Path planning system based on fruit and vegetable picking robot

Abstract

The invention discloses a path planning system based on a fruit and vegetable picking robot, and relates to the field of agricultural machinery, the path planning system comprises an image acquisition module, an image processing module and a picking path planning module, the image acquisition module is used for photographing the position of a fruit and vegetable plant within the picking radius of the picking robot to obtain an environment image with fruits and vegetables; the image processing module is used for processing the environment images, separating and extracting mature fruit and vegetable images in the environment images and calculating position data of mature fruits and vegetables; and the harvesting path planning module plans an optimal picking path of a mechanical arm of the picking robot based on the position data of the mature fruits and vegetables. The positions of all mature fruits and vegetables in the picking radius of the picking robot can be accurately judged in an image collecting and processing mode, then the optimal picking path is obtained and planned based on the positions of all mature fruits and vegetables, on one hand, the picking efficiency can be guaranteed, and on the other hand, the picking efficiency is improved; on the other hand, other immature fruits and vegetables can be prevented from being damaged during picking.

Description

Technical Field

[0001] The present invention relates to the field of agricultural machinery, and in particular to a path planning system based on a fruit and vegetable picking robot. Background Art

[0002] As is known to all, with the development of society, this series of problems have been effectively solved. Digital agriculture and smart agriculture have become the inevitable path, and integrating information technology into agricultural production has become the main research topic. As part of intelligent agricultural machinery and equipment, agricultural robots have received extensive attention and have a very broad prospect. Agricultural robots are a type of robot with the characteristics of service robots. They have the ability to perceive environmental information, understand the scene and accurately control, and are used in agricultural application scenarios;

[0003] For example, the authorization announcement number is CN106105566B, the authorization announcement date is 2018.07.06, and the name is an intelligent citrus picking robot and citrus picking method. The robot includes a walking mechanism, a robotic arm, a workbench, a recovery device, a control system and a power supply system. The robotic arm, the control system and the power supply system are installed on the workbench. The front end of the robotic arm is provided with an end effector and a visual system. The visual system is data-connected with the control system. The control system controls the movement of the robotic arm through the robotic arm drive unit. The control system controls the movement of the walking mechanism through the walking drive unit. The power supply system provides working power for the control system and the walking mechanism. The robotic arm includes a first arm, a second arm, a third arm, a fourth arm, a fifth arm and a sixth arm... which are movably connected in sequence.

[0004] As in the above application, in the existing picking robots, image recognition is used to pick fruits and vegetables to distinguish between mature fruits and vegetables and immature fruits and vegetables, and then the mature fruits and vegetables are picked through a control system. However, the picking path generally takes the nearest picking path, and the contact and squeezing problem of immature fruits and vegetables on the picking path is not considered. Therefore, in the process of picking fruits and vegetables by existing picking robots, immature fruits and vegetables are often damaged. This damage often affects the growth and formation of some more "delicate" fruits and vegetables (such as tomatoes and strawberries), thereby affecting the quality of the fruits and vegetables in the later stage. Summary of the invention

[0005] (I) Purpose of the invention

[0006] In view of this, the purpose of the present invention is to propose a path planning system based on a fruit and vegetable picking robot, so that the picking robot can contact other fruits and vegetables as little as possible on the shortest picking path. On the one hand, it can ensure the picking efficiency, and on the other hand, it can avoid damage to other immature fruits and vegetables during picking.

[0007] (II) Technical solution

[0008] In order to achieve the above technical objectives, the present invention provides a path planning system based on a fruit and vegetable picking robot, which includes an image acquisition module, an image processing module, and a picking path planning module, wherein:

[0009] The image acquisition module is used to take pictures of the positions of fruit and vegetable plants within the picking radius of the picking robot to obtain an environmental image containing fruits and vegetables;

[0010] The image processing module is used to process the environment image, separate and extract the ripe fruit and vegetable images in the environment image, and calculate the position data of the ripe fruits and vegetables;

[0011] The harvesting path planning module plans the optimal picking path for the picking robot arm based on the position data of mature fruits and vegetables.

[0012] As a further description of the above technical solution: the environmental image is obtained by photographing a camera installed on the mechanical arm of the picking robot, and the camera is a high-definition binocular camera.

[0013] As a further description of the above technical solution: the image processing module processes the environment image in the following steps:

[0014] The method of biological testing and database establishment is adopted to identify fruits and vegetables by color features, and the collected images of fruits, vegetables and background colors are statistically analyzed, and the mean, maximum, minimum and standard deviation of each color feature component are calculated;

[0015] Based on the results of feature statistical analysis, the ripe fruit and vegetable images are extracted from the environmental images through the threshold segmentation method;

[0016] Perform Gaussian blur processing on the extracted ripe fruit and vegetable images to obtain binary images;

[0017] The binary image is filtered by the erosion and dilation method, and then the image is opened and closed to obtain the processed image.

[0018] As a further description of the above technical solution: the method for calculating the position data of ripe fruits and vegetables is as follows:

[0019] Perform edge detection on the processed image to obtain the two-dimensional pixel coordinates and radius data of the fruits and vegetables in the image;

[0020] Depth information is obtained through binocular stereo vision, and the RGB image and depth image are fused to determine the three-dimensional spatial position of ripe fruits and vegetables, that is, the position data of ripe fruits and vegetables.

[0021] As a further description of the above technical solution: Based on the position data of ripe fruits and vegetables, the specific method of planning the optimal picking path of the picking robot arm is as follows:

[0022] Based on the three-dimensional spatial positions of all mature fruits and vegetables within the picking radius of the picking robot and the current three-dimensional spatial position of the manipulator of the picking robot, first-level picking routes are established in sequence according to the distance between the fruits and vegetables and the manipulator, and each first-level picking route is connected end to end to form a pre-picking path;

[0023] Based on the pre-picking path, the layout of fruits and vegetables on the picking path is obtained. Based on the layout of fruits and vegetables on the picking path, the picking path is optimized to obtain the optimal picking path.

[0024] As a further description of the above technical solution: Based on the pre-picking path, the method for obtaining the layout of fruits and vegetables on the picking path is as follows:

[0025] Extract all fruit and vegetable positions from the environment image captured by the image acquisition module;

[0026] Analyze the layout of the fruit and vegetable positions to determine whether there are any obstructed fruits and vegetables on the pre-picking path. If it is determined that there are obstructed fruits and vegetables on the pre-picking path, change the primary picking route where the obstructed fruits and vegetables are located and re-establish it as a secondary picking route;

[0027] Based on the secondary picking routes, the optimal picking path is formed by reorganizing the planning.

[0028] As a further description of the above technical solution: the method of changing the primary picking route where the fruits and vegetables are blocked and re-establishing it as a secondary picking route is as follows:

[0029] Based on the primary picking route where the obstructed fruits and vegetables are located, determine the distribution of all fruits and vegetables within a unit distance around the obstructed fruits and vegetables;

[0030] Based on the distribution of all fruits and vegetables within a unit distance around the obstructed fruits and vegetables, the direction with the lowest fruit and vegetable distribution density is selected as the moving direction, and the end point of the first-level picking route where the obstructed fruits and vegetables are located is moved in the moving direction until the area of ​​the obstructed fruits and vegetables contacted on the first-level picking path is the smallest, and then the movement is stopped to form a pre-secondary picking path;

[0031] A picking turning point is established on the pre-secondary picking path, and the picking turning point position and the position of the fruits and vegetables to be picked are connected to form a secondary picking path.

[0032] As a further description of the above technical solution: the method of establishing a picking inflection point on the pre-secondary picking path is as follows:

[0033]

[0034] Among them, P is the distance from the picking inflection point to the starting point of the pre-secondary picking path, L is the distance from the starting point of the pre-secondary picking path to the obstructed fruits and vegetables, ∠α is the angle between the pre-secondary picking path and the horizontal direction, and R is the contour radius of the obstructed fruits and vegetables.

[0035] As a further description of the above technical solution: the calculation method of the unit distance is as follows:

[0036] Take n ripe fruits and vegetables, and record the radii of the n ripe fruits and vegetables as R1, R2, ... Rn in sequence. When the manipulator moves, the circumferential radius required is recorded as D. The calculation method of the unit distance K is as follows:

[0037]

[0038] As a further description of the above technical solution: Based on the secondary picking route, the method of reorganizing and planning to form the optimal picking path is as follows:

[0039] Eliminate the changed primary picking routes on the pre-picking path, and replace the changed secondary picking routes one by one on the picking path to obtain a complete optimized picking path, that is, the optimal picking path.

[0040] In the above technical scheme, the present invention provides a path planning system based on a fruit and vegetable picking robot. The system can accurately determine the positions of all mature fruits and vegetables within the picking radius of the picking robot through image acquisition and processing, and then obtain and plan the optimal picking path based on the positions of all mature fruits and vegetables, so that the picking robot can contact other fruits and vegetables as little as possible on the shortest picking path. On the one hand, it can ensure the picking efficiency, and on the other hand, it can avoid damage to other immature fruits and vegetables during picking. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying creative work.

[0042] Figure 1 A relationship diagram between a world coordinate system and a camera coordinate system in an embodiment of a path planning system based on a fruit and vegetable picking robot provided by the present invention;

[0043] Figure 2 A relationship diagram of a camera coordinate system and an image plane coordinate system in an embodiment of a path planning system based on a fruit and vegetable picking robot provided by the present invention;

[0044] Figure 3 A relationship diagram between a pixel coordinate system and an image plane coordinate system in an embodiment of a path planning system based on a fruit and vegetable picking robot provided by the present invention;

[0045] Figure 4 A coordinate relationship diagram of a binocular camera model in an embodiment of a path planning system based on a fruit and vegetable picking robot provided by the present invention;

[0046] Figure 5 A system block diagram of a path planning system based on a fruit and vegetable picking robot provided by the present invention;

[0047] Figure 6 A flow chart of a path planning system based on a fruit and vegetable picking robot provided by the present invention. DETAILED DESCRIPTION

[0048] The following description is merely exemplary in nature and is not intended to limit the present disclosure, application, and use. It should be understood that in all of these figures, the same or similar reference numerals indicate the same or similar parts and features. The various drawings only schematically represent the concepts and principles of the embodiments of the present disclosure, and do not necessarily show the specific dimensions and proportions of the various embodiments of the present disclosure. Specific parts in specific drawings may be exaggerated to illustrate the relevant details or structures of the embodiments of the present disclosure.

[0049] Reference Figure 1-6 :This embodiment provides a technical solution: a path planning system based on a fruit and vegetable picking robot, including an image acquisition module, an image processing module, and a picking path planning module, wherein:

[0050] The image acquisition module is used to take pictures of the positions of fruit and vegetable plants within the picking radius of the picking robot to obtain an environmental image containing fruits and vegetables;

[0051] The image processing module is used to process the environment image, separate and extract the ripe fruit and vegetable images in the environment image, and calculate the position data of the ripe fruits and vegetables;

[0052] The harvesting path planning module plans the optimal picking path for the picking robot arm based on the location data of mature fruits and vegetables.

[0053] This embodiment provides a path planning system based on a fruit and vegetable picking robot. Specifically, an environmental image is obtained by photographing a camera installed on a mechanical arm of the picking robot, and the camera is a high-definition binocular camera.

[0054] This embodiment provides a path planning system based on a fruit and vegetable picking robot. Specifically, the image processing module processes the environment image in the following steps:

[0055] The method of biological testing and database establishment is used to identify fruits and vegetables through color features. Taking tomatoes as an example, Table 1 shows the feature statistical analysis of the tomato background color image, and the mean, maximum, minimum and standard deviation of each color feature component are calculated. The results are as follows;

[0056]

[0057]

[0058] Table 1

[0059] It can be seen from Table 1 above that the R component value of tomato is the largest in the RGB color space, and the H component and S component of tomato and background are significantly different in the HIS color space. According to the above statistical results, based on the feature statistical analysis results, the ripe tomato image is extracted from the environmental image by the threshold segmentation method;

[0060] There are many irrelevant factors in the processed image, which is difficult to identify. Therefore, the image needs to be further processed. The extracted ripe fruit and vegetable images are Gaussian blurred to obtain a binary image (the information of the binary image is easier to process).

[0061] The erosion and dilation method is used to perform image filtering on the binary image (there are more clutter and noise spots in the original image), and then the opening operation is performed on it and then the closing operation is performed to obtain the processed image. It should be noted that the main content of the opening operation is to perform the erosion operation first, and then the dilation operation. The background noise spots of the processed picture are basically removed, and a clearer fruit is obtained after the noise spots are removed. The closing operation is to perform the dilation operation first, and then the erosion operation, which can remove some holes in the fruit and vegetable image and facilitate the subsequent edge detection.

[0062] This embodiment provides a path planning system based on a fruit and vegetable picking robot. Specifically, the method for calculating the position data of mature fruits and vegetables is as follows:

[0063] Perform edge detection on the processed image (the purpose of edge detection is to significantly reduce the amount of data and eliminate irrelevant information, retaining important structures in the image), obtain the two-dimensional pixel coordinates and radius data of the fruits and vegetables in the image. Specifically, the Canny operator is used to find the best compromise between precise positioning and anti-noise interference. The processing result is a layer of fine white dots formed on the edge of the tomato. Then, Kirchhoff circle detection is performed. After the processing, most of the information in the image has been eliminated, and only the fruit and vegetable information is retained;

[0064] The depth information is obtained through binocular stereo vision, and the RGB image and the depth image are integrated to determine the three-dimensional spatial position of the ripe fruits and vegetables, that is, the position data of the ripe fruits and vegetables (because the fruit and vegetable images taken by the camera only have two-dimensional spatial coordinates, the robot arm needs three-dimensional spatial coordinates when picking fruits and vegetables, so it is necessary to establish a connection between two-dimensional and three-dimensional). It should be noted that the theory of camera imaging is pinhole imaging, and the camera imaging system contains four coordinate systems: world coordinate system, camera coordinate system, image coordinate system and pixel coordinate system (such as Figure 1 shows the relationship between the world coordinate system and the camera coordinate system).

[0065] Specifically, the method for calculating the three-dimensional spatial position of mature fruits and vegetables is as follows:

[0066] Establish world coordinate system O W X W Y W Z W , the world coordinate of point P is X W Y W Z W , establish the coordinate system O at the optical center of the camera C X C Y C Z C ,like Figure 1 The figure shows the relationship between the world coordinate system and the camera coordinate system. The two coordinate systems can completely overlap after the rotation matrix R and the translation matrix T, as shown in formula (1).

[0067]

[0068] like Figure 2 is the relationship between the camera coordinate system and the image plane coordinate system. The coordinates of object P in the camera coordinate system are (X C ,Y C ,Z C ). C o is the focal length f. From the figure, we can see that two similar triangles ΔABO are formed. C ~ΔoCO C and ΔPBO C ~ΔpCO C , so the following relationship is satisfied, as shown in formula (2).

[0069]

[0070] After sorting, we can get formula (3):

[0071]

[0072] The matrix representation is formula (4):

[0073]

[0074] The relationship between the pixel coordinate system and the image plane coordinate system realizes the conversion between millimeters and pixels, such as Figure 3 As shown:

[0075] It can be seen from the figure that there is the following relationship between the pixel coordinate system and the image plane coordinate system, as shown in formula (5):

[0076]

[0077] After sorting, we get formula (6):

[0078]

[0079] Combining the three coordinate transformations together, we can get the relationship between the world coordinate system and the pixel coordinate system, and convert the pixel unit into the length unit, as shown in formula (7):

[0080]

[0081] in is the internal parameter of the camera, is the external parameter of the camera, expressed as formula (8):

[0082]

[0083] The single camera model multiplies the internal and external parameters into a 3×4 matrix, and the above formula is transformed into formula (9):

[0084]

[0085] Expanding and reorganizing, we can get formula (10):

[0086]

[0087] In formula (9), S 1 Substituting the other two terms into equation (10), we can obtain equation (11):

[0088]

[0089] Solve the three-dimensional coordinates of the object in the world coordinate system (X W ,Y W ,Z W ), there are three unknowns in the two equations, and no unique solution can be obtained. A binocular camera must be used to obtain the three-dimensional coordinates of the spatial object. The coordinate relationship of the binocular camera model is as follows: Figure 4 As shown:

[0090] Determine the first camera coordinate system as the world coordinate system, as shown in formula (12):

[0091]

[0092] The other camera coordinate system is transformed by the rotation matrix R and translation matrix T relative to the first camera coordinate system, as shown in formula (13):

[0093]

[0094] After expansion, it is expressed as formula (14):

[0095]

[0096] It can be simplified as formula (15):

[0097]

[0098] At this time, the three unknown quantities in the four equations can be solved by least quadratic fitting and LM iteration, that is, the binocular camera model can be solved, and the three-dimensional coordinates of the target object space (X W ,Y W ,Z W ).

[0099] This embodiment provides a path planning system based on a fruit and vegetable picking robot. Specifically, based on the position data of mature fruits and vegetables, a specific method for planning the optimal picking path of the mechanical arm of the picking robot is as follows:

[0100] Based on the three-dimensional spatial positions of all mature fruits and vegetables within the picking radius of the picking robot and the current three-dimensional spatial position of the manipulator of the picking robot, first-level picking routes are established in sequence according to the distance between the fruits and vegetables and the manipulator, and each first-level picking route is connected end to end to form a pre-picking path;

[0101] Based on the pre-picking path, the layout of fruits and vegetables on the picking path is obtained. Based on the layout of fruits and vegetables on the picking path, the picking path is optimized to obtain the optimal picking path.

[0102] This embodiment provides a path planning system based on a fruit and vegetable picking robot. Specifically, based on the pre-picking path, a method for obtaining the layout of fruits and vegetables on the picking path is as follows:

[0103] Extracting all fruit and vegetable positions (including immature fruits and vegetables) in the environmental image captured by the image acquisition module;

[0104] Analyze the layout of the fruit and vegetable positions to determine whether there are any obstructed fruits and vegetables on the pre-picking path. If it is determined that there are obstructed fruits and vegetables on the pre-picking path, change the primary picking route where the obstructed fruits and vegetables are located and re-establish it as a secondary picking route;

[0105] Based on the secondary picking routes, the optimal picking path is formed by reorganizing the planning.

[0106] This embodiment provides a path planning system based on a fruit and vegetable picking robot. Specifically, a method for changing the primary picking route where the fruits and vegetables are blocked and re-establishing it as a secondary picking route is as follows:

[0107] Based on the primary picking route where the obstructed fruits and vegetables are located, determine the distribution of all fruits and vegetables within a unit distance around the obstructed fruits and vegetables;

[0108] Based on the distribution of all fruits and vegetables within a unit distance around the obstructed fruits and vegetables, the direction with the lowest fruit and vegetable distribution density is selected as the moving direction, and the end point of the first-level picking route where the obstructed fruits and vegetables are located is moved in the moving direction until the area of ​​the obstructed fruits and vegetables contacted on the first-level picking path is the smallest, and then the movement is stopped to form a pre-secondary picking path;

[0109] A picking turning point is established on the pre-secondary picking path, and the picking turning point position and the position of the fruits and vegetables to be picked are connected to form a secondary picking path.

[0110] This embodiment provides a path planning system based on a fruit and vegetable picking robot. Specifically, a method for establishing a picking turning point on a pre-secondary picking path is as follows:

[0111]

[0112] Among them, P is the distance from the picking inflection point to the starting point of the pre-secondary picking path, L is the distance from the starting point of the pre-secondary picking path to the obstructed fruits and vegetables, ∠α is the angle between the pre-secondary picking path and the horizontal direction, and R is the contour radius of the obstructed fruits and vegetables.

[0113] This embodiment provides a path planning system based on a fruit and vegetable picking robot. Specifically, the calculation method of the unit distance is as follows:

[0114] Take n ripe fruits and vegetables, and record the radii of the n ripe fruits and vegetables as R1, R2, ... Rn in sequence. When the manipulator moves, the circumferential radius required is recorded as D. The calculation method of the unit distance K is as follows:

[0115]

[0116] This embodiment provides a path planning system based on a fruit and vegetable picking robot. Specifically, based on the secondary picking route, a method for re-arranging and planning to form an optimal picking path is as follows:

[0117] Eliminate the changed primary picking routes on the pre-picking path, replace the changed secondary picking routes one by one with the picking path, and obtain a complete optimized picking path, that is, the optimal picking path. In summary: the system can accurately determine the positions of all mature fruits and vegetables within the picking radius of the picking robot through image acquisition and processing, and then obtain and plan the optimal picking path based on the positions of all mature fruits and vegetables, so that the picking robot can contact other fruits and vegetables as little as possible on the shortest picking path. On the one hand, it can ensure the picking efficiency, and on the other hand, it can avoid damage to other immature fruits and vegetables during picking, especially for some fruits and vegetables with a softer texture. The manipulator of the picking robot may contact and squeeze the fruits and vegetables during the picking process, which can easily cause damage to the fruits and vegetables, affecting their growth and subsequent sales after maturity.

[0118] The exemplary implementation scheme of the present disclosure is described in detail above with reference to the preferred embodiments. However, it can be understood by those skilled in the art that, without departing from the concept of the present disclosure, various modifications and variations can be made to the above-mentioned specific embodiments, and various technical features and structures proposed in the present disclosure can be combined in various ways without exceeding the protection scope of the present disclosure, which is determined by the attached claims.

Claims

1. A path planning system based on a fruit and vegetable picking robot, characterized in that: It includes an image acquisition module, an image processing module, and a picking path planning module, among which: The image acquisition module is used to take pictures of the positions of fruit and vegetable plants within the picking radius of the picking robot to obtain an environmental image containing fruits and vegetables; The image processing module is used to process the environment image, separate and extract the ripe fruit and vegetable images in the environment image, and calculate the position data of the ripe fruits and vegetables; The harvesting path planning module plans the optimal picking path for the picking robot arm based on the position data of mature fruits and vegetables.

2. A path planning system based on a fruit and vegetable picking robot according to claim 1, characterized in that: The environmental image is obtained by photographing a camera installed on the mechanical arm of the picking robot, and the camera is a high-definition binocular camera.

3. A path planning system based on a fruit and vegetable picking robot according to claim 1, characterized in that: The image processing module processes the environment image in the following steps: The method of biological testing and database establishment is adopted to identify fruits and vegetables by color features, and the collected images of fruits, vegetables and background colors are statistically analyzed, and the mean, maximum, minimum and standard deviation of each color feature component are calculated; Based on the results of feature statistical analysis, the ripe fruit and vegetable images are extracted from the environmental images through the threshold segmentation method; Perform Gaussian blur processing on the extracted ripe fruit and vegetable images to obtain binary images; The binary image is filtered by the erosion and dilation method, and then the image is opened and closed to obtain the processed image.

4. A path planning system based on a fruit and vegetable picking robot according to claim 3, characterized in that: The method for calculating the location data of ripe fruits and vegetables is as follows: Perform edge detection on the processed image to obtain the two-dimensional pixel coordinates and radius data of the fruits and vegetables in the image; Depth information is obtained through binocular stereo vision, and the RGB image and depth image are fused to determine the three-dimensional spatial position of ripe fruits and vegetables, that is, the position data of ripe fruits and vegetables.

5. The path planning system based on a fruit and vegetable picking robot according to claim 1, characterized in that: Based on the location data of ripe fruits and vegetables, the specific method for planning the optimal picking path of the picking robot arm is as follows: Based on the three-dimensional spatial positions of all mature fruits and vegetables within the picking radius of the picking robot and the current three-dimensional spatial position of the manipulator of the picking robot, first-level picking routes are established in sequence according to the distance between the fruits and vegetables and the manipulator, and each first-level picking route is connected end to end to form a pre-picking path; Based on the pre-picking path, the layout of fruits and vegetables on the picking path is obtained. Based on the layout of fruits and vegetables on the picking path, the picking path is optimized to obtain the optimal picking path.

6. A path planning system based on a fruit and vegetable picking robot according to claim 5, characterized in that: Based on the pre-picking path, the method for obtaining the layout of fruits and vegetables on the picking path is as follows: Extract all fruit and vegetable positions from the environment image captured by the image acquisition module; Analyze the layout of the fruit and vegetable positions to determine whether there are any obstructed fruits and vegetables on the pre-picking path. If it is determined that there are obstructed fruits and vegetables on the pre-picking path, change the primary picking route where the obstructed fruits and vegetables are located and re-establish it as a secondary picking route; Based on the secondary picking routes, the optimal picking path is formed by reorganizing the planning.

7. A path planning system based on a fruit and vegetable picking robot according to claim 6, characterized in that: The method of changing the first-level picking route where the fruits and vegetables are blocked and re-establishing it as a second-level picking route is as follows: Based on the primary picking route where the obstructed fruits and vegetables are located, determine the distribution of all fruits and vegetables within a unit distance around the obstructed fruits and vegetables; Based on the distribution of all fruits and vegetables within a unit distance around the obstructed fruits and vegetables, the direction with the lowest fruit and vegetable distribution density is selected as the moving direction, and the end point of the first-level picking route where the obstructed fruits and vegetables are located is moved in the moving direction until the area of ​​the obstructed fruits and vegetables contacted on the first-level picking path is the smallest, and then the movement is stopped to form a pre-secondary picking path; A picking turning point is established on the pre-secondary picking path, and the picking turning point position and the position of the fruits and vegetables to be picked are connected to form a secondary picking path.

8. The path planning system based on the fruit and vegetable picking robot according to claim 7, characterized in that: The method of establishing a picking inflection point on the pre-secondary picking path is as follows: Among them, P is the distance from the picking inflection point to the starting point of the pre-secondary picking path, L is the distance from the starting point of the pre-secondary picking path to the obstructed fruits and vegetables, ∠α is the angle between the pre-secondary picking path and the horizontal direction, and R is the contour radius of the obstructed fruits and vegetables.

9. The path planning system based on a fruit and vegetable picking robot according to claim 7, characterized in that: The unit distance is calculated as follows: Take n ripe fruits and vegetables, and record the radii of the n ripe fruits and vegetables as R1, R2, ... Rn in sequence. When the manipulator moves, the circumferential radius required is recorded as D. The calculation method of the unit distance K is as follows:

10. The path planning system based on a fruit and vegetable picking robot according to claim 6, characterized in that: Based on the secondary picking route, the method of reorganizing and planning to form the optimal picking path is as follows: Eliminate the changed primary picking routes on the pre-picking path, and replace the changed secondary picking routes one by one on the picking path to obtain a complete optimized picking path, that is, the optimal picking path.

Images