Automatic inspection control method of agricultural inspection robot

Abstract

The invention discloses an automatic inspection control method for an agricultural inspection robot, and relates to the technical field of inspection control, and the method comprises the following steps: S1, collecting the real-time position and real-time state data of the agricultural inspection robot at the current moment; s2, determining a predicted trajectory of the agricultural inspection robot at the next moment; s3, track adjustment is conducted on the agricultural inspection robot, and inspection control is completed. According to the invention, the agricultural inspection robot stably travels along the planned trajectory; and meanwhile, the accuracy and stability of trajectory tracking of the agricultural inspection robot are improved.

Description

Technical Field

[0001] The invention relates to the field of patrol inspection control technology, and in particular to an automatic patrol inspection control method of an agricultural patrol inspection robot. Background Art

[0002] Traditional agricultural inspections mainly rely on manual labor, which is not only time-consuming and labor-intensive, but also limited in efficiency and accuracy by subjective factors and physical condition of people. With the development of intelligent technology, agricultural inspection robots are gradually applied to agricultural environments such as farmland and greenhouses to achieve real-time monitoring and early warning of crop growth environment, pest and disease conditions, etc. However, existing agricultural inspection robots still have shortcomings in automatic inspection control. When agricultural robots are working in the field, trajectory tracking control becomes a major challenge due to factors such as complex terrain and uneven crop distribution. Therefore, it is of great significance to develop a method that can accurately and stably track and control the trajectory of agricultural inspection robots. Summary of the invention

[0003] In order to solve the above problems, the present invention proposes an automatic inspection control method of an agricultural inspection robot.

[0004] The technical solution of the present invention is: an automatic inspection control method of an agricultural inspection robot comprises the following steps:

[0005] S1, collect the real-time position and real-time status data of the agricultural inspection robot at the current moment;

[0006] S2. Determine the predicted trajectory of the agricultural inspection robot at the next moment based on the real-time position and real-time status data at the current moment;

[0007] S3. According to the predicted trajectory and ideal position of the agricultural inspection robot at the next moment, the trajectory of the agricultural inspection robot is adjusted to complete the inspection control.

[0008] Furthermore, in S1, the real-time status data of the agricultural inspection robot includes the peak power of the motor of the driving wheel and the moment of inertia of the driven wheel.

[0009] Furthermore, S2 includes the following sub-steps:

[0010] S21, generating a driving state coefficient for the left rear driving wheel according to the peak power of the motor of the left rear driving wheel, and generating a driving state coefficient for the right rear driving wheel according to the peak power of the motor of the right rear driving wheel;

[0011] S22, constructing a rear wheel driving state matrix according to the driving state coefficient of the left rear driving wheel and the driving state coefficient of the right rear driving wheel;

[0012] S23, inputting the rear wheel drive state matrix, the rotational inertia of the left front driven wheel, and the rotational inertia of the right front driven wheel into the support regression model to obtain the front wheel driven state coefficient;

[0013] S24. Determine the predicted trajectory of the agricultural inspection robot at the next moment according to the real-time position of the agricultural inspection robot at the current moment, the rear wheel driving state matrix and the front wheel driven state coefficient.

[0014] The beneficial effect of the above further scheme is: in the present invention, taking into account factors such as complex farmland terrain and uneven crop distribution, the agricultural inspection robot generally adopts a four-wheel crawler structure, in which the rear wheel is the main driving wheel, the front wheel is the driven wheel, and the driving wheel is driven by two motors. Due to the different motor speeds, a differential is generated, thereby realizing the steering function. The four wheels of the agricultural inspection robot are named the left front driven wheel, the right front driven wheel, the left rear driving wheel and the right rear driving wheel. According to the motor conditions of the two driving wheels, the state matrix of the rear wheel is determined. The state matrix of the rear wheel has an impact on the trajectory of the front wheel. Therefore, the state matrix of the rear wheel is combined with the rotational inertia of the front wheel to determine the state coefficient of the front wheel. The state matrix and state coefficient of the front and rear wheels are used to determine the predicted trajectory at the next moment. The prediction is accurate and simulates the close driven relationship between the front and rear wheels.

[0015] Furthermore, in S21, the driving state coefficient d of the left rear driving wheel L The calculation formula is:

[0016] ;

[0017] Where P vlaue_L Represents the peak power of the motor of the left rear drive wheel, η L represents the transmission efficiency of the left rear drive wheel, m represents the mass of the agricultural inspection robot, g represents the acceleration of gravity, β represents the slope of the terrain where the agricultural inspection robot is located at the current moment, and T L Represents the motor torque of the left rear drive wheel, n L Indicates the motor speed of the left rear drive wheel;

[0018] In S21, the right rear drive wheel generates a driving state coefficient d R The calculation formula is:

[0019] ;

[0020] Where P vlaue_R Represents the peak power of the motor of the right rear drive wheel, η R Indicates the transmission efficiency of the right rear drive wheel, T R Represents the motor torque of the right rear drive wheel, n R Indicates the motor speed of the right rear drive wheel.

[0021] Further, in S22, the expression of the rear wheel drive state matrix D is:

[0022] ;

[0023] Where, d L Indicates the driving state coefficient generated by the left rear driving wheel, d R It represents the driving state coefficient generated by the right rear driving wheel, and I represents the unit matrix.

[0024] Furthermore, in S23, the expression supporting the regression model Q is:

[0025] ;

[0026] In the formula, u L represents the moment of inertia of the left front driven wheel, u R represents the moment of inertia of the right front driven wheel, γ represents the penalty factor, D represents the rear wheel drive state matrix, ||·|| represents the F-norm operation, σ represents the bandwidth parameter of the Gaussian kernel, and exp(·) represents the exponential function.

[0027] Further, S24 includes the following sub-steps:

[0028] S241, performing mean operation on the value of the rear wheel driving state matrix and the front wheel driven state coefficient to obtain a four-wheel adjustment threshold;

[0029] S242. Determine the predicted trajectory of the agricultural inspection robot at the next moment according to the real-time position of the agricultural inspection robot at the current moment and the four-wheel adjustment threshold.

[0030] The beneficial effect of the above further scheme is: in the present invention, the state characteristic parameters of the front and rear wheels are used to predict the trajectory at the next moment, and the movement state of the four wheels of the agricultural inspection robot as a whole is fully considered, and the prediction is accurate.

[0031] Furthermore, in S242, the expression of the predicted trajectory (x1, y1) of the agricultural inspection robot at the next moment is:

[0032] ;

[0033] Where x1 represents the horizontal coordinate of the predicted trajectory at the next moment, y1 represents the vertical coordinate of the predicted trajectory at the next moment, x0 represents the horizontal coordinate of the real-time position of the agricultural inspection robot, y0 represents the vertical coordinate of the real-time position of the agricultural inspection robot, and ω represents the four-wheel adjustment threshold.

[0034] Furthermore, in S3, a PID controller is used to adjust the trajectory of the agricultural inspection robot.

[0035] The beneficial effect of the above further scheme is: in the present invention, in trajectory tracking, the PID control algorithm corresponding to the PID controller can adjust the vehicle's steering angle, acceleration and other parameters according to the deviation between the predicted trajectory of the tire and the ideal trajectory, so that the tire gradually approaches the ideal trajectory.

[0036] The beneficial effects of the present invention are as follows: the automatic inspection control method of the agricultural inspection robot of the present invention fully considers the coordination and driving mode between the robot tires, constructs the driven state coefficient and the driving state matrix for the front and rear wheels respectively, and predicts the trajectory at the next moment through the state parameters, so as to make corrections when the predicted trajectory deviates from the ideal position, and obtain a reference trajectory that is more suitable for the current working environment, so that the agricultural inspection robot can travel stably along the planned trajectory; at the same time, the accuracy and stability of the trajectory tracking of the agricultural inspection robot are improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] Figure 1 The present invention is a flow chart of the automatic inspection control method of the agricultural inspection robot. DETAILED DESCRIPTION

[0038] The embodiments of the present invention are further described below in conjunction with the accompanying drawings.

[0039] like Figure 1 As shown, the present invention provides an automatic inspection control method of an agricultural inspection robot, comprising the following steps:

[0040] S1, collect the real-time position and real-time status data of the agricultural inspection robot at the current moment;

[0041] S2. Determine the predicted trajectory of the agricultural inspection robot at the next moment based on the real-time position and real-time status data at the current moment;

[0042] S3. According to the predicted trajectory and ideal position of the agricultural inspection robot at the next moment, the trajectory of the agricultural inspection robot is adjusted to complete the inspection control.

[0043] In the embodiment of the present invention, in S1, the real-time status data of the agricultural inspection robot includes the peak power of the motor of the driving wheel and the moment of inertia of the driven wheel.

[0044] In this embodiment of the present invention, S2 includes the following sub-steps:

[0045] S21, generating a driving state coefficient for the left rear driving wheel according to the peak power of the motor of the left rear driving wheel, and generating a driving state coefficient for the right rear driving wheel according to the peak power of the motor of the right rear driving wheel;

[0046] S22, constructing a rear wheel driving state matrix according to the driving state coefficient of the left rear driving wheel and the driving state coefficient of the right rear driving wheel;

[0047] S23, inputting the rear wheel drive state matrix, the rotational inertia of the left front driven wheel, and the rotational inertia of the right front driven wheel into the support regression model to obtain the front wheel driven state coefficient;

[0048] S24. Determine the predicted trajectory of the agricultural inspection robot at the next moment according to the real-time position of the agricultural inspection robot at the current moment, the rear wheel driving state matrix and the front wheel driven state coefficient.

[0049] In the present invention, considering the complex farmland terrain and uneven crop distribution, the agricultural inspection robot generally adopts a four-wheel crawler structure, in which the rear wheel is the main driving wheel, the front wheel is the driven wheel, and the driving wheel is driven by two motors. Due to the different motor speeds, a differential is generated to achieve a steering function. The four wheels of the agricultural inspection robot are named the left front driven wheel, the right front driven wheel, the left rear driving wheel, and the right rear driving wheel. According to the motor conditions of the two driving wheels, the state matrix of the rear wheel is determined. The state matrix of the rear wheel has an impact on the trajectory of the front wheel. Therefore, the state matrix of the rear wheel is combined with the rotational inertia of the front wheel to determine the state coefficient of the front wheel. The state matrix and state coefficient of the front and rear wheels are used to determine the predicted trajectory of the next moment. The prediction is accurate, simulating the close driven relationship between the front and rear wheels.

[0050] In the embodiment of the present invention, in S21, the driving state coefficient d of the left rear driving wheel is L The calculation formula is:

[0051] ;

[0052] Where P vlaue_L Represents the peak power of the motor of the left rear drive wheel, η L represents the transmission efficiency of the left rear drive wheel, m represents the mass of the agricultural inspection robot, g represents the acceleration of gravity, β represents the slope of the terrain where the agricultural inspection robot is located at the current moment, and T L Represents the motor torque of the left rear drive wheel, n L Indicates the motor speed of the left rear drive wheel;

[0053] In S21, the right rear drive wheel generates a driving state coefficient d R The calculation formula is:

[0054] ;

[0055] Where P vlaue_R Represents the peak power of the motor of the right rear drive wheel, η R Indicates the transmission efficiency of the right rear drive wheel, T R Represents the motor torque of the right rear drive wheel, n R Indicates the motor speed of the right rear drive wheel.

[0056] In the embodiment of the present invention, in S22, the expression of the rear wheel drive state matrix D is:

[0057] ;

[0058] Where, d L Indicates the driving state coefficient generated by the left rear driving wheel, d R It represents the driving state coefficient generated by the right rear driving wheel, and I represents the unit matrix.

[0059] In the embodiment of the present invention, in S23, the expression supporting the regression model Q is:

[0060] ;

[0061] In the formula, u L represents the moment of inertia of the left front driven wheel, u R represents the moment of inertia of the right front driven wheel, γ represents the penalty factor, D represents the rear wheel drive state matrix, ||·|| represents the F-norm operation, σ represents the bandwidth parameter of the Gaussian kernel, and exp(·) represents the exponential function.

[0062] In this embodiment of the present invention, S24 includes the following sub-steps:

[0063] S241, performing mean operation on the value of the rear wheel driving state matrix and the front wheel driven state coefficient to obtain a four-wheel adjustment threshold;

[0064] S242. Determine the predicted trajectory of the agricultural inspection robot at the next moment according to the real-time position of the agricultural inspection robot at the current moment and the four-wheel adjustment threshold.

[0065] In the present invention, the state characteristic parameters of the front and rear wheels are used to predict the trajectory at the next moment, and the motion state of the four wheels of the agricultural inspection robot as a whole is fully considered, and the prediction is accurate.

[0066] In the embodiment of the present invention, in S242, the expression of the predicted trajectory (x1, y1) of the agricultural inspection robot at the next moment is:

[0067] ;

[0068] Where x1 represents the horizontal coordinate of the predicted trajectory at the next moment, y1 represents the vertical coordinate of the predicted trajectory at the next moment, x0 represents the horizontal coordinate of the real-time position of the agricultural inspection robot, y0 represents the vertical coordinate of the real-time position of the agricultural inspection robot, and ω represents the four-wheel adjustment threshold.

[0069] In the embodiment of the present invention, in S3, a PID controller is used to adjust the trajectory of the agricultural inspection robot.

[0070] In the present invention, in trajectory tracking, the PID control algorithm corresponding to the PID controller can adjust parameters such as the steering angle and acceleration of the vehicle according to the deviation between the predicted trajectory of the tire and the ideal trajectory, so that the tire gradually approaches the ideal trajectory.

[0071] Those skilled in the art will appreciate that the embodiments described herein are intended to help readers understand the principles of the present invention, and should be understood that the protection scope of the present invention is not limited to such specific statements and embodiments. Those skilled in the art can make various other specific variations and combinations that do not deviate from the essence of the present invention based on the technical revelations disclosed by the present invention, and these variations and combinations are still within the protection scope of the present invention.

Claims

1. An automatic inspection control method for an agricultural inspection robot, characterized in that: The following steps are involved: S1, collect the real-time position and real-time status data of the agricultural inspection robot at the current moment; S2. Determine the predicted trajectory of the agricultural inspection robot at the next moment based on the real-time position and real-time status data at the current moment; S3. According to the predicted trajectory and ideal position of the agricultural inspection robot at the next moment, the trajectory of the agricultural inspection robot is adjusted to complete the inspection control.

2. The automatic inspection control method of the agricultural inspection robot according to claim 1, characterized in that: In S1, the real-time status data of the agricultural inspection robot includes the peak power of the motor of the driving wheel and the rotational inertia of the driven wheel.

3. The automatic inspection control method of the agricultural inspection robot according to claim 1, characterized in that: The S2 comprises the following sub-steps: S21, generating a driving state coefficient for the left rear driving wheel according to the peak power of the motor of the left rear driving wheel, and generating a driving state coefficient for the right rear driving wheel according to the peak power of the motor of the right rear driving wheel; S22, constructing a rear wheel driving state matrix according to the driving state coefficient of the left rear driving wheel and the driving state coefficient of the right rear driving wheel; S23, inputting the rear wheel drive state matrix, the rotational inertia of the left front driven wheel, and the rotational inertia of the right front driven wheel into the support regression model to obtain the front wheel driven state coefficient; S24. Determine the predicted trajectory of the agricultural inspection robot at the next moment according to the real-time position of the agricultural inspection robot at the current moment, the rear wheel driving state matrix and the front wheel driven state coefficient.

4. The automatic inspection control method of the agricultural inspection robot according to claim 3 is characterized in that: In S21, the driving state coefficient d of the left rear driving wheel L The calculation formula is: ； Where P vlaue_L Represents the peak power of the motor of the left rear drive wheel, η L represents the transmission efficiency of the left rear drive wheel, m represents the mass of the agricultural inspection robot, g represents the acceleration of gravity, β represents the slope of the terrain where the agricultural inspection robot is located at the current moment, and T L Represents the motor torque of the left rear drive wheel, n L Indicates the motor speed of the left rear drive wheel; In S21, the right rear driving wheel generates a driving state coefficient d R The calculation formula is: ； Where P vlaue_R Represents the peak power of the motor of the right rear drive wheel, η R Indicates the transmission efficiency of the right rear drive wheel, T R Represents the motor torque of the right rear drive wheel, n R Indicates the motor speed of the right rear drive wheel.

5. The automatic inspection control method of the agricultural inspection robot according to claim 3, characterized in that: In S22, the expression of the rear wheel drive state matrix D is: ； Where, d L Indicates the driving state coefficient generated by the left rear driving wheel, d R It represents the driving state coefficient generated by the right rear driving wheel, and I represents the unit matrix.

6. The automatic inspection control method of the agricultural inspection robot according to claim 3, characterized in that: In S23, the expression supporting the regression model Q is: ； In the formula, u L represents the moment of inertia of the left front driven wheel, u R represents the moment of inertia of the right front driven wheel, γ represents the penalty factor, D represents the rear wheel drive state matrix, ||·|| represents the F-norm operation, σ represents the bandwidth parameter of the Gaussian kernel, and exp(·) represents the exponential function.

7. The automatic inspection control method of the agricultural inspection robot according to claim 3, characterized in that: The S24 comprises the following sub-steps: S241, performing mean operation on the value of the rear wheel driving state matrix and the front wheel driven state coefficient to obtain a four-wheel adjustment threshold; S242. Determine the predicted trajectory of the agricultural inspection robot at the next moment according to the real-time position of the agricultural inspection robot at the current moment and the four-wheel adjustment threshold.

8. The automatic inspection control method of the agricultural inspection robot according to claim 7, characterized in that: In S242, the expression of the predicted trajectory (x1, y1) of the agricultural inspection robot at the next moment is: ； Where x1 represents the horizontal coordinate of the predicted trajectory at the next moment, y1 represents the vertical coordinate of the predicted trajectory at the next moment, x0 represents the horizontal coordinate of the real-time position of the agricultural inspection robot, y0 represents the vertical coordinate of the real-time position of the agricultural inspection robot, and ω represents the four-wheel adjustment threshold.

9. The automatic inspection control method of the agricultural inspection robot according to claim 1, characterized in that: In S3, a PID controller is used to adjust the trajectory of the agricultural inspection robot.

Images