Material grasping method and device based on material sorting equipment

Abstract

The present invention provides a material grasping method and device based on a material sorting device. The method includes: in response to the vibration completion instruction of the vibration disk, acquiring the image information of each target material in the target material group on the vibration disk; determining the sub-states of the respective target materials based on the image information, and obtaining the material distribution state of the target material group according to the sub-states of all the target materials; generating a grasping instruction in the case where the material distribution state meets a preset grasping condition, the grasping instruction being used to control a plurality of suction nozzles at the end of the manipulator of the material sorting device to respectively grasp the respective target materials one by one; and generating an information feedback instruction in the case where the material distribution state does not meet the preset grasping condition, the information feedback instruction being used to control the vibration disk to start and / or emit a warning signal. This method and device improve the success rate of a single grasping by the manipulator and the material grasping efficiency, and solve the technical problem of low material grasping efficiency in the prior art.

Description

Technical Field

[0001] The present invention relates to the technical field of material sorting, and in particular to a material grasping method and device based on a material sorting device. Background Art

[0002] Before feeding bulk materials, it is often necessary to use a vibrating and spreading plate to disperse and flatten the materials to facilitate the grasping by a manipulator. However, in the existing technology, after the vibrating and spreading plate finishes vibrating, the materials may be stacked or face upwards, and the manipulator cannot effectively grasp them. During the working process, after one grasping, the manipulator needs to return to its original position first and then perform a second grasping. Due to situations such as stacking, the success rate of a single grasping by the manipulator is relatively low, and the manipulator needs to reciprocate multiple times to complete the material grasping, resulting in low material grasping efficiency. Summary of the Invention

[0003] The present invention provides a material grasping method and device based on a material sorting device to solve the technical problem of low material grasping efficiency in the existing technology.

[0004] The present invention provides a material grasping method based on a material sorting device, and the method includes:

[0005] In response to the vibration completion instruction of the vibrating and spreading plate, obtain the image information of each target material in the target material group on the vibrating and spreading plate;

[0006] Based on the image information, determine the sub-states of the target materials, and obtain the material distribution state of the target material group according to the sub-states of all the target materials;

[0007] When the material distribution state meets the preset grasping condition, generate a grasping instruction, and the grasping instruction is used to control a plurality of suction nozzles at the end of the manipulator of the material sorting device to respectively grasp each target material one by one;

[0008] When the material distribution state does not meet the preset grasping condition, generate an information feedback instruction, and the information feedback instruction is used to control the vibrating and spreading plate to start and / or emit a warning signal.

[0009] In some embodiments, based on the image information, determine the sub-states of the target materials, and obtain the material distribution state of the target material group according to the sub-states of all the target materials, which specifically includes:

[0010] Obtain the area data and quantity data of the target materials in the image;

[0011] If it is determined according to the area data and the quantity data that the sub-state of the target material is a stacked state, then count the number of the target materials in the target material group that are in the stacked state;

[0012] If the number of the target materials in the stacked state reaches a first threshold, it is determined that the material distribution state does not meet the preset grasping condition, and the feedback instruction is generated.

[0013] In some embodiments, determining that the sub-state of the target material is the stacked state according to the area data and the quantity data specifically includes:

[0014] If the target material is a non-transparent material, obtain the single area of the target material, and determine that the sub-state of the target material is the stacked state when the single area is greater than a preset area threshold;

[0015] If the target material is a transparent material, obtain the total area of the target material group and the number of the target materials included in the target material group, calculate the quotient of the total area and the number of the target materials to obtain an average area, and determine that the sub-state of the target material is the stacked state when the average area is less than the set area of the target material stored in advance.

[0016] In some embodiments, determining the sub-state of the target material based on the image information and obtaining the material distribution state of the target material group according to the sub-states of all the target materials specifically includes:

[0017] Obtain the characteristic data of the target material;

[0018] If it is determined that the sub-state of the target material is the state of facing upwards according to the characteristic data, count the number of the target materials in the target material group that are in the state of facing upwards;

[0019] If the number of the target materials in the state of facing upwards reaches a second threshold, it is determined that the material distribution state does not meet the preset grasping condition, and the feedback instruction is generated.

[0020] In some embodiments, obtaining the characteristic data of the target material specifically includes:

[0021] Extract the material contour features in the image information and determine multiple identification positions in the material contour features;

[0022] Obtain the standard deviation of brightness of each of the identification positions respectively, and calculate the average value of the standard deviations of brightness;

[0023] When the average value of the standard deviations of brightness is less than a preset brightness threshold, determine that the sub-state of the target material is the state of facing upwards.

[0024] In some embodiments, obtaining the characteristic data of the target material specifically includes:

[0025] Extract the material direction feature in the image information;

[0026] Based on the direction feature, extract the regional brightness in multiple regions and calculate the average value of the regional brightness of each region;

[0027] When the average value of the regional brightness is less than the preset regional brightness threshold, determine that the sub-state of the target material is face-up.

[0028] In some embodiments, obtaining the feature data of the target material specifically includes:

[0029] Extract the material specific shape feature in the image information;

[0030] When the extracted material characteristic shape feature contains the preset characteristic shape, determine that the sub-state of the target material is face-towards state;

[0031] Wherein the preset specific shape includes at least one of angle, hole position and shape.

[0032] In some embodiments, when the material distribution state meets the preset grasping condition, generate a grasping instruction, and the grasping instruction is used to control a plurality of suction nozzles at the end of the manipulator of the material sorting device to respectively grasp each target material one by one. After that, it further includes:

[0033] Obtain the position data of the target suction nozzle;

[0034] When the position data meets the grasping condition, the manipulator grasps the target material corresponding to the position of the target suction nozzle according to the grasping instruction;

[0035] Based on the working state of the vacuum cylinder of the target suction nozzle, determine whether the target suction nozzle grasps successfully;

[0036] When the target suction nozzle fails to grasp, send the number of the target suction nozzle and the shortage quantity to the image acquisition device of the material sorting device;

[0037] After completing the subsequent grasping, generate the next round of material taking request instruction based on the number of the target suction nozzle and the shortage quantity.

[0038] The present invention also provides a material grasping device based on a material sorting device, and the device includes:

[0039] An image data acquisition unit, configured to obtain the image information of each target material in the target material group on the vibrating tray in response to the vibrating completion instruction of the vibrating tray;

[0040] A material distribution determination unit, configured to determine the sub-states of each of the target materials based on the image information, and obtain the material distribution state of the target material group according to the sub-states of all the target materials;

[0041] A grasping instruction generation unit, configured to generate a grasping instruction when the material distribution state meets a preset grasping condition, where the grasping instruction is used to control a plurality of suction nozzles at the end of the manipulator of the material sorting device to respectively grasp each of the target materials in a one-to-one correspondence;

[0042] A feedback instruction generation unit, configured to generate an information feedback instruction when the material distribution state does not meet the preset grasping condition, where the information feedback instruction is used to control the vibration disk to start and / or issue a warning signal.

[0043] The present invention further provides a material sorting device, including a vibration disk, a storage bin, a manipulator with suction nozzles, and a controller; wherein, the number of the suction nozzles is multiple, the controller includes a memory, a processor, and a computer program stored on the memory and executable on the processor, and when the processor executes the program, the steps of the material grasping method as described above are implemented.

[0044] The material grasping method based on a material sorting device provided by the present invention includes: in response to a vibration completion instruction of a vibration disk, acquiring image information of each target material in a target material group on the vibration disk; determining the sub-states of each of the target materials based on the image information, and obtaining the material distribution state of the target material group according to the sub-states of all the target materials; generating a grasping instruction when the material distribution state meets a preset grasping condition, where the grasping instruction is used to control a plurality of suction nozzles at the end of the manipulator of the material sorting device to respectively grasp each of the target materials in a one-to-one correspondence; generating an information feedback instruction when the material distribution state does not meet the preset grasping condition, where the information feedback instruction is used to control the vibration disk to start and / or issue a warning signal.

[0045] During the working process, the image acquisition device of the device will collect the image information of the target materials on the vibration disk in real time. When it is determined that the material distribution state in the image information does not meet the grasping condition, a start signal is sent to the vibration disk or a warning signal is issued, so as to restart the vibration disk to further vibrate the materials, so as to overcome the problem that the grasping condition is not met. After the materials meet the grasping condition, the manipulator is started to perform grasping, which avoids the multiple reciprocating movements of the manipulator, improves the success rate of a single grasping of the manipulator, improves the grasping efficiency of the materials, and solves the technical problem of low material grasping efficiency in the prior art.

[0046] Further, in some embodiments, after the material grasping fails, the number of the target suction nozzle and the shortage quantity are sent to the image acquisition device of the material sorting equipment, and after the subsequent grasping is completed, a next round of material taking request instruction is generated. That is to say, when there are multiple suction nozzles, when an individual suction nozzle fails to grasp, the shortage quantity is determined. When the shortage quantity does not reach the pre-set threshold, the subsequent grasping process is first completed, and then the manipulator is returned and the next process is entered, further improving the quantity and efficiency of single grasping. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the drawings in the following description are some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0048] Figure 1 One of the flow diagrams of the material grasping method based on the material sorting equipment provided by the present invention;

[0049] Figure 2 One of the flow diagrams of the material grasping method based on the material sorting equipment provided by the present invention;

[0050] Figure 3 One of the flow diagrams of the material grasping method based on the material sorting equipment provided by the present invention;

[0051] Figure 4 One of the flow diagrams of the material grasping method based on the material sorting equipment provided by the present invention;

[0052] Figure 5 and Figure 6 Effect diagram of contour feature matching;

[0053] Figure 7 One of the flow diagrams of the material grasping method based on the material sorting equipment provided by the present invention;

[0054] Figure 8 Effect diagram of direction feature matching;

[0055] Figure 9 One of the flow diagrams of the material grasping method based on the material sorting equipment provided by the present invention;

[0056] Figure 10 Example diagram of materials with different shapes;

[0057] Figure 11Seventh flowchart of the material grasping method based on the material sorting device provided by the present invention;

[0058] Figure 12 Structural block diagram of the material grasping device based on the material sorting device provided by the present invention. Detailed implementation manners

[0059] To make the objectives, technical solutions and advantages of the present invention clearer, the technical solutions in the present invention will be clearly and completely described below with reference to the accompanying drawings in the present invention. Obviously, the described embodiments are some but not all of the embodiments of the present invention. For the embodiments applied to the present invention, all other embodiments obtained by those of ordinary skill in the art without making creative efforts shall fall within the protection scope of the present invention.

[0060] To solve the problems in the prior art that the grasping efficiency of bulk materials such as electronic devices is low and the number of materials grasped at one time is small, the present invention provides a material grasping method and device based on a material sorting device. Based on a manipulator structure with multiple suction nozzles, the material grasping efficiency is improved and the number of materials grasped at one time is increased through preset instruction triggering conditions.

[0061] Please refer to Figure 1 , Figure 1 First flowchart of the material grasping method based on the material sorting device provided by the present invention.

[0062] In a specific implementation manner, the material grasping method based on the material sorting device provided by the present invention includes the following steps:

[0063] S101: In response to the vibration completion instruction of the vibration disk, obtain the image information of each target material in the target material group on the vibration disk. The number of target materials included in the target material group can be set according to the working conditions. For example, each target material group includes 8 target materials. In an actual use scenario, when sorting materials, the materials in the storage bin enter the vibration disk, and after the vibration disk completes the vibration, the controller will generate a vibration completion instruction. After obtaining this vibration completion instruction, the image acquisition device (such as a camera) starts to acquire the image information of each target material in the target material group on the vibration disk. Alternatively, the camera can also continuously acquire image information, and when the vibration completion instruction is obtained, the obtained image information is used as valid image information.

[0064] S102: Determine the sub - states of each of the target materials based on the image information, and obtain the material distribution state of the target material group according to the sub - states of all the target materials. For example, determine whether there is material stacking at each target material or whether the target material is in the reverse side through the image information. When there is material stacking or the reverse - side state at the target material, count the number of target materials with stacking or reverse - side states in the target material group.

[0065] S103: Generate a grasping instruction when the material distribution state meets the preset grasping conditions. The grasping instruction is used to control the multiple suction nozzles at the end of the manipulator of the material sorting device to respectively grasp each of the target materials one by one. In a specific usage scenario, to improve the efficiency of material grasping, the suction nozzles set at the end of the manipulator can be a group of suction nozzles, with multiple suction nozzles in each group. When the target material group includes 8 target materials, the number of suction nozzles can be 6 + N. Use a group of suction nozzles to sequentially suck multiple target materials. When the number of target materials with stacking or reverse - side states does not reach the preset number, for example, when 6 + 2 suction nozzles grasp 8 target materials, if the number of target materials with stacking or reverse - side states is less than 3, such as 1 or 2, it is determined that the material distribution state meets the grasping conditions.

[0066] S104: Generate an information feedback instruction when the material distribution state does not meet the preset grasping conditions. The information feedback instruction is used to control the vibration - scattering plate to start and / or issue a warning signal. When the number of target materials with stacking or reverse - side states reaches the preset number, for example, when 6 + 2 suction nozzles grasp 8 target materials, if the number of target materials with stacking or reverse - side states is greater than 3, such as 4 or 5, it is determined that the material distribution state does not meet the grasping conditions.

[0067] In a usage scenario, taking the case where each group of suction nozzles includes 6 + 2 suction nozzles and each group of target material groups includes 8 target materials as an example, each suction nozzle is set with a nozzle number. During the working process, use a camera to take images of each target material, respectively determine whether there is material stacking or reverse - side state for each target material according to the images, and count the number of target materials with material stacking or reverse - side states. When the counted number of target materials with material stacking or reverse - side states is 2, it is determined that the material distribution state meets the preset grasping conditions. When the counted number of target materials with material stacking or reverse - side states is 4, it is determined that the material distribution state does not meet the preset grasping conditions.

[0068] In some embodiments, as Figure 2 shown, determining the sub - state of the target material based on the image information and obtaining the material distribution state of the target material group according to the sub - states of all the target materials specifically includes the following steps:

[0069] S201: Obtain the area data and quantity data of the target material in the image; that is, use the camera above the vibrating and spreading plate to capture an image of the target material, and through conventional image processing techniques, the area data of the target material and the quantity data of the target material that can be captured can be obtained.

[0070] S202: If it is determined that the sub-state of the target material is a stacked state based on the area data and the quantity data, then count the number of the target materials in the target material group that are in the stacked state.

[0071] Specifically, if the target material is an opaque material, obtain the single area of the target material. When the single area is greater than a preset area threshold, determine that the sub-state of the target material is a stacked state; if the target material is a transparent material, obtain the total area of the target material group and the number of the target materials included in the target material group, calculate the quotient of the total area and the number of the target materials to obtain an average area. When the average area is less than the set area of the target material stored in advance, determine that the sub-state of the target material is a stacked state.

[0072] S203: If the number of the target materials in the stacked state reaches a first threshold, determine that the material distribution state does not meet the preset grasping condition, and generate the feedback instruction. This first threshold can be determined according to the actual working condition requirements, the number of suction nozzles in each group of suction nozzles, and the number of target materials in each group of target material groups. For example, it can be three, four or more. Still taking the above scenario as an example, taking the case where each group of suction nozzles includes 6 + 2 suction nozzles and each group of target material groups includes 8 target materials as an example, when the number of target materials in the stacked state reaches 3, determine that the material distribution state does not meet the preset grasping condition, and generate the feedback instruction.

[0073] In some embodiments, as Figure 3 shown, determine the sub-state of the target material based on the image information, and obtain the material distribution state of the target material group according to the sub-states of all the target materials, specifically including the following steps:

[0074] S301: Obtain the characteristic data of the target material;

[0075] S302: If it is determined that the sub-state of the target material is the state of facing upwards based on the characteristic data, then count the number of the target materials in the target material group that are in the state of facing upwards; it should be understood that the reverse side refers to the side opposite to the required surface. For example, when the surface recognized by the suction nozzle is the front side, then the back side of the material is the reverse side, and when the surface recognized by the suction nozzle is the back side, then the front side of the material is the reverse side.

[0076] S303: If the number of the target materials in the face-up state reaches the second threshold, it is determined that the material distribution state does not meet the preset grasping condition, and the feedback instruction is generated.

[0077] Among them, as Figure 4 shown, obtaining the characteristic data of the target material specifically includes the following steps:

[0078] S401: Extract the material contour features in the image information, and determine multiple identification positions in the material contour features;

[0079] S402: Obtain the brightness standard deviation of each of the identification positions respectively, and calculate the average value of the brightness standard deviations;

[0080] S403: In the case where the average value of the brightness standard deviations is less than the preset brightness threshold, it is determined that the sub-state of the target material is the face-up state.

[0081] Specifically, as Figure 5 and Figure 6 shown, taking the most obvious contour feature of the target material as the matching benchmark, and then taking the matched contour as the benchmark, at the fixed identification positions, the vision system first defines the standard brightness standard deviation of the front and back of the identification. If the brightness difference is greater than the brightness threshold, it is the front, and if it is less than the brightness threshold, it is the back. Further, due to the deviation of the matching position, the accuracy of feature matching can be improved by setting multiple identifications. For example, Figure 6 the characteristic positions respectively identified in the four rectangular blocks in

[0082] In some embodiments, as Figure 7 shown, obtaining the characteristic data of the target material specifically includes the following steps:

[0083] S701: Extract the material direction feature in the image information;

[0084] S702: Taking the direction feature as the benchmark, extract the regional brightness in multiple regions, and calculate the average value of the regional brightness;

[0085] S703: In the case where the average value of the regional brightness is less than the preset regional brightness threshold, it is determined that the sub-state of the target material is the face-up state.

[0086] Specifically, taking a certain feature on the front as the direction standard to define the opposite direction of the back. Taking this feature as the benchmark, take the brightness of multiple regions, and calculate the difference of the average values of the brightness of multiple regions. When the difference value is greater than the regional brightness threshold, it is the front, otherwise it is the back. As Figure 8As shown, the shaded area of the entire image pixels is counted, and all individual discrete materials are separated using BLOB. Suppose 20 are obtained. Then, with the BLOB result as the center, a small range ROT is drawn to obtain the target material corresponding to the box, which is the material in the reverse-up state.

[0087] In some embodiments, as Figure 9 shown, obtaining the characteristic data of the target material specifically includes the following steps:

[0088] S901: Extract the specific shape features of the material in the image information;

[0089] S902: If the extracted specific shape features of the material do not include the preset specific shape, then determine that the sub-state of the target material is the reverse-facing state;

[0090] Wherein the preset specific shape includes at least one of angle, hole position, and shape.

[0091] As Figure 10 shown, in actual products, the materials may have various shapes, such as Figure 10 Eight different material shapes are given in. According to the determination of the vision system, the features on the upper surface of the normal product (such as angle, hole position, and shape, etc.) are used to calibrate the front and back sides.

[0092] In addition, for materials with relatively small sizes, the white dot test method can also be used. The brightness uniformity is used for testing. It is defined that the brightness difference of the overall area of the front side is uneven, and the brightness difference of the back side is uniform for determination during vibration.

[0093] When controlling the suction nozzle to grasp the target material according to the grasping instruction, the situation of grasping failure may occur. If only a small part of the suction nozzles in a group fail to grasp, there is no need to re-grasp, and the next process can be carried out, thus improving the grasping efficiency.

[0094] For this reason, in some embodiments, as Figure 11 shown, when the material distribution state meets the preset grasping conditions, a grasping instruction is generated. The grasping instruction is used to control the suction nozzle at the end of the manipulator of the material sorting device to grasp the target material. After that, it further includes:

[0095] S1101: Obtain the position data of the target suction nozzle;

[0096] S1102: When the position data meets the grasping conditions, the manipulator grasps the target material corresponding to the position of the target suction nozzle according to the grasping instruction;

[0097] S1103: Determine whether the target nozzle has successfully grasped based on the working state of the vacuum cylinder of the target nozzle;

[0098] S1104: In the case where the target nozzle fails to grasp, send the number of the target nozzle and the shortage quantity of materials to the image acquisition device of the material sorting equipment;

[0099] S1105: After completing subsequent grasping, generate a next-round material taking request instruction based on the number of the target nozzle and the shortage quantity of materials.

[0100] When the material grasping fails, send the number of the target nozzle and the shortage quantity of materials to the image acquisition device of the material sorting equipment, and after completing subsequent grasping, generate a next-round material taking request instruction. That is to say, when there are multiple nozzles, when an individual nozzle fails to grasp, by setting the empirical value N to determine the shortage quantity of materials, when the shortage quantity does not reach the preset threshold, the subsequent grasping process is first completed, then the manipulator is returned and the next process is entered, further improving the quantity and efficiency of single-time grasping.

[0101] In the above specific implementation manner, the material grasping method provided by the present invention based on a material sorting equipment obtains the image information of the target material on the vibrating and loosening tray by responding to the vibrating and loosening completion instruction of the vibrating and loosening tray; determines the material distribution state of the target material based on the image information; and generates a grasping instruction for controlling the nozzle at the end of the manipulator of the material sorting equipment to grasp the target material when the material distribution state meets the preset grasping condition; and generates an information feedback instruction for controlling the vibrating and loosening tray to start and / or issue a warning signal when the material distribution state does not meet the preset grasping condition.

[0102] During the working process, the image acquisition device of the equipment will collect the image information of the target material on the vibrating and loosening tray in real time. When it is determined that the material distribution state in the image information does not meet the grasping condition, a start signal is sent to the vibrating and loosening tray or a warning signal is issued, so as to restart the vibrating and loosening tray to further vibrate and loosen the material to overcome the problem of not meeting the grasping condition. After the material meets the grasping condition, the manipulator is started to grasp, avoiding multiple reciprocating movements of the manipulator, improving the success rate of single-time grasping of the manipulator, improving the material grasping efficiency, and solving the technical problem of low material grasping efficiency in the prior art.

[0103] In addition to the above method, the present invention also provides a material grasping device based on a material sorting equipment, as Figure 12 shown, the device includes:

[0104] An image data acquisition unit 1201, configured to obtain image information of a target material on the vibrating and spreading tray in response to a vibrating and spreading completion instruction of the vibrating and spreading tray;

[0105] A material distribution determination unit 1202, configured to determine a material distribution state of the target material based on the image information;

[0106] A grasping instruction generation unit 1203, configured to generate a grasping instruction when the material distribution state meets a preset grasping condition, where the grasping instruction is used to control a suction nozzle at the end of a manipulator of the material sorting device to grasp the target material;

[0107] A feedback instruction generation unit 1204, configured to generate an information feedback instruction when the material distribution state does not meet the preset grasping condition, where the information feedback instruction is used to control the vibrating and spreading tray to start and / or issue a warning signal.

[0108] The present invention provides a material grasping method based on a material sorting device, and the method includes:

[0109] In response to a vibrating and spreading completion instruction of the vibrating and spreading tray, obtain image information of each target material in a target material group on the vibrating and spreading tray;

[0110] Determine a sub-state of each target material based on the image information, and obtain a material distribution state of the target material group according to the sub-states of all the target materials;

[0111] When the material distribution state meets a preset grasping condition, generate a grasping instruction, where the grasping instruction is used to control a plurality of suction nozzles at the end of a manipulator of the material sorting device to respectively grasp each target material in a one-to-one correspondence;

[0112] When the material distribution state does not meet the preset grasping condition, generate an information feedback instruction, where the information feedback instruction is used to control the vibrating and spreading tray to start and / or issue a warning signal.

[0113] In some embodiments, determining a sub-state of the target material based on the image information and obtaining a material distribution state of the target material group according to the sub-states of all the target materials specifically includes:

[0114] Obtain area data and quantity data of the target material in the image;

[0115] If it is determined according to the area data and the quantity data that the sub-state of the target material is a stacked state, then count the number of target materials in the target material group that are in the stacked state;

[0116] If the number of the target materials in the stacked state reaches the first threshold, it is determined that the material distribution state does not meet the preset grasping condition, and the feedback instruction is generated.

[0117] In some embodiments, determining that the sub-state of the target material is the stacked state according to the area data and the quantity data specifically includes:

[0118] If the target material is a non-transparent material, obtain the single area of the target material. In the case where the single area is greater than the preset area threshold, determine that the sub-state of the target material is the stacked state;

[0119] If the target material is a transparent material, obtain the total area of the target material group and the number of the target materials included in the target material group, calculate the quotient of the total area and the number of the target materials to obtain the average area. In the case where the average area is less than the set area of the target material stored in advance, determine that the sub-state of the target material is the stacked state.

[0120] In some embodiments, determining the sub-state of the target material based on the image information and obtaining the material distribution state of the target material group according to the sub-states of all the target materials specifically includes:

[0121] Obtain the feature data of the target material;

[0122] If it is determined that the sub-state of the target material is the state of facing upwards according to the feature data, count the number of the target materials in the target material group that are in the state of facing upwards;

[0123] If the number of the target materials in the state of facing upwards reaches the second threshold, it is determined that the material distribution state does not meet the preset grasping condition, and the feedback instruction is generated.

[0124] In some embodiments, obtaining the feature data of the target material specifically includes:

[0125] Extract the material contour features in the image information and determine multiple identification positions in the material contour features;

[0126] Obtain the brightness standard deviation of each of the identification positions respectively, and calculate the average value of the brightness standard deviations;

[0127] In the case where the average value of the brightness standard deviations is less than the preset brightness threshold, determine that the sub-state of the target material is the state of facing upwards.

[0128] In some embodiments, obtaining the feature data of the target material specifically includes:

[0129] Extract the material direction feature in the image information;

[0130] Taking the direction feature as a reference, extract the regional brightness in multiple regions and calculate the average value of the brightness of each region;

[0131] When the average value of the regional brightness is less than a preset regional brightness threshold, determine that the sub-state of the target material is the reverse side facing up state.

[0132] In some embodiments, obtaining the feature data of the target material specifically includes:

[0133] Extract the specific shape feature of the material in the image information;

[0134] When the extracted specific shape feature of the material contains a preset specific shape, determine that the sub-state of the target material is the reverse facing state;

[0135] Wherein the preset specific shape includes at least one of an angle, a hole position, and a shape.

[0136] In some embodiments, when the material distribution state meets a preset grasping condition, generate a grasping instruction, and the grasping instruction is used to control a plurality of suction nozzles at the end of the manipulator of the material sorting device to respectively grasp each target material one by one. After that, it further includes:

[0137] Obtain the position data of the target suction nozzle;

[0138] When the position data meets the grasping condition, the manipulator grasps the target material corresponding to the position of the target suction nozzle according to the grasping instruction;

[0139] Based on the working state of the vacuum cylinder of the target suction nozzle, determine whether the target suction nozzle grasps successfully;

[0140] When the target suction nozzle fails to grasp, send the number of the target suction nozzle and the number of missing materials to the image acquisition device of the material sorting device;

[0141] After completing subsequent grasping, generate a next round of material taking request instruction based on the number of the target suction nozzle and the number of missing materials.

[0142] In the above specific embodiments, the material grabbing system based on the material sorting equipment provided by the present invention obtains the image information of the target material on the vibrating and loosening tray by responding to the vibrating and loosening completion instruction of the vibrating and loosening tray; determines the material distribution state of the target material based on the image information; and generates a grabbing instruction when the material distribution state meets the preset grabbing conditions, where the grabbing instruction is used to control the suction nozzle at the end of the manipulator of the material sorting equipment to grab the target material; and generates an information feedback instruction when the material distribution state does not meet the preset grabbing conditions, where the information feedback instruction is used to control the vibrating and loosening tray to start and / or issue a warning signal.

[0143] During the working process, the image acquisition device of the equipment will collect the image information of the target material on the vibrating and loosening tray in real time. When it is determined that the material distribution state in the image information does not meet the grabbing conditions, a start signal or a warning signal is sent to the vibrating and loosening tray, so as to restart the vibrating and loosening tray and further vibrate and loosen the material to overcome the problem of not meeting the grabbing conditions. When the material meets the grabbing conditions, the manipulator is then started to grab, avoiding multiple reciprocating movements of the manipulator, improving the success rate of a single grab by the manipulator, improving the grabbing efficiency of the material, and solving the technical problem of low material grabbing efficiency in the prior art.

[0144] The present invention also provides a material sorting equipment, including a vibrating and loosening tray, a storage bin, a manipulator with a suction nozzle, and a controller; wherein, the number of the suction nozzles is multiple, the controller includes a memory, a processor, and a computer program stored on the memory and executable on the processor, and when the processor executes the program, the steps of the above-mentioned material grabbing method are implemented.

[0145] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place, or may be distributed to multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment. Those of ordinary skill in the art can understand and implement it without creative labor.

[0146] Through the description of the above embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on such an understanding, the above technical solution, in essence, or the part that contributes to the prior art can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0147] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements for some of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A material grasping method based on a material sorting device, characterized in that, The method includes: In response to the vibration and scattering completion instruction of the vibration and scattering plate, obtaining the image information of each target material in the target material group on the vibration and scattering plate; Based on the image information, determining the sub-states of the target materials, and obtaining the material distribution state of the target material group according to the sub-states of all the target materials; When the material distribution state meets the preset grasping condition, generating a grasping instruction, where the grasping instruction is used to control multiple suction nozzles at the end of the manipulator of the material sorting device to respectively grasp each of the target materials one by one; When the material distribution state does not meet the preset grasping condition, generating an information feedback instruction, where the information feedback instruction is used to control the vibration and scattering plate to start and / or emit a warning signal; Based on the image information, determining the sub-states of the target materials, and obtaining the material distribution state of the target material group according to the sub-states of all the target materials, specifically including: Obtaining the area data and quantity data of the target materials in the image; If it is determined according to the area data and the quantity data that the sub-state of the target material is a stacked state, then counting the number of target materials in the target material group that are in the stacked state; If the number of target materials in the stacked state reaches a first threshold, determining that the material distribution state does not meet the preset grasping condition, and generating the feedback instruction; According to the area data and the quantity data, determining that the sub-state of the target material is a stacked state, specifically including: If the target material is a non-transparent material, obtaining the single area of the target material, and determining that the sub-state of the target material is a stacked state when the single area is greater than a preset area threshold; If the target material is a transparent material, obtaining the total area of the target material group and the number of target materials included in the target material group, calculating the quotient of the total area and the number of target materials to obtain an average area, and determining that the sub-state of the target material is a stacked state when the average area is less than the set area of the target material stored in advance.

2. The material grasping method based on the material sorting equipment according to claim 1, characterized in that Based on the image information, determining the sub-states of the target materials, and obtaining the material distribution state of the target material group according to the sub-states of all the target materials, specifically including: Obtaining the characteristic data of the target materials; If it is determined according to the characteristic data that the sub-state of the target material is a state of facing upwards, then counting the number of target materials in the target material group that are in the state of facing upwards; If the number of target materials in the state of facing upwards reaches a second threshold, determining that the material distribution state does not meet the preset grasping condition, and generating the feedback instruction.

3. The material grasping method based on the material sorting equipment according to claim 2, wherein Obtaining the characteristic data of the target materials, specifically including: Extracting the material contour features in the image information, and determining multiple identification positions in the material contour features; Respectively obtaining the brightness standard deviations of the identification positions, and calculating the average value of the brightness standard deviations; When the average value of the brightness standard deviations is less than a preset brightness threshold, determining that the sub-state of the target material is a state of facing upwards.

4. The material grasping method based on the material sorting equipment according to claim 2, wherein Obtain the characteristic data of the target material, specifically including: Extract the material direction feature in the image information; Based on the direction feature, extract the regional brightness in multiple regions and calculate the average value of each regional brightness; When the average value of the regional brightness is less than the preset regional brightness threshold, determine that the sub-state of the target material is the reverse side up state.

5. The material grasping method based on the material sorting device according to claim 2, wherein Obtain the characteristic data of the target material, specifically including: Extract the specific shape feature of the material in the image information; When the extracted specific shape feature of the material includes the preset characteristic shape, determine that the sub-state of the target material is the reverse orientation state; Wherein the preset specific shape includes at least one of an angle, a hole position, and a shape.

6. The material grasping method based on the material sorting device according to claim 5, wherein When the material distribution state meets the preset grasping condition, generate a grasping instruction, and the grasping instruction is used to control the multiple suction nozzles at the end of the manipulator of the material sorting device to respectively grasp each target material one by one. After that, it further includes: Obtain the position data of the target suction nozzle; When the position data meets the grasping condition, the manipulator grasps the target material corresponding to the position of the target suction nozzle according to the grasping instruction; Based on the working state of the vacuum cylinder of the target suction nozzle, determine whether the target suction nozzle grasps successfully; When the target suction nozzle fails to grasp, send the number of the target suction nozzle and the shortage quantity to the image acquisition device of the material sorting device; After completing subsequent grasping, generate a next-round material fetching request instruction based on the number of the target suction nozzle and the shortage quantity.

7. A material grasping device based on a material sorting device, characterized in that, The device includes: An image data acquisition unit, configured to obtain the image information of each target material in the target material group on the vibrating disk in response to the vibrating completion instruction of the vibrating disk; A material distribution determination unit, configured to determine the sub-state of each target material based on the image information, and obtain the material distribution state of the target material group according to the sub-states of all the target materials; A grasping instruction generation unit, configured to generate a grasping instruction when the material distribution state meets the preset grasping condition, and the grasping instruction is used to control the multiple suction nozzles at the end of the manipulator of the material sorting device to respectively grasp each target material one by one; A feedback instruction generation unit, configured to generate an information feedback instruction when the material distribution state does not meet the preset grasping condition, and the information feedback instruction is used to control the vibrating disk to start and / or issue a warning signal.

8. A material sorting device, comprising a vibrating and loosening tray, a storage bin, a manipulator with a suction nozzle, and a controller; wherein, The number of the suction nozzles is multiple, and the controller includes a memory, a processor, and a computer program stored on the memory and executable on the processor. It is characterized in that when the processor executes the program, it implements the steps of the material grasping method according to any one of claims 1 to 6.

Images