A path planning method for a handling robot

Abstract

The present invention discloses a path planning method for a transport robot, which relates to the technical field of path planning and includes the following steps: S1, obtaining a real-life picture of a farmland, and determining a ridge area according to the real-life picture as a basic area for path planning; S2, obtaining a starting point and a destination for transporting goods, and generating an adaptive planning function for the starting point and the destination in the basic area for path planning; S3, generating a transport path for the transport robot using the adaptive planning function. The present invention generates a final transport path using an adaptive planning function with strong applicability, so the path planning method of the present invention enables the transport robot to better adapt to the complex and changeable farmland environment, and improves the flexibility and reliability of the transport robot.

Description

Technical Field

[0001] The present invention relates to the technical field of path planning, and in particular to a path planning method for a transport robot. Background Art

[0002] With the development of intelligent agriculture, agricultural handling robots are increasingly used in agricultural production. However, the farmland environment is complex and changeable, including undulating terrain, uneven crop distribution, and random obstacles (such as farm tools and stones), which poses challenges to the path planning of handling robots. Traditional path planning methods perform well in static or relatively simple environments, but in a dynamically changing environment such as farmland, they cannot take into account the special terrain conditions of the farmland, and their efficiency and adaptability are limited. Summary of the invention

[0003] In order to solve the above problems, the present invention proposes a path planning method for a transport robot.

[0004] The technical solution of the present invention is: a path planning method for a handling robot comprises the following steps:

[0005] S1. Obtain a real-life picture of the farmland, and determine the ridge area based on the real-life picture as the basic area for path planning;

[0006] S2. Obtain the transport starting point and transport end point of the goods, and generate an adaptive planning function for the transport starting point and transport end point in the path planning basic area;

[0007] S3. Generate a transport path for the transport robot using an adaptive planning function.

[0008] Furthermore, S2 includes the following sub-steps:

[0009] S21, obtaining the transportation starting point and transportation end point of the goods;

[0010] S22, dividing the path planning basic area into a number of planning nodes, and setting mobile particles at the starting point of the cargo transportation;

[0011] S23, calculating the movement coupling equation of the moving particle at each planning node according to the transportation starting point and transportation end point of the goods;

[0012] S24, obtaining an optimized movement value according to a movement coupling equation of the moving particle at each planning node;

[0013] S25. Generate an adaptive planning function using the optimized movement value.

[0014] The beneficial effect of the above further scheme is: in the present invention, mobile particles are used to simulate the real-time position of the mobile robot, the mobile optimization value is determined according to the power consumption of the mobile particles at each planning node and the planning node, and then an adaptive planning function of the entire path planning basic area is constructed according to the distance between the planning starting point and the transport starting point. This function is used to participate in the path planning of S3.

[0015] Furthermore, in S23, the mobile coupling equation Y of the mobile particle at the i-th planning node is i The expression is:

[0016] ;

[0017] In the formula, a represents the obstacle weight of the planning node, b represents the crop lodging weight of the planning node, and H star_i represents the power consumption value of the mobile particle from the starting point of the cargo transportation to the i-th planning node, H end_i represents the power consumption of the mobile particle from the i-th planning node to the destination of the cargo transportation, H i-1_i represents the energy consumption of the moving particle from the i-1th planning node to the i-1th planning node, H i_i+1 Represents the energy consumption of the moving particle from the i-th planning node to the i+1-th planning node.

[0018] If the terrain of the planning node is not flat or there are crops lodging on the ridge, it will affect the handling efficiency of the handling robot, so these two factors need to be considered. The obstacle weight of the planning node is used to characterize whether there is a low-lying or undulating terrain at the planning node. If so, the obstacle weight can be 2, and if not, the obstacle weight can be 1. The crop lodging weight of the planning node is used to characterize whether there is crop lodging around the planning node. If so, the crop lodging weight can be 2, and if not, the crop lodging weight can be 1. The power consumption value refers to the change in battery power when the handling robot travels from one point to another in the shortest path.

[0019] Further, in S24, the movement value Y is optimized * The calculation formula is:

[0020] ;

[0021] In the formula, η represents the regularization coefficient, Y represents the mobile coupling equation of the planning node, and ||·|| F represents the F-norm operation, H star_end It represents the power consumption value of the moving particle from the starting point to the end point of the cargo transportation, and H0 represents the initial power value of the transportation robot.

[0022] The power value of a handling robot usually refers to the total amount of power that its battery or power system can provide, which determines how long the robot can continue to work after a single charge or power supply.

[0023] Furthermore, in S25, the expression of the adaptive planning function Z is:

[0024] ;

[0025] Where, d i represents the straight-line distance between the i-th planning node and the transport starting point, I represents the number of planning nodes, and Y * represents the optimized move value, and e represents the exponent.

[0026] Furthermore, S3 includes the following sub-steps:

[0027] S31, calculating the planning generalization value using the adaptive planning function;

[0028] S32, using the planning generalization value as a penalty factor of a support vector machine, and using the support vector machine to generate an initial transport path in the path planning basic area;

[0029] S33: Generate a transport path based on the initial transport path.

[0030] The beneficial effect of the above further scheme is that in the present invention, the support vector machine can be used to extract and describe the path, a nonlinear support vector machine classifier can be used to extract a safe path, and a mathematical method (such as a cubic polynomial, a Bezier curve, etc.) can be used to describe and fit the path. The relocate local search operator is a heuristic algorithm for path optimization, which is used to adjust and optimize the generated path to make it more efficient and meet actual needs.

[0031] Furthermore, in S31, the calculation formula of the planning generalization value G is:

[0032] ;

[0033] Where Z represents the adaptive planning function and c represents a constant.

[0034] Furthermore, in S33, the initial transport path is optimized using the relocate local search operator to generate a transport path.

[0035] The beneficial effects of the present invention are as follows: the present invention discloses a path planning method for a transport robot, which takes into account the special terrain environment of farmland, divides the path planning basic area of ​​the farmland into nodes, and determines the adaptive planning function of the movement of mobile particles at each node; the final transport path is generated by using a highly applicable adaptive planning function, so the path planning method of the present invention enables the transport robot to better adapt to the complex and changeable farmland environment, and improves the flexibility and reliability of the transport robot. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] Figure 1 Flowchart of the path planning method for a handling robot. DETAILED DESCRIPTION

[0037] The embodiments of the present invention will be further described below in conjunction with the accompanying drawings.

[0038] like Figure 1 As shown, the present invention provides a path planning method for a handling robot, comprising the following steps:

[0039] S1. Obtain a real-life picture of the farmland, and determine the ridge area based on the real-life picture as the basic area for path planning;

[0040] S2. Obtain the transport starting point and transport end point of the goods, and generate an adaptive planning function for the transport starting point and transport end point in the path planning basic area;

[0041] S3. Generate a transport path for the transport robot using an adaptive planning function.

[0042] In this embodiment of the present invention, S2 includes the following sub-steps:

[0043] S21, obtaining the transportation starting point and transportation end point of the goods;

[0044] S22, dividing the path planning basic area into a number of planning nodes, and setting mobile particles at the starting point of the cargo transportation;

[0045] S23, calculating the movement coupling equation of the moving particle at each planning node according to the transportation starting point and transportation end point of the goods;

[0046] S24, obtaining an optimized movement value according to a movement coupling equation of the moving particle at each planning node;

[0047] S25. Generate an adaptive planning function using the optimized movement value.

[0048] In the present invention, mobile particles are used to simulate the real-time position of the mobile robot, and the mobile optimization value is determined according to the power consumption of the mobile particles at each planning node and the planning node. Then, an adaptive planning function of the entire path planning basic area is constructed according to the distance between the planning starting point and the transport starting point. This function is used to participate in the path planning of S3.

[0049] In the embodiment of the present invention, in S23, the mobile coupling equation Y of the mobile particle at the i-th planning node is i The expression is:

[0050] ;

[0051] In the formula, a represents the obstacle weight of the planning node, b represents the crop lodging weight of the planning node, and H star_i represents the power consumption value of the mobile particle from the starting point of the cargo transportation to the i-th planning node, H end_i represents the power consumption of the mobile particle from the i-th planning node to the destination of the cargo transportation, H i-1_i represents the energy consumption of the moving particle from the i-1th planning node to the i-1th planning node, H i_i+1 Represents the energy consumption of the moving particle from the i-th planning node to the i+1-th planning node.

[0052] If the terrain of the planning node is not flat or there are crops lodging on the ridge, it will affect the handling efficiency of the handling robot, so these two factors need to be considered. The obstacle weight of the planning node is used to characterize whether there is a low-lying or undulating terrain at the planning node. If so, the obstacle weight can be 2, and if not, the obstacle weight can be 1. The crop lodging weight of the planning node is used to characterize whether there is crop lodging around the planning node. If so, the crop lodging weight can be 2, and if not, the crop lodging weight can be 1. The power consumption value refers to the change in battery power when the handling robot travels from one point to another in the shortest path.

[0053] In the embodiment of the present invention, in S24, the optimized movement value Y * The calculation formula is:

[0054] ;

[0055] In the formula, η represents the regularization coefficient, Y represents the mobile coupling equation of the planning node, and ||·|| F represents the F-norm operation, H star_end It represents the power consumption value of the moving particle from the starting point to the end point of the cargo transportation, and H0 represents the initial power value of the transportation robot.

[0056] The power value of a handling robot usually refers to the total amount of power that its battery or power system can provide, which determines how long the robot can continue to work after a single charge or power supply.

[0057] In the embodiment of the present invention, in S25, the expression of the adaptive planning function Z is:

[0058] ;

[0059] Where, d i represents the straight-line distance between the i-th planning node and the transport starting point, I represents the number of planning nodes, and Y * represents the optimized move value, and e represents the exponent.

[0060] In this embodiment of the present invention, S3 includes the following sub-steps:

[0061] S31, calculating the planning generalization value using the adaptive planning function;

[0062] S32, using the planning generalization value as a penalty factor of a support vector machine, and using the support vector machine to generate an initial transport path in the path planning basic area;

[0063] S33: Generate a transport path based on the initial transport path.

[0064] In the present invention, support vector machines can be used to extract and describe paths, nonlinear support vector machine classifiers can be used to extract safe paths, and mathematical methods (such as cubic polynomials, Bezier curves, etc.) can be used to describe and fit the paths. The relocate local search operator is a heuristic algorithm for path optimization, which is used to adjust and optimize the generated paths to make them more efficient and meet actual needs.

[0065] In the embodiment of the present invention, in S31, the calculation formula of the planning generalization value G is:

[0066] ;

[0067] Where Z represents the adaptive planning function and c represents a constant.

[0068] In the embodiment of the present invention, in S33, the initial transport path is optimized using the relocate local search operator to generate a transport path.

[0069] 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. A path planning method for a handling robot, characterized in that: The following steps are involved: S1. Obtain a real-life picture of the farmland, and determine the ridge area based on the real-life picture as the basic area for path planning; S2. Obtain the transport starting point and transport end point of the goods, and generate an adaptive planning function for the transport starting point and transport end point in the path planning basic area; S3, using an adaptive planning function to generate a transport path for the transport robot; The S2 comprises the following sub-steps: S21, obtaining the transportation starting point and transportation end point of the goods; S22, dividing the path planning basic area into a number of planning nodes, and setting mobile particles at the starting point of the cargo transportation; S23, calculating the movement coupling equation of the moving particle at each planning node according to the transportation starting point and transportation end point of the goods; S24, obtaining an optimized movement value according to a movement coupling equation of the moving particle at each planning node; S25, using the optimized movement value to generate an adaptive planning function; In S23, the mobile particle at the i-th planning node has the mobile coupling equation Y i The expression is: ； In the formula, a represents the obstacle weight of the planning node, b represents the crop lodging weight of the planning node, and H star_i represents the power consumption value of the mobile particle from the starting point of the cargo transportation to the i-th planning node, H end_i represents the power consumption of the mobile particle from the i-th planning node to the destination of the cargo transportation, H i-1_i represents the energy consumption of the moving particle from the i-1th planning node to the i-th planning node, H i_i+1 Represents the power consumption value of the moving particle from the i-th planning node to the i+1-th planning node; In S24, the moving value Y is optimized * The calculation formula is: ； In the formula, η represents the regularization coefficient, Y represents the mobile coupling equation of the planning node, and ||·|| F represents the F-norm operation, H star_end represents the power consumption value of the moving particle from the starting point to the end point of the cargo transportation, and H0 represents the initial power value of the transportation robot; In S25, the expression of the adaptive planning function Z is: ； Where, d i represents the straight-line distance between the i-th planning node and the transport starting point, I represents the number of planning nodes, and Y * represents the optimized move value, and e represents the exponent.

2. The path planning method for a handling robot according to claim 1, characterized in that: The S3 comprises the following sub-steps: S31, calculating the planning generalization value using the adaptive planning function; S32, using the planning generalization value as a penalty factor of a support vector machine, and using the support vector machine to generate an initial transport path in the path planning basic area; S33: Generate a transport path based on the initial transport path.

3. The path planning method for a handling robot according to claim 2, characterized in that: In S31, the calculation formula of the planning generalization value G is: ； Where Z represents the adaptive planning function and c represents a constant.

4. The path planning method for a handling robot according to claim 2, characterized in that: In S33, the initial transport path is optimized using the relocate local search operator to generate a transport path.

Images