CN114885672B - Common head cabbage picking system - Google Patents
Common head cabbage picking system Download PDFInfo
- Publication number
- CN114885672B CN114885672B CN202210329799.3A CN202210329799A CN114885672B CN 114885672 B CN114885672 B CN 114885672B CN 202210329799 A CN202210329799 A CN 202210329799A CN 114885672 B CN114885672 B CN 114885672B
- Authority
- CN
- China
- Prior art keywords
- cabbage
- head
- image
- picking
- actual
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 244000178937 Brassica oleracea var. capitata Species 0.000 title claims abstract description 81
- 240000007124 Brassica oleracea Species 0.000 claims abstract description 64
- 235000003899 Brassica oleracea var acephala Nutrition 0.000 claims abstract description 64
- 235000011301 Brassica oleracea var capitata Nutrition 0.000 claims abstract description 64
- 235000001169 Brassica oleracea var oleracea Nutrition 0.000 claims abstract description 64
- 238000000034 method Methods 0.000 claims abstract description 32
- 241000427033 Stomolophus meleagris Species 0.000 claims description 55
- 238000005520 cutting process Methods 0.000 claims description 23
- 238000012549 training Methods 0.000 claims description 18
- 238000013528 artificial neural network Methods 0.000 claims description 13
- 238000006243 chemical reaction Methods 0.000 claims description 12
- 238000003306 harvesting Methods 0.000 claims description 8
- 235000013311 vegetables Nutrition 0.000 claims description 8
- 238000003062 neural network model Methods 0.000 claims description 3
- 230000000903 blocking effect Effects 0.000 claims description 2
- 230000005540 biological transmission Effects 0.000 description 5
- 235000011299 Brassica oleracea var botrytis Nutrition 0.000 description 3
- 240000003259 Brassica oleracea var. botrytis Species 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000013527 convolutional neural network Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 235000011331 Brassica Nutrition 0.000 description 1
- 241000219198 Brassica Species 0.000 description 1
- 235000017647 Brassica oleracea var italica Nutrition 0.000 description 1
- 241000219193 Brassicaceae Species 0.000 description 1
- 241000196324 Embryophyta Species 0.000 description 1
- 240000002853 Nelumbo nucifera Species 0.000 description 1
- 235000006508 Nelumbo nucifera Nutrition 0.000 description 1
- 235000006510 Nelumbo pentapetala Nutrition 0.000 description 1
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000005856 abnormality Effects 0.000 description 1
- 206010000496 acne Diseases 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 238000005056 compaction Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000002349 favourable effect Effects 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 230000000149 penetrating effect Effects 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
Classifications
-
- A—HUMAN NECESSITIES
- A01—AGRICULTURE; FORESTRY; ANIMAL HUSBANDRY; HUNTING; TRAPPING; FISHING
- A01D—HARVESTING; MOWING
- A01D45/00—Harvesting of standing crops
- A01D45/26—Harvesting of standing crops of cabbage or lettuce
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/70—Determining position or orientation of objects or cameras
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10028—Range image; Depth image; 3D point clouds
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20081—Training; Learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20084—Artificial neural networks [ANN]
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- General Engineering & Computer Science (AREA)
- Computing Systems (AREA)
- Software Systems (AREA)
- Molecular Biology (AREA)
- Computational Linguistics (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Mathematical Physics (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Biology (AREA)
- Environmental Sciences (AREA)
- Harvesting Machines For Specific Crops (AREA)
Abstract
The invention discloses a common head cabbage picking system, which drives a picking actuator through a mechanical arm arranged on a self-propelled chassis to pick cabbage leaf heads one by one, so that the cabbage leaf heads are prevented from being pushed mutually in the continuous picking process, and the damage to the surface of the leaf heads is reduced; and the head of the common head cabbage is intelligently identified and automatically positioned through image acquisition and computer operation, so that the basis for identification and grabbing is provided for picking actions, and the process of picking the common head cabbage one by one is more intelligent.
Description
Technical Field
The invention belongs to agricultural machinery, and particularly relates to a common head cabbage picking system.
Background
The common head cabbage is a plant of Brassicaceae and Brassica, and is composed of cabbage, korean cabbage, and broccoli.
At present, when the common head cabbage is harvested, the whole harvesting mode is adopted to harvest the leaf heads of the common head cabbage, the common head cabbage harvester harvests the common head cabbage in batches through a harvesting mechanism at the front end in the advancing process, when the common head cabbage is continuously picked by the existing picking device, the leaf heads of the common head cabbage are mutually pushed, more damage can be caused on the surface of the leaf head, and the leaf heads of the common head cabbage are easily damaged when the leaf heads of the common head cabbage are separated from surrounding vegetable leaves.
In addition, the maturing period of the common head cabbage is difficult to control very accurately, and when most common head cabbage is matured and can be picked in the same common head cabbage planting field, about 20% -30% of common head cabbage is still immature, and batch harvesting can lead to immature common head cabbage being picked.
Disclosure of Invention
The invention mainly aims to provide a common head cabbage picking system so as to realize automatic picking of cabbage leaf heads one by one, reduce mutual pushing among the cabbage leaf heads and reduce the loss of the surface of the cabbage leaf heads.
In order to achieve the above object and other objects related to the above object, the present invention provides the following technical solutions:
a method for picking common head cabbage, comprising:
providing a common head cabbage picking device, wherein the common head cabbage picking device comprises a self-propelled chassis, a mechanical arm arranged on the self-propelled chassis and a picking actuator arranged at the free end of the mechanical arm, and an image acquisition device is arranged on the common head cabbage picking device;
collecting an image of the common head cabbage vegetable field through the image collecting device;
identifying cabbage heads in the image;
selecting a recognized cabbage leaf head in the image as a cabbage leaf head to be picked according to a preset mode;
reconstructing a three-dimensional model of the cabbage head to be picked according to the image, and determining an actual target position corresponding to the cabbage head to be picked in an actual coordinate system according to the image;
acquiring the actual current position of the picking actuator in an actual coordinate system;
determining the execution action of the mechanical arm and the movement track of the picking actuator according to the actual current position, the actual target position and the dynamic model of the common head cabbage picking device;
and after the picking actuator moves to the actual target position, controlling the picking actuator to execute picking action.
Optionally, the moving track includes:
the first moving track is a track of the picking actuator moving from the actual current position to an actual middle position, and the actual middle position is positioned right above the cabbage leaf heads to be picked; and
the second moving track is a track for the picking actuator to move from the actual middle position to the actual target, and is a vertical track perpendicular to the ground surface of the common head cabbage;
the execution actions comprise a first execution action and a second execution action, wherein the first execution action corresponds to the first track, and the second execution action corresponds to the second track.
Optionally, the method for identifying cabbage leaf heads in the image includes:
inputting the image into a neural network which is trained, and outputting a recognition result, wherein the recognition result comprises the region of the cabbage head in the image.
Optionally, the cabbage heads to be picked are cabbage heads of mature common head cabbage, and the identification result further comprises whether the common head cabbage is mature.
Optionally, the identification result further comprises the type of the common head cabbage.
Optionally, the neural network is a YOLO-based convolutional neural network.
Optionally, the training method of the trained neural network model includes:
acquiring an initial image sample set, wherein the initial image sample set comprises a plurality of images, and each image contains a common head cabbage;
marking the images in the initial image sample set to obtain a training sample set, wherein marking contents of each image comprise the region of the cabbage head in the image, the type of the common head cabbage and whether the common head cabbage is mature;
and inputting the training sample set into a pre-trained neural network for training, and forming the trained neural network after training is completed.
Optionally, the image acquisition device is a depth camera, and the method for determining the actual target position corresponding to the cabbage head to be picked in the actual coordinate system according to the image includes:
presetting a conversion model, wherein the conversion model is a conversion relation between a virtual position in the image and an actual position in the actual coordinate system;
obtaining a corresponding virtual target position of the cabbage head to be picked in the image, wherein the virtual target position is a head junction center position of the cabbage head to be picked in the image;
and determining the actual target position according to the virtual target position and the conversion relation, wherein the actual target position comprises a plane position and a height position.
Correspondingly, the invention also provides a common head cabbage picking system, which comprises:
a self-propelled chassis;
the picking actuator is used for executing picking actions of cutting roots and clamping the cabbage heads;
the picking actuator is arranged on the free end of the mechanical arm and moves along with the free end of the mechanical arm;
the image acquisition device is used for acquiring an image of the common head cabbage vegetable field;
a processor for acquiring an actual current position of the picking actuator in an actual coordinate system; identifying cabbage heads in the image; selecting a recognized cabbage leaf head in the image as a cabbage leaf head to be picked according to a preset mode; reconstructing a three-dimensional model of the cabbage head to be picked according to the image, and determining an actual target position corresponding to the cabbage head to be picked in an actual coordinate system according to the image; determining the execution action of the mechanical arm and the movement track of the picking actuator according to the actual current position, the actual target position and the dynamic model of the common head cabbage picking device; and after the picking actuator moves to the actual target position, controlling the picking actuator to execute picking action.
Optionally, the self-propelled chassis includes a collecting area and a mounting area in a top view direction, the mechanical arm has a fixed end, the fixed end of the mechanical arm is disposed in the mounting area, and the collecting area is used for collecting cabbage heads;
wherein the processor is further configured to: and after the picking action is finished, controlling the mechanical arm to act, enabling the picking actuator to move to the position above the collecting area, and controlling the picking actuator to release the cabbage leaf heads.
According to the common head cabbage picking system, the picking actuator is driven by the mechanical arm, so that the common head cabbage can be picked one by one, pushing of the common head cabbage and the common head cabbage in the picking process is avoided, and damage to the surface of the common head cabbage is reduced; and the cabbage head is identified by the image acquired by the image acquisition device, so that a basis is provided for actions in the picking process, the picking process one by one is more intelligent, and the automatic picking of the common head cabbage one by one can be realized.
Drawings
FIG. 1 shows a flow chart of the method for picking common head cabbage of the present invention;
FIG. 2 is a schematic diagram of a head cabbage picking device;
FIG. 3 is a schematic view of a self-propelled chassis;
FIG. 4 is a schematic view of the structure of the picking actuator (with the blades retracted outwardly);
FIG. 5 is a schematic view of the structure of the picking actuator (with the blades gathered inwardly);
FIG. 6 is a schematic view of the structure of the clamp base of FIG. 4;
FIG. 7 is a schematic view of the swing assembly of FIG. 4;
FIG. 8 is a schematic view of the assembly of the swing assembly, blades and hollow end plates of the clamp of FIG. 4 in a state;
FIG. 9 is an exploded view of FIG. 8;
FIG. 10 is a schematic view of the blade of FIG. 4 from a perspective;
fig. 11 is a schematic view of the blade of fig. 4 from another perspective.
The fixture comprises a fixture base 100, a containing cylinder 110, a hollow end plate 120, a hollowed-out area 110a and a guide chute 121;
blade 200, drive pin 210, slider 220, cutting edge 201, back edge 202, rounded contour 203, first surface 200a, second surface 200b;
the swing assembly 300, the upper swing plate 310, the lower swing plate 320, the U-shaped groove 301, the connecting part 321 and the avoidance space 300a;
a drive mechanism 400, a motor 410, a drive gear 420, and a driven rack 430;
a self-propelled chassis 500, a collection area 501, and an installation area 502;
a mechanical arm 600, a fixed end 601 and a free end 602;
picking actuator 700.
Detailed Description
In the following description, numerous specific details are set forth in order to provide a more thorough understanding of the present invention. It will be apparent, however, to one skilled in the art that the invention may be practiced without one or more of these details. In other instances, well-known features have not been described in detail in order to avoid obscuring the invention.
It should be understood that the present invention may be embodied in various forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the invention to those skilled in the art. In the drawings, like numbers refer to like elements throughout.
The invention discloses a method for picking common head cabbage, which comprises the following steps:
s000, providing a common head cabbage picking device, wherein the common head cabbage picking device comprises a self-propelled chassis, a mechanical arm arranged on the self-propelled chassis and a picking actuator arranged at the free end of the mechanical arm, and an image acquisition device is arranged on the common head cabbage picking device;
s100, acquiring an image of the common head cabbage vegetable field through the image acquisition device;
s200, identifying cabbage heads in the image;
s300, selecting a recognized cabbage leaf head in the image as a cabbage leaf head to be picked according to a preset mode;
s400, reconstructing a three-dimensional model of the cabbage head to be picked according to the image, and determining an actual target position corresponding to the cabbage head to be picked in an actual coordinate system according to the image;
s500, acquiring an actual current position of the picking actuator in an actual coordinate system;
s600, determining the execution action of the mechanical arm and the movement track of the picking actuator according to the actual current position, the actual target position and the dynamic model of the common head cabbage picking device;
and S700, after the picking actuator moves to the actual target position, controlling the picking actuator to execute picking action.
According to the method for picking the common head cabbage, disclosed by the invention, the picking actuator is driven by the mechanical arm, so that the common head cabbage can be picked one by one, the pushing of the common head cabbage and the common head cabbage in the picking process is avoided, and the damage to the surface of the common head cabbage is reduced; and the cabbage head is identified by the image acquired by the image acquisition device, so that a basis is provided for actions in the picking process, the picking process one by one is more intelligent, and the cabbage head can be automatically picked one by one.
For ease of understanding, the picking actuator may be a picking actuator as shown in the figures, and referring to fig. 4 to 11 in combination, the picking actuator 700 includes a jig base 100 provided at a free end 602 of a robot arm 600 and a blade 200 movably provided at a bottom region of the jig base 100, the jig base 100 having a receiving cylinder 110 with an open bottom, the receiving cylinder 110 for receiving cabbage heads to be picked from the open bottom region; blade 200 has a cutting edge facing the open area, and the movable position of blade 200 includes a first position that is blocked in the open area or a second position that is clear of the open area, and blade 200 receives the She Qiuqie pieces of cabbage in the cartridge by moving from the second position to the first position and carries the cut heads of the cabbage in cartridge 110.
For ease of understanding, in fig. 4, the blade is in the second position and in fig. 5, the blade is in the first position.
In fig. 2, the mechanical arm 600 is an AUBO-110 mechanical arm 600, and in the practical implementation process, the mechanical arm 600 only needs to meet the requirement of being capable of driving the picking actuator 700 to any position within the moving range, and has enough high degree of freedom.
That is, the picking action corresponds to an action involving cutting and clamping, although clamping herein is not actually required to clamp, but rather refers to positioning the heads of the cabbage leaves in the picking actuator, as seen in connection with fig. 4-11, i.e., blocking the knots of the heads of the cabbage leaves in the receiving canister.
In some embodiments, the movement trajectory in S600 includes:
the first moving track is a track of the picking actuator moving from the actual current position to an actual middle position, and the actual middle position is positioned right above the cabbage leaf heads to be picked; and
the second moving track is a track for the picking actuator to move from the actual middle position to the actual target, and is a vertical track perpendicular to the ground surface of the common head cabbage;
the execution actions comprise a first execution action and a second execution action, wherein the first execution action corresponds to the first track, and the second execution action corresponds to the second track.
The track mode can enable the picking actuator and the cabbage heads to be picked not to interfere with each other in the picking process, and is favorable for smoothly completing picking.
For ease of understanding, referring to fig. 4, when picking actuator 700 is moved to directly above the heads of the cabbage to be picked via the first movement trajectory, the bottom open area of housing drum 110 is located directly above the heads of the cabbage to be picked; continuing to move the picking actuator 700 downwards according to the second moving track, the knots of the cabbage heads to be picked are covered in the accommodating cylinder 110, and after the picking actuator is controlled to perform picking action, and after the picking actuator is moved to a proper position, the picking actuator is controlled to move from the second position to the first position to finish cutting, so that the blade 200 is blocked in the bottom open area of the accommodating cylinder 110, which is equivalent to finishing clamping the knots of the cabbage heads.
In some embodiments, in S200, the method of identifying cabbage leaf balls in the image comprises: s210, inputting the image into a neural network after training, and outputting a recognition result, wherein the recognition result comprises the region of the cabbage leaf head in the image.
Specifically, in some embodiments, the neural network is a YOLO-based convolutional neural network.
If the cabbage head is identified by the conventional image identification method, the method can be only suitable for identifying a single type of cabbage head, but in the application, the method for identifying the cabbage head in the image by using the neural network can be suitable for more types of cabbages, such as cabbage, cauliflower, purple cabbage and the like, compared with the conventional image identification method, and in addition, the identification accuracy is higher when the cabbage head is identified by using the neural network.
In some embodiments, the heads of the cabbages to be picked are heads of mature cabbages, and the identification result further comprises whether the cabbages are mature. At the moment, the automatic picking of the mature common head cabbage can be realized, the immature common head cabbage cannot be picked, the situation that the cabbage leaf heads of the immature common head cabbage are picked is avoided, and waste can be reduced.
In some embodiments, the identification result further includes a type of head cabbage. The common head cabbage type comprises cabbage, pimple white, cabbage, korean vegetable, lotus white, cauliflower, purple cabbage, etc.
In some embodiments, for the neural network model that has been trained in S210, the training method thereof includes:
s201, acquiring an initial image sample set, wherein the initial image sample set comprises a plurality of images, and each image contains a common head cabbage;
s202, marking the images in the initial image sample set to obtain a training sample set, wherein marking contents of each image comprise the region of the cabbage head in the image, the type of the common head cabbage and whether the common head cabbage is mature or not;
s203, inputting the training sample set into a pre-trained neural network for training, and forming the trained neural network after training is completed.
In S202, the image is marked, usually manually, and the markers of whether the head cabbage is mature or not may be marked as mature head cabbage and immature head cabbage, and in the manual marking, whether the head of the common head cabbage is mature or not can be judged by the texture, the compaction degree and the like of the head of the cabbage, the head of the common head cabbage which is mature is compact, and the head of the cabbage which is immature is loose.
In some embodiments, the image capturing device is a depth camera, and in S400, the method for determining, according to the image, an actual target position of the cabbage head to be picked, which corresponds to the actual target position in the actual coordinate system, includes:
presetting a conversion model, wherein the conversion model is a conversion relation between a virtual position in the image and an actual position in the actual coordinate system;
obtaining a corresponding virtual target position of the cabbage head to be picked in the image, wherein the virtual target position is a head junction center position of the cabbage head to be picked in the image;
and determining the actual target position according to the virtual target position and the conversion relation, wherein the actual target position comprises a plane position and a height position.
Correspondingly, referring to fig. 2, the invention further provides a common head cabbage picking system, which comprises:
a self-propelled chassis 500;
the picking actuator 700 is used for performing picking actions of cutting roots and clamping the cabbage head;
the mechanical arm 600 is arranged on the self-propelled chassis 500, and the picking actuator 700 is arranged on the free end 602 of the mechanical arm 600 and moves along with the free end 602 of the mechanical arm 600;
an image acquisition device (not shown) for acquiring an image of the cabbage field,
a processor (not shown) for acquiring an actual current position of the picking actuator 700 in an actual coordinate system; identifying cabbage heads in the image; selecting a recognized cabbage leaf head in the image as a cabbage leaf head to be picked according to a preset mode; reconstructing a three-dimensional model of the cabbage head to be picked according to the image, and determining an actual target position corresponding to the cabbage head to be picked in an actual coordinate system according to the image; determining the execution action of the mechanical arm and the movement track of the picking actuator according to the actual current position, the actual target position and the dynamic model of the common head cabbage picking device; and after the picking actuator moves to the actual target position, controlling the picking actuator to execute picking action.
In practical implementation, the image acquisition device is arranged on the picking actuator or the self-propelled chassis, and of course, the image acquisition device is preferably arranged on the picking actuator.
Note that, the coordinate system may use a fixed section of the robot arm 600 as an origin, and of course, a certain portion on the self-propelled chassis 500 may be used as an origin.
The first processor may be a central processing unit (Central Processing Unit, abbreviated as CPU), an Application Specific Integrated Circuit (ASIC), a Digital Signal Processor (DSP), a Digital Signal Processing Device (DSPD), a Programmable Logic Device (PLD), a Field Programmable Gate Array (FPGA), a controller, a microcontroller, a microprocessor, or other electronic components.
In some embodiments, referring to fig. 3 in combination, the self-propelled chassis 500 includes a collecting area 501 and a mounting area 502 in a top view, the mechanical arm has a fixed end 601, the fixed end 601 of the mechanical arm 600 is disposed in the mounting area, and the collecting area 501 is used for collecting cabbage leaf heads;
wherein the processor is further configured to: and after the picking action is finished, controlling the mechanical arm 600 to act, enabling the picking actuator 700 to move above the collecting area 501, and controlling the picking actuator 700 to release the cabbage leaf balls.
In some embodiments, referring to fig. 4-11 in combination, a picking implement 700 includes a jig base 100 disposed at a free end 602 of a robotic arm 600 and a blade 200 movably disposed at a bottom region of the jig base 100, the jig base 100 having an open-bottom receiving canister 110, the receiving canister 110 for receiving cabbage heads to be picked from the open-bottom region; blade 200 has a cutting edge facing the open area, and the movable position of blade 200 includes a first position that is blocked in the open area or a second position that is clear of the open area, and blade 200 receives the She Qiuqie pieces of cabbage in the cartridge by moving from the second position to the first position and carries the cut heads of the cabbage in cartridge 110.
In some embodiments, referring to fig. 4 to 11 in combination, the bottom end of the accommodating cylinder 110 is connected with a hollow end plate 120, the number of the blades 200 is at least three, each blade 200 is uniformly distributed along the circumferential direction of the fixture base 100, each blade 200 is tiled on the same plane, and a guiding structure is arranged between each blade 200 and the hollow end plate 120; the picking actuator 700 further comprises a revolving assembly 300 and a driving mechanism 400, wherein the revolving assembly 300 is rotatably arranged on the clamp base 100, a transmission structure is arranged between the revolving assembly 300 and the blade 200, the transmission structure is used for converting revolving power of the revolving assembly 300 into moving power of the blade 200 along the guiding structure, the revolving direction of the revolving assembly 300 comprises a first revolving direction and a second revolving direction opposite to the first revolving direction, and the moving direction of the blade 200 comprises a first moving direction and a second moving direction; the drive mechanism 400 is used to provide motive power for the gyration of the gyration assembly 300.
When the revolving assembly 300 revolves along the first revolving direction, the blades 200 move together along the first moving direction, that is, move from the second position to the first position, for She Qiuqie cabbage in the accommodating cylinder and bear the cabbage leaf heads in the accommodating cylinder; when the swing assembly 300 swings in the second swing direction, each blade 200 moves in the second moving direction to retract, that is, move from the first position to the second position, releasing the cabbage head in the accommodating drum.
Here, the first rotation direction and the second rotation direction both belong to the rotation direction of the first rotation assembly 300, and the first movement direction and the second movement direction belong to the movement direction of the blade 200. The first direction of rotation and the second direction of rotation are opposite: if the first direction of revolution indicates a counterclockwise direction, the second direction of revolution indicates a clockwise direction; if the first direction of revolution indicates a clockwise direction, the second direction of revolution indicates a counterclockwise direction. The first moving direction and the second moving direction are opposite, and the first moving direction and the second moving direction are matched with the guiding direction of the guiding structure.
When picking, firstly controlling the cabbage picking actuator to move to the position above the cabbage leaf heads to be picked, and controlling the clamp to descend so that the cabbage leaf heads to be picked can be covered in the accommodating cylinder 110 in the area where the bottom of the accommodating cylinder 110 is open, and the height positions of the blades 200 correspond to the rhizome parts, at the moment, referring to fig. 4, six blades 200 are arranged, and each blade 200 is kept in an outwards retreated state; then, the driving mechanism 400 is controlled, so that the revolving assembly 300 rotates anticlockwise (under the top view angle) under the action of the driving mechanism 400, and referring to fig. 5, the revolving assembly 300 drives the blades 200 to move inwards to approach each other, and each blade 200 cuts from the root of the cabbage head; after cutting, each blade 200 can support the head of the cabbage in the accommodating tube 110, the whole clamp is moved to move the harvested cabbage to any target position, and the driving mechanism 400 is used for controlling the revolving assembly 300 to rotate clockwise (under the overlook view), so that the blades 200 can move reversely, namely outwards to enable the harvested cabbage to fall at the target position; and moving the clamp again to pick the next common head cabbage. Of course, in some cases, it is also possible that the blades 200 draw together when the swing assembly 300 is rotated clockwise, and the blades 200 retract outwardly when rotated counterclockwise.
When the blades 200 are close to the limit position, the rhizome of the cabbage leaf may be completely cut, or only a part of the rhizome of the cabbage leaf may be cut, and the rest of the non-cut part may be pulled out during the upward movement of the blades 200 along with the jig, according to the different arrangement modes of the cutters.
Of course, in actual implementation, the blades 200 may be rotatably disposed on the fixture base 100 (not shown), and the number of the blades 200 may be one or multiple (not shown); however, when the blade is one piece, no matter the blade moves in a rotating mode or in a moving mode, a larger space is needed outside the accommodating cylinder for the blade to move so as to avoid the cabbage leaves when the cabbage heads are put in or released, on one hand, the vegetable leaves around the cabbage heads can block the movement of the blade to influence the reliability of the picking process, and on the other hand, when the cabbage heads are harvested in a vegetable field with denser common head, the surrounding cabbage heads can be damaged even; when a plurality of blades are arranged and move in a rotating mode, a closed cutting area in the following embodiment is difficult to enclose, and the cutting is realized by moving the plurality of blades, so that the cutting effect is better.
In some embodiments, referring to fig. 4-11 in combination, the guide structure includes a slider 220 disposed on the blade 200 and a guide chute 121 disposed on the hollow end plate 120, the slider 220 being disposed in cooperation within the guide chute 121; the transmission structure comprises a transmission pin 210 arranged on the blade 200 and a U-shaped groove 301 arranged on the rotary assembly 300, wherein the transmission pin 210 is matched and arranged in the U-shaped groove 301, and the extension line of the U-shaped groove 301 is intersected with the rotary central axis of the rotary assembly 300.
In some embodiments, referring to fig. 4-11 in combination, the blade 200 has a first surface 200a facing the hollow endplate 120 and a second surface 200b facing away from the hollow endplate 120, the slider 220 is disposed on the first surface 200a, and the drive pin 210 is disposed on the second surface 200 b. In this way, it is equivalent to distributing the guiding structure and the driving structure on different surfaces by using the thickness of the blade 200 itself, so that the guiding structure and the driving structure do not interfere with each other.
In some embodiments, referring to fig. 4 to 11 in combination, the swing assembly 300 includes an upper swing plate 310 and a lower swing plate 320, the upper swing plate 310 is a hollow plate, the upper swing plate 310 is concentrically fitted around the accommodating cylinder 110, and the driving mechanism 400 is disposed between the accommodating cylinder 110 and the upper swing plate 310; the lower rotating plate 320 is concentrically arranged with the upper rotating plate 310, and the upper rotating plate 310 is fixedly connected with the lower rotating plate 320; wherein the hollow end plate 120 is positioned between the upper and lower turn plates 310 and 320 such that the entire turn assembly 300 is hung on the hollow end plate 120, and the lower turn plate 320 is provided with a hollow area corresponding to the open area, and the blade 200 is positioned between the hollow end plate 120 and one of the turn plates.
At this time, if the blades are positioned between the hollow end plate and the lower rotating plate, the upper rotating plate 310, the hollow end plate 120, the blades 200, and the lower rotating plate 320 are stacked and distributed from top to bottom. In this way, the hollow end plate 120 can be used to support the swing assembly 300 without additional parts, which is advantageous for reducing the cost. And the hollow end plate 120 is placed between the two swing plates by combining the upper swing plate 310 and the lower swing plate 320, the entire swing assembly 300 can be reliably positioned.
In some embodiments, referring to fig. 4 to 11 in combination, the outer contour of the blade 200 includes a cutting edge 201 corresponding to the cutting edge and a back edge 202 forming an included angle with the cutting edge 201, the intersection of the cutting edge 201 and the back edge 202 is a tip of the blade 200, and the limit travel position of each tip gathering inwards coincides with the rotation central axis of the fixture base 100; the edge 201 of any blade 200 is always in abutment or contact with the back 202 of an adjacent blade 200, such that the edge of each blade 200 encloses a closed cutting area Q. By the structure, in the process that each blade 200 moves along the guiding direction under the drive of the rotary component 300, each blade 200 can always enclose a closed cutting area, in the cutting process, the roots and stems of the cabbage leaf heads are uniformly cut everywhere, and the phenomenon of clamping stagnation in the cutting process is avoided. When the cutting edge D of each blade 200 coincides with the center axis of rotation, the closed area between the blades 200 disappears, and the root of the cabbage head can be completely cut off, so that the root is cut off without drawing in the subsequent step, and the blade 200 does not need to bear the drawing force of the cantilever, thereby being more advantageous in improving the life of the blade 200, compared with the half-cut method.
In some embodiments, referring to fig. 7, the upper rotating plate 310 and the lower rotating plate 320 are connected by a connecting portion 321, the connecting portion 321 is uniformly distributed along the circumferential direction of the lower rotating plate 320, and a dodging space 300a for dodging the blade 200 is formed between two adjacent connecting portions 321 along the circumferential direction; referring to fig. 8, the blade 200 is also provided with an arc profile 203 for avoiding the connecting portion 321, the arc profile 203 is connected between the cutting edge 201 and the back edge 202, and when the stroke position of the blade 200 is an outward-retracted limit position, a part of the arc profile 203 extends out of the avoidance space 300a and extends out of the swivel assembly 300. The avoidance space 300a can avoid the cutter, is convenient for observing the action process of the cutter, and is beneficial to timely finding out the abnormality when the cutter is abnormal in action; the arc profile 203 of the cutter enables the local part of the cutter penetrating out of the avoidance space 300a to rapidly leave the blade when touching the blade at the periphery of the cabbage head, reduces the impact of the blade striking the cutter, and ensures the harvesting reliability. In addition, the partial extension of the knife out of the relief space 300a is beneficial to keeping the overall swing assembly 300 small in size and reducing interference of the clamp with the external blade during harvesting. In fig. 7, the connecting portion 321 is integrally formed with the lower swing plate 320, and the connecting portion 321 and the upper swing plate 310 are connected by a fastener such as a bolt.
In some embodiments, referring to fig. 4 and 5, the driving mechanism 400 includes a motor 410, a driving gear 420, and a driven rack 430, the motor 410 is mounted on an outer wall of the receiving cylinder 110, the driving gear 420 is connected with the motor 410, the driven rack 430 is disposed on the swing assembly 300, and the driven rack 430 is engaged with the driving gear 420. In actual implementation, the driven rack 430 may also be replaced with a driven gear ring.
In fig. 4 and 5, the driven rack 430 is disposed on the upper swing plate 310 of the swing assembly 300.
When the picking action is required to be executed, the processor sends an instruction to the motor, so that the picking action is controlled.
In some embodiments, the image capturing device is disposed on the top (not shown) in the accommodating barrel 110, and the image capturing device is used for capturing an image of the cabbage field, and referring to fig. 6, the outer wall of the accommodating barrel 110 is uniformly provided with a hollow area 110a, and the hollow area 110a can provide suitable external conditions for the image capturing device, so that external light can smoothly enter the accommodating barrel 110. Of course, in practical implementation, the outer wall of the accommodating cylinder 110 may not be hollowed out.
In the description of the present invention, unless explicitly stated and limited otherwise, the "upper" or "lower" of a first feature in a second feature may include the first and second features being in direct contact, or may include the first and second features not being in direct contact but being in contact with each other through another feature therebetween.
In the description of the invention, the singular forms "a", "an" and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will be further understood that the terms "comprises" and/or "comprising," when used in this specification, specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof.
The above embodiments are merely illustrative of the principles of the present invention and its effectiveness, and are not intended to limit the invention. Modifications and variations may be made to the above-described embodiments by those skilled in the art without departing from the spirit and scope of the invention. Accordingly, it is intended that all equivalent modifications and variations of the invention be covered by the claims, which are within the ordinary skill of the art, be within the spirit and scope of the present disclosure.
Claims (2)
1. A head cabbage harvesting system, comprising:
a self-propelled chassis;
the picking actuator is used for executing picking actions of cutting roots and clamping the cabbage heads;
the picking actuator is arranged on the free end of the mechanical arm and moves along with the free end of the mechanical arm;
the image acquisition device is used for acquiring an image of the common head cabbage vegetable field;
a processor for acquiring an actual current position of the picking actuator in an actual coordinate system; identifying cabbage heads in the image; selecting a recognized cabbage leaf head in the image as a cabbage leaf head to be picked according to a preset mode; reconstructing a three-dimensional model of the cabbage head to be picked according to the image, and determining an actual target position corresponding to the cabbage head to be picked in an actual coordinate system according to the image; determining the execution action of the mechanical arm and the movement track of the picking actuator according to the actual current position, the actual target position and the dynamic model of the common head cabbage picking device; after the picking actuator moves to the actual target position, controlling the picking actuator to execute picking action;
the picking actuator comprises a clamp base arranged at the free end of the mechanical arm and a blade movably arranged at the bottom area of the clamp base, wherein the clamp base is provided with a containing cylinder with an open bottom, and the containing cylinder is used for placing cabbage leaf heads to be picked from the bottom open area; the blade is provided with a cutting edge facing the open area, the movable position of the blade comprises a first position blocking the open area and a second position avoiding the open area, and the blade is used for accommodating She Qiuqie cabbages in the barrel by moving from the second position to the first position and carrying the head of the cabbages with the cut roots in the barrel;
the method for identifying the cabbage leaf heads in the image comprises the following steps: inputting the image into a neural network after training, and outputting a recognition result, wherein the recognition result comprises the region of the cabbage head in the image;
the training method of the neural network model after training comprises the following steps:
acquiring an initial image sample set, wherein the initial image sample set comprises a plurality of images, and each image contains a common head cabbage;
marking the images in the initial image sample set to obtain a training sample set, wherein marking contents of each image comprise the region of the cabbage head in the image, the type of the common head cabbage and whether the common head cabbage is mature;
inputting the training sample set into a pre-trained neural network for training, and forming the trained neural network after training is completed;
the image acquisition device is a depth camera, and the method for determining the corresponding actual target position of the cabbage head to be picked in the actual coordinate system according to the image comprises the following steps:
presetting a conversion model, wherein the conversion model is a conversion relation between a virtual position in the image and an actual position in the actual coordinate system;
obtaining a corresponding virtual target position of the cabbage head to be picked in the image, wherein the virtual target position is a head junction center position of the cabbage head to be picked in the image;
and determining the actual target position according to the virtual target position and the conversion relation, wherein the actual target position comprises a plane position and a height position.
2. The head cabbage picking system of claim 1, wherein the self-propelled chassis includes a collection area and a mounting area in a top view, the robotic arm having a fixed end, the fixed end of the robotic arm being disposed in the mounting area, the collection area for collecting head cabbage leaves;
the processor is further used for controlling the mechanical arm to act after the picking action is finished, enabling the picking actuator to move to the position above the collecting area and controlling the picking actuator to release the cabbage leaf heads.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210329799.3A CN114885672B (en) | 2022-03-31 | 2022-03-31 | Common head cabbage picking system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210329799.3A CN114885672B (en) | 2022-03-31 | 2022-03-31 | Common head cabbage picking system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114885672A CN114885672A (en) | 2022-08-12 |
| CN114885672B true CN114885672B (en) | 2024-02-09 |
Family
ID=82714733
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210329799.3A Active CN114885672B (en) | 2022-03-31 | 2022-03-31 | Common head cabbage picking system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114885672B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101683037A (en) * | 2008-09-26 | 2010-03-31 | 中国农业大学 | Controller for fruit picking robot |
| CN102113434A (en) * | 2011-01-14 | 2011-07-06 | 江苏大学 | Picking method of picking robot under fruit oscillation condition |
| CN103091193A (en) * | 2013-02-21 | 2013-05-08 | 江苏丘陵地区镇江农业科学研究所 | Method and device for rapidly measuring compactness of head of head cabbage |
| CN110089350A (en) * | 2018-01-31 | 2019-08-06 | 上海沃迪智能装备股份有限公司 | A kind of Mushroom Picking Robot system and picking method |
| CN111837640A (en) * | 2020-06-28 | 2020-10-30 | 重庆文理学院 | Hillside orchard intelligence picking robot based on visual identification |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| GB201721595D0 (en) * | 2017-12-21 | 2018-02-07 | Kms Projects Ltd | Harvesting of crops |
-
2022
- 2022-03-31 CN CN202210329799.3A patent/CN114885672B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101683037A (en) * | 2008-09-26 | 2010-03-31 | 中国农业大学 | Controller for fruit picking robot |
| CN102113434A (en) * | 2011-01-14 | 2011-07-06 | 江苏大学 | Picking method of picking robot under fruit oscillation condition |
| CN103091193A (en) * | 2013-02-21 | 2013-05-08 | 江苏丘陵地区镇江农业科学研究所 | Method and device for rapidly measuring compactness of head of head cabbage |
| CN110089350A (en) * | 2018-01-31 | 2019-08-06 | 上海沃迪智能装备股份有限公司 | A kind of Mushroom Picking Robot system and picking method |
| CN111837640A (en) * | 2020-06-28 | 2020-10-30 | 重庆文理学院 | Hillside orchard intelligence picking robot based on visual identification |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114885672A (en) | 2022-08-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108377740B (en) | Automatic fruit picking equipment | |
| CN107371612B (en) | A kind of strawberry picking electric tool | |
| US20100292841A1 (en) | Robot with 3d grasping capability | |
| CN210124126U (en) | Foldable and extensible head for agave harvest | |
| CN111758397B (en) | Intelligent pepper picking device based on visual identification | |
| CN208079851U (en) | A kind of automatic seed harvester of fruit | |
| CN114902866B (en) | Common head cabbage picking device and picking method | |
| CN114885672B (en) | Common head cabbage picking system | |
| KR102438342B1 (en) | End effector of robot | |
| CN111919583A (en) | Weeding and soil loosening robot for gardens | |
| CA2747098A1 (en) | Tete d'ebranchage-tronconnage | |
| CN108450436A (en) | A kind of facility plastic greenhouse deinsectization robot | |
| CN108156952A (en) | A kind of fruit/vegetable harvesting device | |
| CN108575129A (en) | A kind of facility plastic greenhouse weed-eradicating robot | |
| CN116276976A (en) | Chilli picking manipulator based on visual recognition and end execution mechanism thereof | |
| CN209999226U (en) | manipulator for picking berries planted in overhead manner | |
| CN209403069U (en) | A kind of fruit and vegetable intelligence picker system | |
| KR102511629B1 (en) | End Effector for Crop Implements | |
| CN207612640U (en) | A kind of miniature hot pickled mustard tuber harvester | |
| CN114902865A (en) | Executor is picked to common head cabbage | |
| CN109937698A (en) | A kind of booster type fruit picker and its application method | |
| CN113728798A (en) | Multi-joint accurate positioning safflower harvesting mechanical arm and harvesting method | |
| CN113366973B (en) | Automatic pineapple picking robot capable of keeping fruit buds and application thereof | |
| CN210352209U (en) | Fruit and vegetable picking manipulator | |
| CN112715144A (en) | Rose harvesting robot device and method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |