A picking manipulator based on artificial intelligence visual recognition

Abstract

The present invention relates to the technical field of picking machinery, and specifically to a picking manipulator based on artificial intelligence vision recognition, including a mounting base. The present invention comprehensively analyzes and calculates the overlapping area of the picking area corresponding to the outer contour of each picked fruit, the number of overlapping feature points in the skin texture of each picked fruit, and the light intensity of each picked fruit corresponding to each picking area to obtain the picking state evaluation index of each picked fruit corresponding to the picking area. Then, the picking state evaluation index of each picked fruit corresponding to the picking area is compared with the set picking state evaluation index threshold to obtain the corresponding picking signal, enabling the picking manipulator to adjust the control parameters according to the corresponding picking signal to determine whether to perform the picking operation on the fruit and the recycling position of the fruit after picking, significantly improving the picking efficiency of the picking manipulator for the fruit, and being able to automatically classify the picked fruit, improving the picking effect of the fruit.

Description

Technical Field

[0001] The present invention relates to the technical field of picking machinery, and particularly to a picking manipulator based on artificial intelligence visual recognition. Background Art

[0002] Automated production and processing is an inevitable trend, and agricultural production is naturally no exception. Popularizing automated equipment in agricultural production to improve production efficiency and reduce labor costs is the future development direction of agricultural production. Fruit planting occupies a crucial position in agricultural production.

[0003] Developing an agricultural picking robot based on machine vision with high efficiency and low cost has long-term significance. Summary of the Invention

[0004] Aiming at the deficiencies of the prior art, the present invention provides a picking manipulator based on artificial intelligence visual recognition to solve the above-mentioned technical defects.

[0005] To achieve the above objectives, the present invention is realized through the following technical solutions: A picking manipulator based on artificial intelligence visual recognition, including a mounting base, characterized in that: a rotating chassis is rotatably arranged on the top of the mounting base, a fixed frame is fixedly arranged on the top of the rotating chassis, and a first movable frame is rotatably arranged on the top of the fixed frame. One side of the fixed frame is rotatably provided with an adjusting cylinder, and the driving end of the adjusting cylinder is movably connected to the bottom of the first movable frame;

[0006] One side of the top of the first movable frame is rotatably provided with a first mounting frame, a servo linear slide is fixedly arranged on one side of the first mounting frame, and a second movable frame is slidably arranged on the surface of the servo linear slide. One side of the top of the second movable frame is fixedly provided with a second motor, and the other side of the top of the second movable frame is rotatably provided with a second mounting frame. One end of the output shaft of the second motor is fixedly connected to one side of the second mounting frame. One side of the second mounting frame is fixedly provided with a third motor, and one end of the output shaft of the third motor is fixedly provided with a driving lead screw. One side of the second mounting frame is fixedly provided with a picking frame, and three picking arms are movably arranged on one side of the picking frame;

[0007] A visual recognition module, a fruit state analysis module, a fruit picking evaluation module, an execution terminal and a database are arranged inside the picking arm. The visual recognition module is respectively connected to the fruit state analysis module and the database, the fruit state analysis module is respectively connected to the fruit picking evaluation module and the database, and the fruit picking evaluation module is respectively connected to the execution terminal and the database.

[0008] Preferably, a driving motor is fixedly arranged at the top of the inner wall of the installation base, and a driving gear is fixedly arranged on the output shaft of the driving motor. An internal gear ring is fixedly arranged on the inner wall of the rotating chassis, and the surface of the driving gear is in meshing transmission with the inner wall of the internal gear ring.

[0009] Preferably, a first motor is also fixedly arranged on the other side of the top of the first movable frame, and the output shaft of the first motor is fixedly connected to one side of the first mounting frame.

[0010] Preferably, an adjusting frame is arranged on the surface of the driving lead screw in a threaded manner, and three adjusting rods are respectively movably arranged on the outer peripheral surface of the adjusting frame. One ends of the three adjusting rods are respectively movably connected to one ends of the three picking arms.

[0011] Preferably, three limiting rods are also fixedly arranged on one side of the second mounting frame, and one ends of the three limiting rods are all slidably connected to the inside of the adjusting frame.

[0012] Preferably, the visual recognition module is used to collect data on the picking positions, external shape image sets, and light intensities of the picking fruits corresponding to each picking area when the picking manipulator picks.

[0013] Preferably, the fruit state analysis module is used to analyze the picking states of the picking fruits corresponding to each picking area when the picking manipulator picks. The specific analysis process is as follows:

[0014] Extract the surface images of the picking fruits corresponding to each picking area from the external shape image sets of the picking fruits corresponding to each picking area when the picking manipulator picks, obtain the surface images of the picking fruits corresponding to each picking area, and obtain the external shape contours and skin textures of the picking fruits corresponding to each picking area based on the surface images of the picking fruits corresponding to each picking area.

[0015] Compare the external shape contours of the picking fruits corresponding to each picking area with the external shape contours of the reference picking fruits stored in the database to obtain the overlapping area of the external shape contours of the picking fruits corresponding to each picking area and the reference picking fruits, which is denoted as the overlapping area of the external shape contours of the picking fruits corresponding to each picking area.

[0016] Obtain the reference skin textures of each picking fruit from the database, and extract a number of feature points on the reference skin textures. Compare the skin textures of the picking fruits corresponding to each picking area with the skin textures of the reference picking fruits stored in the database for the overlapping of feature points to obtain the number of overlapping feature points between the skin textures of the picking fruits corresponding to each picking area and the skin textures of the reference picking fruits, which is denoted as the number of overlapping feature points in the skin textures of the picking fruits corresponding to each picking area.

[0017] Preferably, the fruit picking evaluation module is used to evaluate the picking status of each picking area corresponding to each picked fruit during picking. The specific evaluation method is as follows:

[0018] The fruit picking evaluation parameters of each picking area corresponding to each picked fruit are composed of the overlapping area of the outer contour of each picked fruit corresponding to the picking area, the number of overlapping feature points in the skin texture of each picked fruit, and the light intensity of each picking area corresponding to each picked fruit;

[0019] Extract the values of the overlapping area, the number of overlaps, and the light intensity of each picking area corresponding to each picked fruit from the fruit picking evaluation parameters of each picking area corresponding to each picked fruit, and record them as S j i 、Q j i and L j i , i represents the number of each picked fruit, i = 1, 2,..., n, n represents the total of the numbers of each picked fruit, j represents the number of each picking area, j = 1, 2,..., m, m represents the total of the numbers of each picking area;

[0020] According to the formula Calculate the picking status evaluation index of each picking area corresponding to each picked fruit, Represents the allowable overlapping area difference of each picking area corresponding to each picked fruit, Represents the allowable number of overlaps difference of each picking area corresponding to each picked fruit, Represents the allowable light intensity difference of each picking area corresponding to each picked fruit, Represents the overlapping area of the outer contour of the (i - 1)-th picked fruit corresponding to the picking area, Represents the number of overlapping feature points in the skin texture of the (i - 1)-th picked fruit corresponding to the picking area, Represents the light intensity of the (i - 1)-th picked fruit corresponding to the picking area, and a1, a2, and a3 respectively represent the weight factors corresponding to the set overlapping area, the number of overlaps, and the light intensity.

[0021] Preferably, compare the picking status evaluation index of each picking area corresponding to each picked fruit with the set picking status evaluation index threshold. The specific comparison results are as follows:

[0022] If ≥ q1, it means that the picking status of each picking area corresponding to each picked fruit is normal, generate a normal signal and send it to the execution terminal;

[0023] If q1 > If q1 > q2, it indicates that the picking status of each picked fruit in the picking area is of poor quality. A poor-quality signal is generated and sent to the execution terminal.

[0024] If q1 ≤ q2, it indicates that the picking status of each picked fruit in the picking area is abnormal. An abnormal signal is generated and sent to the execution terminal.

[0025] Among them, both q1 and q2 represent the threshold values of the picking status evaluation index for each picked fruit corresponding to the set picking area, and q1 > q2 > 0.

[0026] Preferably, the execution terminal performs corresponding operations based on the signals generated by the fruit picking evaluation module. The specific operation methods are as follows:

[0027] After receiving the normal signal, the execution terminal controls the picking manipulator to pick the fruit and put it into the normal collection box. After receiving the poor-quality signal, it controls the picking manipulator to pick the fruit and put it into the diseased fruit collection box. After receiving the abnormal signal, it controls the picking manipulator not to pick the fruit.

[0028] Compared with the prior art, the following beneficial effects are achieved:

[0029] 1. In the present invention, the flexible control of the position of one picking arm of the picking manipulator is realized through the first movable frame, the second movable frame and the second mounting frame, so that the three picking arms on one side of the second mounting frame move to one side of the picked fruit. Finally, the output shaft of the third motor is controlled to rotate clockwise, and the driving lead screw is used to drive the adjusting frame to slide along the limiting rod to one side, so that the three picking arms expand outward. Then, the second movable frame is driven by the servo linear slide table to move to the side of the picked fruit, so that the picked fruit is located between the three picking arms. By controlling the output shaft of the third motor to rotate counterclockwise, the three picking arms wrap the picked fruit, and finally the second movable frame is controlled to reset along the first mounting frame to complete the picking operation of the fruit, significantly improving the picking effect of the picking manipulator on the fruit.

[0030] 2. In the present invention, by setting a visual recognition module on the picking manipulator, data collection is carried out on the picking position, fruit image and light intensity of the picked fruit in each picking area during the picking process. Based on the picking position of the picked fruit in each picking area, the rapid positioning of the picking manipulator is realized, improving the picking efficiency of the picking manipulator on the fruit. Through the data collection of the fruit image and light intensity of the picked fruit in each picking area, it is convenient to provide strong data support for the subsequent control of the picking parameters of the picking manipulator on the picked fruit.

[0031] 3. In the present invention, by comprehensively analyzing and calculating the overlapping area of the outer contour of each picked fruit corresponding to the picking area, the number of overlapping feature points in the skin texture of each picked fruit, and the light intensity of each picked fruit corresponding to each picking area, the picking state evaluation index of each picked fruit corresponding to the picking area is obtained. Then, the picking state evaluation index of each picked fruit corresponding to the picking area is compared with the set threshold of the picking state evaluation index to obtain the corresponding picking signal, enabling the picking manipulator to adjust the control parameters according to the corresponding picking signal to determine whether to perform the picking operation on the fruit and the recovery position of the fruit after picking, significantly improving the picking efficiency of the picking manipulator for the fruit, and being able to automatically classify the picked fruits, thereby enhancing the picking effect of the fruits. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] Figure 1 It is a schematic diagram of the structure of a picking manipulator based on artificial intelligence vision recognition according to an embodiment of the present invention;

[0033] Figure 2 It is a schematic diagram of the structure of the drive motor and the drive gear according to an embodiment of the present invention;

[0034] Figure 3 It is a schematic diagram of the structure of the first motor and the second movable frame according to an embodiment of the present invention;

[0035] Figure 4 It is a schematic diagram of the structure of the servo linear slide and the first mounting frame according to an embodiment of the present invention;

[0036] Figure 5 It is a schematic diagram of the structure of the picking frame and the picking arm according to an embodiment of the present invention;

[0037] Figure 6 It is a system principle block diagram of a picking manipulator based on artificial intelligence vision recognition according to an embodiment of the present invention.

[0038] In the figure, 1. mounting base; 2. rotating chassis; 3. fixing frame; 4. first movable frame; 5. adjusting cylinder; 6. drive motor; 7. drive gear; 8. internal gear ring; 9. first mounting frame; 10. servo linear slide; 11. second movable frame; 12. first motor; 13. second motor; 14. second mounting frame; 15. third motor; 16. drive lead screw; 17. picking frame; 18. picking arm; 19. adjusting frame; 20. adjusting rod; 21. limiting rod. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0039] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0040] Embodiment 1:

[0041] Please refer to Figures 1 to 6 As shown in the figure, a picking manipulator based on artificial intelligence visual recognition includes a mounting base 1. A rotating chassis 2 is rotatably provided at the top of the mounting base 1. A fixing frame 3 is fixedly provided at the top of the rotating chassis 2. A first movable frame 4 is rotatably provided at the top of the fixing frame 3. An adjusting cylinder 5 is rotatably provided on one side of the fixing frame 3. The driving end of the adjusting cylinder 5 is movably connected to the bottom of the first movable frame 4. Among them, a driving motor 6 is fixedly provided at the top of the inner wall of the mounting base 1. The output shaft of the driving motor 6 is fixedly provided with a driving gear 7. An internal gear ring 8 is fixedly provided on the inner wall of the rotating chassis 2. The surface of the driving gear 7 is meshed and driven with the inner wall of the internal gear ring 8.

[0042] Furthermore, a first mounting frame 9 is rotatably provided on one side of the top of the first movable frame 4. A servo linear slide 10 is fixedly provided on one side of the first mounting frame 9. A second movable frame 11 is slidably provided on the surface of the servo linear slide 10. A first motor 12 is also fixedly provided on the other side of the top of the first movable frame 4. The output shaft of the first motor 12 is fixedly connected to one side of the first mounting frame 9. A second motor 13 is fixedly provided on one side of the top of the second movable frame 11. A second mounting frame 14 is rotatably provided on the other side of the top of the second movable frame 11. One end of the output shaft of the second motor 13 is fixedly connected to one side of the second mounting frame 14.

[0043] Furthermore, a third motor 15 is fixedly provided on one side of the second mounting frame 14. One end of the output shaft of the third motor 15 is fixedly provided with a driving lead screw 16. A picking frame 17 is fixedly provided on one side of the second mounting frame 14. Three picking arms 18 are movably provided on one side of the picking frame 17. Among them, the three picking arms 18 are arranged at equal angles with respect to the central axis of the picking frame 17. The picking arms 18 are composed of a plurality of movable connecting rods and pin shafts; a regulating frame 19 is threadedly provided on the surface of the driving lead screw 16. Three regulating rods 20 are movably provided on the outer peripheral surface of the regulating frame 19. One end of each of the three regulating rods 20 is movably connected to one end of each of the three picking arms 18.

[0044] Furthermore, three limiting rods 21 are also fixedly provided on one side of the second mounting frame 14. One end of each of the three limiting rods 21 is slidably connected to the inside of the regulating frame 19.

[0045] It should be noted that when picking fruits, the output shaft of the driving motor 6 drives the rotating chassis 2 to drive the fixing frame 3 to rotate through the meshing transmission between the driving gear 7 and the internal gear ring 8, so as to adjust the picking direction of the picking manipulator. Then, by controlling the driving end of the adjusting cylinder 5 to extend, the top of the first movable frame 4 is lifted upward to adjust the picking height of the picking manipulator. Then, the servo linear slide 10 is used to control the second movable frame 11 to slide along the first mounting frame 9 to one side, so that the picking arm 18 on one side of the second movable frame 11 approaches the fruit to be picked. At the same time, the output shaft of the first motor 12 is used to control the angle of the first mounting frame 9, and the output shaft of the second motor 13 is used to control the angle of the second mounting frame 14, so that the three picking arms 18 on one side of the second mounting frame 14 move to one side of the fruit to be picked. Finally, the output shaft of the third motor 15 is used to control the driving lead screw 16 to rotate clockwise, and the driving lead screw 16 is used to drive the adjusting frame 19 to slide along the limiting rod 21 to one side, so that the three picking arms 18 are unfolded outward. Then, the servo linear slide 10 drives the second movable frame 11 to move to the side of the fruit to be picked, so that the fruit to be picked is located between the three picking arms 18. By controlling the output shaft of the third motor 15 to rotate counterclockwise, the three picking arms 18 wrap the fruit to be picked. Finally, the second movable frame 11 is controlled to reset along the first mounting frame 9 to complete the fruit picking operation.

[0046] Embodiment 2:

[0047] Please refer to Figure 6 As shown, as a further specific description of the solution in the above embodiment, a visual recognition module, a fruit state analysis module, a fruit picking evaluation module, and a database are provided inside the picking arm 18. The visual recognition module is respectively connected to the fruit state analysis module and the database, the fruit state analysis module is respectively connected to the fruit picking evaluation module and the database, and the fruit picking evaluation module is respectively connected to the execution terminal and the database.

[0048] The visual recognition module is used to collect data on the picking positions, fruit images, and light intensities of each picking area corresponding to each picked fruit during the picking process of the picking manipulator. The specific collection process is as follows:

[0049] The image data of each picking area corresponding to the picking manipulator during the picking process is collected through the camera installed on the picking arm 18. At the same time, the positions of the picked fruits are marked in the collected image data, and the coordinates and position data of the picking manipulator are recorded simultaneously. The distance data between the picking manipulator and the picked fruit is obtained in cooperation with the distance measuring sensor. The picking positions of each picking area corresponding to each picked fruit during the picking process of the picking manipulator are calculated by calculating the distance data between the picking manipulator and the picked fruit and the relative position coordinates between the picking manipulator and the picked fruit.

[0050] Among them, after obtaining the distance data between the picking manipulator and the picked fruit and the relative position coordinates between the picking manipulator and the picked fruit, the distance data is substituted into the relative position coordinates between the picking manipulator and the picked fruit, so as to obtain the picking positions of the picking manipulator corresponding to each picked fruit in each picking area during picking.

[0051] By controlling the picking arm 18 to move to one side of the picked fruit, then using the camera set on the picking arm 18 to obtain the image of the picked fruit, and by adjusting the position of the picking arm 18 relative to the picked fruit, an external image set of the picked fruit corresponding to each picking area of the picking manipulator during picking is obtained.

[0052] The light intensity sensor set on the picking arm 18 is used to obtain the light intensity data of the light intensity of each picked fruit corresponding to each picking area of the picking manipulator during picking, so as to obtain the light intensity of the picked fruit during picking.

[0053] In a specific embodiment, in the present invention, by setting a visual recognition module on the picking manipulator, data collection is carried out on the picking position, fruit image and light intensity of the picked fruit corresponding to each picking area during the picking process of the fruit. Based on the picking position of the picked fruit in each picking area, the rapid positioning of the picking manipulator is realized, and the picking efficiency of the picking manipulator for the fruit is improved. By collecting data on the fruit image and light intensity of the picked fruit in each picking area, it is convenient to provide strong data support for the subsequent control of the picking parameters of the picking manipulator for the picked fruit.

[0054] The fruit state analysis module is used to analyze the picking state of each picked fruit corresponding to each picking area of the picking manipulator during picking. The specific analysis process is as follows:

[0055] Extract the surface image of each picked fruit corresponding to the picking area from the external image set of each picked fruit corresponding to each picking area of the picking manipulator during picking, obtain the surface image of each picked fruit corresponding to the picking area, and obtain the external contour and skin texture of each picked fruit corresponding to the picking area based on the surface image of each picked fruit corresponding to the picking area;

[0056] Compare the external contour of each picked fruit corresponding to the picking area with the external contour of the reference picked fruit stored in the database to obtain the overlapping area of the external contour of each picked fruit corresponding to the picking area and the reference picked fruit, which is recorded as the overlapping area of the external contour of each picked fruit corresponding to the picking area;

[0057] Obtain the reference skin textures of each picked fruit from the database. Meanwhile, extract several feature points from the reference skin textures. Compare the skin textures of the picked fruits corresponding to the picking areas with the skin textures of the reference picked fruits stored in the database for the coincidence of feature points, and obtain the number of coincident feature points between the skin textures of the picked fruits corresponding to the picking areas and the skin textures of the reference picked fruits, which is denoted as the number of coincident feature points in the skin textures of the picked fruits corresponding to the picking areas.

[0058] It should be noted that the outer contour of the reference picked fruit includes the size and shape of the picked fruit after ripening, and the feature points in the skin texture of the reference picked fruit include aspects such as color, concavity and convexity, and texture.

[0059] The fruit picking evaluation module is used to evaluate the picking status of each picked fruit corresponding to each picking area when the picking manipulator is picking. The specific evaluation method is as follows:

[0060] The fruit picking evaluation parameters corresponding to each picked fruit in each picking area are composed of the overlapping area of the outer contour of each picked fruit corresponding to the picking area, the number of coincident feature points in the skin texture of each picked fruit, and the light intensity of each picked fruit corresponding to each picking area.

[0061] Extract the values of the overlapping area, the number of coincidences, and the light intensity corresponding to each picked fruit in each picking area from the fruit picking evaluation parameters corresponding to each picked fruit in each picking area, and denote them as S j i 、Q j i and L j i , where i represents the number of each picked fruit, i = 1, 2,..., n, n represents the total sum of the numbers of each picked fruit, j represents the number of each picking area, j = 1, 2,..., m, and m represents the total sum of the numbers of each picking area.

[0062] According to the formula Calculate the picking status evaluation index corresponding to each picked fruit in the picking area, represents the allowable overlapping area difference corresponding to each picked fruit in the picking area, represents the allowable number of coincidences difference corresponding to each picked fruit in the picking area, represents the allowable light intensity difference corresponding to each picked fruit in the picking area, represents the overlapping area of the outer contour of the (i - 1)-th picked fruit corresponding to the picking area, represents the number of coincident feature points in the skin texture of the (i - 1)-th picked fruit corresponding to the picking area, Denoted as the light intensity corresponding to the (i - 1)-th picked fruit in the picking area, a1, a2, and a3 respectively denote the weight factors corresponding to the set overlapping area, overlapping quantity, and light intensity.

[0063] Obtain the threshold of the picking status evaluation index corresponding to each picked fruit in the set picking area through the database, and compare the picking status evaluation index corresponding to each picked fruit in the picking area with the set threshold of the picking status evaluation index. The specific comparison results are as follows:

[0064] If ≥ q1, it indicates that the picking status of each picked fruit corresponding to the picking area is normal, generate a normal signal and send it to the execution terminal;

[0065] If q1 > > q2, it indicates that the picking status of each picked fruit corresponding to the picking area is inferior, generate an inferior signal and send it to the execution terminal;

[0066] If ≤ q2, it indicates that the picking status of each picked fruit corresponding to the picking area is abnormal, generate an abnormal signal and send it to the execution terminal.

[0067] Among them, q1 and q2 both denote the thresholds of the picking status evaluation index corresponding to each picked fruit in the set picking area, and q1 > q2 > 0.

[0068] In a specific embodiment, in the present invention, the picking status evaluation index corresponding to each picked fruit in the picking area is obtained through comprehensive analysis and calculation of the overlapping area of the outer contour of each picked fruit corresponding to the picking area, the overlapping quantity of the feature points in the skin texture of each picked fruit, and the light intensity corresponding to each picked fruit in each picking area. Then, the picking status evaluation index corresponding to each picked fruit in the picking area is compared with the set threshold of the picking status evaluation index to obtain the corresponding picking signal, enabling the picking manipulator to adjust the control parameters according to the corresponding picking signal to determine whether to pick the fruit and the recycling position after picking the fruit, significantly improving the picking efficiency of the picking manipulator for the fruit, and being able to realize the automatic classification processing of the picked fruit, improving the picking effect of the fruit.

[0069] The execution terminal performs corresponding operations based on the signals generated by the fruit picking evaluation module. The specific operation methods are as follows:

[0070] After receiving the normal signal, the execution terminal controls the picking manipulator to pick the fruit and put it into the normal collection box. After receiving the inferior signal, it controls the picking manipulator to pick the fruit and put it into the diseased fruit collection box. After receiving the abnormal signal, it controls the picking manipulator not to pick the fruit.

[0071] The database is used to store the contour of the reference picked fruit, the skin texture, and the threshold of the picking state evaluation index corresponding to each picked fruit in the picking area.

[0072] Meanwhile, the content not detailedly described in this specification belongs to the prior art well known to those skilled in the art.

[0073] It should be noted that, in this text, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the term "comprising", "including" or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements not only includes those elements, but also includes other elements not expressly listed, or further includes elements inherent to such process, method, article or device.

[0074] Although the embodiments of the present invention have been shown and described, for those of ordinary skill in the art, it can be understood that various changes, modifications, substitutions and variations can be made to these embodiments without departing from the principle and spirit of the present invention. The scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A picking manipulator based on artificial intelligence visual recognition, characterized in that: The picking arm (18) comprises a visual recognition module, a fruit state analysis module, a fruit picking evaluation module, an execution terminal and a database, wherein the visual recognition module is connected to the fruit state analysis module and the database respectively, the fruit state analysis module is connected to the fruit picking evaluation module and the database respectively, and the fruit picking evaluation module is connected to the execution terminal and the database respectively; The visual recognition module is used to collect data on the picking position, shape image set, and light intensity of each picking area corresponding to each picked fruit when the picking robot is picking; The fruit state analysis module is used to analyze the picking state of each picking area corresponding to each picked fruit when the picking robot is picking. The specific analysis process is as follows: Extracting the surface image of each picked fruit in the picking area from the shape image set of each picked fruit in each picking area when the picking robot is picking, obtaining the surface image of each picked fruit in the picking area, and obtaining the shape contour and skin texture of each picked fruit in the picking area based on the surface image of each picked fruit in the picking area; Compare the outlines of each picked fruit corresponding to the picking area with the outlines of reference picked fruits stored in the database to obtain the overlapping area of ​​the outlines of each picked fruit corresponding to the picking area and the reference picked fruit, which is recorded as the overlapping area of ​​the outlines of each picked fruit corresponding to the picking area; The reference skin texture of each picked fruit is obtained from the database, and a number of feature points are extracted from the reference skin texture. The skin texture of each picked fruit in the picking area is compared with the skin texture of the reference picked fruit stored in the database for overlap of feature points, and the number of overlaps of feature points in the skin texture of each picked fruit in the picking area and the skin texture of the reference picked fruit is obtained, which is recorded as the number of overlaps of feature points in the skin texture of each picked fruit in the picking area; The fruit picking evaluation module is used to evaluate the picking status of each picking area corresponding to each picked fruit when the picking manipulator is picking. The specific evaluation method is as follows: The fruit picking evaluation parameters of each picking area corresponding to each picked fruit are formed by the overlapping area of ​​the picking area corresponding to the outer contour of each picked fruit, the overlapping number of feature points in the skin texture of each picked fruit, and the light intensity of each picking area corresponding to each picked fruit; From the fruit picking evaluation parameters of each picking area corresponding to each picked fruit, the values ​​of the overlap area, overlap number and light intensity of each picking area corresponding to each picked fruit are extracted and recorded as S j i , Q j i and L j i , i represents the number of each picked fruit, i=1,2,...,n, n represents the sum of the numbers of each picked fruit, j represents the number of each picking area, j=1,2,...,m, m represents the sum of the numbers of each picking area; According to the formula Calculate the picking status evaluation index of each picked fruit in the picking area. It is expressed as the difference in the allowed overlapping area of ​​each picked fruit in the picking area. It is expressed as the difference in the number of allowed overlaps of each fruit picked in the picking area. It is expressed as the difference in the allowable light intensity of each fruit to be picked in the picking area. It is represented by the overlapping area of ​​the outline of the i-1th picked fruit in the picking area. It is represented by the number of overlapping feature points in the skin texture of the i-1th picked fruit in the picking area. It is represented as the light intensity of the picking area corresponding to the i-1th picked fruit, and a1, a2, and a3 are weight factors corresponding to the set overlap area, overlap number, and light intensity, respectively; The picking state evaluation index of each picked fruit in the picking area is compared with the set picking state evaluation index threshold, and the specific comparison results are as follows: like ≥q1, it means that the picking status of each fruit in the picking area is normal, and a normal signal is generated and sent to the execution terminal; If q1> >q2, it means that the picking status of each fruit in the picking area is poor quality, and a poor quality signal is generated and sent to the execution terminal; like ≤q2, it means that the picking status of each fruit in the picking area is abnormal, and an abnormal signal is generated and sent to the execution terminal; Wherein, q1 and q2 are both the picking state evaluation index thresholds corresponding to the set picking area for each picked fruit, and q1>q2>0; The execution terminal performs corresponding operations based on the signal generated by the fruit picking evaluation module, and the specific operation method is as follows: After receiving a normal signal, the execution terminal controls the picking robot to pick the fruit and put it into a normal collection frame. After receiving a poor quality signal, the execution terminal controls the picking robot to pick the fruit and put it into a diseased fruit collection frame. After receiving an abnormal signal, the execution terminal controls the picking robot not to pick the fruit.

2. The picking manipulator based on artificial intelligence visual recognition according to claim 1 is characterized in that: It also comprises a mounting base (1), a rotating chassis (2) is rotatably provided on the top of the mounting base (1), a fixed frame (3) is fixedly provided on the top of the rotating chassis (2), and a first movable frame (4) is rotatably provided on the top of the fixed frame (3), an adjusting cylinder (5) is rotatably provided on one side of the fixed frame (3), and a driving end of the adjusting cylinder (5) is movably connected to the bottom of the first movable frame (4); A first mounting frame (9) is rotatably provided on one side of the top of the first movable frame (4), a servo linear slide (10) is fixedly provided on one side of the first mounting frame (9), and a second movable frame (11) is slidably provided on the surface of the servo linear slide (10), a second motor (13) is fixedly provided on one side of the top of the second movable frame (11), and a second mounting frame (14) is rotatably provided on the other side of the top of the second movable frame (11), one end of the output shaft of the second motor (13) is fixedly connected to one side of the second mounting frame (14), a third motor (15) is fixedly provided on one side of the second mounting frame (14), and a driving screw rod (16) is fixedly provided on one end of the output shaft of the third motor (15), a picking frame (17) is fixedly provided on one side of the second mounting frame (14), and three picking arms (18) are movably provided on one side of the picking frame (17).

3. The picking manipulator based on artificial intelligence visual recognition according to claim 2 is characterized in that: A driving motor (6) is fixedly arranged on the top of the inner wall of the mounting base (1), and a driving gear (7) is fixedly arranged on the output shaft of the driving motor (6); an inner gear ring (8) is fixedly arranged on the inner wall of the rotating chassis (2), and the surface of the driving gear (7) meshes with the inner wall of the inner gear ring (8) for transmission.

4. The picking manipulator based on artificial intelligence visual recognition according to claim 2 is characterized in that: A first motor (12) is also fixedly arranged on the other side of the top of the first movable frame (4), and the output shaft of the first motor (12) is fixedly connected to one side of the first mounting frame (9).

5. The picking manipulator based on artificial intelligence visual recognition according to claim 2 is characterized in that: An adjustment frame (19) is provided on the surface of the driving screw rod (16) in a threaded manner, and three adjustment rods (20) are movably provided on the outer peripheral surface of the adjustment frame (19), and one end of the three adjustment rods (20) is movably connected to one end of three picking arms (18).

6. The picking manipulator based on artificial intelligence visual recognition according to claim 2 is characterized in that: Three limiting rods (21) are also fixedly arranged on one side of the second mounting frame (14), and one end of the three limiting rods (21) are all slidably connected to the inside of the adjustment frame (19).

Images