed by the kinematic model algorithm to obtain the driving motor speed and the speed of the mowing motor of the smart lawn mower.

[0095] Step 7: Figure 2 As shown in the figure, the input of the PID control algorithm is the speed of the intelligent lawn mower drive motor and the speed of the mowing motor. The PID control algorithm outputs a pwm signal to the motor drive module, and the motor drive module outputs a voltage value to the DC motor. The DC motor speed measured by the encoder is fed back to the PID control algorithm, and the motor closed-loop feedback control is performed through the PID control algorithm.

[0096] In this example, Matlab / Simulink simulation is used to build a fuzzy controller, discretize the average height of weeds into a series of point values ​​in the range of 0 to 70, and discretize the density of the mowing area into a series of point values ​​in the range of 0 to 100. Through simulation, we can get Figures 3 to 6 , Figure 3 is the curve of the intelligent lawn mower's forward speed changing with the average weed height h when the density s is 100, 80, and 20. Figure 4 is the curve of the mowing motor speed changing with the average weed height h when the density s is 100, 80, and 20. Figure 5 is the curve of the change of the forward speed of the intelligent lawn mower with the density s when the average height of the weeds h is 60, 35, Figure 6 The curve of the mowing motor speed changing with the density s when the average height of weeds h is 60, 35;

[0097] Depend on Figures 3 to 6 The change curve is obtained, and the fuzzy control algorithm can intelligently adjust the forward speed and motor speed of the smart lawn mower according to the average height of weeds and the density of the mowing area, so as to achieve the requirements of improving mowing efficiency and avoiding missing mowing.

[0098] In summary, the present invention uses a fuzzy control algorithm to simulate human thinking, intelligently controls the forward speed of the lawn mower and the speed of the mowing motor, and improves the working efficiency of the intelligent lawn mower.

[0099] The above shows and describes the main features, basic principles and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited to the above embodiments, and the above embodiments and descriptions are only for explaining the principles of the present invention. Without departing from the spirit and scope of the present invention, the present invention may be modified or altered in various ways according to actual conditions, and these equivalent changes and modifications also fall within the scope defined by the claims of the present invention.

Claims

1. A method for controlling the forward speed of an intelligent lawn mower and the speed of a lawn mowing motor, characterized in that: The method comprises the following steps: S1, the video of the mowing area taken by the camera of the smart mower is stitched to form a picture of the mowing area; S2, calculating the average height H of weeds in the mowing area by the convex lens imaging principle; S3, the mowing area image is preprocessed, threshold segmented, binarized and eroded to obtain the density S of the mowing area; S4, the average height of weeds H and the density of mowing area S are used as fuzzy variables and input into the fuzzy controller; S5, fuzzify the fuzzy variables, converting the precise quantity into the fuzzy quantity; S6, inputting the fuzzy quantity of the average height of the weeds and the fuzzy quantity of the density of the mowing area into the fuzzy logic decision module, and the fuzzy quantity of the forward speed of the intelligent lawn mower and the speed of the mowing motor are used as the output of the fuzzy logic decision module, and the fuzzy quantity of the forward speed of the intelligent lawn mower and the speed of the mowing motor are obtained through fuzzy reasoning; S7. Convert the fuzzy quantities of the forward speed of the intelligent lawn mower and the speed of the lawn mowing motor into precise quantities as the output of the fuzzy controller.

2. A method for controlling the forward speed of an intelligent lawn mower and the speed of a lawn mowing motor as claimed in claim 1, characterized in that: In step S1, the images are first registered to achieve correct stitching and obtain the actual mowing area.

3. The method for controlling the forward speed of an intelligent lawn mower and the speed of a lawn mowing motor according to claim 1, characterized in that: The forward speed and mowing motor speed of the smart lawn mower are controlled by simulating human thinking. The average height of weeds and the density of the mowing area are used as the input of the fuzzy controller, and the forward speed and mowing motor speed of the smart lawn mower are used as the output of the fuzzy controller.

4. A method for controlling the forward speed of an intelligent lawn mower and the speed of a lawn mowing motor as claimed in claim 3, characterized in that: The fuzzy controller has a rule base and a knowledge base. The rule base stores control rules, and the knowledge base stores membership functions. The control rules can be obtained by expert experience, observation, fuzzy model-based methods and self-organization methods.

5. The method for controlling the forward speed of an intelligent lawn mower and the speed of a lawn mowing motor as claimed in claim 3, characterized in that: Before fuzzy reasoning, it is necessary to first determine the fuzzy quantity of the fuzzy variable and its corresponding membership function, and establish fuzzy control rules based on expert experience.

6. A method for controlling the forward speed of an intelligent lawn mower and the speed of a lawn mowing motor as claimed in claim 5, characterized in that: The method has four fuzzy variables with their own membership functions; the fuzzy quantities of the fuzzy variables specifically include: Average height blur of weeds includes very low, low, medium, high, and very high; The density fuzzy amount of the mowing area includes sparse, medium, and dense; The fuzzy amount of the forward speed of the smart lawn mower includes large, medium, and small; The mowing motor speed fuzzy quantity includes fast and slow.

7. A method for controlling the forward speed of an intelligent lawn mower and the speed of a lawn mowing motor as claimed in claim 1, characterized in that: In step S6, the fuzzy reasoning method of the fuzzy logic decision module in the fuzzy controller of the intelligent lawn mower is the Mamdani reasoning method.

8. An intelligent lawn mower forward speed and lawn mowing motor speed control system, which is applied to the method according to any one of claims 1 to 7, characterized in that: Hardware including cameras, controllers, actuators, and power supplies; The controller includes a visual processing algorithm, a fuzzy control algorithm, a kinematic analysis algorithm, and a PID control algorithm for controlling the motor speed; The camera is connected to the controller, and the collected image of the mowing area is sent to the controller, and the average height and density of the grass are obtained through the visual processing algorithm in the controller; The average height of the grass and the density of the grass are used as inputs of the fuzzy control algorithm, and the forward speed of the intelligent lawn mower and the speed of the mowing motor are obtained through the fuzzy control algorithm; The forward speed of the smart lawn mower and the speed of the mowing motor are sent to the kinematic model analysis algorithm, the forward speed of the lawn mower is converted into the speed of the driving motor of the smart lawn mower, and the forward motor and the speed of the mowing motor of the smart lawn mower are controlled by the PID control algorithm to achieve precise adjustment of the forward speed of the smart lawn mower and the speed of the mowing motor; The actuator is divided into two parts, namely, a motor drive module and a DC motor with an encoder. The controller sends a PWM signal, and the motor drive module converts the PWM signal into a voltage signal and sends it to the DC motor with an encoder. The DC motor with an encoder is the travel drive motor and mowing motor of the intelligent lawn mower. The encoder serves as a detection unit to feed back the speed of the travel drive motor of the intelligent lawn mower to the PID control algorithm.

Images