Picking path generation method and device of tea leaf picking robot

Abstract

The invention provides a picking path generation method and device of a tea leaf picking robot. The method comprises the steps that tea bud and leaf information is obtained based on a visual system of the tea leaf picking robot, and a tea bud and leaf three-dimensional envelope body is generated based on the tea bud and leaf information. And constructing a multi-objective optimization model, calculating an optimal picking path of the mechanical arm under multiple objectives according to the multi-objective optimization model, and performing curve fitting on the optimal picking path of the mechanical arm to obtain a picking path of the tea leaf picking robot. The tea bud and leaf information comprises tea bud and leaf picking point position coordinates and three-dimensional space postures of tea buds and leaves. According to the method provided by the invention, the picking path of the tea leaf picking robot can be automatically generated according to the three-dimensional space coordinates and postures of the tea buds and leaves by utilizing the three-dimensional space coordinates and postures of the tea buds and leaves, so that the tea bud and leaf picking success rate, efficiency and cruising ability of the tea leaf picking robot are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of image processing and path generation, and in particular to a method and device for generating a picking path for a tea picking robot. Background Art

[0002] Tea is rich in tea polyphenols, amino acids, vitamins, and other bioactive ingredients and nutrients that benefit health. Its unique pharmacological properties make it widely popular among consumers. However, the rising cost of tea production, especially the harvesting of premium teas, has become a key factor restricting the industry's profitability. The harvesting of premium teas is highly dependent on manual labor, which can account for over 70% of the entire production process. This is not only the most labor-intensive but also the most costly step. This process is subject to significant seasonal and time-sensitive constraints, with short operation cycles and intensive tasks, requiring a large amount of manpower to perform repetitive tasks within a limited timeframe.

[0003] For premium tea picking robotic systems, planning the robotic arm's motion trajectory is one of the core technical challenges of its control system. Efficient and reasonable picking path planning directly determines the robot's operating efficiency and harvesting results. To meet the current development needs of automated premium tea picking machinery, a pressing technical challenge is how to design and optimize the picking sequence and generate the robotic arm's motion trajectory based on this sequence to achieve efficient, energy-efficient, and minimally damaging harvesting operations.

[0004] Therefore, a method is needed to utilize the three-dimensional spatial coordinates and posture of tea buds and leaves to automatically generate a picking path for a tea picking robot according to the three-dimensional spatial coordinates and posture, thereby improving the success rate and efficiency of the tea picking robot's tea bud picking. Summary of the Invention

[0005] In order to overcome the problems existing in the related art, the purpose of the present invention is to provide a picking path generation method and device for a tea picking robot, wherein the method can utilize the three-dimensional spatial coordinates and posture of tea buds and leaves, and automatically generate the picking path of the tea picking robot according to the three-dimensional spatial coordinates and posture, thereby improving the success rate and efficiency of the tea picking robot in picking tea buds and leaves.

[0006] A method for generating a picking path for a tea picking robot, comprising:

[0007] Acquire tea bud and leaf information based on the visual system of the tea picking robot;

[0008] generating a three-dimensional envelope of tea buds and leaves based on the tea bud and leaf information;

[0009] Construct multi-objective optimization models;

[0010] Calculating the optimal picking path of the robotic arm under multiple objectives according to the multi-objective optimization model;

[0011] Curve fitting is performed on the optimal picking path of the robotic arm to obtain the picking path of the tea picking robot.

[0012] In a preferred technical solution of the present invention, the visual system based on the tea picking robot obtains tea bud information, including:

[0013] The visual system of the tea picking robot is used to calculate the direction vector of the petiole axis of the tea bud in three-dimensional space. The direction vector of the petiole axis of the tea bud is used to reflect the three-dimensional spatial posture of the tea bud;

[0014] The position coordinates of the tea bud picking point are determined according to the spatial geometric relationship between the petiole axis direction vector of the tea bud and the leaf growth direction of the tea bud.

[0015] In a preferred technical solution of the present invention, the step of generating a three-dimensional envelope of tea buds and leaves based on the tea bud and leaf information includes:

[0016] The direction vector of the petiole axis of the tea bud is used as the direction vector of the cylinder's central axis;

[0017] The position coordinates of the tea bud picking point are used as the coordinates of the bottom center point;

[0018] Obtain the cylinder radius and cylinder height, and draw the three-dimensional envelope of the tea bud leaf according to the cylinder axis direction vector, the coordinates of the bottom center point, the cylinder radius and the cylinder height.

[0019] In a preferred technical solution of the present invention, the construction of a multi-objective optimization model includes:

[0020] Combined with the constraints of the robotic arm, the path length function of the end effector of the tea picking robot is constructed;

[0021] Constructing a collision risk function for the end-effector of a tea-picking robot;

[0022] Construct the energy consumption function of the end effector of the tea picking robot;

[0023] The path length function, minimum collision risk function and energy consumption function are combined for optimization to obtain the optimal solution set under multiple objectives.

[0024] In a preferred technical solution of the present invention, the step of constructing a path length function of the end effector of the tea picking robot includes:

[0025] Based on the polygonal motion rules of tea buds in three-dimensional space, the path length function is calculated according to the following formula:

[0026]

[0027] Among them, n is the number of tea buds, P end,i is the three-dimensional coordinate of the i-th prepared picking point along the petiole axis, P end,i+1 is the three-dimensional coordinate of the i+1th preparatory picking point along the petiole axis, P pick,i is the three-dimensional coordinate of the i-th tea bud picking point; n is the starting coordinate of the robot arm, P end,1 is the three-dimensional coordinate of the first preparatory picking point along the petiole axis, and D is the path length function.

[0028] In a preferred technical solution of the present invention, the process of constructing a collision risk function for the end effector of the tea picking robot includes:

[0029] The collision risk function is calculated according to the following formula:

[0030]

[0031] Among them, V i is the three-dimensional envelope volume of the i-th tea bud, V j is the three-dimensional envelope volume of the j-th tea bud, is the indicator function, n is the number of tea buds, and R is the collision risk function; if the collision risk function is 1, the tea bud with the largest z-axis coordinate is selected.

[0032] In a preferred technical solution of the present invention, the energy consumption function of the end effector of the tea picking robot is constructed, including:

[0033] Based on the minimum energy consumption rule of each joint of the robotic arm, the energy consumption function is calculated according to the following formula:

[0034]

[0035] Among them, m is the number of joints of the robot arm, θ i,j is the angle value of the jth joint of the robot arm at the i-th point, θ i+1,j is the angle value of the jth joint of the robot arm at the i+1th point, θ n,j is the angle value of the jth joint of the robot arm at the nth point, θ 0,j is the angle value of the jth joint in the initial position of the robot arm, and E is the energy consumption function.

[0036] In a preferred technical solution of the present invention, the optimization of the combined path length function, the minimum collision risk function and the energy consumption function to obtain the optimal solution set under multiple objectives includes:

[0037] The multi-objective optimization model is optimized according to the following formula:

[0038]

[0039] F(x)=[D,R,E] T ;

[0040] in, is the kinematic constraint of the robot arm, min is the minimum function, F(x) is the function of the multi-objective optimization model, Z is the minimum value of the function of the multi-objective optimization model, D is the path length function, R is the collision risk function, E is the energy consumption function, x is the selected path, and T is the matrix transpose.

[0041] In a preferred technical solution of the present invention, the curve fitting of the optimal picking path of the robotic arm includes:

[0042] According to the following formula, a cubic B-spline curve is selected to fit the expected path to obtain the motion trajectory curve:

[0043]

[0044] Among them, n+1 is the number of control points, N i,3 (t) is the cubic B-spline basis function, P i is the i-th control point, S(t) is the motion trajectory curve, t is the node vector, t min is the minimum node vector, t max is the maximum node vector.

[0045] A tea picking path generating device for a tea picking robot, comprising:

[0046] The tea bud and leaf information acquisition module is used to acquire tea bud and leaf information based on the visual system of the tea picking robot;

[0047] A tea bud leaf three-dimensional envelope generating module, configured to generate a tea bud leaf three-dimensional envelope based on the tea bud leaf information;

[0048] Model building module, used to build multi-objective optimization models;

[0049] A path calculation module, used to calculate the optimal picking path of the robotic arm under multiple objectives according to the multi-objective optimization model;

[0050] The path fitting module is used to perform curve fitting on the optimal picking path of the robotic arm to obtain the picking path of the tea picking robot.

[0051] The beneficial effects of the present invention are:

[0052] The present invention provides a method for generating a tea picking path for a tea-picking robot. The method includes acquiring tea bud information based on the robot's visual system. The tea bud information includes the coordinates of the tea bud picking point and the three-dimensional spatial posture of the tea bud. A three-dimensional envelope of the tea bud is generated based on the cylinder's central axis direction vector, the coordinates of the bottom center point, the cylinder radius, and the cylinder height. A multi-objective optimization model is constructed, and a path length function, a collision risk function, and an energy consumption function are established for the robot's end effector. The multi-objective optimization model is optimized based on the path length function, the collision risk function, and the energy consumption function to obtain a multi-objective optimal solution set. Based on the multi-objective optimal solution set of the multi-objective optimization model, an optimal picking path for a robot arm is calculated under the multi-objective conditions. The optimal picking path for the robot arm is curve-fitted to obtain a picking path for the tea-picking robot. The method provided by the present invention can automatically generate a picking path for the tea-picking robot based on the three-dimensional spatial coordinates and posture of the tea bud, thereby improving the tea bud picking success rate and efficiency of the tea-picking robot. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] Figure 1 is a flow chart of a method for generating a picking path for a tea picking robot according to the present invention;

[0054] Figure 2 This is a flow chart of the present invention for generating a three-dimensional envelope of tea buds and leaves based on tea bud and leaf information. DETAILED DESCRIPTION

[0055] The preferred embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. Although preferred embodiments of the present invention are shown in the accompanying drawings, it should be understood that the present invention can be implemented in various forms and should not be limited by the embodiments described herein. Rather, these embodiments are provided to make the present invention more thorough and complete and to fully convey the scope of the present invention to those skilled in the art.

[0056] Example 1

[0057] like Figure 1 As shown, this embodiment provides a method for generating a picking path for a tea picking robot, comprising:

[0058] S1: Obtain tea bud and leaf information based on the visual system of the tea picking robot.

[0059] S2: Generate a three-dimensional envelope of tea buds and leaves based on the tea bud and leaf information.

[0060] S3: Build a multi-objective optimization model.

[0061] S4: Calculate the optimal picking path of the robotic arm under multiple objectives according to the multi-objective optimization model.

[0062] S5: Performing curve fitting on the optimal picking path of the robotic arm to obtain the picking path of the tea picking robot.

[0063] The visual system based on the tea picking robot obtains tea bud and leaf information, including:

[0064] S11: Use the visual system of the tea picking robot to calculate the petiole axis direction vector of the tea bud in three-dimensional space. The petiole axis direction vector of the tea bud is used to reflect the three-dimensional spatial posture of the tea bud.

[0065] S12: determining the position coordinates of the tea bud picking point according to the spatial geometric relationship between the petiole axis direction vector of the tea bud and the leaf growth direction of the tea bud.

[0066] The tea-picking robot has a vision system, a power system, a picking system, and a signal processing system. The picking system includes a robotic arm, the power system includes a battery and a connecting shaft, and the vision system includes a camera. The battery provides power to the other components of the tea-picking robot. The camera captures images of tea buds and leaves in a tea garden. After receiving the images, the signal processing system executes steps S1-S5 to generate the picking path for the tea-picking robot.

[0067] Tea buds are leaf buds that differentiate at the tips of tea tree branches. The petiole connects the leaf blade to the stem of the tea bud. The petiole supports the leaf and transports nutrients, such as organic and inorganic elements, as well as water. Within the leaf structure of tea plants, the length and thickness of the petiole are influenced by factors such as the variety and the growing environment.

[0068] The vision system captures three-dimensional images of tea buds and leaves in the tea garden. The signal processing system sequentially performs grayscale conversion, image filtering, and edge detection on the tea bud and leaf images, extracting the petiole base and petiole tip points. The petiole base point is the point where the petiole connects to the tea stem, while the petiole tip point is the point where the petiole connects to the leaf blade.

[0069] Subtract the 3D coordinates of the petiole base from the 3D coordinates of the petiole tip to obtain the petiole axis vector of the tea bud in 3D space, i.e., the main growth axis of the tea bud. This petiole axis vector can reflect the 3D spatial posture of the tea bud. After determining the petiole axis vector, the intersection of the petiole axis vector and the leaf growth direction is detected to obtain the location coordinates of the tea bud picking point.

[0070] like Figure 2 As shown, the method of generating a three-dimensional envelope of tea buds and leaves based on the tea bud and leaf information includes:

[0071] S21: The direction vector of the petiole axis of the tea bud leaf is used as the direction vector of the central axis of the cylinder.

[0072] S22: The position coordinates of the tea bud picking point are used as the coordinates of the bottom surface center point.

[0073] S23: Obtain the radius and height of the cylinder, and draw the three-dimensional envelope of the tea bud leaf according to the cylinder central axis direction vector, the coordinates of the bottom center point, the cylinder radius, and the cylinder height.

[0074] The 3D envelope of the tea bud leaf is cylindrical. Its orientation is determined by the petiole axis vector, and its bottom is positioned by the coordinates of the bottom center. The size of the 3D envelope is determined by the cylinder radius and height. The 3D envelope is drawn by combining the cylinder's central axis vector, the bottom center coordinates, the cylinder radius, and the cylinder height.

[0075] The curve fitting of the optimal picking path of the robotic arm includes:

[0076] According to the following formula, a cubic B-spline curve is selected to fit the expected path to obtain the motion trajectory curve:

[0077]

[0078] Among them, n+1 is the number of control points, N i,3 (t) is the cubic B-spline basis function, P i is the i-th control point, S(t) is the motion trajectory curve, t is the node vector, t min is the minimum node vector, t max is the maximum node vector.

[0079] Cubic B-spline curves offer advantages such as good local controllability, shape preservation, and numerical stability. They are defined by a set of control points and a knot vector. By fitting the desired path with a cubic B-spline curve, a smooth and continuous motion trajectory curve is obtained.

[0080] The method for generating a tea picking path for a tea-picking robot provided in this embodiment includes acquiring tea bud information based on the robot's vision system. The tea bud information includes the coordinates of the tea bud picking point and the tea bud's three-dimensional spatial posture. A three-dimensional envelope of the tea bud is generated based on the cylinder's central axis direction vector, the coordinates of the bottom center point, the cylinder radius, and the cylinder height. A multi-objective optimization model is constructed, and a path length function, a collision risk function, and an energy consumption function are established for the robot's end effector. The multi-objective optimization model is optimized based on the path length, collision risk, and energy consumption functions to obtain a multi-objective optimal solution set. Based on the multi-objective optimal solution set of the multi-objective optimization model, an optimal picking path for the robot arm is calculated. The optimal picking path for the robot arm is curve-fitted to obtain a picking path for the tea-picking robot. The method provided by the present invention can automatically generate a picking path for the tea-picking robot based on the three-dimensional spatial coordinates and posture of the tea bud, thereby improving the tea bud picking success rate and efficiency of the tea-picking robot.

[0081] Example 2

[0082] like Figure 1 As shown, this embodiment provides a method for generating a picking path for a tea picking robot. This embodiment is based on Example 1 and describes the differences from Example 1. The method includes:

[0083] S1: Obtain tea bud and leaf information based on the visual system of the tea picking robot.

[0084] S2: Generate a three-dimensional envelope of tea buds and leaves based on the tea bud and leaf information.

[0085] S3: Build a multi-objective optimization model.

[0086] S4: Calculate the optimal picking path of the robotic arm under multiple objectives according to the multi-objective optimization model.

[0087] S5: Performing curve fitting on the optimal picking path of the robotic arm to obtain the picking path of the tea picking robot.

[0088] The multi-objective optimization model is constructed, comprising:

[0089] S31: Combined with the constraints of the robotic arm, construct the path length function of the end effector of the tea picking robot.

[0090] S32: Construct a collision risk function for the end effector of a tea picking robot.

[0091] S33: Construct the energy consumption function of the end effector of the tea picking robot.

[0092] S34: Combine the path length function, minimum collision risk function and energy consumption function for optimization to obtain the optimal solution set under multiple objectives.

[0093] The method of constructing a path length function of the end effector of the tea picking robot includes:

[0094] Based on the polygonal motion rules of tea buds in three-dimensional space, the path length function is calculated according to the following formula:

[0095]

[0096] Among them, n is the number of tea buds, P end,i is the three-dimensional coordinate of the i-th prepared picking point along the petiole axis, P end,i+1 is the three-dimensional coordinate of the i+1th preparatory picking point along the petiole axis, P pick,i is the three-dimensional coordinate of the i-th tea bud picking point; n is the starting coordinate of the robot arm, P end,1 is the three-dimensional coordinate of the first preparatory picking point along the petiole axis, and D is the path length function.

[0097] A three-stage undisturbed polygonal motion rule of lifting, translation and descending based on the three-dimensional spatial posture of tea buds is constructed. end,i and P pick,i The second norm of the difference between the i-th pre-picking point and the i-th tea bud picking point can be used to measure the difference between the three-dimensional coordinates of the i-th pre-picking point and the i-th tea bud picking point. end,i+1 and P end,i The difference between adjacent pre-picking points can be measured by the two-norm of the difference. n With P end,1 The second norm of the difference can measure the difference between the starting coordinates of the robot arm and the three-dimensional coordinates of the first preparatory picking point.

[0098] The method of constructing a collision risk function for the end effector of the tea picking robot includes:

[0099] The collision risk function is calculated according to the following formula:

[0100]

[0101] Among them, V i is the three-dimensional envelope volume of the i-th tea bud, V j is the three-dimensional envelope volume of the j-th tea bud, is the indicator function, n is the number of tea buds, and R is the collision risk function; if the collision risk function is 1, the tea bud with the largest z-axis coordinate is selected.

[0102] When the three-dimensional envelope of two tea buds Vi and V j When there is mutual interference, that is, when there is an overlapping area, the indicator function is 1, and the upper tea leaves are preferred, that is, the tea buds with larger z-axis coordinates are selected. i and V j When there is no mutual interference, that is, when there is no overlapping area, the indicator function is 0.

[0103] The energy consumption function of the end effector of the tea picking robot is constructed, including:

[0104] Based on the minimum energy consumption rule of each joint of the robotic arm, the energy consumption function is calculated according to the following formula:

[0105]

[0106] Among them, m is the number of joints of the robot arm, θ i,j is the angle value of the jth joint of the robot arm at the i-th point, θ i+1,j is the angle value of the jth joint of the robot arm at the i+1th point, θ n,j is the angle value of the jth joint of the robot arm at the nth point, θ 0,j is the angle value of the jth joint in the initial position of the robot arm, and E is the energy consumption function.

[0107] A norm is used to measure the difference between the angle values ​​of joints with the same serial number at adjacent points, and a norm is used to measure the difference between the angle values ​​of the jth joint at the nth point and the jth joint at the initial position.

[0108] The optimization is performed by combining the path length function, the minimum collision risk function and the energy consumption function to obtain the optimal solution set under multiple objectives, including:

[0109] The multi-objective optimization model is optimized according to the following formula:

[0110]

[0111] F(x)=[D,R,E] T ;

[0112] in, is the kinematic constraint of the robot arm, min is the minimum function, F(x) is the function of the multi-objective optimization model, Z is the minimum value of the function of the multi-objective optimization model, D is the path length function, R is the collision risk function, E is the energy consumption function, x is the selected path, and T is the matrix transpose.

[0113] This embodiment takes the path length objective function D, the collision risk function R and the energy consumption model view E as three independent optimization objectives, and realizes Pareto front selection through non-dominated sorting and congestion calculation based on the multi-objective optimization algorithm. The specific steps are to use the NSGA-II algorithm to perform population initialization, non-dominated sorting, congestion calculation, cross-mutation and environmental selection, and finally generate the pareto front surface. The pareto front surface refers to the surface formed in space by all optimal sets, and selects the path with the smallest priority path, the lowest collision risk and the lowest energy consumption. Optimizing the path length function, the collision risk function and the energy consumption function at the same time can minimize the motion path of the robotic arm, reduce the collision between the robotic arm and the tea buds during the process of picking tea buds, and reduce the motion energy consumption of each joint of the robotic arm.

[0114] Example 3

[0115] This embodiment provides a tea picking path generation device for a tea picking robot, comprising:

[0116] The tea bud and leaf information acquisition module is used to acquire tea bud and leaf information based on the visual system of the tea picking robot;

[0117] A tea bud leaf three-dimensional envelope generating module, configured to generate a tea bud leaf three-dimensional envelope based on the tea bud leaf information;

[0118] Model building module, used to build multi-objective optimization models;

[0119] A path calculation module, used to calculate the optimal picking path of the robotic arm under multiple objectives according to the multi-objective optimization model;

[0120] The path fitting module is used to perform curve fitting on the optimal picking path of the robotic arm to obtain the picking path of the tea picking robot.

[0121] The tea picking robot's picking path generation device of this embodiment is used to execute the tea picking robot's picking path generation method in Embodiment 1 and Embodiment 2.

[0122] It should be noted that, in this document, the terms "comprises," "includes," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, apparatus, article, or method comprising a series of elements includes not only those elements but also other elements not explicitly listed, or elements inherent to such process, apparatus, article, or method. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of other identical elements in the process, apparatus, article, or method comprising the element.

[0123] The above description is only a preferred embodiment of the present application and does not limit the patent scope of the present application. Any equivalent structure or equivalent process transformation made using the contents of the present application specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present application.

Claims

1. A method for generating a picking path for a tea picking robot, characterized in that: include: Acquire tea bud and leaf information based on the visual system of the tea picking robot; generating a three-dimensional envelope of tea buds and leaves based on the tea bud and leaf information; Construct multi-objective optimization models; Calculating the optimal picking path of the robotic arm under multiple objectives according to the multi-objective optimization model; Curve fitting is performed on the optimal picking path of the robotic arm to obtain the picking path of the tea picking robot.

2. The tea picking path generation method of the tea picking robot according to claim 1, characterized in that: The visual system based on the tea picking robot obtains tea bud and leaf information, including: The visual system of the tea picking robot is used to calculate the direction vector of the petiole axis of the tea bud in three-dimensional space. The direction vector of the petiole axis of the tea bud is used to reflect the three-dimensional spatial posture of the tea bud; The position coordinates of the tea bud picking point are determined according to the spatial geometric relationship between the petiole axis direction vector of the tea bud and the leaf growth direction of the tea bud.

3. The tea picking path generation method of the tea picking robot according to claim 2, characterized in that: The step of generating a three-dimensional envelope of tea buds and leaves based on the tea bud and leaf information includes: The direction vector of the petiole axis of the tea bud is used as the direction vector of the cylinder's central axis; The position coordinates of the tea bud picking point are used as the coordinates of the bottom center point; Obtain the cylinder radius and cylinder height, and draw the three-dimensional envelope of the tea bud leaf according to the cylinder axis direction vector, the coordinates of the bottom center point, the cylinder radius and the cylinder height.

4. The tea picking path generation method of the tea picking robot according to claim 1, characterized in that: The multi-objective optimization model is constructed, comprising: Combined with the constraints of the robotic arm, the path length function of the end effector of the tea picking robot is constructed; Constructing a collision risk function for the end-effector of a tea-picking robot; Construct the energy consumption function of the end effector of the tea picking robot; The path length function, minimum collision risk function and energy consumption function are combined for optimization to obtain the optimal solution set under multiple objectives.

5. The tea picking path generation method of the tea picking robot according to claim 4, characterized in that: The method of constructing a path length function of the end effector of the tea picking robot includes: Based on the polygonal motion rules of tea buds in three-dimensional space, the path length function is calculated according to the following formula: Among them, n is the number of tea buds, P end,i is the three-dimensional coordinate of the i-th prepared picking point along the petiole axis, P end,i+1 is the three-dimensional coordinate of the i+1th preparatory picking point along the petiole axis, P pick,i is the three-dimensional coordinate of the i-th tea bud picking point; n is the starting coordinate of the robot arm, P end,1 is the three-dimensional coordinate of the first preparatory picking point along the petiole axis, and D is the path length function.

6. The tea picking path generation method of the tea picking robot according to claim 4, characterized in that: The method of constructing a collision risk function for the end effector of the tea picking robot includes: The collision risk function is calculated according to the following formula: Among them, V i is the three-dimensional envelope volume of the i-th tea bud, V j is the three-dimensional envelope volume of the j-th tea bud, is the indicator function, n is the number of tea buds, and R is the collision risk function; if the collision risk function is 1, the tea bud with the largest z-axis coordinate is selected.

7. The tea picking path generation method of the tea picking robot according to claim 4, characterized in that: The energy consumption function of the end effector of the tea picking robot is constructed, including: Based on the minimum energy consumption rule of each joint of the robotic arm, the energy consumption function is calculated according to the following formula: Among them, m is the number of joints of the robot arm, θ i,j is the angle value of the jth joint of the robot arm at the i-th point, θ i+1,j is the angle value of the jth joint of the robot arm at the i+1th point, θ n,j is the angle value of the jth joint of the robot arm at the nth point, θ 0,j is the angle value of the jth joint in the initial position of the robot arm, and E is the energy consumption function.

8. The tea picking path generation method of the tea picking robot according to claim 4, characterized in that: The optimization is performed by combining the path length function, the minimum collision risk function and the energy consumption function to obtain the optimal solution set under multiple objectives, including: The multi-objective optimization model is optimized according to the following formula: F(x)=[D,R,E] T ; in, is the kinematic constraint of the robot arm, min is the minimum function, F(x) is the function of the multi-objective optimization model, Z is the minimum value of the function of the multi-objective optimization model, D is the path length function, R is the collision risk function, E is the energy consumption function, x is the selected path, and T is the matrix transpose.

9. The tea picking path generation method of the tea picking robot according to claim 1, characterized in that: The curve fitting of the optimal picking path of the robotic arm includes: According to the following formula, a cubic B-spline curve is selected to fit the expected path to obtain the motion trajectory curve: Among them, n+1 is the number of control points, N i,3 (t) is the cubic B-spline basis function, P i is the i-th control point, S(t) is the motion trajectory curve, t is the node vector, t min is the minimum node vector, t max is the maximum node vector.

10. A tea picking path generating device for a tea picking robot, characterized in that: include: The tea bud and leaf information acquisition module is used to acquire tea bud and leaf information based on the visual system of the tea picking robot; A tea bud leaf three-dimensional envelope generating module, configured to generate a tea bud leaf three-dimensional envelope based on the tea bud leaf information; Model building module, used to build multi-objective optimization models; A path calculation module, used to calculate the optimal picking path of the robotic arm under multiple objectives according to the multi-objective optimization model; The path fitting module is used to perform curve fitting on the optimal picking path of the robotic arm to obtain the picking path of the tea picking robot.

Images