Automatic row alignment method, device, storage medium, program product and system

Abstract

The invention provides an automatic row alignment method and device, a storage medium, a program product and a system. The method comprises the following steps: acquiring transverse deviation and course deviation of a vehicle in a farmland; determining a first steering angle by adopting an adaptive feedback mechanism based on the lateral deviation and the course deviation; a sliding mode controller function is constructed based on the lateral deviation and the course deviation, and a second steering angle is calculated through the sliding mode controller function; determining a target steering angle according to the first steering angle and the second steering angle; and controlling the vehicle to run through the target steering angle so as to realize automatic row control. According to the embodiment of the invention, the transverse deviation and the course deviation of the vehicle in the farmland are obtained, the two deviations can accurately reflect the position and direction difference of the vehicle relative to the crop row center line, and the target steering angle is calculated in combination with an adaptive feedback mechanism and a sliding mode control algorithm, so that the accuracy and the stability of automatic row control are enhanced, and the accuracy and the stability of automatic row control are improved. And the seedling pressing problem caused by deviation is reduced.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of agricultural automation, in particular to an automatic alignment method, device, storage medium, program product and system. BACKGROUND

[0002] With the continuous progress of science and technology, the research and development of agricultural automation machinery equipment in China has been increasingly improved, and has gradually changed from traditional manual seeding and harvesting methods to automation, mechanization and intelligentization.

[0003] At present, existing agricultural machinery, such as combine harvesters, self-propelled spraying machines, cotton picking machines, etc., are gradually equipped with automatic alignment functions, aiming to reduce the burden of drivers and improve work efficiency. In order to reduce the damage rate and loss rate of crops during harvesting or spraying, and reduce labor intensity, the common navigation system is composed of GNSS satellite positioning and INS inertial navigation, combined with hydraulic or motor system for path control, and combined with visual recognition or laser radar sensing to perceive the working path.

[0004] When crops are sown, the seeder travels and sows according to the preset path, but due to external factors (such as wind speed, terrain undulation, etc.), it will cause seed drift. In this case, if spraying or harvesting is carried out according to the original preset path, it may cause the risk of seedling compression due to inaccurate alignment. SUMMARY

[0005] The purpose of the embodiments of the present application is to provide an automatic alignment method, device, storage medium, program product and system to improve the accuracy of automatic alignment of vehicles when driving in farmland.

[0006] In a first aspect, the embodiments of the present application provide an automatic alignment method, comprising: obtaining a lateral deviation and a heading deviation of a vehicle in a farmland; wherein the lateral deviation refers to the vertical distance of a specific reference point on the vehicle from the center line of the crop row; and the heading deviation refers to the included angle difference between the current heading angle of the vehicle and the center line of the crop row; determining a first steering angle based on the lateral deviation and the heading deviation using an adaptive feedback mechanism; constructing a sliding mode controller function based on the lateral deviation and the heading deviation, and calculating a second steering angle through the sliding mode controller function; determining a target steering angle according to the first steering angle and the second steering angle; controlling the vehicle to travel through the target steering angle to realize automatic alignment.

[0007] The embodiments of the present application can obtain the lateral deviation and the heading deviation of the vehicle in the farmland, the two deviations can accurately reflect the difference in position and direction of the vehicle relative to the center line of the crop row, and the target steering angle is calculated in combination with the adaptive feedback mechanism and the sliding mode control algorithm, so that the accuracy and stability of automatic row alignment are enhanced, and the seedling pressing problem caused by deviation is reduced.

[0008] In a possible implementation of the first aspect, based on the lateral deviation and the heading deviation, the adaptive feedback mechanism is adopted to determine the first steering angle, including: An adaptive feedback control rate function is generated according to the lateral deviation and the heading deviation; the adaptive feedback control rate function includes a lateral gain and a heading gain, and the lateral gain and the heading gain are obtained by gradient descent cost function optimization.

[0009] In the embodiments of the present application, since the lateral deviation and the heading deviation are key factors directly reflecting the relative position and direction of the vehicle and the center line of the crop row, the adaptive feedback control rate function can be constructed by using the two deviations, the precise control of the vehicle steering can be realized, the adaptive feedback mechanism can dynamically adjust the control strategy according to the actual deviation condition, the steering angle of the vehicle can be more accurately corrected, and the precision of automatic row alignment of the vehicle is improved.

[0010] In a possible implementation of the first aspect, the adaptive feedback control rate function is ; The gradient descent cost function is ; wherein, is the first steering angle; is an optimization target cost; ; is the lateral deviation; is the heading deviation; , , , is an adaptive coefficient, , , , the value of is obtained by fitting according to the recursive least square method with a forgetting factor; is the lateral gain; is the heading gain; is a weight coefficient.

[0011] According to the adaptive feedback control rate function, the lateral deviation and the heading deviation, the embodiments of the present application can generate the steering control signal that matches the actual deviation condition of the vehicle in real time and accurately, improve the precision of automatic row alignment of the vehicle, and ensure that the vehicle stably travels along the center line of the crop row.

[0012] In a possible implementation manner of the first aspect, the first-order approaching sliding mode controller function is constructed based on the lateral deviation and the heading deviation, and the second turning angle is calculated by the sliding mode controller, including: constructing a first-order approaching sliding mode controller function based on the lateral deviation and the heading deviation; generating a Lyapunov constraint function and a stability condition function according to the lateral deviation and the heading deviation; solving the first-order approaching sliding mode controller function by the Lyapunov constraint function and the stability condition function to obtain the second turning angle.

[0013] The first-order approaching sliding mode controller function is constructed by the lateral deviation and the heading deviation, so that the vehicle can quickly approach the expected sliding mode surface in the deviation state, that is, the vehicle can quickly adjust to the ideal state close to the crop row center line, the time for the vehicle to deviate from the center line in the automatic alignment process is reduced, and the efficiency of the automatic alignment is improved.

[0014] In a possible implementation manner of the first aspect, the first-order approaching sliding mode controller function is ; the Lyapunov constraint function is ; the stability condition function is ; wherein, ; is the lateral deviation; is the heading deviation; is a weight coefficient; is a switching gain.

[0015] The first-order approaching sliding mode controller function can make the lateral deviation and the heading deviation of the vehicle quickly converge to zero, and the introduction of the Lyapunov constraint function and the stability condition function can theoretically strictly prove the stability of the system, so that the vehicle can stably run under various initial deviation conditions.

[0016] In a possible implementation manner of the first aspect, the vehicle is provided with an alignment device, and the alignment device includes a guide touch rod; the method further includes: obtaining a maximum included angle of the guide touch rod; wherein the maximum included angle is an included angle formed by the guide touch rod and crops in the process of driving the vehicle in a farmland; determining the lateral deviation according to the maximum included angle and a length of the guide touch rod.

[0017] The lateral deviation is determined by the maximum included angle of the guide touch rod and the length of the guide touch rod, which provides a data basis for subsequent calculation of the target turning angle.

[0018] In a possible implementation manner of the first aspect, the method further includes: acquire a lateral deviation change amount of the vehicle in a time period and a driving distance of the vehicle; determine a heading deviation based on the lateral deviation change amount and the driving distance.

[0019] The embodiment of the present application determines the heading deviation based on the lateral deviation change amount and the driving distance, and provides data basis for subsequent calculation of the target steering angle.

[0020] In a possible implementation of the first aspect, the vehicle is provided with a positioning module and a rowing device, the rowing device includes a guide touch rod, a signal strength of the positioning module is greater than a preset threshold, and the method further includes: acquiring positioning module position information collected by the positioning module; calculating guide touch rod position information according to the positioning module position information and a positional relationship between the positioning module and the guide touch rod; determining a navigation line of the crops according to the guide touch rod position information corresponding to the plurality of time points and an included angle of the guide touch rod; determining the lateral deviation and the heading deviation according to the navigation line and position information of the vehicle.

[0021] The embodiment of the present application calculates the actual navigation line of the crops in combination with the positioning information collected by the positioning module and the included angle of the guide touch rod, and then determines the lateral deviation and the heading deviation according to the actual navigation line and the position information of the vehicle, thereby improving the calculation accuracy of the lateral deviation and the heading deviation.

[0022] In a possible implementation of the first aspect, before the first steering angle is determined based on the lateral deviation and the heading deviation by using the adaptive feedback mechanism, the method further includes: generating an error dynamic model according to the lateral deviation, the heading deviation, a driving speed of the vehicle and a wheelbase of the vehicle; The error dynamic model is ; wherein, is the lateral deviation; is the heading deviation; is the driving speed; is the wheelbase of the vehicle; is the target steering angle.

[0023] In the embodiment of the present application, the error dynamic model can accurately describe the change trend of the lateral deviation and the heading deviation in the driving process of the vehicle, and provide more accurate deviation dynamic information for subsequent adaptive feedback control; and the model considers parameters such as the driving speed and the wheelbase of the vehicle, and can adapt to the automatic rowing demand under different vehicle types and driving speeds.

[0024] In the second aspect, the embodiment of the present application provides an automatic rowing device, including: The bias obtaining module is configured to obtain a lateral bias and a heading bias of the vehicle in the farmland, wherein the lateral bias refers to a vertical distance of a specific reference point on the vehicle from a center line of a crop row, and the heading bias refers to an included angle difference between a current heading angle of the vehicle and the center line of the crop row. The first steering angle determining module is configured to determine a first steering angle based on the lateral bias and the heading bias by using an adaptive feedback mechanism. The second steering angle determining module is configured to construct a sliding mode controller function based on the lateral bias and the heading bias, and to obtain a second steering angle by calculation of the sliding mode controller function. The target steering angle determining module is configured to determine a target steering angle according to the first steering angle and the second steering angle. The control module is configured to control the vehicle to travel by using the target steering angle, so as to realize automatic alignment with the crop row.

[0025] In a third aspect, an embodiment of the present application provides a non-transitory computer readable storage medium, comprising: The non-transitory computer readable storage medium stores computer instructions, and the computer instructions cause a computer to execute the method in any possible implementation manner of the first aspect.

[0026] In a fourth aspect, an embodiment of the present application provides a computer program product, comprising computer program instructions, which, when read and executed by a processor, execute the method in any possible implementation manner of the first aspect.

[0027] In a fifth aspect, an embodiment of the present application provides an automatic alignment system, which comprises an alignment controller and an alignment device; the alignment device is arranged on a vehicle. The alignment device comprises a guide touch rod, a boundary detection sensor and an elastic reset structure. The guide touch rod is connected with the boundary detection sensor and the elastic reset structure respectively; the guide touch rod generates an angular displacement by contacting the crops, and the angular displacement is measured by the boundary detection sensor. The boundary detection sensor is connected with the alignment controller on the vehicle, and the boundary detection sensor sends the angular displacement to the alignment controller. The elastic reset structure is configured to provide a restoring force to the guide touch rod after the guide touch rod leaves the crops. The alignment controller is configured to execute the method of the first aspect, generate a target steering angle, and control the electric steering wheel to rotate, so as to align the vehicle with the crop row.

[0028] In a possible implementation manner of the fifth aspect, the system further comprises an electric steering wheel; the electric steering wheel is connected with the alignment controller. The pair of row controllers sends control instructions to the electric steering wheel according to the target steering angle obtained by calculation, so as to control the vehicle to travel. The automatic row following system provided by the embodiment of the application realizes high-precision, intelligent and dynamic response of the vehicle along the crop row by integrating the high-precision row following device and the algorithm based on the sliding mode control combined with adaptive feedback control, and reduces the seedling pressing problem caused by deviation.

[0029] Other features and advantages of the present application will be set forth in the following description, and in part will become apparent to those skilled in the art from the description, or can be learned by practice of the present application. The objects and other advantages of the present application can be realized and attained by means of the instrumentalities particularly pointed out in the written description and claims hereof, as well as the appended drawings. BRIEF DESCRIPTION OF DRAWINGS

[0030] In order to more clearly illustrate the technical solutions of the embodiments of the application, the following will briefly introduce the drawings needed to be used in the embodiments of the application. It should be understood that the following drawings only show some of the embodiments of the application, and therefore should not be regarded as a limitation to the scope. For those skilled in the art, other related drawings can also be obtained without creative labor on the basis of these drawings.

[0031] Figure 1 A schematic diagram of an automatic row following system provided by the embodiment of the application; Figure 2 A schematic diagram of a row following device structure provided by the embodiment of the application; Figure 3 A schematic diagram of an automatic row following method flow provided by the embodiment of the application; Figure 4 A schematic diagram of the relative position relationship between the vehicle and the crop row provided by the embodiment of the application; Figure 5 A schematic diagram of a guide touch rod provided by the embodiment of the application; Figure 6 A schematic diagram of an included angle calculation of a guide touch rod provided by the embodiment of the application; Figure 7 A schematic diagram of a heading deviation calculation provided by the embodiment of the application; Figure 8 A schematic diagram of an automatic row following method principle provided by the embodiment of the application; Figure 9 A schematic diagram of an automatic row following device structure provided by the embodiment of the application; Figure 10 A schematic diagram of an electronic device physical structure provided by the embodiment of the application.

[0032] LIST OF ELEMENTS IN THE DRAWINGS 1-mounting bracket; 2-boundary detection sensor; 3-elastic reset structure; 4-pairing device rotating body; 5-pairing device rotating main shaft; 6-guiding touch rod adjusting block; 7-guiding touch rod limiting torsion spring; 8-guiding touch rod; 9-protection cover. DETAILED DESCRIPTION

[0033] The embodiments of the technical solutions of the present application will be described in detail below with reference to the drawings. The following embodiments are only used to more clearly illustrate the technical solutions of the present application, and therefore only serve as examples, and cannot limit the protection scope of the present application.

[0034] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs; the terms used herein are only for the purpose of describing specific embodiments and are not intended to limit the present application; the terms "include" and "have" and any variations thereof in the specification and claims of the present application and the above description of drawings are intended to cover non-exclusive inclusion.

[0035] In the description of the embodiments of the present application, the technical terms "first", "second", etc. are only used to distinguish different objects, and cannot be understood as indicating or implying relative importance or implicitly indicating the number, specific order or primary and secondary relationship of the indicated technical features. In the description of the embodiments of the present application, the meaning of "multiple" is more than two, unless otherwise explicitly and specifically limited.

[0036] In this paper, the phrase "embodiment" means that the specific features, structures or properties described in conjunction with the embodiment can be included in at least one embodiment of the present application. The appearance of this phrase in various places in the specification does not necessarily mean the same embodiment, nor is it an independent or alternative embodiment that is not mutually exclusive with other embodiments. The skilled person in the art explicitly and implicitly understands that the embodiments described herein can be combined with other embodiments.

[0037] In the description of the embodiments of the present application, the term "and / or" is only a description of the association relationship between the associated objects, which means that there can be three relationships, for example, A and / or B, which can represent the three cases of A alone, A and B together, and B alone. In addition, the character " / " in this paper generally represents that the front and rear associated objects have an "or" relationship.

[0038] In the description of the embodiments of the present application, the term "multiple" refers to more than two (including two), and similarly, "multiple groups" refers to more than two groups (including two groups), and "multiple pieces" refers to more than two pieces (including two pieces).

[0039] In the description of the embodiments of the present application, unless otherwise explicitly specified and limited, the technical terms "mounting", "connecting", "connecting", "fixing" and the like should be understood in a broad sense, for example, can be fixedly connected, or can be detachably connected, or can be integrated; can be mechanically connected, or can be electrically connected; can be directly connected, or can be indirectly connected through an intermediate medium, or can be the internal communication of two elements or the interaction relationship between two elements. For those skilled in the art, the specific meanings of the above terms in the embodiments of the present application can be understood according to the specific circumstances.

[0040] With the continuous progress of science and technology, the field of agriculture is rapidly developing towards automation and intelligence. As a key component of agricultural machinery, automatic driving technology can significantly improve agricultural production efficiency, reduce labor intensity, and improve operation quality, which is of great significance to the realization of precision agriculture. Through precise path tracking, agricultural machinery can perform operations such as transplanting, seeding, fertilizing, and harvesting in farmland, ensuring consistency and accuracy of operation, thereby improving crop yield and quality, and reducing resource waste.

[0041] In existing navigation systems, due to complex terrain, tree cover or building interference, the stability and accuracy of GNSS signals are difficult to guarantee, which significantly increases the risk of deviation of the operation path. In addition, taking corn as an example, due to the influence of terrain undulation or wind speed, the seed will drift during seeding. In this case, the subsequent pesticide machine or harvester will not be able to accurately operate along the seeding navigation line, increasing the risk of seedling compression and missing collection.

[0042] Based on this, the embodiments of the present application provide an automatic alignment method, which determines a first steering angle by using an adaptive feedback mechanism based on the lateral deviation and heading deviation of the vehicle, and determines a second steering angle by using a sliding mode controller function, and then determines a target steering angle based on the first steering angle and the second steering angle, thereby reducing the risk of seedling compression caused by deviation.

[0043] It can be understood that the automatic alignment method provided by the embodiments of the present application can be applied to various agricultural machinery, such as corn harvesters, cotton harvesters, and corn pesticide machines. For scenarios that require alignment when using agricultural machinery for farming, the method provided by the present application can be used.

[0044] Figure 1 An automatic alignment system provided by the embodiments of the present application is shown in FIG. 1. Figure 1 The system includes an alignment controller and an alignment device, wherein the alignment device is arranged on a vehicle, and the vehicle is taken as a corn harvester. The alignment controller can also be arranged on the vehicle and connected with the alignment device and the electric steering wheel.

[0045] Figure 2A schematic diagram of a row unit structure provided in the embodiments of the present application is shown in Figure 2 The row unit includes a guide touch rod 8, a boundary detection sensor 2, and an elastic reset structure 3. It can be understood that the row unit can include a mounting bracket 1, a row unit rotating body 4, a row unit rotating main shaft 5, a guide touch rod adjusting block 6, a guide touch rod limiting torsion spring 7, and a protective cover 9, in addition to the above-mentioned components. For a corn harvester, it includes a row unit for separating and guiding the corn harvester to pick ears. The row unit is arranged at the front end of the row unit of the vehicle, and the longitudinal direction thereof is parallel to the forward direction of the vehicle. In order to improve the stability of the device during operation, the row unit is fixed to the mounting base through a shockproof bracket. The row unit is used to detect whether the row unit is just inserted into the gap between two corns (that is, whether the row unit is just on the center line of the gap between the two corn plants). When the corn harvester drives forward in the corn field, if the row unit is on the center line between the two corn plants, the guide touch rod will not contact the corn plants; if the row unit deviates from the center line, the guide touch rod collides with the corn plants. The guide touch rod is connected with the boundary detection sensor, and drives the boundary detection sensor to produce angular displacement, so that the boundary detection sensor can detect the included angle between the guide touch rod and the horizontal line, and send the included angle to the row control controller.

[0046] The elastic reset structure is connected with the guide touch rod, and is used to provide a restoring force to the guide touch rod after the guide touch rod leaves the crops, so that the guide touch rod can maintain a sensitive following state, and improve the detection stability and operation adaptability.

[0047] The row control controller can calculate the lateral deviation and the heading deviation of the corn harvester based on the included angle, calculate the target steering angle based on the lateral deviation and the heading deviation, control the rotation of the electric steering wheel through the target steering angle, and finally control the driving direction of the corn harvester. The method for calculating the lateral deviation, the heading deviation, and the target steering angle by the row control controller is described in the following embodiments.

[0048] It should be noted that the vehicle can also include an electric steering wheel and a display, wherein the electric steering wheel is used to receive the control instruction sent by the row control controller based on the target steering angle, so as to realize the control of the driving direction of the vehicle. The display is used to display key operation information such as vehicle speed, lateral deviation, heading deviation, target steering angle, and the like in real time. In addition, the vehicle also includes other components that meet the operation requirements, and the embodiments of the present application do not make specific limitations thereto.

[0049] In order to realize high-precision automatic alignment control of the harvester along the crop row, the system needs to dynamically adjust the wheel angle of the vehicle according to the deviation value detected by the alignment device in real time, so as to correct the driving direction. The adjustment strategy has proportional adjustment characteristics: when the deviation is large, the steering adjustment amplitude is increased accordingly to realize rapid correction; when the deviation is small, the steering amplitude is reduced to avoid excessive correction and ensure the alignment stability and control accuracy.

[0050] Based on the above system, the embodiment of the present application provides an automatic alignment method, Figure 3 For the automatic alignment method provided by the embodiment of the present application, a flowchart is shown in Figure 3 The method comprises the following steps: Step 301: obtaining the lateral deviation and the heading deviation of the vehicle in the farmland; wherein the lateral deviation refers to the vertical distance of a specific reference point on the vehicle from the center line of the crop row; the heading deviation refers to the included angle difference between the current heading angle of the vehicle and the center line of the crop row; Step 302: determining the first steering angle based on the lateral deviation and the heading deviation by using an adaptive feedback mechanism; Step 303: constructing a sliding mode controller function based on the lateral deviation and the heading deviation, and calculating the second steering angle through the sliding mode controller function; Step 304: determining the target steering angle according to the first steering angle and the second steering angle; Step 305: controlling the vehicle to drive through the target steering angle to realize automatic alignment.

[0051] In the specific implementation process, the lateral deviation refers to the vertical distance of a specific reference point (such as the header of a corn harvester) on the vehicle from the center line of the crop row, which reflects the deviation degree of the vehicle in the lateral direction. The lateral deviation can be obtained by real-time acquisition of the vehicle position and the crop row position through the vehicle-mounted sensor (such as GNSS sensor combined with RTK technology) or visual sensor (such as camera, laser radar), and calculation of the vertical distance between the two. It can also be obtained by detection of the alignment device arranged on the vehicle.

[0052] The heading deviation refers to the included angle difference between the current heading angle of the vehicle and the center line of the crop row, which reflects the deviation degree of the vehicle in the direction of the crop row. Specifically, it can be calculated through the attitude sensor (such as IMU, inertial measurement unit) of the vehicle or the steering wheel angle sensor combined with the vehicle dynamics model. It can also be obtained by detection of the alignment device arranged on the vehicle.

[0053] The lateral deviation is used to evaluate whether the vehicle deviates from the center line of the crop row, and the heading deviation is used to evaluate whether the driving direction of the vehicle is consistent with the direction of the crop row. Therefore, the lateral deviation and the heading deviation are both key inputs of the automatic alignment control. It should be noted that the way of obtaining the lateral deviation and the heading deviation based on the detection of the alignment device is described in the following embodiments.

[0054] Figure 4 The relative position relationship between the vehicle and the crop row provided by the embodiments of the present application can be summarized as nine typical working conditions, which correspond to different degrees and directions of deviation, and are used to guide the judgment and response strategy of the row control system. The nine working conditions are shown in the following table:

[0055] The adaptive feedback mechanism is a control strategy that can dynamically adjust control parameters according to the input and output of the system to optimize the performance of the system and adapt to changes in the environment or system characteristics. In the embodiments of the present application, the adaptive feedback mechanism adjusts the control parameters by monitoring the lateral deviation and heading deviation in real time, thereby achieving precise control of the driving direction of the vehicle.

[0056] In the specific implementation process, a control rate function can be defined according to the lateral deviation and the heading deviation to calculate the first steering angle. In the process of calculating the first steering angle, a cost function is used to quantify the size of the deviation. The lateral gain and the heading gain in the control rate function can be calculated using the gradient descent method or other optimization algorithms.

[0057] The core idea of the sliding mode control is to guide the system state to a predefined sliding surface and slide on the surface to achieve the desired system performance. The sliding surface is a hyperplane that guides the system state to the desired trajectory. The purpose of the sliding mode controller is to guide the system state to the sliding surface and maintain sliding on the surface. The stability of the sliding mode control is analyzed by the Lyapunov stability theory, and the second steering angle is finally obtained.

[0058] After obtaining the first steering angle and the second steering angle, the sum of the two can be used as the target steering angle. The vehicle is controlled by calculating the target steering angle obtained to make the vehicle drive as much as possible on the center line of the crop row.

[0059] The embodiments of the present application obtain the lateral deviation and the heading deviation of the vehicle in the farmland, which can accurately reflect the difference in position and direction of the vehicle relative to the center line of the crop row. Combined with the adaptive feedback mechanism and the sliding mode control algorithm to calculate the target steering angle, the accuracy and stability of the automatic row alignment are enhanced, and the problem of seedling damage caused by deviation is reduced.

[0060] On the basis of the above embodiments, based on the lateral deviation and the heading deviation, the adaptive feedback mechanism is used to determine the first steering angle, which includes: An adaptive feedback control rate function is generated according to the lateral deviation and the heading deviation. The adaptive feedback control rate function includes a lateral gain and a heading gain, and the lateral gain and the heading gain are obtained by optimizing the gradient descent cost function.

[0061] In the specific implementation process, the adaptive feedback control rate function is designed to design a basic and parameter-adjustable controller , which can calculate part of the steering command according to the current lateral deviation and heading deviation, and the goal is to quickly reduce the front error. The lateral gain and the heading gain can automatically adapt to environmental changes (such as terrain conditions). Its working principle is to use linear feedback control rate, but its lateral gain and heading gain are not fixed, but are constantly updated and optimized through online parameter estimation.

[0062] wherein the adaptive feedback control rate function is ; is the first steering angle; is the lateral deviation; is the heading deviation; is the lateral gain; is the heading gain.

[0063] To calculate the specific values of the lateral gain and the heading gain, the coefficient equation can be constructed.

[0064] , , , is the adaptive coefficient, , , , The values of are obtained by fitting with the recursive least squares method with a forgetting factor; Then, by defining the gradient descent cost function , the lateral gain and the heading gain are optimized, and the goal is to minimize , that is, to minimize the lateral deviation and the heading deviation at the same time. is the weight coefficient, which determines whether more attention is paid to eliminating the lateral deviation or the heading deviation, wherein The larger the value is, the more attention is paid to the heading deviation.

[0065] In the gradient descent method, the gradient is calculated according to and The lateral gain is calculated according to , and the heading gain is calculated according to .

[0066] wherein is the learning rate, which controls the step size of parameter update, and by constantly iterating the lateral gain and the heading gain , the cost function is minimized.

[0067] The adaptive feedback control rate function is combined with the lateral deviation and the heading deviation to generate a steering control signal that matches the actual deviation of the vehicle in real time and accurately, improve the precision of automatic alignment of the vehicle, and ensure stable driving of the vehicle along the center line of the crop row.

[0068] On the basis of the above embodiment, a sliding mode controller function is constructed based on the lateral deviation and the heading deviation, and a second steering angle is obtained by calculation of the sliding mode controller, including: A first-order approaching sliding mode controller function is constructed based on the lateral deviation and the heading deviation; A Lyapunov constraint function and a stable condition function are generated according to the lateral deviation and the heading deviation; The first-order approaching sliding mode controller function is solved by the Lyapunov constraint function and the stable condition function to obtain the second steering angle.

[0069] In the specific implementation process, the first-order approaching sliding mode controller function constructed based on the lateral deviation and the heading deviation is: .

[0070] wherein, is a sliding surface, ; is the lateral deviation; is the heading deviation; is a weight coefficient for balancing the relative importance of the lateral deviation and the heading deviation in the sliding surface, and therefore, the value can be the same as the value of in the above embodiment. is a switching gain for controlling the strength of the sliding mode control. is a sign function for realizing switching control of the sliding surface.

[0071] The Lyapunov constraint function is: ; The stable condition function is ; wherein, is the derivative of the Lyapunov function. μ is a positive constant to ensure that the system state converges to the sliding surface in a finite time.

[0072] The calculation method of the derivative of the Lyapunov constraint function is: . Wherein, is the rate of change of the sliding surface, which is determined by the system dynamics and the control input.

[0073] The derivative of the Lyapunov constraint function obtained by calculation is substituted into the sliding mode controller function: . and are the rate of change of the lateral deviation and the rate of change of the heading deviation, respectively.

[0074] By configuring appropriate switching gain and weight coefficient, so that , thereby obtaining specific values of switching gain and weight coefficient. Substituting switching gain and weight coefficient into the above first-order approaching sliding mode controller function, the second steering angle is obtained.

[0075] The embodiment of the application can make the vehicle quickly approach the expected sliding film surface in the deviation state by constructing the first-order sliding mode controller function based on the lateral deviation and the heading deviation, that is, the vehicle can quickly adjust to the ideal state close to the crop row center line, thereby reducing the time of deviating from the center line of the vehicle in the automatic alignment process and improving the efficiency of automatic alignment.

[0076] On the basis of the above embodiment, the vehicle is provided with an alignment device, and the alignment device comprises a guide touch rod. The method further comprises: obtaining the maximum included angle of the guide touch rod; wherein the maximum included angle is an included angle formed by the guide touch rod and the crops when the vehicle is in contact with the crops during the driving in the farmland; determining the lateral deviation according to the maximum included angle and the length of the guide touch rod.

[0077] In the specific implementation process, Figure 5 a guide touch rod schematic diagram provided by the embodiment of the application is shown in Figure 5 . The guide touch rod is a mechanical device installed on the vehicle, which is usually located at the front end or side of the vehicle. When the vehicle drives in the farmland, the guide touch rod is in contact with the crops, and the relative position between the vehicle and the crop row is sensed through the deflection angle of the touch rod.

[0078] During the driving of the vehicle, if the guide touch rod is in contact with the crops, as the vehicle continues to drive forward, the included angle between the guide touch rod and the horizontal line will become larger and larger until the guide touch rod is no longer in contact with the crops, at which time the guide touch rod returns to the initial state under the action of the elastic reset structure. Moreover, if the vehicle is always deviated from the center line of the crop row during the driving, the guide touch rod will periodically appear the maximum included angle. Therefore, the maximum included angle refers to the maximum included angle formed by the guide touch rod and the crops during the driving of the vehicle. The included angle reflects the degree of lateral deviation between the vehicle and the crop row.

[0079] The deflection angle of the touch rod is measured in real time by the boundary detection sensor connected with the guide touch rod. The maximum deflection angle of the guide touch rod during the driving of the vehicle is recorded .

[0080] When the guide touch rod is in contact with the crops, there is a geometric relationship between the deflection angle θ of the touch rod and the lateral deviation .

[0081] When the deflection angle of the touch rod reaches the maximum value , the lateral deviation It also reached its maximum value.

[0082] Length of guide rod It is known and is usually determined during vehicle design. Lateral deviation. The maximum included angle of the guide rod can be used and contact rod length The calculation yielded the result.

[0083] The formula for calculating lateral deviation is: .

[0084] Figure 6 This application provides a schematic diagram for calculating the included angle of a guide rod, as shown in the embodiment. Figure 6 As shown. The included angle of the guide rod can also be obtained through calculation. After the device is installed, its longitudinal axis forms a preset angle with respect to the horizontal line. The included angle θ is based on the length of the device's guide rod. Its horizontal projection distance The formula is derived as follows: .

[0085] In this embodiment, the lateral deviation is determined by the maximum included angle of the guide rod and the length of the guide rod, providing a data basis for subsequent calculation of the target steering angle.

[0086] Based on the above embodiments, the method further includes: Obtain the change in lateral deviation of the vehicle and the distance the vehicle travels over a period of time; The heading deviation is determined based on the change in lateral deviation and the travel distance.

[0087] In the specific implementation process Figure 7 A schematic diagram for calculating heading deviation is provided as an embodiment of this application, such as... Figure 7 As shown in the diagram, A and B are two crops. Ideally, the vehicle should travel along the straight line formed by A and B. However, in reality, the vehicle has lateral and directional deviations. The straight line OP represents the vehicle's direction of travel, and its speed is V. This represents the lateral deviation of the vehicle at point A on the crop. This represents the lateral deviation of the vehicle at point B on the crop.

[0088] heading deviation The calculation formula is: .

[0089] The embodiments of this application determine the heading deviation by measuring the change in lateral deviation and the travel distance, providing a data basis for subsequent calculation of the target steering angle.

[0090] On the basis of the above-mentioned embodiments, a positioning module and a rowing device are arranged on the vehicle, the rowing device includes a guide touch rod; the method further comprises: obtaining the positioning module position information collected by the positioning module; calculating the guide touch rod position information according to the positioning module position information and the positional relationship between the positioning module and the guide touch rod; determining the navigation line of the crops according to the guide touch rod position information and the included angle of the guide touch rod corresponding to multiple time points respectively; determining the lateral deviation and the heading deviation according to the navigation line and the position information of the vehicle.

[0091] In the specific implementation process, the positioning module is usually installed on the vehicle for obtaining the positioning module position information. It should be noted that the positioning module can be a GNSS (Global Navigation Satellite System) receiver, and high-precision positioning can be achieved by combining with the RTK (Real-Time Kinematic) technology. In the embodiments of the present application, the implementation is for the case where the signal strength of the positioning module is strong. Since the application scenario of the present application requires a finer granularity of position, and the installation positions of the positioning module and the guide touch rod on the vehicle are fixed, the relative positional relationship between the positioning module and the guide touch rod is known. Through the position information of the positioning module and the relative positional relationship between the two, the actual position of the guide touch rod in the farmland, i.e. the guide touch rod position information, is calculated. This can be achieved by coordinate transformation, i.e. converting the coordinate system of the positioning module to the coordinate system of the guide touch rod. It should be noted that if the positioning module and the guide touch rod are arranged next to each other, the positioning module position information obtained by the positioning module can be used as the guide touch rod position information.

[0092] When the guide touch rod contacts the crops, a certain included angle is formed, which reflects the relative positional relationship between the vehicle and the crop row. The included angle of the guide touch rod is measured in real time by the boundary detection sensor.

[0093] The guide touch rod position information and the included angle information at multiple time points are collected. According to these information, the navigation line of the crops is determined by using curve fitting or other algorithms. The navigation line represents the ideal path of the crop row, and the header on the vehicle should try to keep driving on this path.

[0094] The vertical distance from the current position of the vehicle to the navigation line is calculated, which is the lateral deviation. It can be determined by geometric calculation or projection method. The included angle difference between the current heading angle of the vehicle and the direction of the navigation line is calculated, which is the heading deviation. The current heading angle can be obtained by the attitude sensor (such as IMU) of the vehicle, and then compared with the direction of the navigation line.

[0095] The embodiments of the present application combine the positioning information collected by the positioning module and the included angle of the guiding lever to calculate the ideal navigation line of the crops, and then determine the lateral deviation and the heading deviation according to the ideal navigation line and the position information of the vehicle, thereby improving the calculation accuracy of the lateral deviation and the heading deviation.

[0096] On the basis of the above-mentioned embodiments, before determining the first steering angle based on the lateral deviation and the heading deviation by using the adaptive feedback mechanism, the method further comprises: generating an error dynamic model according to the lateral deviation, the heading deviation, the driving speed of the vehicle and the wheelbase of the vehicle; The error dynamic model is ; wherein, is the lateral deviation; is the heading deviation; is the driving speed; is the wheelbase of the vehicle; is the target steering angle.

[0097] In the specific implementation process, before calculating the target steering angle, an error dynamic model can be generated according to the lateral deviation, the heading deviation, the driving speed of the vehicle and the wheelbase of the vehicle; the error dynamic model can more accurately describe the dynamic changes of the lateral deviation and the heading deviation in the driving process of the vehicle, and provide a more accurate mathematical basis for the subsequent control strategy design. Moreover, by including the driving speed and the wheelbase of the vehicle in the model, the control system can better adapt to the deviation changes under different vehicle parameters and driving states, and improve the accuracy and stability of the automatic driving.

[0098] The change rate of the lateral deviation is related to the driving speed V of the vehicle and the heading deviation, and the specific relationship is: .

[0099] This is because the change of the lateral deviation depends on the lateral deviation caused by the heading deviation when the vehicle is driving at the speed V.

[0100] The change rate of the heading deviation is related to the target steering angle of the vehicle, the driving speed and the wheelbase of the vehicle, and the specific relationship is: . The target steering angle will affect the turning rate of the vehicle, thereby changing the heading deviation.

[0101] The lateral deviation change rate and the heading deviation change rate are combined into an error dynamic model, which is specifically: ; This model describes the relationship between the lateral deviation and the heading deviation over time, and considers the influence of the driving speed and the wheelbase of the vehicle on the deviation.

[0102] In the embodiments of the present application, the error dynamic model can accurately describe the change trend of the lateral deviation and the heading deviation in the vehicle driving process, and provide more accurate deviation dynamic information for subsequent adaptive feedback control; and the model considers the vehicle driving speed and the wheelbase and other parameters, and can adapt to the automatic alignment requirements under different vehicle types and driving speeds.

[0103] Figure 8 The automatic alignment method provided in the embodiments of the present application is shown in a schematic diagram as Figure 8 The tracking control strategy of the alignment system adopts a method of combining a sliding mode control with an adaptive feedback control. The lateral deviation and the heading deviation of the vehicle relative to the crop row are obtained by the alignment device in real time, and are fed back to the alignment controller. The alignment controller dynamically calculates an expected steering angle as a target steering angle based on the current lateral deviation, the heading deviation and the vehicle driving speed.

[0104] The target steering angle is used to drive the electric steering wheel system to adjust the actual steering angle of the vehicle wheel, so that the vehicle rotates towards the target direction, thereby realizing accurate tracking of the crop row. During the adjustment process, the sign (positive / negative) of the control quantity determines the rotation direction of the electric steering wheel, i.e., whether the vehicle should turn left or right; and the magnitude of the control quantity corresponds to the rotation speed of the electric steering wheel, thereby reflecting the amplitude and response speed of the steering adjustment.

[0105] The sliding mode controller has strong robustness and fast response capability by introducing a switching control law and a sliding mode surface design, and can stably realize the vehicle alignment tracking control in the presence of parameter disturbances or nonlinear disturbances.

[0106] The specific algorithm flow is as follows: In the first step, based on the lateral deviation and the directional deviation information detected by the alignment device, a corresponding mathematical error model is established in combination with a vehicle kinematic model, and an error dynamic expression of the kinematic parameters in the state space is further derived.

[0107] .

[0108] wherein, is the lateral deviation; is the heading deviation; is the driving speed; is the wheelbase of the vehicle; is the target steering angle, i.e., the target control angle.

[0109] In the second step, an adaptive feedback control law is constructed, the feedback gain is estimated, and the coefficient equation is constructed. .

[0110] Adaptive coefficients in feedback gain are estimated in real time using recursive least square method with forgetting factor , , , Optimization of feedback gain is performed by defining gradient descent cost function to minimize control error and improve response speed.

[0111] Third step, construct a first-order approaching sliding mode controller where weight coefficient of directional deviation is dynamically adjusted by adaptive feedback mechanism, and sliding mode control algorithm with finite time convergence characteristics is designed to enhance the robustness of the system to external disturbance by constructing Lyapunov function according to Lyapunov index stability condition .

[0112] Fourth step, combine sliding mode control with adaptive feedback control to further significantly improve the adaptability and control stability of automatic alignment controller in complex field environment.

[0113] The automatic alignment method proposed in the embodiments of the present application realizes high-precision, intelligent and dynamic response alignment control of agricultural operation vehicles along crop rows by integrating high-precision alignment devices, algorithms based on sliding mode control combined with adaptive feedback control, electric steering actuators and navigation auxiliary units. Therefore, the method has significant technical effects in many aspects: (1) Improve alignment precision and reduce crop damage The system can detect the lateral and heading deviation between the vehicle and the crop row in real time, and quickly respond to adjust the vehicle direction through the controller.

[0114] Field tests show that the maximum deviation can be controlled within ±10 cm, meeting the operation requirements of precision agriculture, especially for densely planted crops such as corn and cotton.

[0115] Reduce the problems of seedling compression, missed planting and missed harvesting caused by deviation, and effectively improve the yield of crops per unit area.

[0116] (2) High degree of operation automation, reducing manual intervention The vehicle can automatically complete the alignment operation without manual intervention, significantly reducing the operation intensity and fatigue level of the driver.

[0117] Supports operation at night and in low-visibility conditions to meet the actual needs of users for "harvesting".

[0118] (3) Intelligent control strategy, soft and efficient adjustment process​ The control input determines the steering direction based on the direction of the deviation (positive / negative), and adjusts the control input based on the deviation magnitude and speed to achieve proportional adaptive steering.

[0119] Avoid "snake-like" routes or frequent excessive adjustments to improve the smoothness of the work route.

[0120] (4) Modular design, strong compatibility, and easy to promote The system has a simple structure and can be adapted to various types of harvesters.

[0121] The system has controllable costs and high cost-effectiveness.

[0122] Figure 9 This is a schematic diagram of an automatic alignment device provided in an embodiment of this application. The device can be a module, program segment, or code on an electronic device. It should be understood that this device is similar to the one described above. Figure 3 The method implementation corresponds to this and can be executed. Figure 3 The specific functions of the device involved in the various steps of the method embodiment can be found in the description above; to avoid repetition, detailed descriptions are omitted here. The device includes: a deviation acquisition module 901, a first steering angle determination module 902, a second steering angle determination module 903, a target steering angle determination module 904, and a control module 905, wherein: The deviation acquisition module 901 is used to acquire the lateral deviation and heading deviation of the vehicle in the farmland; wherein, the lateral deviation refers to the vertical distance of a specific reference point on the vehicle to the center line of the crop row; the heading deviation refers to the angle difference between the current heading angle of the vehicle and the center line of the crop row. The first steering angle determination module 902 is used to determine the first steering angle based on lateral deviation and heading deviation using an adaptive feedback mechanism. The second steering angle determination module 903 is used to construct a sliding mode controller function based on lateral deviation and heading deviation, and to calculate the second steering angle through the sliding mode controller function; The target steering angle determination module 904 is used to determine the target steering angle based on the first steering angle and the second steering angle; The control module 905 is used to control the vehicle's movement by the target steering angle to achieve automatic alignment.

[0123] Based on the above embodiments, the first steering angle determination module 902 is specifically used for: An adaptive feedback control law function is generated based on the lateral deviation and the heading deviation; the adaptive feedback control law function includes a lateral gain and a heading gain, which are obtained by optimization using a gradient descent cost function.

[0124] Based on the above embodiments, the adaptive feedback control law function is: ; The gradient descent cost function is ; wherein, is the first steering angle; is the optimization target cost; ; is the lateral deviation; is the heading deviation; , , , is an adaptive coefficient, , , , the value of is obtained according to a recursive least square fitting with a forgetting factor; is the lateral gain; is the heading gain; is a weight coefficient.

[0125] On the basis of the above embodiment, the second steering angle determination module 903 is specifically configured to: construct a first-order approaching sliding mode controller function based on the lateral deviation and the heading deviation; generate a Lyapunov constraint function and a stable condition function according to the lateral deviation and the heading deviation; obtain the second steering angle by solving the first-order approaching sliding mode controller function through the Lyapunov constraint function and the stable condition function.

[0126] On the basis of the above embodiment, the first-order approaching sliding mode controller function is ; the Lyapunov constraint function is ; the stable condition function is ; wherein, ; is the lateral deviation; is the heading deviation; is a weight coefficient; is a switching gain.

[0127] On the basis of the above embodiment, a row-following device is arranged on the vehicle, and the row-following device includes a guide touch rod; the device further includes a lateral deviation calculation module configured to: obtain a maximum included angle of the guide touch rod; wherein the maximum included angle is an included angle formed by the guide touch rod and crops when the vehicle is driving in a farmland; determine the lateral deviation according to the maximum included angle and a length of the guide touch rod.

[0128] Based on the above embodiments, the vehicle is equipped with a positioning module and a alignment device, the alignment device including a guide rod; the device also includes a deviation calculation module, used for: Obtain the location information of the positioning module collected by the positioning module; The position information of the guide contact rod is calculated based on the position information of the positioning module and the positional relationship between the positioning module and the guide contact rod. The navigation line for crops is determined based on the position information of the guide rods at multiple time points and the included angle of the guide rods. The lateral deviation and heading deviation are determined based on the navigation line and the vehicle's position information.

[0129] Based on the above embodiments, the device further includes a heading deviation calculation module, used for: The change in lateral deviation of the vehicle and the distance traveled by the vehicle within a time period are obtained. The heading deviation is determined based on the change in lateral deviation and the travel distance.

[0130] Based on the above embodiments, the device further includes an error dynamic model generation module, used for: A dynamic error model is generated based on the lateral deviation, the heading deviation, the vehicle's speed, and the vehicle's wheelbase. The error dynamic model is as follows: ; in, The lateral deviation; The heading deviation is mentioned above; The driving speed; The wheelbase of the vehicle; The target steering angle is [value].

[0131] Figure 10 This is a schematic diagram of the physical structure of the row controller provided in the embodiments of this application, such as... Figure 10 As shown, the electronic device includes: a processor 1001, a memory 1002, and a bus 1003; wherein: The processor 1001 and the memory 1002 communicate with each other through the bus 1003; The processor 1001 is configured to invoke program instructions in the memory 1002 to perform the method provided by each of the above method embodiments, for example, including: obtaining a lateral deviation and a heading deviation of the vehicle in the farmland; wherein the lateral deviation refers to the vertical distance of a specific reference point on the vehicle from the center line of the crop row; the heading deviation refers to the included angle difference between the current heading angle of the vehicle and the center line of the crop row; determining a first steering angle based on the lateral deviation and the heading deviation by using an adaptive feedback mechanism; constructing a sliding mode controller function based on the lateral deviation and the heading deviation, and calculating a second steering angle through the sliding mode controller function; determining a target steering angle according to the first steering angle and the second steering angle; and controlling the vehicle to travel through the target steering angle, so as to realize automatic alignment.

[0132] The processor 1001 can be an integrated circuit chip with signal processing capability. The processor 1001 can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; or can be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic device, a discrete gate or transistor logic device, a discrete hardware component. It can implement or execute the various methods, steps and logic block diagrams disclosed in the embodiments of the present application. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor.

[0133] The memory 1002 can include, but is not limited to, a random access memory (RAM), a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), etc.

[0134] The embodiment discloses a computer program product, the computer program product comprises a computer program stored on a non-transitory computer readable storage medium, the computer program comprises program instructions, when the program instructions are executed by a computer, the computer can execute the method provided by each method embodiment described above, for example, comprising: obtaining a lateral deviation and a heading deviation of a vehicle in a farmland; wherein the lateral deviation refers to the vertical distance of a specific reference point on the vehicle from the center line of a crop row; the heading deviation refers to the included angle difference between the current heading angle of the vehicle and the center line of the crop row; determining a first steering angle based on the lateral deviation and the heading deviation by using an adaptive feedback mechanism; constructing a sliding mode controller function based on the lateral deviation and the heading deviation, and obtaining a second steering angle by calculating the sliding mode controller function; determining a target steering angle according to the first steering angle and the second steering angle; and controlling the vehicle to travel through the target steering angle, so as to realize automatic alignment.

[0135] The embodiment provides a non-transitory computer readable storage medium, the non-transitory computer readable storage medium stores computer instructions, the computer instructions enable the computer to execute the method provided by each method embodiment described above, for example, comprising: obtaining a lateral deviation and a heading deviation of a vehicle in a farmland; wherein the lateral deviation refers to the vertical distance of a specific reference point on the vehicle from the center line of a crop row; the heading deviation refers to the included angle difference between the current heading angle of the vehicle and the center line of the crop row; determining a first steering angle based on the lateral deviation and the heading deviation by using an adaptive feedback mechanism; constructing a sliding mode controller function based on the lateral deviation and the heading deviation, and obtaining a second steering angle by calculating the sliding mode controller function; determining a target steering angle according to the first steering angle and the second steering angle; and controlling the vehicle to travel through the target steering angle, so as to realize automatic alignment.

[0136] In the embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other manners. The above described device embodiments are only schematic. For example, the division of the units is only a logical function division. There can be another division manner for the actual implementation, for example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the displayed or discussed mutual couplings or direct couplings or communication connections between the units can be indirect couplings or communication connections through some interfaces, devices or units, and can be electrical, mechanical or other forms.

[0137] In addition, the units described as separate components can or can not be physically separate, and the components displayed as units can or can not be physical units, that is, they can be located in one place, or can be distributed on multiple network units. Some or all of the units can be selected according to actual needs to achieve the purposes of the embodiments.

[0138] Further, each functional module in each embodiment of the present application can be integrated together to form an independent part, or each module can exist independently, or two or more modules can be integrated to form an independent part.

[0139] In this document, relational terms such as first and second and the like can be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions.

[0140] The above description is merely illustrative of the application, and not in limitation of the principles of the application. Various modifications and changes can be made by those of ordinary skill in the art which fall within the spirit and scope of the application without departing from the spirit and scope of the application. Any modification, equivalent replacement, improvement, etc. made within the spirit and principles of the application should be included in the protection scope of the application.

Claims

1. A method of automatically aligning a row, characterized by, The method comprises: acquiring a lateral deviation and a heading deviation of the vehicle in the farmland; wherein the lateral deviation refers to a vertical distance of a specific reference point on the vehicle from a center line of a crop row; and the heading deviation refers to an included angle difference between a current heading angle of the vehicle and the center line of the crop row; determining a first steering angle by using an adaptive feedback mechanism based on the lateral deviation and the heading deviation; constructing a sliding mode controller function based on the lateral deviation and the heading deviation, and calculating a second steering angle by using the sliding mode controller function; determining a target steering angle according to the first steering angle and the second steering angle; and controlling the vehicle to travel by using the target steering angle, so as to realize automatic alignment with the crop row.

2. The method of claim 1, wherein, The method of determining the first steering angle by using the adaptive feedback mechanism based on the lateral deviation and the heading deviation comprises: generating an adaptive feedback control rate function according to the lateral deviation and the heading deviation; the adaptive feedback control rate function comprises a lateral gain and a heading gain, and the lateral gain and the heading gain are obtained by optimizing a gradient descent cost function.

3. The method of claim 2, wherein, The adaptive feedback control rate function is ; The gradient descent cost function is ; wherein, is the first steering angle; is the optimization target cost; ; is the lateral deviation; is the heading deviation; is an adaptive coefficient, the values of are obtained according to a recursive least square method with a forgetting factor; is the lateral gain; is the heading gain; is a weight coefficient.​​​​​​ 4. The method of claim 1, wherein, The method of constructing the sliding mode controller function based on the lateral deviation and the heading deviation, and calculating the second steering angle by using the sliding mode controller function comprises: constructing a first-order approaching sliding mode controller function based on the lateral deviation and the heading deviation; generating a Lyapunov constraint function and a stability condition function according to the lateral deviation and the heading deviation; solving the first-order approaching sliding mode controller function by using the Lyapunov constraint function and the stability condition function, to obtain the second steering angle.

5. The method of claim 4, wherein, The first order approaching sliding mode controller function is ; The Lyapunov constraint function is ; The stable condition function is ; wherein, ; is the lateral deviation; is the heading deviation; is a weight coefficient; is a switching gain.

6. The method of claim 1, wherein, The vehicle is provided with an alignment device, and the alignment device comprises a guide touch rod; the method further comprises: acquiring a maximum included angle of the guide touch rod; wherein the maximum included angle is an included angle formed by the guide touch rod and crops during the travel of the vehicle in the farmland; determining the lateral deviation according to the maximum included angle and a length of the guide touch rod.

7. The method of claim 6, wherein, The method further comprises: acquiring a lateral deviation change amount of the vehicle in a time period and a travel distance of the vehicle; determining the heading deviation based on the lateral deviation change amount and the travel distance.

8. The method of claim 1, wherein, The vehicle is provided with a positioning module and an alignment device, and the alignment device comprises a guide touch rod; a signal strength of the positioning module is greater than a preset threshold; the method further comprises: acquiring positioning module position information collected by the positioning module; calculating guide touch rod position information according to the positioning module position information and a positional relationship between the positioning module and the guide touch rod; determining a navigation line of crops according to the guide touch rod position information and the included angle of the guide touch rod at a plurality of time points respectively; determining the lateral deviation and the heading deviation according to the navigation line and position information of the vehicle.

9. The method according to any one of claims 1 to 8, characterized in that, Before determining the first steering angle by using the adaptive feedback mechanism based on the lateral deviation and the heading deviation, the method further comprises: generating an error dynamic model according to the lateral deviation, the heading deviation, a travel speed of the vehicle, and a wheelbase of the vehicle. The error dynamic model is ; wherein, is the lateral deviation; is the heading deviation; is the travel speed; is the vehicle wheelbase; is the target steering angle.

10. An automatic aligning device characterized by comprising: The method comprises: The bias acquisition module is configured to acquire a lateral bias and a heading bias of the vehicle in the farmland, wherein the lateral bias refers to a vertical distance of a specific reference point on the vehicle from a center line of a crop row, and the heading bias refers to an included angle difference between a current heading angle of the vehicle and the center line of the crop row. The first steering angle determination module is configured to determine a first steering angle based on the lateral bias and the heading bias by using an adaptive feedback mechanism. The second steering angle determination module is configured to construct a sliding mode controller function based on the lateral bias and the heading bias, and to obtain a second steering angle by calculation based on the sliding mode controller function. The target steering angle determination module is configured to determine a target steering angle based on the first steering angle and the second steering angle. The control module is configured to control the vehicle to travel by using the target steering angle, so as to realize automatic alignment with the crop row.

11. A non-transitory computer-readable storage medium, comprising: The non-transitory computer readable storage medium stores computer instructions, and the computer instructions, when executed by a computer, cause the computer to perform the method according to any one of claims 1-9.

12. A computer program product, characterised in that, The computer program instructions, when read and executed by a processor, perform the method according to any one of claims 1-9.

13. An automatic alignment system characterized by, The alignment device is arranged on the vehicle. The alignment device comprises a guide touch rod, a boundary detection sensor and an elastic reset structure. The guide touch rod is connected with the boundary detection sensor and the elastic reset structure, respectively. The guide touch rod generates an angular displacement by contacting the crops, and the angular displacement is measured by the boundary detection sensor. The boundary detection sensor is connected with the alignment controller on the vehicle, and sends the angular displacement to the alignment controller. The elastic reset structure is configured to provide a restoring force to the guide touch rod after the guide touch rod leaves the crops.

14. The system of claim 13, wherein, The alignment controller is configured to perform the method according to any one of claims 1-8. The system further comprises an electric steering wheel. The alignment controller sends a control instruction to the electric steering wheel according to the target steering angle obtained by calculation, so as to control the vehicle to travel.

Images