Hangzhou white chrysanthemum picking robot and flower picking method thereof

Abstract

The invention relates to a Hangzhou white chrysanthemum picking robot and a flower picking method thereof. The Hangzhou white chrysanthemum picking robot comprises a hub motor, a rack, a battery, a collecting box, a negative pressure fan, an industrial control box, a parallel mechanical arm, a hose, a tail end picking mechanism, a binocular depth camera, a box cover and a buckle. The parallel mechanical arm comprises a static platform, a servo motor, a driving arm, a driven arm and a movable platform; the tail end picking mechanism comprises a horn mouth, an electric push rod and a clamping jaw. The parallel mechanical arm is installed on the upper portion of the front end of the rack. The collecting box is mounted at the rear part of the rack; the tail end picking mechanism is mounted on a movable platform of the parallel mechanical arm; the small end of the horn mouth of the tail end picking mechanism is connected with one side of the collecting box through a hose; the other side of the collecting box is connected with a negative pressure fan; the binocular depth camera is mounted in the middle of the upper part of the parallel mechanical arm; a visual perception system and an intelligent recognition algorithm are integrated, so that the robot can distinguish the positions of the chrysanthemum morifolium flowers, accurate picking is achieved, and the labor cost is reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of picking robots, and in particular to a chrysanthemum picking robot and a flower recognition method thereof. Background Art

[0002] Chrysanthemum is a traditional precious Chinese medicinal material with a long history and rich cultural connotations. It has the effects of stopping diarrhea, relieving inflammation, improving eyesight, lowering blood pressure, lowering blood lipids, and strengthening the body. It is widely used in medicinal materials, skin care products and food.

[0003] Chrysanthemums are harvested in stages and grow towards the sun. The chrysanthemums are mostly located on the surface of the plant, and the embryos and buds are mostly arranged below the chrysanthemums, presenting a three-dimensional distribution from top to bottom. Chrysanthemums have diverse planting patterns, uneven plants, complex flower spatial arrangements, different opening times, and complex picking conditions. Picking is the most labor-intensive part of the production operation and is also the most difficult part to achieve mechanization.

[0004] The picking of chrysanthemums mainly relies on manual labor. Since the flowers of chrysanthemums are small and fragile, precise manual picking is required to maintain the integrity of the flowers. Existing equipment is usually comb-toothed, which cannot accurately identify chrysanthemums, and there are problems such as missed picking, flower damage, and high impurity rate. Therefore, it is urgent to provide a more efficient, flexible and accurate chrysanthemum picking robot that can quickly and accurately identify and pick mature flowers. Summary of the invention

[0005] In order to overcome the deficiencies of the prior art, a chrysanthemum picking robot and a flower recognition method thereof are provided. The specific technical solutions of the present invention are as follows: A chrysanthemum picking robot comprises a wheel hub motor, a frame, a battery, a collection box, a negative pressure fan, an industrial control box, a parallel mechanical arm, a hose, a terminal picking mechanism, a binocular depth camera, a box cover, and a buckle. The parallel mechanical arm comprises a static platform, a servo motor, an active arm, a driven arm, and a dynamic platform. There are four wheel hub motors, which are respectively installed at the four corners of the bottom of the frame; the parallel mechanical arm is installed at the upper front end of the frame; there are three active arms, one end of which is hinged to the static platform and the other end is hinged to the driven arm; there are three driven arms, one end of which is hinged to the dynamic platform and the other end is hinged to the active arm; The collection box is installed at the rear of the frame; the terminal picking mechanism is installed on the moving platform of the parallel robotic arm; the small end of the bell-shaped mouth of the terminal picking mechanism is connected to one side of the collection box through a hose; the other side of the collection box is connected to the negative pressure fan; there are two box covers, which are hinged to the bottom of the collection box respectively, and there are two buckles, which are installed on the two box covers respectively; there are three batteries, which are installed in the middle and rear part of the frame and below the collection box; the industrial control box is installed above the battery and below the collection box; the binocular depth camera is installed in the upper middle position of the parallel robotic arm.

[0006] A flower picking method of a chrysanthemum picking robot comprises the following steps: S1: Start the binocular depth camera to take pictures of chrysanthemums and output images with depth information to the industrial control box; S2: According to the depth information image output in S1, the plane coordinates of each chrysanthemum in the image are identified through the Yolo11n deep learning model, and then the corresponding depth information is read from the depth information image through the plane coordinates, so as to obtain the three-dimensional space coordinates of each chrysanthemum; S3: Perform surface fitting on the three-dimensional spatial coordinates of each chrysanthemum to obtain the surface information of the top surface of the chrysanthemum cluster, and then divide it into several small surfaces, calculate the coordinates of the center point of each small surface, and solve a shortest picking path through a genetic algorithm according to the coordinates of the center point of each small surface, and send the picking path information to the parallel robotic arm; S4: The parallel robotic arm drives the end picking mechanism to move above the first point of the picking path, the gripper opens, moves down a certain distance, completely envelops the chrysanthemum flowers in the small curved area, closes the gripper, and then the parallel robotic arm drives the end picking mechanism to move up, and the chrysanthemum flowers are picked off by pulling force; S5: Start the negative pressure fan to suck the chrysanthemum flowers into the collection box through the trumpet and the hose; S6: Repeat steps S4-S5 until all the flowers in the several small curved surface areas divided in step S3 are picked.

[0007] S7: After the chrysanthemum picking robot finishes picking one area, it continues to move forward and moves to the next picking area, repeating steps S1-S6, and so on to complete the picking of chrysanthemums in the field.

[0008] Compared with the prior art, the present invention has the following beneficial effects: (1) The end picking mechanism provided by the present invention has comb-toothed claws on both sides that act on the receptacle by pulling force to break the flower stalk, thereby picking flowers. No force is applied to the petals, which can reduce flower damage. The comb teeth on both sides can pick 10-15 flowers at the same time to ensure picking efficiency.

[0009] (2) The chrysanthemum picking robot provided by the present invention integrates a visual perception system and an intelligent recognition algorithm, so that the robot can distinguish the position of chrysanthemum flowers, achieve accurate picking, and reduce the missed picking rate and impurity rate.

[0010] (3) The chrysanthemum picking robot provided by the present invention, after picking chrysanthemums in one area and moving to the next picking area, obtains the surrounding environment information through the binocular depth camera and transmits the image to the industrial control box. The industrial control box identifies the side lines of the field ridge image on both sides and then calculates the direction of travel. The rotation speed and speed difference of the hub motor are controlled according to the direction information, so as to realize the autonomous travel and navigation of the chrysanthemum picking robot, thereby reducing the labor cost. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] Figure 1 A schematic diagram of a three-dimensional structure of the present invention from a first viewing angle; Figure 2 A schematic diagram of a three-dimensional structure of the present invention from a second viewing angle; Figure 3 It is a schematic diagram of the open state of the clamping claws of the end picking mechanism of the present invention. In the figure: 1. Hub motor; 2. Frame; 3. Battery; 4. Collection box; 5. Negative pressure fan; 6. Industrial control box; 7. Parallel robotic arm; 8. Hose; 9. End picking mechanism; 10. Binocular depth camera; 11. Box cover; 12. Buckle; 13. Static platform; 14. Servo motor; 15. Active arm; 16. Slave arm; 17. Moving platform; 18. Bell mouth; 19. Electric push rod; 20. Gripper. DETAILED DESCRIPTION

[0012] In order to make the purpose, technical scheme and advantages of the implementation of the present invention clearer, the technical scheme in the embodiment of the present invention will be described in more detail below in conjunction with the drawings in the embodiment of the present invention. In the drawings, the same or similar reference numerals throughout represent the same or similar elements or elements with the same or similar functions. The described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments in the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention. The embodiments described below with reference to the drawings and directional terms are exemplary and are intended to be used to explain the present invention, and should not be understood as limitations on the present invention.

[0013] Reference Figure 1-3 As shown: A chrysanthemum picking robot includes a hub motor 1, a frame 2, a battery 3, a collection box 4, a negative pressure fan 5, an industrial control box 6, a parallel mechanical arm 7, a hose 8, a terminal picking mechanism 9, a binocular depth camera 10, a box cover 11, and a buckle 12. The parallel mechanical arm includes a static platform 13, a servo motor 14, an active arm 15, a driven arm 16, and a dynamic platform 17. There are 4 wheel hub motors 1, which are respectively installed at the four corners of the bottom of the frame 2; the parallel mechanical arm 7 is installed at the upper front end of the frame 2; there are 3 active arms 15, one end of which is hinged to the static platform 13 and the other end is hinged to the driven arm 16; there are 3 driven arms 16, one end of which is hinged to the moving platform 17 and the other end is hinged to the active arm 15; the collection box 4 is installed at the rear of the frame 2; the terminal picking mechanism 9 is installed on the moving platform 17 of the parallel mechanical arm 7; the bell mouth of the terminal picking mechanism 9 The small end of 18 is connected to one side of the collection box 4 through a hose 8; the other side of the collection box 4 is connected to the negative pressure fan 5; there are two box covers 11, which are hinged to the bottom of the collection box 4 respectively, and there are two buckles 12, which are respectively installed on the two box covers 11; there are three batteries 3, which are installed in the middle and rear part of the frame 2 and below the collection box 4; the industrial control box 6 is installed above the battery 3 and below the collection box 4, and the binocular depth camera 10 is installed in the upper middle position of the parallel robot arm 7; As an embodiment of the present invention, the end picking mechanism 9 further includes an electric push rod 19 and a clamping claw 20. There are two clamping claws 20, which are symmetrically arranged on both sides of the bell mouth 18 and hinged to the side wall of the large end of the bell mouth 18; one end of the electric push rod 19 is hinged to the moving platform 17, and the other end is hinged to the clamping claw 20, and the clamping claw 20 is evenly distributed with comb-like structures; As an implementation mode of the present invention, the hub motor 1 is an integral drive system, with the industrial control box 6 as the core controller. The Kalman filter algorithm and the incremental PID control algorithm are installed in the industrial control box 6 to ensure the smooth movement of the robot.

[0014] As an embodiment of the present invention, the industrial control box 6 includes a microcomputer and a motion controller equipped with an embedded Windows system, uses Python as a programming language and calls multiple Python function libraries, including: OpenCV, Camera, threading and GPIO; wherein the GPIO library is used to control the motion controller pin to output high and low levels to control the movement of the parallel robot arm 7 and the hub motor 1.

[0015] A flower picking method of a chrysanthemum picking robot comprises the following steps: A chrysanthemum picking robot moves to a work site; S1: Start the binocular depth camera 10 to take pictures of chrysanthemums, and output images with depth information to the industrial control box 6; S2: According to the depth information image output in S1, the plane coordinates of each chrysanthemum in the image are identified through the Yolo11n deep learning model, and then the corresponding depth information is read from the depth information image through the plane coordinates, so as to obtain the three-dimensional space coordinates of each chrysanthemum; S3: Perform surface fitting on the three-dimensional spatial coordinates of each chrysanthemum to obtain the surface information of the top surface of the chrysanthemum flower cluster, and then divide it into several small surfaces, calculate the coordinates of the center point of each small surface, plan a picking path according to the coordinates of the center point of each small surface, and send the picking path information to the parallel robot arm 7; S4: The parallel robot arm 7 drives the end picking mechanism 9 to move above the first point of the picking path, the clamp 20 opens, moves down a certain distance, completely envelops the chrysanthemum flowers in the small curved area, closes the clamp 20, and then the parallel robot arm 7 drives the end picking mechanism 9 to move up, and the chrysanthemum flowers are picked off by pulling force; S5: Start the negative pressure fan 5 to suck the chrysanthemum flowers into the collection box 4 through the trumpet mouth 18 and the hose 8.

[0016] S6: Repeat steps S4-S5 until all the flowers in the several small curved surface areas divided in step S3 are picked.

[0017] S7: After the chrysanthemum picking robot finishes picking one area, it continues to move forward and moves to the next picking area, repeating steps S1-S6, and so on to complete the picking of chrysanthemums in the field.

[0018] As an implementation mode of the present invention, the Yolo11n deep learning model training in step S2 further includes the following steps: S21: Collect a large number of chrysanthemum sample images from different plots and lighting conditions, and mark the location of the center area of ​​the flowers; S22: Using the chrysanthemum images of different plots and lighting conditions as input parameters of the deep information model, training the deep neural network model, extracting feature maps of different scales, and fusing the feature maps of different scales to obtain a sample library of comprehensive feature maps.

[0019] As an embodiment of the present invention, the chrysanthemum deep neural network model in step S2 includes a convolutional neural network, and the convolutional neural network includes a convolutional layer, a pooling layer, and a fully connected layer. Wherein, the function of the convolutional layer is to extract information from the input chrysanthemum picture, which is called image features, and these information are called image features. These features are embodied by each pixel in the image in a combined or independent manner, such as the texture features, size, and color features of the picture, and then the features extracted from the convolutional layer are selected by the pooling layer, and the pooling layer is followed by a fully connected layer, which converts all feature matrices of the pooling layer into a one-dimensional feature vector, and automatically extracts and utilizes the multi-scale features of the chrysanthemum image through the deep neural network model.

[0020] As an embodiment of the present invention, the projection of the curved surface of the top surface of the chrysanthemum flower cluster in step S3 in the vertical direction is a rectangle, and the projection of the small curved surface in the vertical direction is a rectangle, and is congruent with the rectangular cross-section of the large end of the trumpet mouth 18 of the terminal picking mechanism 9.

[0021] As an embodiment of the present invention, the clamping jaw 20 of the end effector 9 in S4 is provided with a comb-tooth structure, the cross-section of a single comb tooth is stepped, and the gap between two comb teeth is from large to small.

[0022] As an embodiment of the present invention, when the chrysanthemum picking robot finishes picking one area and moves to the next picking area in step S7, the surrounding environment information is obtained through the binocular depth camera 10, and the image is transmitted to the industrial control box 6. The industrial control box 6 identifies the side lines of the field ridge image on both sides, and then calculates the direction of travel. The rotation speed and speed difference of the four hub motors 1 are controlled according to the direction information to realize the autonomous movement and navigation of the chrysanthemum picking robot.

[0023] The above is a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principle of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. A chrysanthemum picking robot, characterized in that: The invention comprises a wheel hub motor (1), a frame (2), a battery (3), a collection box (4), a negative pressure fan (5), an industrial control box (6), a parallel mechanical arm (7), a hose (8), a terminal picking mechanism (9), a binocular depth camera (10), a box cover (11), and a buckle (12); the parallel mechanical arm (7) comprises a static platform (13), a servo motor (14), a master arm (15), a slave arm (16), and a dynamic platform (17); there are four wheel hub motors (1) respectively mounted at the four corners of the bottom of the frame (2); the parallel mechanical arm (7) is mounted on the upper front end of the frame (2); there are three master arms (15), one end of which is hinged to the static platform (13) and the other end is hinged to the slave arm (16); there are three slave arms (16), one end of which is hinged to the dynamic platform (17) and the other end is hinged to the master arm (15). The collecting box (4) is mounted at the rear of the frame (2); the terminal picking mechanism (9) is mounted on the moving platform (17) of the parallel robot arm (7); the small end of the bell mouth (18) of the terminal picking mechanism (9) is connected to one side of the collecting box (4) through a hose (8); the other side of the collecting box (4) is connected to the negative pressure fan (5); there are two box covers (11), which are respectively hinged to the bottom of the collecting box (4); there are two buckles (12), which are respectively mounted on the two box covers (11); there are three batteries (3), which are mounted at the middle and rear of the frame (2) and located below the collecting box (4); the industrial control box (6) is mounted above the battery (3) and below the collecting box (4); the binocular depth camera (10) is mounted in the middle of the three servo motors (14) on the upper part of the parallel robot arm (7).

2. The chrysanthemum picking robot according to claim 1, characterized in that: The end picking mechanism (9) further comprises an electric push rod (19) and a clamping claw (20). There are two clamping claws (20) in total, which are symmetrically arranged on both sides of the bell mouth (18) and hinged to the side wall of the large end of the bell mouth (18). One end of the electric push rod (19) is hinged to the moving platform (17), and the other end is hinged to the clamping claw (20). The clamping claw (20) is evenly distributed with comb-tooth structures.

3. The chrysanthemum picking robot according to claim 1, characterized in that: The industrial control box (6) includes a microcomputer equipped with an embedded Windows 10 IoT system and a motion controller, uses Python as a programming language and calls multiple Python function libraries, including: OpenCV, Camera, threading and GPIO, wherein the GPIO library is used to control the high and low levels of the motion controller pin output to control the movement of the parallel robot arm (7) and the wheel hub motor (1).

4. A flower picking method of a chrysanthemum picking robot, characterized in that: The steps include: S1: Start the binocular depth camera (10) to take pictures of chrysanthemums, and output the images with depth information to the industrial control box (6); S2: According to the depth information image output in S1, the plane coordinates of each chrysanthemum in the image are identified through the improved Yolo11n deep learning model, and then the corresponding depth information is read from the depth information image through the plane coordinates, so as to obtain the three-dimensional space coordinates of each chrysanthemum; S3: Perform surface fitting on the three-dimensional spatial coordinates of each chrysanthemum to obtain the surface information of the top surface of the chrysanthemum cluster, and then divide it into several small surfaces, calculate the coordinates of the center point of each small surface, and solve a shortest picking path through a genetic algorithm based on the coordinates of the center point of each small surface, and send the picking path information to the parallel robot arm (7); S4: The parallel robot arm (7) drives the terminal picking mechanism (9) to move above the first point of the picking path, the clamp (20) opens, moves down a certain distance, completely envelops the chrysanthemum flowers in the small curved area, closes the clamp (20), and then the parallel robot arm (7) drives the terminal picking mechanism (9) to move upward, and the chrysanthemum flowers are picked off by pulling force; S5: starting the negative pressure fan (5) to suck the chrysanthemum flowers into the collection box (4) through the trumpet (18) and the hose (8); S6: repeating steps S4-S5 until all flowers in the small curved surface areas divided in step S3 are picked; S7: After finishing picking one area, continue to move forward to the next picking area, repeat the steps of S3-S6, and repeat this process to complete the picking of chrysanthemums in the field.

5. The flower picking method of a chrysanthemum picking robot according to claim 4, characterized in that: The improved Yolo11 deep learning model in S2 is trained by the following steps: S21: Collect a large number of chrysanthemum sample images from different plots and lighting conditions, and mark the location of the center area of ​​the flowers; S22: Using the chrysanthemum images of different plots and lighting conditions as input parameters of the deep information model, training the deep neural network model, extracting feature maps of different scales, and fusing the feature maps of different scales to obtain a sample library of comprehensive feature maps.

6. The flower picking method of a chrysanthemum picking robot according to claim 4, characterized in that: The projection of the curved surface of the top surface of the chrysanthemum flower cluster in S3 in the vertical direction is a rectangle, and the projection of the small curved surface in the vertical direction is a rectangle, and is congruent with the rectangular cross-section of the large end of the bell mouth (18) of the terminal picking mechanism (9).

7. The flower picking method of a chrysanthemum picking robot according to claim 4, characterized in that: The clamping claws of the terminal picking mechanism in S4 are provided with a comb-tooth structure, the cross-section of a single comb tooth is stepped, and the gap between two comb teeth is from large to small.

8. The flower picking method of a chrysanthemum picking robot according to claim 4, characterized in that: When the chrysanthemum picking robot finishes picking one area and moves to the next picking area in step S7, it obtains information about the surrounding environment through the binocular depth camera (10) and transmits the image to the industrial control box (6). The industrial control box (6) identifies the side lines of the field ridge image and then calculates the direction of travel. The rotation speed and speed difference of the four wheel hub motors (1) are controlled according to the direction information, thereby realizing autonomous travel and navigation of the chrysanthemum picking robot.

Images