CN114275425A - Automatic-check robot seeding and sorting system, method, equipment and medium - Google Patents

Abstract

The application provides an automatic-check-entering robot sowing sorting system, method, equipment and medium, which realize the function of completely executing sowing operation by automatic equipment, and realize the functions of storing, transporting, visually analyzing, grabbing, transferring, transplanting, entering check and the like of materials through a material storage unit, a feeding unit, a visual analysis unit, a robot unit, a material bar code identification and material transplanting unit, a lifting and traversing type material placing unit and a transferring goods shelf unit, so that the operation efficiency is greatly improved, the information of the whole sorting process can be traced, and the control and supervision of the whole process are realized; the sorting system greatly expands the sorting capacity of the equipment due to the introduction of the robot unit; the sorting system also greatly reduces the error rate and avoids the error operation or error bill-throwing caused by manual operation in the traditional sowing sorting system; and because of the reduction of operators, the operation flow is simplified to the greatest extent, and the management cost of enterprises is greatly reduced.

Description

Automatic-check robot seeding and sorting system, method, equipment and medium

Technical Field

The application relates to the technical field of logistics, in particular to an automatic entering robot seeding and sorting system, method, equipment and medium.

Background

In an e-commerce warehouse system, the commodity ex-warehouse throughput is large, the commodity types are various, the commodity sorting aiming at different orders is completely completed by manpower at present, the work content is simple, the repeatability is high, a large amount of manpower is consumed, and the labor intensity is high.

At present, in a commodity sorting mode which is commonly used in a seeding type sorting process, a plurality of orders (i.e. the requisition demands of a plurality of customers) are collected into a batch by the seeding type sorting process, the quantity of each commodity is collected respectively, and then the customers are sorted one by one, and the seeding type sorting process is similar to seeding in shape, so that the sorting process is also called as 'commodity collection and sorting'. Therefore, the sowing type sorting is characterized in that a plurality of orders or a plurality of customers need to be processed each time; the operation is complex, the difficulty coefficient is large, and the sorting machine is suitable for sorting orders with large variety and quantity. Since batch orders can be efficiently processed by sowing type picking, the average time for completing one order is shorter than that of picking type picking, and therefore, the traditional picking type picking mode is gradually changed into sowing type picking by all the large-scale electronic commerce and warehousing enterprises in the present.

However, seed-sowing sorting has its inherent drawbacks: firstly, the operation difficulty of sowing type sorting is large, the labor intensity is high, various differences exist among orders due to the fact that a plurality of orders need to be processed simultaneously, and operators are very tired due to frequent switching among material frames at different positions, so that the whole operation difficulty of the sorting process is large; secondly, the management of the flow is very difficult, the requirement on the sorting flow management is higher, and the requirements on management information systems, personnel, regulations and the like are higher.

In view of this, there is a need in the sorting field for a method and a system that can automatically pick out and put in a warehouse and automatically pick the goods to an order box to replace manual sorting.

Disclosure of Invention

In view of the above-mentioned shortcomings of the prior art, it is an object of the present application to provide an automated entering robotic seeding and sorting system, method, apparatus and medium for solving the problems of low sorting efficiency and the like in the prior art.

To achieve the above and other related objects, a first aspect of the present application provides an automatic-entering robotic seeding and sorting system, comprising: the storage unit is used for storing materials; the feeding unit is used for placing and conveying the material storage unit; the visual analysis unit is used for carrying out visual scanning on the conveyed materials after the conveyed materials enter the visual scanning area so as to acquire image information of the conveyed materials and analyze material grabbing information; the material grabbing information at least comprises grabbing point position information, grabbing attitude information and target position information; the robot unit is in communication connection with the visual analysis unit and is used for receiving the position information and the grabbing posture information of the grabbing points from the visual analysis unit, grabbing the materials in corresponding grabbing postures and transferring the materials to the material bar code recognition and material transplanting unit; the material bar code identification and material transplanting unit comprises a bar code scanner and a material pushing mechanism; the bar code scanner is used for scanning bar codes on the surfaces of the materials; the material pushing mechanism is used for pushing the materials into the transplanting mechanism of the lifting and transverse moving type discharging unit after the code scanning is finished; the lifting and transverse moving type discharging unit is in communication connection with the visual analysis unit and is used for receiving target position information from the visual analysis unit and then delivering the materials to corresponding grids in the transfer shelf unit through lifting and transverse moving; the transfer rack unit comprises a plurality of grids for feeding materials.

In some embodiments of the first aspect of the present application, the obtaining manner of the grasp point position information and the grasp posture information includes: the visual analysis unit obtains space geometric information of the material by scanning the outline of the material so as to obtain the position information and the grabbing posture information of the material; the acquisition mode of the target position information comprises any one or more of the following combinations: mode 1) a visual analysis unit obtains size information of a material by scanning the outline of the material, and obtains target position information related to the size grade of the material according to the size information; the transfer shelf unit is provided with a plurality of layers of shelves, and the shelves at different layers are used for accommodating materials with different size grades; mode 2) the visual analysis unit obtains shape information of the material by scanning the outline of the material and obtains target position information related to the shape category of the material according to the shape information analysis; the transfer shelf unit is provided with a plurality of layers of shelves, and the shelves on different layers are used for accommodating materials of different shapes and categories; mode 3) the visual analysis unit reads the target position information of the material by scanning the graphic code on the surface of the material.

In some embodiments of the first aspect of the present application, the material barcode recognition and material transplanting unit includes: the transparent material bearing platform is used for bearing materials; the side code scanners are arranged around the light-transmitting material bearing platform; the top code scanner is arranged right above the light-transmitting material bearing platform; the bottom code scanner is arranged right below the light-transmitting material bearing platform; after the robot unit transfers the materials to the light-transmitting material bearing platform, a plurality of side bar codes are used for scanning bar codes on a plurality of side surfaces of the materials; the top bar code scanner is used for scanning bar codes on the top surface of the material; the bottom bar code scanner is used for scanning bar codes on the bottom surface of the material through the light-transmitting material bearing platform; after the yard is scanned, the material pushing mechanism pushes the material into the transplanting mechanism of the lifting and transverse moving type discharging unit.

In some embodiments of the first aspect of the present application, the material barcode recognition and material transplanting unit includes: the material bearing platform is used for bearing materials; the side code scanners are arranged around the material bearing platform; the top code scanner is arranged right above the material bearing platform; the bottom code scanner is arranged outside the material bearing platform and is positioned below the material moving path; when the robot unit transfers the material to pass through a scanning area right above the bottom bar scanner, the bottom bar scanner scans bar codes on the bottom surface of the material; after the materials are transferred to the material bearing platform, a plurality of side code scanners are used for scanning bar codes on a plurality of side surfaces of the materials, and a top code scanner is used for scanning bar codes on the top surface of the materials; after the yard is scanned, the material pushing mechanism pushes the material into the transplanting mechanism of the lifting and transverse moving type discharging unit.

In some embodiments of the first aspect of the present application, the material barcode recognition and material transplanting unit includes: the material bearing platform is used for bearing materials; the material bearing platform comprises a first conveying line which is located at a higher position and has a slower conveying speed and a second conveying line which is located at a lower position and has a faster speed; the side bar code scanners are arranged on the periphery of the material bearing platform and used for scanning bar codes on a plurality of side surfaces of the material; the top bar code scanner is arranged at the top of the material bearing platform and used for scanning bar codes on the top surface of the materials; the bottom bar code scanner is arranged on the outer side of the material bearing platform and positioned below the material moving path, and is used for scanning bar codes on the bottom surface of the material when the material passes right above the bottom bar code scanner; the monitoring camera is arranged above the material bearing platform and used for detecting the number of the materials; the monitoring camera is arranged above the material bearing platform and used for detecting the number of the materials; the stacking platform separates stacked materials through two conveying lines with height difference and speed difference; if the counting number of the monitoring cameras exceeds 1, sending a control signal to the transplanting hopper after the photoelectric sensor detects that the material passes through so as to enable the transplanting hopper to send the current material into an abnormal grid; if the number of the counting pieces of the monitoring camera is 1, when the photoelectric sensor detects that the materials pass through, a control signal is sent to the transplanting hopper, so that the transplanting hopper sends the current materials into a normal grid.

In some embodiments of the first aspect of the present application, the material barcode recognition and material transplanting unit includes: the material bearing platform is rotated to bear materials; a pair of side code scanners which are arranged at the side of the rotary material bearing platform and are oppositely arranged; the top code scanner is arranged at the top of the rotary material bearing platform; the bottom code scanner is arranged outside the rotary material bearing platform and is positioned below the material moving path; when the robot unit transfers the material to pass through a scanning area right above the bottom bar scanner, the bottom bar scanner scans bar codes on the bottom surface of the material; after the materials are transferred to the material bearing platform, bar codes are scanned on two side surfaces of the materials by a pair of side bar scanners, and bar codes are scanned on the other two side surfaces after the materials are rotated by less than 180 degrees by rotating the material bearing platform; after the yard is scanned, the material pushing mechanism pushes the material into the transplanting mechanism of the lifting and transverse moving type discharging unit.

In some embodiments of the first aspect of the present application, the material barcode recognition and material transplanting unit includes: the material bearing platform is used for bearing materials; the rotary side code scanner is arranged on the side of the material bearing platform; the top code scanner is arranged at the top of the material bearing platform; the bottom code scanner is arranged outside the material bearing platform and is positioned below the material moving path; when the robot unit transfers the material to pass through a scanning area right above the bottom bar scanner, the bottom bar scanner scans bar codes on the bottom surface of the material; after the materials are transferred to the material bearing platform, firstly, bar codes are scanned on one side surface of the materials through a side bar code scanner, and then, after the materials are rotated by less than 360 degrees through a rotary side bar code scanner, bar codes are scanned on the other three side surfaces of the materials; after the yard is scanned, the material pushing mechanism pushes the material into the transplanting mechanism of the lifting and transverse moving type discharging unit.

In some embodiments of the first aspect of the present application, the material barcode recognition and material transplanting unit includes: the material bearing platform is used for bearing materials; the bottom code scanner is arranged outside the material bearing platform and is positioned below the material moving path; the top code scanner is arranged at the top of the material bearing platform; a rotary side code scanner arranged at the side of the material bearing platform; when the robot unit transfers the material to pass through a scanning area right above the bottom bar scanner, the bottom bar scanner scans bar codes on the bottom surface of the material; after the materials are transferred to the material bearing platform, bar codes are scanned on one side surface of the materials through a side bar code scanner, and then the materials are rotated through a rotating shaft of the robot unit, so that the side bar code scanner scans the other three side surfaces of the materials; after the code scanning is finished, the robot unit puts the materials on the material bearing platform and pushes the materials into the next procedure through the material pushing mechanism, or the robot unit directly puts the materials into the next procedure.

In some embodiments of the first aspect of the present application, the pusher mechanism comprises: the device comprises an air cylinder mechanism, a push plate and a sliding chute; the cylinder mechanism is connected with and pushes the push plate; the material bearing platform is positioned on the pushing path of the push plate; the transplanting mechanism in the chute guide lifting and transverse moving type discharging unit; after the yard is swept, the cylinder mechanism promotes the material on the material platform will be held to the push pedal outwards release to make the material along the spout falls into in the transplanting mechanism among the lift and sideslip formula blowing unit.

In some embodiments of the first aspect of the present application, the surface of the loading platform is in a shape of alternating concave and convex; the end part of the push plate, which is contacted with the material bearing platform, is also in a concave-convex alternate shape; and the concave part of the material bearing platform is correspondingly contacted with the convex part at the end part of the push plate, so that the sheet materials are pushed out in a concave-convex crossed connection mode.

In some embodiments of the first aspect of the present application, the elevation and lateral movement type discharging unit comprises: a lifting mechanism, a transverse moving mechanism and a transplanting mechanism; the transplanting mechanism is arranged on the lifting mechanism; the lifting mechanism is arranged on the transverse moving mechanism; the transplanting mechanism is driven by the lifting mechanism to do lifting movement and driven by the transverse moving mechanism to do transverse moving movement.

In some embodiments of the first aspect of the present application, the transplanting mechanism comprises a cylinder push-push type transplanting mechanism comprising: the material receiving hopper is used for receiving materials; the corner mechanism is used for connecting and rotating the head orientation of the material receiving hopper; the material inlet detection sensor is arranged on the material receiving hopper and used for detecting whether materials enter the material receiving hopper or not and sending detection signals to the transverse moving mechanism and the lifting mechanism when detecting that the materials enter the material receiving hopper so as to enable the transverse moving mechanism and the lifting mechanism to perform corresponding transverse moving and lifting movement and then reach the corresponding grid openings; the transverse pushing mechanism is arranged on the material receiving hopper; the transverse moving scraper is arranged in the material receiving hopper and pushes the materials in the hopper into the lattice openings of the transfer shelf units after being pushed by the transverse moving mechanism.

In some embodiments of the first aspect of the present application, the transplanting mechanism comprises a belt conveyor type transplanting mechanism comprising: the material receiving hopper is used for receiving materials; the corner mechanism is used for connecting and rotating the head orientation of the material receiving hopper; the material inlet detection sensor is arranged on the material receiving hopper and used for detecting whether materials enter the material receiving hopper or not and sending detection signals to the transverse moving mechanism and the lifting mechanism when detecting that the materials enter the material receiving hopper so as to enable the transverse moving mechanism and the lifting mechanism to perform corresponding transverse moving and lifting movement and then reach the corresponding grid openings; and the belt mechanism is used for pushing the materials into the grids of the transfer shelf unit.

In some embodiments of the first aspect of the present application, the transfer rack unit comprises: each layer of goods shelf is provided with a material frame bearing plate, and each layer of material frame bearing plate is provided with a plurality of grids; the grid openings comprise normal grid openings for placing normal material for scanning the code and abnormal grid openings for placing abnormal material for scanning the code; the bearing plate is a rotatable bearing plate, so that the direction of the cell is changed by rotating the bearing plate.

To achieve the above and other related objects, a second aspect of the present application provides an automatic-entering robotic seeding sorting method applied to the computational analysis unit; the method comprises the following steps: collecting a material image in an incoming material box; calculating the area size information and material classification information of the material absorbable surface according to the material image; and selecting the sucking discs suitable for the material according to the calculation result.

In some embodiments of the second aspect of the present application, the calculating the material classification information of the material absorbable surface includes: collecting material data; manually calibrating based on the collected material data, and calibrating the corresponding material type; dividing the calibration data into a training set and a test set according to a preset proportion; training a convolutional neural network by utilizing a training set, wherein the convolutional neural network is trained to output a prediction result of material types; testing the trained convolutional neural network by using a test set, and verifying the classification effect of the model on the material; and performing material prediction analysis on the current new material by the convolutional neural network after training and testing.

To achieve the above and other related objects, a third aspect of the present application provides a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements the automated entering robotic seeding sorting method.

To achieve the above and other related objects, a fourth aspect of the present application provides a visual analysis apparatus comprising: a processor and a memory; the memory is used for storing a computer program, and the processor is used for executing the computer program stored by the memory so as to enable the equipment to execute the automatic entering robot seeding and sorting method.

As described above, the automatic entering-into-check robot seeding and sorting system, method, device and medium of the present application have the following beneficial effects: the invention realizes the function of completely executing the sowing operation by the automatic equipment, realizes the functions of storing, conveying, visual analysis, grabbing and transferring, transplanting, entering into check and the like of the materials through the material storage unit, the feeding unit, the visual analysis unit, the robot unit, the material bar code identification and material transplanting unit, the lifting and transverse moving type material placing unit and the transferring goods shelf unit, greatly improves the operation efficiency, and realizes the control and supervision of the whole process by tracing the information of the whole sorting process; the sorting system greatly expands the sorting capacity of the equipment due to the introduction of the robot unit; the sorting system also greatly reduces the error rate and avoids the error operation or error bill-throwing caused by manual operation in the traditional sowing sorting system; and because of the reduction of operators, the operation flow is simplified to the greatest extent, and the management cost of enterprises is greatly reduced.

Drawings

Fig. 1A is a top view of an automated, self-collating robotic seed sorting system according to an embodiment of the present application.

Fig. 1B is a perspective view of an automated, self-collating robotic seeding and sorting system according to an embodiment of the present application.

Fig. 2 is a schematic structural diagram of a material barcode recognition and material transplanting unit according to an embodiment of the present application.

Fig. 3 is a schematic structural diagram of a material barcode recognition and material transplanting unit according to an embodiment of the present application.

Fig. 4 is a schematic structural diagram of a material barcode recognition and material transplanting unit according to an embodiment of the present application.

Fig. 5 is a schematic structural diagram of a material barcode recognition and material transplanting unit according to an embodiment of the present application.

Fig. 6 is a schematic structural diagram of a material barcode recognition and material transplanting unit according to an embodiment of the present application.

Fig. 7 is a schematic structural diagram of a material barcode recognition and material transplanting unit according to an embodiment of the present application.

Fig. 8 is a schematic structural view of a lifting and traversing type discharging unit according to an embodiment of the present application.

Fig. 9A is a schematic structural diagram of a cylinder transverse pushing type transplanting mechanism according to an embodiment of the present application.

Fig. 9B is a schematic structural diagram of a belt conveyor type transplanting mechanism according to an embodiment of the present application.

Fig. 10A is a front view of a transfer rack unit in an embodiment of the present application.

Fig. 10B shows a side view of a transfer rack unit in an embodiment of the present application.

Fig. 11 is a schematic diagram illustrating a robot unit grasping a material according to an embodiment of the present application.

Fig. 12 is a flowchart illustrating an automatic entering robotic seeding and sorting method according to an embodiment of the present application.

Fig. 13 is a schematic structural diagram of a visual analysis apparatus according to an embodiment of the present application.

Detailed Description

The following description of the embodiments of the present application is provided by way of specific examples, and other advantages and effects of the present application will be readily apparent to those skilled in the art from the disclosure herein. The present application is capable of other and different embodiments and its several details are capable of modifications and/or changes in various respects, all without departing from the spirit of the present application. It is to be noted that the features in the following embodiments and examples may be combined with each other without conflict.

It is noted that in the following description, reference is made to the accompanying drawings which illustrate several embodiments of the present application. It is to be understood that other embodiments may be utilized and that mechanical, structural, electrical, and operational changes may be made without departing from the spirit and scope of the present application. The following detailed description is not to be taken in a limiting sense, and the scope of embodiments of the present application is defined only by the claims of the issued patent. The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. Spatially relative terms, such as "upper," "lower," "left," "right," "lower," "below," "lower," "above," "upper," and the like, may be used herein to facilitate describing one element or feature's relationship to another element or feature as illustrated in the figures.

In this application, unless expressly stated or limited otherwise, the terms "mounted," "connected," "secured," "retained," and the like are to be construed broadly and can, for example, be fixedly connected, detachably connected, or integrally connected; 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 application can be understood by those of ordinary skill in the art as appropriate.

Also, as used herein, the singular forms "a", "an" and "the" are intended to include the plural forms as well, unless the context indicates otherwise. It will be further understood that the terms "comprises," "comprising," and/or "comprising," when used in this specification, specify the presence of stated features, operations, elements, components, items, species, and/or groups, but do not preclude the presence, or addition of one or more other features, operations, elements, components, items, species, and/or groups thereof. The terms "or" and/or "as used herein are to be construed as inclusive or meaning any one or any combination. Thus, "A, B or C" or "A, B and/or C" means "any of the following: a; b; c; a and B; a and C; b and C; A. b and C ". An exception to this definition will occur only when a combination of elements, functions or operations are inherently mutually exclusive in some way.

At present, the sorting modes involved in warehouse management generally include sowing type sorting and fruit picking type sorting. The sowing type sorting is that a plurality of orders (namely the requisition demands of a plurality of customers) are gathered into a batch, the quantity of each commodity is gathered respectively, and then all the customers are sorted one by one, and the shape is similar to sowing; the seeding type sorting method has the characteristics of complex operation and high difficulty coefficient when a plurality of orders are processed each time. Picking fruit type sorting is to pick each order (namely each customer), and picking personnel or equipment go round each goods storage position to take out the needed goods, which are similar to fruit picking; the fruit picking type sorting method has the characteristics that each person only processes one order at a time, and the method is simple and easy to operate.

However, both seeding type sorting and fruit picking type sorting in the prior art have many disadvantages, the fruit picking type sorting efficiency is low, the seeding type sorting operation difficulty is high, the labor intensity is high, the requirement on sorting flow management is higher, and the requirements on management information systems, personnel, regulation and regulation systems and the like are higher.

In view of the above, the invention provides an automatic entering robot sowing and sorting system, aiming at providing an automatic sorting scheme based on a robot, realizing the function of completely executing sowing operation by automatic equipment, greatly improving the operation efficiency, and realizing the control and supervision of the whole process by tracing the information of the whole sorting process; the sorting system greatly expands the sorting capacity of the equipment due to the introduction of the robot unit; the error rate is greatly reduced, and the error operation or the error bill throwing caused by manual operation in the traditional sowing and sorting system are avoided; and because of the reduction of operators, the operation flow is simplified to the greatest extent, and the management cost of enterprises is greatly reduced. In order to make the objects, technical solutions and advantages of the present invention more apparent, the technical solutions in the embodiments of the present invention are further described in detail by the following embodiments in conjunction with the accompanying drawings. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.

As shown in fig. 1A and 1B, a top view and a perspective view of an automated entering robotic seeding and sorting system according to an embodiment of the present invention are shown. The robot seeding letter sorting system that this embodiment demonstrates specifically includes: the device comprises material storage units 101A-101D, feeding units 102A-102B, a visual analysis unit 103, a robot unit 104, a lifting and transverse type discharging unit 105, a transfer shelf unit 106 and a material bar code identification and material transplanting unit 107.

The material storage units 101A to 101D are used for storing various types of materials, and specifically, a material frame or a tray can be selected to realize a material storage function, which is not limited in this embodiment. It should be understood that the material involved in the present invention includes not only express products in the e-commerce storage field, but also all materials circulating in the production field, such as raw materials, fuels, parts, semi-finished products, external accessories, leftover materials or waste materials. The present embodiment also does not limit the production field to which the material belongs, including but not limited to: electronic materials, optical materials, plastic materials, metal materials, packaging materials or auxiliary materials, etc.

The feeding units 102A to 102B are used for placing the material storage units 101A to 101D, so as to drive the material storage units 101A to 101D to move into a scanning area of the visual analysis unit 103, or to be driven into an operation area of the robot unit, or to be driven to output outwards. In addition, the material transfer between the material storage units 101A to 101D and the material feeding units 102A to 102B can be completed by manpower, or can be realized by a mechanical device, which is not limited in this embodiment.

In a preferred implementation manner of the present embodiment, since the feeding units 102A to 102B deliver a plurality of types of materials with different volumes and weights, the load impacts on the feeding unit 102 are different during the process of transferring the materials from the storage units 101A to 101D to the feeding units 102A to 102B and during the process of transporting the feeding unit 102 by the feeding unit 102, for example, during the process of placing the materials into the storage unit 101A, the feeding unit 102A further drives the storage unit 101A to transport along the direction D1, and the like. The feeder unit 102 is therefore preferably a roller conveyor line of a roller conveyor, adapted to carry various types of materials of different volume and weight (such as boxes, bags, pallets, etc.), able to carry heavy articles, having a very good resistance to load impacts, and able to perform a better coupling between the rollers, enabling the conveyor to better carry complex and stacked articles. However, the feeding unit 102 in this embodiment may also use a belt conveyor, a screw conveyor, a plate chain conveyor, a mesh belt conveyor, a chain conveyor, or the like, and this embodiment is not limited thereto.

The visual scanning area of the visual analysis unit 103 at least covers the transportation path of the transported material, and is used for visually scanning the transported material after the transported material enters the visual scanning area, collecting image information of the transported material, and analyzing and acquiring material grabbing information. For example, in fig. 1A, after the material is placed into the material storage unit, the material storage unit passes through a scanning area of the visual analysis unit 103 during the conveying process (for example, the position of the material storage unit 101B in fig. 1A), and the visual analysis unit 103 acquires an image of the material in the scanning area, so as to analyze and acquire material grabbing information; the material grabbing information includes, but is not limited to, grabbing point position information, grabbing posture information, target position information and the like of the material.

Further, the visual analysis unit 103 may be a camera module comprising camera means, storage means and processing means. The image capturing device includes but is not limited to: cameras, video cameras, camera modules integrated with optical systems or CCD chips, camera modules integrated with optical systems and CMOS chips, and the like. In order to increase the size of the visual scanning area, the visual analysis unit 103 may be a wide-angle lens or a fisheye lens, and the cameras may be arranged around the periphery or on top of the camera, which is not limited in this embodiment.

Further, the vision analysis unit 103 obtains the space geometric information (including but not limited to length, angle, or relationship between point, line and plane) of the material by scanning the outline of the material, and accordingly obtains the position information and the posture information of the grabbing point suitable for grabbing the material, and these information are transmitted to the robot unit 104 through the communication network, and the robot unit 104 can execute the corresponding grabbing action.

For example, a first way for the vision analysis unit 103 to obtain the target location information includes: the visual analysis unit 103 obtains size information (including but not limited to information such as height, width, length, radius, projection area, etc. of the material) of the material by scanning the outline of the material, and analyzes the size information to obtain target position information related to the size grade of the material; the transfer shelf unit 106 is provided with a plurality of layers of shelves, the shelves on different layers are used for accommodating materials with different size levels, and the shelves on the same layer are used for accommodating materials with the same size level; the goods shelf with large accommodating space is used for loading materials with large size grade, and the goods shelf with small accommodating space is used for loading materials with small size grade; therefore, the target position information of the material can be obtained through analysis after the size information of the material is obtained.

For example, the second way for the vision analysis unit 103 to obtain the target location information includes: the visual analysis unit 103 obtains shape information (including but not limited to a rectangular parallelepiped shape, a spherical shape, a cylindrical shape, or the like) of the material by scanning the outline of the material, and analyzes the shape information to obtain target position information related to the shape category of the material; the transfer shelf unit 106 is provided with a plurality of layers of shelves, the shelves on different layers are used for accommodating materials of different shapes and types, and the shelves on the same layer are used for accommodating materials with the same shape; therefore, the target position information of the material can be obtained through analysis after the shape information of the material is obtained.

As another example, the third way for the vision analysis unit 103 to obtain the target location information includes: the visual analysis unit 103 reads target position information of the material by scanning a graphic code of the surface of the material. For example, a graphic code (including but not limited to a two-dimensional code, a one-dimensional code, or a bar code) pre-stored with target position information (e.g., the nth layer of the transfer shelf unit) of each material is attached to the surface of each material, and the visual analysis unit 103 can obtain the information after scanning and reading the information.

The robot unit 104 establishes a communication connection with the visual analysis unit 103, and is configured to receive material grabbing information (including grabbing point position information, grabbing posture information, and target position information) from the visual analysis unit 103, grab the material, and transfer the material to the material barcode recognition and material transplanting unit 107. It should be noted that the robot unit 104 according to the present embodiment includes but is not limited to: a multi-axis robot (e.g., an XYZ three-axis robot, a four-axis robot, a six-axis robot, or even an eight-axis robot, etc.) capable of realizing multiple degrees of freedom, a Scara robot having 3 rotational joints and capable of being applied to an assembly operation, or a Delta robot capable of realizing high-precision material picking, and the like. In an actual application scene, any automatic device capable of realizing the grabbing and transporting functions can be applied to the technical scheme of the invention.

It is worth mentioning that the existing sowing type sorting system usually completes the sorting by manpower, but because the weight which can be born by manpower is limited, only about 1KG of products can be sorted each time; the robot seeding and sorting system adopted by the invention can at least promote products with the weight of 2KG or more due to the excellent bearing capacity of the robot, thereby greatly promoting the sorting capacity of the sorting system.

The material bar code recognition and material transplanting unit 107 is used for recognizing a bar code on the outer surface of the material and placing the material into a transplanting mechanism of the lifting and traversing type discharging unit 105 in the next process after recognizing the bar code. It should be noted that the material barcode recognition and material transplanting unit 107 can adopt various structures to implement the barcode scanning function and the material transplanting function, and the following will describe in detail 6 commonly used implementations thereof with reference to the drawings of the specification.

As shown in fig. 2, the 1 st implementation manner of the material barcode recognition and material transplanting unit is shown: the material bar code identification and material transplanting unit comprises a light-transmitting material bearing platform 201, side code scanners 202-205 arranged on the periphery of the light-transmitting material bearing platform, a top code scanner 206 arranged right above the light-transmitting material bearing platform, a bottom code scanner 207 arranged right below the light-transmitting material bearing platform and a material pushing mechanism. The material pushing mechanism comprises an air cylinder mechanism 208, a push plate 209 and a sliding groove 210, and the air cylinder mechanism 208 is connected with and pushes the push plate 209; the light-transmitting material bearing platform 201 is positioned on the pushing path of the push plate 209; the chute 210 guides the transplanting mechanism in the lifting and traversing type discharging unit.

The side bar code scanners 202-205 are used for scanning bar codes on multiple side faces of the material; top scanner 206 is used to scan the bar code on the top surface of the material; the bottom code scanner 207 is used for scanning the bar codes on the bottom surface of the material through the light-transmitting material bearing platform; after the yard is scanned, the air cylinder mechanism 208 pushes the push plate 209 to push the material on the material bearing platform 201 outwards, so that the material falls into the transplanting mechanism in the lifting and traversing type discharging unit along the chute 210.

More specifically, the code scanners 202, 203, 204, 205 are side code scanners, respectively disposed on four sides of the transparent material supporting platform 201, and configured to scan four sides of the material, and the barcode attached to any one side of the material can be scanned by one of the code scanners 202, 203, 204, 205. The bar scanner 206 is a top bar scanner, and is located right above the light-transmitting material bearing platform 201, and is used for scanning bar codes on the top of the material. The bar scanner 207 is a bottom bar scanner, is located under the light-transmitting material-bearing platform 201, and is used for scanning bar codes of the bottom of the material after transmitting light-transmitting materials.

As shown in fig. 3, the 2 nd implementation manner of the material barcode recognition and material transplanting unit is shown: the material bar code identification and material transplanting unit comprises a material bearing platform 301, a top code scanner 306 arranged at the top end of the material bearing platform, a plurality of side code scanners 302-305 arranged on the side, a bottom code scanner 307 arranged on the outer side of the platform and positioned below a material moving path, an air cylinder mechanism 308, a push plate 309 and a sliding groove 310. After the robot unit grabs the material and puts into holding material platform 301, side bar code scanner 302 ~ 305 scans the attached bar code on the different sides of material respectively, and top bar code scanner 306 is used for scanning the attached bar code on the material top surface, and when the robot unit grabs the material and passes through the scanning area directly over bottom bar code scanner 307, bottom bar code scanner 307 scans the attached bar code of material bottom surface. After the yard is scanned, the cylinder mechanism 308 drives the push plate 309 to push the material out, so that the material falls into the transplanting mechanism in the next procedure lifting and traversing type discharging unit along the chute 310.

In some preferred embodiments, considering that some parts are very thin, such as about 1mm thick, the push plate can push them out of the loading platform with difficulty. Therefore, a metal plate with concave-convex design can be selected as a material bearing platform, the end part of the push plate is also designed with concave-convex design, the concave part of the material bearing platform is correspondingly contacted with the convex part of the end part of the push plate, and the convex part of the material bearing platform is correspondingly contacted with the concave part of the end part of the push plate, so that the concave part and the convex part are crossed, and the sheet on the material bearing platform can be smoothly pushed out.

More specifically, the scanners 302, 303, 304, 305 are side scanners, and are uniformly arranged along the circumference of the material supporting platform 301 for scanning four sides of the material, and the barcode attached to any side of the material can be scanned by one of the scanners 302, 303, 304, 305. The bar code scanner 306 is a top bar code scanner, and is located right above the light-transmitting material bearing platform 201, and is used for scanning bar codes on the top of the material. The code scanner 307 is a bottom code scanner, and is located outside the transparent material carrying platform 201 and right below the material conveying path, so that the bar code attached to the bottom surface of the material can be scanned when the material passes right above the bottom code scanner.

As shown in fig. 4, a 3 rd implementation manner of the material barcode recognition and material transplanting unit is shown: the material bar code identification and material transplanting unit comprises material bearing platforms 401A-401B, a plurality of side code scanners 402-405 arranged on the side of the material bearing platforms, a top code scanner 406 arranged on the top of the material bearing platforms, a bottom code scanner 407 arranged on the outer sides of the material bearing platforms and located below a material moving path, a photoelectric sensor 408 used for detecting material passing, and a top monitoring 2D camera 409 used for counting. After the robot unit grabs the materials and puts into the material bearing platform, the side bar codes 402-405 respectively scan the attached bar codes on the different sides of the materials, the top bar code scanner 406 is used for scanning the attached bar codes on the top surface of the materials, and when the robot unit grabs the materials and passes through the scanning area right above the bottom bar code scanner 407, the bottom bar code scanner 407 scans the attached bar codes on the bottom surface of the materials.

It should be noted that the material supporting platform in this embodiment includes 2 conveying lines with height difference and speed difference, a conveying line 401A at a higher position with a slower conveying speed, and a conveying line 401B at a lower position with a faster conveying speed, and such design is to separate materials through the height difference and the speed difference so as to avoid an abnormal situation of material stacking, and effectively solve the problem that a visual system cannot identify when two thin materials are overlapped. When the material drops to lower transfer chain 401B from higher transfer chain 401A, the material can take place to turn on one's side, and the material that piles up separates each other because taking place to turn on one's side, and the material that contacts transfer chain 401B earlier accelerates transfer rate along with quick transfer line, produces stroke speed difference between two materials, and distance between each other has just also pulled open.

The top monitoring 2D camera 409 is used for counting to identify the amount of material on the conveyor line; the photoelectric sensor 408 is used to detect the passage of material and provide control signals to control the movement of the transplanting hopper. Specifically, if the number of the materials on the conveying line counted by the top monitoring 2D camera 409 exceeds 1, it is determined that the materials are stacked abnormally; after detecting that the material passes through, the photoelectric sensor 408 sends a control signal to the transplanting hopper so that the transplanting hopper sends the current material into the abnormal opening. If the number of the materials on the conveying line is 1 as counted by the top monitoring 2D camera 409, judging that the condition is normal; after detecting that the material passes through, the photoelectric sensor 408 sends a control signal to the transplanting hopper so that the transplanting hopper sends the current material to the sowing wall.

As shown in fig. 5, the 4 th implementation manner of the material barcode recognition and material transplanting unit is shown: the material bar code identification and material transplanting unit comprises a rotary material bearing platform 501, two side code scanners 502-503 which are oppositely arranged on the side of the rotary material bearing platform, a top code scanner 504 which is arranged on the top of the rotary material bearing platform, a bottom code scanner 505 which is arranged on the outer side of the rotary material bearing platform and is positioned below a material moving path, an air cylinder mechanism 506, a push plate 507 and a sliding groove 508. The rotary material bearing platform comprises a disc and a servo mechanism for driving the disc to rotate, and the servo mechanism drives the disc to rotate by less than 180 degrees. After the robot unit grabs the materials and then puts into the rotary material bearing platform, the side code scanners 502-503 scan two side faces of the materials, the rotary material bearing platform rotates after the code scanning is finished, and the other two side faces of the materials are scanned by the side code scanners 502-503. The top bar code scanner 504 is used to scan the bar code attached to the top surface of the material, and when the robot unit grabs the material through the scanning area directly above the bottom bar code scanner 505, the bottom bar code scanner 505 scans the bar code attached to the bottom surface of the material. After the code scanning is finished, the air cylinder mechanism 506 drives the push plate 507 to push the materials outwards, so that the materials fall into the transplanting mechanism in the lifting and transverse moving type discharging unit of the next working procedure along the sliding groove 508.

It is worth mentioning that this embodiment has realized just using 2 side bar codes of bar code of 4 sides of material of just can scanning through rotatory material platform that holds to reduce and use bar code scanner, reduce the distance between bar code scanner and the material, save installation space, showing reduce cost, and solved 4 weeks of big material and scanned the difficult problem that the bar code has the dead angle.

As shown in fig. 6, the 5 th implementation manner of the material barcode recognition and material transplanting unit is shown: the material bar code identification and material transplanting unit comprises a material bearing platform 601, a rotary side code scanner 602 arranged on the side of the material bearing platform, a top code scanner 603 arranged on the top of the material bearing platform, a bottom code scanner 604 arranged on the outer side of the material bearing platform and positioned below a material moving path, an air cylinder mechanism 605 and a push plate 606. The material bearing platform 601 in this embodiment is fixed, and the side code scanner 602 is driven by the bottom servo mechanism 607 to rotate 360 degrees to scan the bar codes around the material. The top bar code scanner 603 is used to scan the bar code attached to the top surface of the material, and the bottom bar code scanner 604 scans the bar code attached to the bottom surface of the material when the robot unit picks up the material passing through the scanning area directly above the bottom bar code scanner 604. After the code scanning is finished, the air cylinder mechanism 605 drives the push plate 606 to push the materials outwards, so that the materials fall into the transplanting mechanism in the lifting and transverse moving type discharging unit of the next procedure.

It is worth mentioning that this embodiment has realized just using 1 side bar code scanner to scan the bar code of 4 sides of material through rotatory bar code scanner to reduce and use the bar code scanner, reduce the distance between bar code scanner and the material, save installation space, showing reduce cost, and solved 4 weeks of big material and scanned the difficult problem that the bar code has the dead angle, in addition the material is motionless, can realize scanning the bar code more fast.

As shown in fig. 7, a 6 th implementation manner of the material barcode recognition and material transplanting unit is shown: the material bar code identification and material transplanting unit comprises a material bearing platform 701, a bottom code scanner 702 arranged on the outer side of the material bearing platform and positioned below a material moving path, a top code scanner 703 arranged on the top of the material bearing platform, and a rotary side code scanner 704 arranged on the side of the material bearing platform. When the robot unit 700 grabs the material passing through the scanning area right above the bottom bar scanner 702, the bottom bar scanner 702 scans the bar code attached to the bottom surface of the material; then the robot unit 700 carries the material to the scanning area of the side code scanner 704 above the material bearing platform 701, and the rotating shaft of the robot unit 700 is used for driving the material to rotate for 360 degrees, so that the side code scanner 704 scans the bar codes around the material. After the bar codes around the material are scanned, the robot unit 700 places the material on the material bearing platform, and the top bar code scanner 703 scans the bar codes on the top surface of the material. After the code scanning is finished, the air cylinder mechanism 705 drives the push plate 706 to push the material outwards, so that the material falls into the transplanting mechanism in the next procedure lifting and transverse moving type discharging unit along the sliding groove 707.

It is worth mentioning that, this embodiment utilizes the rotation axis of robot cell from taking to realize just using 1 side bar code scanner can scan the bar code of 4 sides of material, and hold material platform or bar code scanner and do not need to rotate moreover, and this yard scheme of sweeping is applicable to very much that light in weight is little size material, reduces and uses bar code scanner to solve the technical problem that there is the dead angle in scanning bar code all around.

Returning to the automated entering robotic seed sorting system shown in fig. 1A and 1B: the lifting and traversing type discharging unit 105 performs a lifting motion in a vertical direction of the transfer rack unit 106 and a traversing motion in a horizontal direction of the transfer rack unit 106. The lifting and traversing type emptying unit 105 is in communication connection with the visual analysis unit 103, and is used for receiving the target position information of the transported material from the visual analysis unit 103, lifting the material to the height corresponding to the target position, and then putting the material on the corresponding shelf in the transfer shelf unit 106. It should be noted that the lifting and traversing discharging unit 105 can realize its driving function through a driving mechanism such as a synchronous belt, a ball screw, a chain, a rack and pinion, a linear motor, etc.

For the convenience of those skilled in the art, the above-mentioned elevating and traversing type discharging unit will be further explained and illustrated with reference to fig. 8. The lifting and transverse moving type discharging unit specifically comprises a lifting mechanism 801, transverse moving mechanisms 802A-802B and a transplanting mechanism 803, wherein the transverse moving mechanisms 802A and 802B perform synchronous transverse moving motion. The transplanting mechanism 803 is arranged on the lifting mechanism 801 and is driven by the lifting mechanism 801 to do lifting movement; the lifting mechanism 801 is arranged between the transverse moving mechanisms 802A and 802B, and the transverse moving mechanisms 802A and 802B perform synchronous transverse moving motion to drive the lifting mechanism 801 to transversely move; the traversing mechanisms 802A and 802B are supported by a support bar 804 and a base 805. The transplanting mechanism 803 is used for carrying the materials transferred by the material bar code identification and material transplanting unit, and executes transplanting action after the materials are driven to the target position, so that the materials carried by the transplanting mechanism are sent into the grids (such as the grids 806A and 806B) of the transfer shelf unit.

Further, the transplanting mechanism 803 includes a carrying surface for carrying the material, the carrying surface has a certain inclination angle with the horizontal direction, and the head portion of the carrying surface faces upward. In order to realize the material transplanting function, the transplanting mechanism of the present embodiment has two implementation structures, including a cylinder transverse pushing type transplanting mechanism and a belt conveying line type transplanting mechanism, which will be described in detail below with reference to fig. 9A and 9B.

The cylinder horizontal pushing type transplanting mechanism shown in fig. 9A includes a corner mechanism 901, a horizontal pushing mechanism 902, a horizontal moving scraper 903, a material receiving hopper 904, and an incoming detection sensor 905. The working process of the cylinder transverse pushing type transplanting mechanism is as follows: the material bar code recognition and material transplanting unit pushes the material into the receiving hopper 904; the material entering detection sensor 905 detects that the material enters, and then sends a detection signal to the lifting mechanism and the transverse moving mechanism in the lifting and transverse moving type discharging unit, and the lifting mechanism and the transverse moving mechanism carry the material to move to the corresponding grid opening of the transfer shelf unit. At this time, the transverse pushing mechanism 902 drives the transverse moving scraper 903 to push the materials into the openings of the transfer shelf units.

Further, when the material is detected to be a sheet, since it may still be difficult to push the material into the grid only by using the transverse pushing mechanism 902 to drive the transverse moving scraper 903, the head of the material receiving hopper 904 faces downward after the corner mechanism 901 rotates by a certain angle for the sheet material, so that the sheet can be conveniently pushed out from the hopper. When the material is detected not to be a sheet, the material can be pushed into the cell only by the transverse pushing mechanism 902 driving the transverse moving scraper 903 without rotating the corner mechanism by a certain angle.

The belt conveyor type transplanting mechanism shown in fig. 9B includes a rotation angle mechanism 906, a belt mechanism 907, a material receiving hopper 908, and an entry detection sensor 909. The working process of the belt conveyor type transplanting mechanism is as follows: the material bar code recognition and material transplanting unit recognizes the bar code and pushes the material into the receiving hopper 908; the material is detected by the in-detection sensor 909 and a detection signal is transmitted to the lifting mechanism and the traversing mechanism in the lifting and traversing type discharging unit, and the lifting mechanism and the traversing mechanism carry the material to move to the corresponding cell of the transfer shelf unit. At this point belt mechanism 907 starts to push the material into the grid of the transfer rack.

Further, when the material is detected to be a sheet, since it may still be difficult to push the material into the grid only by the belt mechanism 907, the head of the material receiving hopper 908 faces downward after the corner mechanism 906 is rotated by a certain angle for the sheet material, so that the sheet is conveniently pushed out from the hopper. When the material is detected not to be a sheet, the material can be pushed into the grid opening only by the belt mechanism 907 without rotating the corner mechanism 906 by a certain angle.

Referring to fig. 10A and 10B, a schematic diagram of the mechanism for transferring shelf units in one embodiment of the present invention is shown. The uppermost layer of the transfer shelf unit is an abnormal grid for placing materials with abnormal bar codes or without scanning the codes, and the lower layers are normal grids for placing materials with successfully scanned codes. Each transfer shelf unit is provided with a multi-layer shelf, and each layer of material frame bearing plate 1001 is provided with a plurality of material frames 1002. In the sowing operation, the transfer shelf unit is manually pushed into the working position along the guide plate 1003, and the electromagnet 1004 is electrically operated to position the transfer shelf unit. The materials fall into the material frame 1002 after being transplanted by the lifting and transverse moving type discharging unit. After seeding is completed, the electromagnet 1004 is powered off manually, the transfer shelf unit is pulled out and moved to a packaging/packaging area, and after packaging/packaging is completed, the express packages are circulated to a downstream conveying system (not shown).

Further, the present embodiment designs the frame support plate 1001 as a rotatable support plate, for example, in fig. 10B, the frame support plate 1001 can rotate in the direction of arrow a or in the opposite direction. Specifically, when the transfer rack unit faces the elevation and lateral movement type discharging unit, the material frame support plate 1001 is rotated to be inclined in a state of being high in the front and low in the rear, which is advantageous in that the support is more stable to prevent the material frame from slipping off. When the transfer shelf unit is pulled out and moved to the packing/packing area, the material frame support plate 1001 rotates in the reverse direction and is in a state of inclining to one side of the operator, so that the operator can take out the material conveniently.

The detailed structure and operation principle of each mechanism in the automatic entering-lattice robot seeding and sorting system of the invention are explained in detail. Hereinafter, the functional algorithm related to the present invention will be further explained.

Fig. 11 shows a schematic diagram of a robot unit gripping a material according to an embodiment of the present invention. The visual analysis unit comprises 3D cameras 1101-1104; the 3D cameras 1101 and 1102 are responsible for image acquisition of the incoming bin 1105; the 3D cameras 1103 and 1104 are used to take pictures of the grabbed material at high speed and calculate the attitude of the material in the air.

In some examples, after the 3D cameras 1101 and 1102 collect the images of the materials in the material storage box 1105, the suction cups suitable for the materials are selected by calculating the size of the area of the material suction surface in the box and the material classification information. It should be noted that the material is determined by the machine learning model, for example, a CNN model (Convolutional Neural Network) is trained to output a material prediction result, and the process is as follows: 1) collecting material data; 2) manually calibrating based on the collected material data, and calibrating the corresponding material type; 3) dividing the calibration data into a training set and a test set according to a preset proportion; 4) training a convolutional neural network by utilizing a training set, wherein the convolutional neural network is trained to output a prediction result of material types; 5) testing the trained convolutional neural network by using a test set, and verifying the classification effect of the model on the material; 6) and performing material prediction analysis on the current new material by using the tested convolutional neural network so as to judge the material of the material.

Further, the robot cell needs to grab the material in the feed bin 1105 in a direction perpendicular to the upper surface of the material for more stable grabbing, which involves a collision detection algorithm of the end effector of the robot cell and the surrounding environment and a robot motion planning algorithm.

The collision detection algorithm is used for judging whether one or more pairs of objects occupy the same area at the same time in a given time domain, and in the operation of the robot, the collision detection between the robot and an obstacle is the basis of the motion planning and the collision avoidance of the robot, and a static interference detection algorithm or a dynamic collision detection algorithm can be usually selected. The static interference detection algorithm is mainly used for detecting whether interference occurs between objects in a static state, and is suitable for scenes with low requirements on real-time performance and high requirements on precision; the dynamic collision detection algorithm aims at the situation that the relative position of an object in a scene changes along with time, and is suitable for scenes with high real-time requirements. The robot motion planning algorithm is used for solving the problems of robot motion path planning, joint space planning, comprehensive planning and the like, and the commonly used motion planning algorithm comprises but is not limited to a graph search method, an RRT algorithm, an artificial potential field method, a BUG algorithm and the like.

In some examples, the 3D cameras 1103 and 1104 are responsible for taking a high-speed picture of the grabbed materials and calculating the postures of the materials in the air, determining matched placing postures according to the calculated postures of the materials, and placing the materials on a material bearing platform of the material barcode recognition and material transplanting unit according to the placing postures. It should be noted that in the embodiment, the execution processes of high-speed photographing, attitude calculation, and the like can be performed synchronously without stopping the operation of the robot arm of the robot unit, which greatly improves the operation efficiency.

In some examples, in order to solve the abnormal situation that the robot unit grabs multiple materials at a time to cause an order error, the present embodiment adopts three coping strategies to timely and effectively detect the abnormal situation:

a first detection mode) 3D cameras 1103 and 1104 calculate three-dimensional sizes of the materials, including information such as length, width and height; and when the materials are placed on a material bearing platform of the material bar code identification and material transplanting unit, returning the material bar code information of the materials, and inquiring the standard size information of the materials from the order system through the material bar code information. If the three-dimensional size of the material obtained by calculation is judged to exceed the standard size, the situation that the material is possibly overlapped in the currently grabbed material can be determined (the robot unit grabs a plurality of materials at one time), and the material is transferred to a waste material grid of the transfer shelf unit; if not, the current material is determined to be a single piece (the robot unit grabs one piece at a time), and the material is transferred to the normal cell of the transfer shelf unit.

The detection mode is two), the end effector of the robot unit is provided with a weight sensor for detecting the weight of the grabbed materials; and when the materials are placed on a material bearing platform of the material bar code identification and material transplanting unit, returning the material bar code information of the materials, and inquiring the standard weight information of the materials from the order system through the material bar code information. If the weight of the material obtained by calculation is judged to exceed the standard weight, the situation that the material is possibly overlapped in the currently grabbed material can be determined (the robot unit grabs a plurality of materials at a time), and the material is transferred to a waste material grid of the transfer shelf unit; if not, the current material is determined to be a single piece (the robot unit grabs one piece at a time) and the material is transferred to the waste bin of the transfer rack unit.

The detection mode is three), whether the robot unit grabs more materials is judged by visually detecting the material edge information; if the situation that the materials are possibly stacked is judged to exist in the currently grabbed materials (the robot unit grabs a plurality of materials at a time), the materials are transferred to the waste material grid opening of the transfer shelf unit; if the current material is judged to be a single piece (the robot unit grabs one piece of material at a time), the material is transferred to the waste material grid of the transfer shelf unit.

It is worth noting that the general outer contour of the material is convex, which results in a non-convex contour of the overall contour if two or more materials are stacked together. Therefore, the material edge information specifically refers to whether the outer contour of the material is a convex hull contour or not through an image shot by a 3D camera; if the contour of the convex hull is determined, the current material is determined to be a single piece (the robot unit grabs one piece of material at a time); if the shape is not the convex hull contour, the situation that the material which is currently grabbed is possibly overlapped can be determined (the robot unit grabs a plurality of materials at a time).

In some examples, in order to ensure that the material is successfully delivered to the material bar code recognition and material loading platform of the material transplanting unit, the robot unit automatically adjusts the transfer speed thereof according to the weight of the material. For example, when the material is heavy, the inertia is large, so the transfer speed is reduced appropriately; when the material is light, the inertia is small, and the speed can be properly increased.

In some examples, in order to improve the code scanning efficiency, all code scanners can be started during the movement of the robot unit, so that the code scanning task can be completed when the robot unit moves towards the code scanners, and the code scanning on the surfaces of all materials can be completed without waiting for the materials to be transferred to the material bar code identification and material carrying platform of the material transplanting unit, thereby accelerating the system efficiency.

In some examples, to ensure that material is dropped into the pockets of the transfer rack unit, the visual analysis unit detects whether material remains in the transplanting mechanism when the transplanting mechanism is returned to the standby position. If the material residue is monitored, a corresponding prompt signal can be sent out to prompt manual intervention to take out the residual material, and the machine can be stopped for system detection.

Fig. 12 is a schematic flow chart illustrating an automatic entering robotic seeding and sorting method according to an embodiment of the present invention. The robot sowing and sorting method provided by the embodiment is applied to the visual analysis unit in the automatic-entering robot sowing and sorting system, and the implementation process comprises the following steps:

step S121: and collecting a material image in the incoming material box.

Step S122: and calculating the area size information and material classification information of the material absorbable surface according to the material image.

Step S123: and selecting the sucking discs suitable for the material according to the calculation result.

In some examples, the process of calculating the material classification information of the material absorbable surface material includes: collecting material data; manually calibrating based on the collected material data, and calibrating the corresponding material type; dividing the calibration data into a training set and a test set according to a preset proportion; training a convolutional neural network by utilizing a training set, wherein the convolutional neural network is trained to output a prediction result of material types; testing the trained convolutional neural network by using a test set, and verifying the classification effect of the model on the material; and performing material prediction analysis on the current new material by the convolutional neural network after training and testing.

Fig. 13 is a schematic structural diagram of a visual computing device according to an embodiment of the present invention. The visual analysis device of the present embodiment includes a processor 131, a memory 132, a communicator 133; the memory 132 is connected to the processor 131 and the communicator 133 through a system bus and performs communication with each other, the memory 132 is used for storing computer programs, the communicator 133 is used for communicating with other devices, and the processor 131 is used for operating the computer programs, so that the electronic terminal executes the steps of the automatic-check robot seeding and sorting method.

The above-mentioned system bus may be a Peripheral Component Interconnect (PCI) bus, an Extended Industry Standard Architecture (EISA) bus, or the like. The system bus may be divided into an address bus, a data bus, a control bus, and the like. For ease of illustration, only one thick line is shown, but this does not mean that there is only one bus or one type of bus. The communication interface is used for realizing communication between the database access device and other equipment (such as a client, a read-write library and a read-only library). The Memory may include a Random Access Memory (RAM), and may further include a non-volatile Memory (non-volatile Memory), such as at least one disk Memory.

The Processor may be a general-purpose Processor, and includes a Central Processing Unit (CPU), a Network Processor (NP), and the like; the Integrated Circuit may also be a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA) or other Programmable logic device, a discrete Gate or transistor logic device, or a discrete hardware component.

The present invention also provides a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements the automated entering robotic seeding sorting method.

In the embodiments provided herein, the computer-readable and writable storage medium may include read-only memory, random-access memory, EEPROM, CD-ROM or other optical disk storage, magnetic disk storage or other magnetic storage devices, flash memory, a USB flash drive, a removable hard disk, or any other medium that can be used to store desired program code in the form of instructions or data structures and that can be accessed by a computer. Also, any connection is properly termed a computer-readable medium. For example, if the instructions are transmitted from a website, server, or other remote source using a coaxial cable, fiber optic cable, twisted pair, Digital Subscriber Line (DSL), or wireless technologies such as infrared, radio, and microwave, then the coaxial cable, fiber optic cable, twisted pair, DSL, or wireless technologies such as infrared, radio, and microwave are included in the definition of medium. It should be understood, however, that computer-readable-writable storage media and data storage media do not include connections, carrier waves, signals, or other transitory media, but are intended to be non-transitory, tangible storage media. Disk and disc, as used in this application, includes Compact Disc (CD), laser disc, optical disc, Digital Versatile Disc (DVD), floppy disk and blu-ray disc where disks usually reproduce data magnetically, while discs reproduce data optically with lasers.

In summary, the present application provides an automatic entering robot seeding sorting system, method, device and medium, the present invention realizes the function of seeding operation completely performed by automatic equipment, and realizes the functions of material storage, transportation, visual analysis, grabbing and transferring, transplanting and entering through a material storage unit, a feeding unit, a visual analysis unit, a robot unit, a material bar code identification and material transplanting unit, a lifting and traversing type material placing unit and a transferring goods shelf unit, so that not only the operation efficiency is greatly improved, but also the information of the whole sorting process can be traced back, and the control and supervision of the whole flow is realized; the sorting system greatly expands the sorting capacity of the equipment due to the introduction of the robot unit; the sorting system also greatly reduces the error rate and avoids the error operation or error bill-throwing caused by manual operation in the traditional sowing sorting system; and because of the reduction of operators, the operation flow is simplified to the greatest extent, and the management cost of enterprises is greatly reduced. Therefore, the application effectively overcomes various defects in the prior art and has high industrial utilization value.

The above embodiments are merely illustrative of the principles and utilities of the present application and are not intended to limit the application. Any person skilled in the art can modify or change the above-described embodiments without departing from the spirit and scope of the present application. Accordingly, it is intended that all equivalent modifications or changes which can be made by those skilled in the art without departing from the spirit and technical concepts disclosed in the present application shall be covered by the claims of the present application.

Claims (18)

1. The utility model provides an automatic robot seeding letter sorting system that checks, its characterized in that includes:

the storage unit is used for storing materials;

the feeding unit is used for placing and conveying the material storage unit;

the visual analysis unit is used for carrying out visual scanning on the conveyed materials after the conveyed materials enter the visual scanning area so as to acquire image information of the conveyed materials and analyze material grabbing information; the material grabbing information at least comprises grabbing point position information, grabbing attitude information and target position information;

the robot unit is in communication connection with the visual analysis unit and is used for receiving the position information and the grabbing posture information of the grabbing points from the visual analysis unit, grabbing the materials in corresponding grabbing postures and transferring the materials to the material bar code recognition and material transplanting unit;

the material bar code identification and material transplanting unit comprises a bar code scanner and a material pushing mechanism; the bar code scanner is used for scanning bar codes on the surfaces of the materials; the material pushing mechanism is used for pushing the materials into the transplanting mechanism of the lifting and transverse moving type discharging unit after the code scanning is finished;

the lifting and transverse moving type discharging unit is in communication connection with the visual analysis unit and is used for receiving target position information from the visual analysis unit and then delivering the materials to corresponding grids in the transfer shelf unit through lifting and transverse moving;

the transfer rack unit comprises a plurality of grids for feeding materials.

2. The automated, entry robotic seed sorting system of claim 1, wherein:

the acquisition mode of the grabbing point position information and the grabbing attitude information comprises the following steps: the visual analysis unit obtains space geometric information of the material by scanning the outline of the material so as to obtain the position information and the grabbing posture information of the material;

the acquisition mode of the target position information comprises any one or more of the following combinations:

mode 1) a visual analysis unit obtains size information of a material by scanning the outline of the material, and obtains target position information related to the size grade of the material according to the size information; the transfer shelf unit is provided with a plurality of layers of shelves, and the shelves at different layers are used for accommodating materials with different size grades;

mode 2) the visual analysis unit obtains shape information of the material by scanning the outline of the material and obtains target position information related to the shape category of the material according to the shape information analysis; the transfer shelf unit is provided with a plurality of layers of shelves, and the shelves on different layers are used for accommodating materials of different shapes and categories;

mode 3) the visual analysis unit reads the target position information of the material by scanning the graphic code on the surface of the material.

3. The automated entering robotic seeding sorting system according to claim 1 wherein the material barcode recognition and material transplanting unit comprises:

the transparent material bearing platform is used for bearing materials;

the side code scanners are arranged around the light-transmitting material bearing platform;

the top code scanner is arranged right above the light-transmitting material bearing platform;

the bottom code scanner is arranged right below the light-transmitting material bearing platform;

after the robot unit transfers the materials to the light-transmitting material bearing platform, a plurality of side bar codes are used for scanning bar codes on a plurality of side surfaces of the materials; the top bar code scanner is used for scanning bar codes on the top surface of the material; the bottom bar code scanner is used for scanning bar codes on the bottom surface of the material through the light-transmitting material bearing platform; after the yard is scanned, the material pushing mechanism pushes the material into the transplanting mechanism of the lifting and transverse moving type discharging unit.

4. The automated entering robotic seeding sorting system according to claim 1 wherein the material barcode recognition and material transplanting unit comprises:

the material bearing platform is used for bearing materials;

the side code scanners are arranged around the material bearing platform;

the top code scanner is arranged right above the material bearing platform;

the bottom code scanner is arranged outside the material bearing platform and is positioned below the material moving path;

when the robot unit transfers the material to pass through a scanning area right above the bottom bar scanner, the bottom bar scanner scans bar codes on the bottom surface of the material; after the materials are transferred to the material bearing platform, a plurality of side code scanners are used for scanning bar codes on a plurality of side surfaces of the materials, and a top code scanner is used for scanning bar codes on the top surface of the materials; after the yard is scanned, the material pushing mechanism pushes the material into the transplanting mechanism of the lifting and transverse moving type discharging unit.

5. The automated entering robotic seeding sorting system according to claim 1 wherein the material barcode recognition and material transplanting unit comprises:

the material bearing platform is used for bearing materials; the material bearing platform comprises a first conveying line which is located at a higher position and has a slower conveying speed and a second conveying line which is located at a lower position and has a faster speed;

the side bar code scanners are arranged on the periphery of the material bearing platform and used for scanning bar codes on a plurality of side surfaces of the material;

the top bar code scanner is arranged at the top of the material bearing platform and used for scanning bar codes on the top surface of the materials;

the bottom bar code scanner is arranged on the outer side of the material bearing platform and positioned below the material moving path, and is used for scanning bar codes on the bottom surface of the material when the material passes right above the bottom bar code scanner;

the monitoring camera is arranged above the material bearing platform and used for detecting the number of the materials;

the photoelectric sensor is arranged near the material bearing platform and used for detecting whether materials pass through or not;

the stacking platform separates stacked materials through two conveying lines with height difference and speed difference; if the counting number of the monitoring cameras exceeds 1, sending a control signal to the transplanting hopper after the photoelectric sensor detects that the material passes through so as to enable the transplanting hopper to send the current material into an abnormal grid; if the number of the counting pieces of the monitoring camera is 1, when the photoelectric sensor detects that the materials pass through, a control signal is sent to the transplanting hopper, so that the transplanting hopper sends the current materials into a normal grid.

6. The automated entering robotic seeding sorting system according to claim 1 wherein the material barcode recognition and material transplanting unit comprises:

the material bearing platform is rotated to bear materials;

a pair of side code scanners which are arranged at the side of the rotary material bearing platform and are oppositely arranged;

the top code scanner is arranged at the top of the rotary material bearing platform;

the bottom code scanner is arranged outside the rotary material bearing platform and is positioned below the material moving path;

when the robot unit transfers the material to pass through a scanning area right above the bottom bar scanner, the bottom bar scanner scans bar codes on the bottom surface of the material; after the materials are transferred to the material bearing platform, bar codes are scanned on two side surfaces of the materials by a pair of side bar scanners, and bar codes are scanned on the other two side surfaces after the materials are rotated by less than 180 degrees by rotating the material bearing platform; after the yard is scanned, the material pushing mechanism pushes the material into the transplanting mechanism of the lifting and transverse moving type discharging unit.

7. The automated entering robotic seeding sorting system according to claim 1 wherein the material barcode recognition and material transplanting unit comprises:

the material bearing platform is used for bearing materials;

the rotary side code scanner is arranged on the side of the material bearing platform;

the top code scanner is arranged at the top of the material bearing platform;

the bottom code scanner is arranged outside the material bearing platform and is positioned below the material moving path;

when the robot unit transfers the material to pass through a scanning area right above the bottom bar scanner, the bottom bar scanner scans bar codes on the bottom surface of the material; after the materials are transferred to the material bearing platform, firstly, bar codes are scanned on one side surface of the materials through a side bar code scanner, and then, after the materials are rotated by less than 360 degrees through a rotary side bar code scanner, bar codes are scanned on the other three side surfaces of the materials; after the yard is scanned, the material pushing mechanism pushes the material into the transplanting mechanism of the lifting and transverse moving type discharging unit.

8. The automated entering robotic seeding sorting system according to claim 1 wherein the material barcode recognition and material transplanting unit comprises:

the material bearing platform is used for bearing materials;

the bottom code scanner is arranged outside the material bearing platform and is positioned below the material moving path;

the top code scanner is arranged at the top of the material bearing platform;

a rotary side code scanner arranged at the side of the material bearing platform;

when the robot unit transfers the material to pass through a scanning area right above the bottom bar scanner, the bottom bar scanner scans bar codes on the bottom surface of the material; after the materials are transferred to the material bearing platform, bar codes are scanned on one side surface of the materials through a side bar code scanner, and then the materials are rotated through a rotating shaft of the robot unit, so that the side bar code scanner scans the other three side surfaces of the materials; after the code scanning is finished, the robot unit puts the materials on the material bearing platform and pushes the materials into the next procedure through the material pushing mechanism, or the robot unit directly puts the materials into the next procedure.

9. The automated, indexed robotic seed sorting system according to claims 3, 4, 6, 7, or 8, wherein the pusher mechanism comprises: the device comprises an air cylinder mechanism, a push plate and a sliding chute; the cylinder mechanism is connected with and pushes the push plate; the material bearing platform is positioned on the pushing path of the push plate; the transplanting mechanism in the chute guide lifting and transverse moving type discharging unit; after the yard is swept, the cylinder mechanism promotes the material on the material platform will be held to the push pedal outwards release to make the material along the spout falls into in the transplanting mechanism among the lift and sideslip formula blowing unit.

10. The automated entering robotic seeding and sorting system of claim 9 wherein the surface of the holding platform is in a concavo-convex alternating shape; the end part of the push plate, which is contacted with the material bearing platform, is also in a concave-convex alternate shape; and the concave part of the material bearing platform is correspondingly contacted with the convex part at the end part of the push plate, so that the sheet materials are pushed out in a concave-convex crossed connection mode.

11. The automated, caged robotic seeding and sorting system of claim 1 wherein the lift and traverse discharge unit comprises: a lifting mechanism, a transverse moving mechanism and a transplanting mechanism; the transplanting mechanism is arranged on the lifting mechanism; the lifting mechanism is arranged on the transverse moving mechanism; the transplanting mechanism is driven by the lifting mechanism to do lifting movement and driven by the transverse moving mechanism to do transverse moving movement.

12. The automated, self-entering robotic seed sorting system of claim 11, wherein said transplanting mechanism comprises a cylinder side-push transplanting mechanism comprising:

the material receiving hopper is used for receiving materials;

the corner mechanism is used for connecting and rotating the head orientation of the material receiving hopper;

the material inlet detection sensor is arranged on the material receiving hopper and used for detecting whether materials enter the material receiving hopper or not and sending detection signals to the transverse moving mechanism and the lifting mechanism when detecting that the materials enter the material receiving hopper so as to enable the transverse moving mechanism and the lifting mechanism to perform corresponding transverse moving and lifting movement and then reach the corresponding grid openings;

the transverse pushing mechanism is arranged on the material receiving hopper;

the transverse moving scraper is arranged in the material receiving hopper and pushes the materials in the hopper into the lattice openings of the transfer shelf units after being pushed by the transverse moving mechanism.

13. The automated, self-entering robotic seed sorting system of claim 11, wherein the transplanting mechanism comprises a belt conveyor type transplanting mechanism comprising:

the material receiving hopper is used for receiving materials;

the corner mechanism is used for connecting and rotating the head orientation of the material receiving hopper;

the material inlet detection sensor is arranged on the material receiving hopper and used for detecting whether materials enter the material receiving hopper or not and sending detection signals to the transverse moving mechanism and the lifting mechanism when detecting that the materials enter the material receiving hopper so as to enable the transverse moving mechanism and the lifting mechanism to perform corresponding transverse moving and lifting movement and then reach the corresponding grid openings;

and the belt mechanism is used for pushing the materials into the grids of the transfer shelf unit.

14. The automated, entry robotic seed sorting system of claim 1, wherein the transfer rack unit comprises: each layer of goods shelf is provided with a material frame bearing plate, and each layer of material frame bearing plate is provided with a plurality of grids; the grid openings comprise normal grid openings for placing normal material for scanning the code and abnormal grid openings for placing abnormal material for scanning the code; the bearing plate is a rotatable bearing plate, so that the direction of the cell is changed by rotating the bearing plate.

15. An automatic entering robot seeding sorting method, characterized in that, it is applied to the visual analysis unit in claim 1; the method comprises the following steps:

collecting a material image in an incoming material box;

calculating the area size information and material classification information of the material absorbable surface according to the material image;

and selecting the sucking discs suitable for the material according to the calculation result.

16. The robotic seeding sorting method according to claim 15, wherein the process of calculating the material classification information of the material absorbable surface includes:

collecting material data;

manually calibrating based on the collected material data, and calibrating the corresponding material type;

dividing the calibration data into a training set and a test set according to a preset proportion;

training a convolutional neural network by utilizing a training set, wherein the convolutional neural network is trained to output a prediction result of material types;

testing the trained convolutional neural network by using a test set, and verifying the classification effect of the model on the material; and performing material prediction analysis on the current new material by the convolutional neural network after training and testing.

17. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the automated entering robotic seeding sorting method according to claim 15 or 16.

18. A visual analysis apparatus, comprising: a processor and a memory;

the memory is used for storing a computer program;

the processor is configured to execute the memory stored computer program to cause the apparatus to perform the automated entering robotic seeding sorting method of claim 15 or 16.

Images