CN112136506A - Robot arm device with fruit maturity distinguishing function - Google Patents
Robot arm device with fruit maturity distinguishing function Download PDFInfo
- Publication number
- CN112136506A CN112136506A CN202011029395.XA CN202011029395A CN112136506A CN 112136506 A CN112136506 A CN 112136506A CN 202011029395 A CN202011029395 A CN 202011029395A CN 112136506 A CN112136506 A CN 112136506A
- Authority
- CN
- China
- Prior art keywords
- fruit
- steering engine
- flexible
- mechanical arm
- paw
- 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.)
- Pending
Links
Images
Classifications
-
- A—HUMAN NECESSITIES
- A01—AGRICULTURE; FORESTRY; ANIMAL HUSBANDRY; HUNTING; TRAPPING; FISHING
- A01D—HARVESTING; MOWING
- A01D46/00—Picking of fruits, vegetables, hops, or the like; Devices for shaking trees or shrubs
- A01D46/30—Robotic devices for individually picking crops
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01L—MEASURING FORCE, STRESS, TORQUE, WORK, MECHANICAL POWER, MECHANICAL EFFICIENCY, OR FLUID PRESSURE
- G01L5/00—Apparatus for, or methods of, measuring force, work, mechanical power, or torque, specially adapted for specific purposes
- G01L5/0061—Force sensors associated with industrial machines or actuators
- G01L5/0076—Force sensors associated with manufacturing machines
- G01L5/009—Force sensors associated with material gripping devices
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N2021/8466—Investigation of vegetal material, e.g. leaves, plants, fruits
Landscapes
- Analytical Chemistry (AREA)
- Chemical & Material Sciences (AREA)
- Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Theoretical Computer Science (AREA)
- Robotics (AREA)
- Multimedia (AREA)
- Environmental Sciences (AREA)
- Health & Medical Sciences (AREA)
- Biochemistry (AREA)
- General Health & Medical Sciences (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Harvesting Machines For Specific Crops (AREA)
Abstract
The invention relates to a robot arm device with a fruit maturity distinguishing function, belongs to the technical field of agricultural robots, and solves the problems that a picking robot in the prior art has poor distinguishing capability on apples with different maturity and is easy to damage fruit peels in a picking process; the fruit picking device comprises a mechanical arm mechanism, a flexible paw mechanism, an RGBD camera and a console, wherein the mechanical arm mechanism comprises a first mechanical arm and a second mechanical arm, the flexible paw mechanism comprises a flexible finger joint mechanism and a paw steering engine for controlling the grabbing action of the flexible finger joint mechanism, the flexible finger joint mechanism comprises three flexible fingers in an enveloping shape, and one side of each flexible finger, which is in contact with a fruit, is provided with a flexible film pressure sensor; the console comprises a control module and a fruit maturity identification module. The invention not only can accurately identify mature and pluckable fruits, but also can ensure that the fruit peel is not damaged when the apples are plucked, thereby greatly saving the waste caused by plucking the immature apples.
Description
Technical Field
The invention belongs to the technical field of agricultural robots, and particularly relates to a robot arm device with a fruit maturity identification function.
Background
The apple yield and the cultivation area in China are the first in the world, and the apple is a traditional dominant export product. In apple production, picking is the most laborious and time-consuming link. At present, the apple picking operation is mainly completed manually, a large amount of labor is needed, and the problems of low picking efficiency, high cost, large labor amount and the like exist along with the continuous deepening of the aging of the population of the society. In general, in the mechanical picking of apples, fruits on apple trees fall off by vibration, and even a method of pulling out the fruits in a large area is used, the specific differences of ripeness, size and the like of the fruits cannot be met, so that the quality of the fruits is greatly influenced. With the development of computer technology, artificial intelligence technology and automatic control technology, robots are gradually replacing manual picking operations, which makes apple picking robots an important requirement for modern production.
The manipulator is picked to apple among the prior art structure complicacy, high in production cost, and the manipulator causes the peel damaged or even destroys the pulp easily when picking the apple, causes serious influence to the quality of fruit, and traditional apple picking manipulator intelligent degree is lower simultaneously, does not possess the ability of discerning the apple maturity, picks immature fruit easily, so not only influences the apple and picks efficiency, can cause the loss to the trade company of planting the fruit tree simultaneously.
Disclosure of Invention
For solving the problem that the structure is complicated, the production cost is high and cause the peel damage or even destroy the pulp easily that the apple picking manipulator exists among the prior art, cause serious influence to the quality of fruit, do not possess the ability of discerning the apple maturity, pick immature fruit easily, provide a robot arm device with fruit maturity and distinguish the function, the device can be applied to the picking robot field of fruits such as apple.
In order to solve the problems, the invention adopts the following technical scheme:
a robot arm device with a fruit maturity identification function comprises a mechanical arm mechanism, a flexible paw mechanism, an RGBD camera and a console, wherein the mechanical arm mechanism comprises a first mechanical arm and a second mechanical arm;
the first end of the first mechanical arm is fixedly connected with an output shaft of a first steering engine arranged on a mechanical arm tower, the second end of the first mechanical arm is connected with the first end of the second mechanical arm through a first mechanical joint, the second end of the second mechanical arm is connected with the flexible paw mechanism through a second mechanical joint, the first mechanical joint and the second mechanical joint are respectively provided with a second steering engine and a third steering engine, and the first steering engine, the second steering engine and the third steering engine are respectively and electrically connected with the control console;
the flexible paw mechanism comprises a flexible finger joint mechanism and a paw steering engine for controlling the grabbing action of the flexible finger joint mechanism, the flexible finger joint mechanism comprises three flexible fingers in an envelope shape, a flexible film pressure sensor is arranged on one side, in contact with fruits, of each flexible finger, and the flexible film pressure sensors and the paw steering engine are respectively and electrically connected with the console;
the RGBD camera is fixedly arranged on a cloud deck, the cloud deck is connected with the mechanical arm tower platform through a support, and the RGBD camera and the cloud deck are respectively and electrically connected with the control console;
the control console comprises a control module and a fruit maturity distinguishing module, the fruit maturity distinguishing module utilizes a trained LeNet-5 convolutional neural network model to distinguish fruit pictures collected by the RGBD camera and sends recognition results to the control module, the control module controls the first steering engine, the second steering engine, the third steering engine and the paw steering engine to rotate according to the recognition results and the fruit pictures collected by the RGBD camera, grabbing actions of target ripe fruits are completed, meanwhile, the control module receives sensing data sent by the flexible film pressure sensor and adjusts rotation of the paw steering engine according to the sensing data.
Compared with the prior art, the invention has the following beneficial effects:
1. the invention provides a robot arm device with a fruit maturity identification function, which achieves the purpose of not damaging peels and pulps while realizing picking of fruits such as apples and the like, and can identify whether the fruits are mature on site, thereby solving the problem that a picking robot in the prior art is easy to damage the fruits and even destroy the pulps in the picking process;
2. the three flexible fingers of the flexible finger joint mechanism are integrally enveloped, so that fruits are easy to grab, meanwhile, the flexible film pressure sensor can timely feed back force during picking without damaging peels and pulps, and compared with other pressure sensors, the flexible finger joint mechanism is higher in sensing precision, sensitive, thin and flexible in shape, more suitable for flexible paws, capable of ensuring the quality of the fruits and prolonging the service life of the flexible paws;
3. the fruit maturity distinguishing module adopts the design of a LeNet-5 convolutional neural network model built under a Tensorflow frame, the model needs to collect a proper data set on site and perform noise reduction treatment, so that the built neural network model is more accurate, the success rate is higher when identifying the on-site apple maturity, the number of layers of a traditional convolutional neural network structure is reduced while the accuracy of training is ensured, the calculation speed is accelerated, and the timeliness is better.
Drawings
FIG. 1 is a schematic block diagram of a robotic arm apparatus having fruit ripeness discrimination in accordance with the present invention;
FIG. 2 is a schematic structural diagram of a robot arm device with fruit ripeness discrimination function according to the present invention;
FIG. 3 is a partially enlarged schematic view of a flexible gripper mechanism in a robotic arm assembly having fruit ripeness discrimination in accordance with the present invention;
the reference numerals include:
1. a flexible gripper mechanism; 2. an RGBD camera; 3. a first robot arm; 4. a second mechanical arm; 5. a robotic arm tower; 6. a paw steering engine; 7. a flexible finger; 8. a flexible membrane pressure sensor; 9. a holder; 10. and (4) a bracket.
Detailed Description
The invention overcomes the defects in the prior art, provides the robot arm device with the function of identifying the maturity of fruits, not only can accurately identify the ripe and pickable fruits, but also ensures that the fruit peel is not damaged when the fruits are picked, greatly saves the waste caused by picking the unripe fruits, is suitable for picking the fruits including but not limited to apples, and has the advantages of high picking efficiency, good quality and the like. The technical solution of the present invention will be described in detail with reference to the accompanying drawings and preferred embodiments.
It should be noted that the embodiments and features of the embodiments may be combined with each other without conflict.
In the description of the present invention, it is to be understood that the terms "center", "longitudinal", "lateral", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", and the like, indicate orientations or positional relationships based on those shown in the drawings, and are used only for convenience in describing the present invention and for simplicity in description, and do not indicate or imply that the referenced devices or elements must have a particular orientation, be constructed and operated in a particular orientation, and thus, are not to be construed as limiting the present invention. Furthermore, the terms "first", "second", etc. are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first," "second," etc. may explicitly or implicitly include one or more of that feature. In the description of the present invention, "a plurality" means two or more unless otherwise specified.
In the description of the present invention, it should be noted that, unless otherwise explicitly specified or limited, the terms "mounted," "connected," and "connected" are to be construed broadly, e.g., as meaning either a fixed connection, a removable connection, or an integral connection; can be mechanically or electrically connected; they may be connected directly or indirectly through intervening media, or they may be interconnected between two elements. The specific meaning of the above terms in the present invention can be understood by those of ordinary skill in the art through specific situations.
In one embodiment, as shown in fig. 1-3, the present invention provides a robotic arm device with fruit ripeness discrimination, the device comprising a robotic arm mechanism, a flexible gripper mechanism 1, an RGBD camera 2, and a console, wherein the robotic arm mechanism comprises a first robotic arm 3 and a second robotic arm 4.
Specifically, a first end of a first mechanical arm 3 is fixedly connected with an output shaft of a first steering engine, the first steering engine is fixedly installed on a mechanical arm tower 5, and the first end of the first mechanical arm 3 can rotate relative to the mechanical arm tower 5; the second end of the first mechanical arm 3 is connected with the first end of the second mechanical arm 4 through a first mechanical joint, and the first mechanical joint is provided with a second steering engine, so that the first end of the second mechanical arm 4 can rotate relative to the second end of the first mechanical arm 3; the second end of the second mechanical arm 4 is connected with the flexible paw mechanism 1 through a second mechanical joint, and the second mechanical joint is provided with a third steering engine, so that the flexible paw mechanism 1 can rotate relative to the second end of the second mechanical arm 4; the first steering engine, the second steering engine and the third steering engine are respectively electrically connected with the console, and the console can drive and control the rotation of the first steering engine, the second steering engine and the third steering engine, so that the driving of the first mechanical arm 3, the second mechanical arm 4 and the flexible paw mechanism 1 is realized.
Referring to fig. 3, the flexible paw mechanism 1 comprises a flexible finger joint mechanism and a paw steering engine 6 for controlling the grabbing action of the flexible finger joint mechanism, wherein the flexible finger joint mechanism comprises three flexible fingers 7 in an enveloping shape, a flexible film pressure sensor 8 is arranged on one side of each flexible finger 7, which is in contact with fruits, and the flexible film pressure sensor 8 and the paw steering engine 6 are respectively and electrically connected with the console. The three enveloping flexible fingers 7 may have the same or different structure, and preferably, in order to more easily grip the fruit, one flexible finger 7 of the three enveloping flexible fingers 7 is arc-shaped, and the other two flexible fingers 7 are fin-shaped, as shown in fig. 3. The flexible film pressure sensor 8 in this embodiment may be implemented by a flexible film pressure sensor in the prior art, and is not described herein again.
Still referring to fig. 2, the RGBD camera 2 is fixedly mounted on the pan/tilt head 9, the pan/tilt head 9 is connected with the robot tower 5 through the support 10, and the RGBD camera 2 and the pan/tilt head 9 are electrically connected with the console respectively. The RGBD camera 2 is used for collecting fruit pictures around the flexible gripper mechanism 1 in real time in the fruit picking process, and sending the collected fruit pictures to the console for processing by the console. The console can control the movement of the pan-tilt 9, thereby adjusting the view of the RGBD camera 2.
The control console in this embodiment can be implemented by a microcomputer, and specifically, the control console includes a control module and a fruit maturity identification module, where the fruit maturity identification module identifies a fruit picture acquired by the RGBD camera 2 by using a trained LeNet-5 convolutional neural network model to obtain an identification result and sends the identification result to the control module; when the recognition result is ripe fruit, the control module determines the position information of the ripe fruit according to a fruit picture acquired by the RGBD camera 2, wherein the mode of determining the position information of the ripe fruit according to the fruit picture can be realized by adopting a fruit position determination method used by a picking robot in the prior art, the position information is expressed into ASCII codes, the ASCII codes are transmitted to a corresponding processing chip through UARTO serial port communication, and the processing chip controls each steering engine on the mechanical arm mechanism and the flexible paw mechanism 1 according to the received ASCII codes, so that the grabbing action of the ripe fruit, namely the target ripe fruit, is completed; the control module controls the first steering engine according to the recognition result and the fruit picture collected by the RGBD camera 2, the second steering engine, the third steering engine and the paw steering engine 6 rotate, when the grabbing action of the target ripe fruit is completed, the control module is also used for receiving sensing data sent by the flexible film pressure sensor 8, and the rotation of the paw steering engine 6 is adjusted according to the sensing data, so that the grabbing force of the flexible paw mechanism 1 is adjusted, the damage to the fruit caused by the fact that the grabbing force of the flexible paw mechanism 1 is too large or too small is avoided, the feedback of the force in the picking process is timely obtained through the flexible film pressure sensor 8, and the quality of the fruit is guaranteed when the grabbing.
Further, the trained LeNet-5 convolutional neural network model in this embodiment is obtained through the following steps:
the method comprises the following steps: obtaining pictures of the same type of fruits, labeling the pictures of the ripe fruits, and making to obtain a training data set; preferably, the accuracy of the training data set reaches more than 95 percent, and the training data set is qualified;
step two: carrying out noise reduction processing on the pictures in the training data set;
step three: building a LeNet-5 convolutional neural network model by using a Tensorflow framework;
step four: and training the built LeNet-5 convolutional neural network model by using the training data set subjected to noise reduction processing to obtain the trained LeNet-5 convolutional neural network model.
Furthermore, the LeNet-5 convolutional neural network model built in the third step has a specific structure as follows:
the first layer, convolutional layer, the size of the convolutional kernel is 100x100x64, the step size is 1;
the second layer, the pooling layer, with a pooling interval of 50x50, with a step length of 1;
the third layer, convolutional layer, the size of convolutional kernel is 50x50x128, step size is 1;
a fourth layer, a pooling layer, with a pooling interval of 25x25 with a step size of 1;
a fifth layer, fully connected layer 1;
sixth layer, full link layer 2.
Further, when the fruit maturity identification module identifies the fruit picture acquired by the RGBD camera 2 by using the trained LeNet-5 convolutional neural network model, the method comprises the following steps:
acquiring a fruit picture acquired by the RGBD camera 2;
carrying out noise reduction processing on the obtained fruit picture;
and identifying the fruit picture subjected to noise reduction treatment by using the trained LeNet-5 convolutional neural network model.
Further, the control console further comprises an electricity storage module, and the electricity storage module is used for supplying power to the RGBD camera 2, the first steering engine, the second steering engine, the third steering engine, the paw steering engine 6, the control console and the flexible film pressure sensor 8.
Compared with the prior art, the invention has the following beneficial effects:
1. the invention provides a robot arm device with a fruit maturity identification function, which achieves the purpose of not damaging peels and pulps while realizing picking of fruits such as apples and the like, and can identify whether the fruits are mature on site, thereby solving the problem that a picking robot in the prior art is easy to damage the fruits and even destroy the pulps in the picking process;
2. the three flexible fingers of the flexible finger joint mechanism are integrally enveloped, so that fruits are easy to grab, meanwhile, the flexible film pressure sensor can timely feed back force during picking without damaging peels and pulps, and compared with other pressure sensors, the flexible finger joint mechanism is higher in sensing precision, sensitive, thin and flexible in shape, more suitable for flexible paws, capable of ensuring the quality of the fruits and prolonging the service life of the flexible paws;
3. the fruit maturity distinguishing module adopts the design of a LeNet-5 convolutional neural network model built under a Tensorflow frame, the model needs to collect a proper data set on site and perform noise reduction treatment, so that the built neural network model is more accurate, the success rate is higher when identifying the on-site apple maturity, the number of layers of a traditional convolutional neural network structure is reduced while the accuracy of training is ensured, the calculation speed is accelerated, and the timeliness is better.
The technical features of the embodiments described above may be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the embodiments described above are not described, but should be considered as being within the scope of the present specification as long as there is no contradiction between the combinations of the technical features.
The above-mentioned embodiments only express several embodiments of the present invention, and the description thereof is more specific and detailed, but not construed as limiting the scope of the invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the inventive concept, which falls within the scope of the present invention. Therefore, the protection scope of the present patent shall be subject to the appended claims.
Claims (7)
1. A robot arm device with a fruit maturity identification function is characterized by comprising a mechanical arm mechanism, a flexible paw mechanism (1), an RGBD camera (2) and a control console, wherein the mechanical arm mechanism comprises a first mechanical arm (3) and a second mechanical arm (4);
the first end of the first mechanical arm (3) is fixedly connected with an output shaft of a first steering engine arranged on a mechanical arm tower (5), the second end of the first mechanical arm (3) is connected with the first end of the second mechanical arm (4) through a first mechanical joint, the second end of the second mechanical arm (4) is connected with the flexible paw mechanism (1) through a second mechanical joint, the first mechanical joint and the second mechanical joint are respectively provided with a second steering engine and a third steering engine, and the first steering engine, the second steering engine and the third steering engine are respectively and electrically connected with the control console;
the flexible paw mechanism (1) comprises a flexible finger joint mechanism and a paw steering engine (6) used for controlling grabbing actions of the flexible finger joint mechanism, the flexible finger joint mechanism comprises three flexible fingers (7) in an enveloping shape, a flexible film pressure sensor (8) is arranged on one side, in contact with fruits, of each flexible finger (7), and the flexible film pressure sensors (8) and the paw steering engine (7) are respectively and electrically connected with the console;
the RGBD camera (2) is fixedly arranged on a cloud deck (9), the cloud deck (9) is connected with the mechanical arm tower (5) through a support (10), and the RGBD camera (2) and the cloud deck (9) are respectively and electrically connected with the control console;
the control console comprises a control module and a fruit maturity distinguishing module, the fruit maturity distinguishing module utilizes a trained LeNet-5 convolutional neural network model to distinguish fruit pictures collected by the RGBD camera (2) and sends recognition results to the control module, the control module controls the first steering engine, the second steering engine, the third steering engine and the paw steering engine (6) to rotate according to the recognition results and the fruit pictures collected by the RGBD camera (2) to complete grabbing actions of target ripe fruits, and meanwhile the control module receives sensing data sent by the flexible film pressure sensor (8) and adjusts rotation of the paw steering engine (6) according to the sensing data.
2. The robotic arm device with fruit ripeness discrimination capability according to claim 1, wherein the trained LeNet-5 convolutional neural network model is obtained by:
the method comprises the following steps: obtaining pictures of the same type of fruits, labeling the pictures of the ripe fruits, and making to obtain a training data set;
step two: performing noise reduction processing on the pictures in the training data set;
step three: building a LeNet-5 convolutional neural network model by using a Tensorflow framework;
step four: and training the built LeNet-5 convolutional neural network model by using the training data set subjected to noise reduction processing to obtain the trained LeNet-5 convolutional neural network model.
3. The robot arm device with the fruit maturity identification function according to claim 2, wherein the built LeNet-5 convolutional neural network model has a specific structure as follows:
the first layer, convolutional layer, the size of the convolutional kernel is 100x100x64, the step size is 1;
the second layer, the pooling layer, with a pooling interval of 50x50, with a step length of 1;
the third layer, convolutional layer, the size of convolutional kernel is 50x50x128, step size is 1;
a fourth layer, a pooling layer, with a pooling interval of 25x25 with a step size of 1;
a fifth layer, fully connected layer 1;
sixth layer, full link layer 2.
4. A robot arm device having a fruit ripeness discriminating function according to claim 2 or 3,
the accuracy of the training data set reaches more than 95 percent, and the training data set is qualified.
5. The robot arm device with fruit maturity discrimination function according to claim 1 or 2, wherein said fruit maturity discrimination module, when using trained LeNet-5 convolutional neural network model to identify the fruit pictures collected by said RGBD camera (2), comprises the following steps:
acquiring a fruit picture acquired by the RGBD camera (2);
carrying out noise reduction processing on the obtained fruit picture;
and identifying the fruit picture subjected to noise reduction treatment by using the trained LeNet-5 convolutional neural network model.
6. The robot arm device with fruit ripeness discriminating function according to claim 1 or 2,
one of the flexible fingers (7) is arc-shaped, and the other two flexible fingers (7) are fin-shaped.
7. The robot arm device with fruit ripeness discriminating function according to claim 1 or 2,
the console further comprises an electricity storage module, and the electricity storage module is used for supplying power to the RGBD camera (2), the first steering engine, the second steering engine, the third steering engine, the paw steering engine (6), the console and the flexible film pressure sensor (8).
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011029395.XA CN112136506A (en) | 2020-09-27 | 2020-09-27 | Robot arm device with fruit maturity distinguishing function |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011029395.XA CN112136506A (en) | 2020-09-27 | 2020-09-27 | Robot arm device with fruit maturity distinguishing function |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112136506A true CN112136506A (en) | 2020-12-29 |
Family
ID=73894796
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011029395.XA Pending CN112136506A (en) | 2020-09-27 | 2020-09-27 | Robot arm device with fruit maturity distinguishing function |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112136506A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112930868A (en) * | 2021-03-30 | 2021-06-11 | 南京农业大学 | Flexible grasping and sucking type picking end effector for small spherical fruits and picking method thereof |
| US20210337734A1 (en) * | 2018-10-08 | 2021-11-04 | Advanced Farm Technologies, Inc. | Autonomous crop harvester |
| CN113602799A (en) * | 2021-08-05 | 2021-11-05 | 西南科技大学 | Airport luggage case carrying system and control method thereof |
| CN116584310A (en) * | 2023-06-07 | 2023-08-15 | 农业农村部南京农业机械化研究所 | Black fungus picking device |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20160073584A1 (en) * | 2014-09-12 | 2016-03-17 | Washington State University | Robotic systems, methods, and end-effectors for harvesting produce |
| CN106233937A (en) * | 2016-05-10 | 2016-12-21 | 西北农林科技大学 | A kind of array extension type mechanical arm kiwifruit fruit picking robot |
| CN107593113A (en) * | 2017-09-21 | 2018-01-19 | 昆明理工大学 | A kind of intelligent fruit picking robot based on machine vision |
| CN108764076A (en) * | 2018-05-15 | 2018-11-06 | 西北农林科技大学 | A kind of kiwifruit fruit group's multiple-target identification method for multi-arm picking robot |
| CN109479522A (en) * | 2018-12-27 | 2019-03-19 | 甘肃农业大学 | A kind of fruit picking robot and its picking method |
| CN210819533U (en) * | 2019-10-29 | 2020-06-23 | 西北农林科技大学 | Transfer robot cultivated in a pot |
| CN112809703A (en) * | 2021-02-10 | 2021-05-18 | 中国人民解放军国防科技大学 | Bottom sowing sea cucumber catching robot based on ESRGAN enhanced super-resolution and CNN image recognition |
-
2020
- 2020-09-27 CN CN202011029395.XA patent/CN112136506A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20160073584A1 (en) * | 2014-09-12 | 2016-03-17 | Washington State University | Robotic systems, methods, and end-effectors for harvesting produce |
| CN106233937A (en) * | 2016-05-10 | 2016-12-21 | 西北农林科技大学 | A kind of array extension type mechanical arm kiwifruit fruit picking robot |
| CN107593113A (en) * | 2017-09-21 | 2018-01-19 | 昆明理工大学 | A kind of intelligent fruit picking robot based on machine vision |
| CN108764076A (en) * | 2018-05-15 | 2018-11-06 | 西北农林科技大学 | A kind of kiwifruit fruit group's multiple-target identification method for multi-arm picking robot |
| CN109479522A (en) * | 2018-12-27 | 2019-03-19 | 甘肃农业大学 | A kind of fruit picking robot and its picking method |
| CN210819533U (en) * | 2019-10-29 | 2020-06-23 | 西北农林科技大学 | Transfer robot cultivated in a pot |
| CN112809703A (en) * | 2021-02-10 | 2021-05-18 | 中国人民解放军国防科技大学 | Bottom sowing sea cucumber catching robot based on ESRGAN enhanced super-resolution and CNN image recognition |
Non-Patent Citations (2)
| Title |
|---|
| 刘树春等: "《深度实践OCR 基于深度学习的文字识别》", 31 May 2020, 机械工业出版社 * |
| 谢能付等: "《智能农业》", 30 June 2020, 中国铁道出版社有限公司 * |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20210337734A1 (en) * | 2018-10-08 | 2021-11-04 | Advanced Farm Technologies, Inc. | Autonomous crop harvester |
| US12004451B2 (en) * | 2018-10-08 | 2024-06-11 | Advanced Farm Technologies, Inc. | Autonomous crop harvester |
| CN112930868A (en) * | 2021-03-30 | 2021-06-11 | 南京农业大学 | Flexible grasping and sucking type picking end effector for small spherical fruits and picking method thereof |
| CN113602799A (en) * | 2021-08-05 | 2021-11-05 | 西南科技大学 | Airport luggage case carrying system and control method thereof |
| CN116584310A (en) * | 2023-06-07 | 2023-08-15 | 农业农村部南京农业机械化研究所 | Black fungus picking device |
| CN116584310B (en) * | 2023-06-07 | 2024-01-19 | 农业农村部南京农业机械化研究所 | Black fungus picking device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112136506A (en) | Robot arm device with fruit maturity distinguishing function | |
| Hayashi et al. | Robotic harvesting system for eggplants | |
| CN103950033B (en) | The mechanical arm of fruit picking robot and end effector and fruit picking method | |
| CN109105001A (en) | A kind of bergamot pear terminal executor of picking robot and picking method | |
| CN113843810A (en) | Machine vision-based quasi-spherical fruit picking robot and fruit picking method thereof | |
| CN107615989B (en) | Automatic equipment of picking of absorption formula strawberry | |
| CN103404307B (en) | Fully-automatic kiwi fruit picking end effector | |
| CN215530078U (en) | Manipulator with snatch and take fruit function | |
| CN109156161A (en) | A kind of fertile mandarin orange picking robot of intelligence | |
| CN209201574U (en) | A kind of bergamot pear terminal executor of picking robot | |
| US11523560B2 (en) | Machine for selectively harvesting plants | |
| Sharma et al. | Designing and implementing a smart transplanting framework using programmable logic controller and photoelectric sensor | |
| CN108990712A (en) | A kind of agaricus bisporus picking machine that distinguishing picking and its control system | |
| CN106525605A (en) | Device and method for measuring lodging resistance of crops | |
| CN111247963A (en) | Banana intelligence system of gathering | |
| CN109760098A (en) | A kind of apple-picking end effector of included video camera | |
| CN113350797A (en) | Crop picking method and device based on digital twins | |
| CN203369124U (en) | Full-automatic kiwi berry picking end actuator | |
| CN114916318B (en) | Automatic fruit harvesting device carried on unmanned aerial vehicle and control method thereof | |
| CN203775716U (en) | Fruit picking manipulator | |
| CN208016381U (en) | A kind of fruit and vegetable picking machinery | |
| CN107484500B (en) | Row adsorption pipeline strawberry picking equipment and picking method | |
| CN113228939B (en) | Intelligent vertical corn header and corn combine | |
| CN114193487B (en) | Flexible manipulator for detecting in-situ quality of fruits and detection method | |
| CN109531571A (en) | A kind of flexible mechanical arm end effector control 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 | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20201229 |
|
| WD01 | Invention patent application deemed withdrawn after publication |