Method and apparatus for grasping objects

Abstract

The object grabbing method and device provided by the present disclosure determine all combinations of grabbing points that can grab the object to be grabbed according to the size information and position information of the object to be grabbed and the size information of the suction cups in the gripper, then sort all combinations of grabbing points according to a preset filtering priority to obtain a sequence of combinations of grabbing points, and finally filter from the sequence of combinations of grabbing points starting from the combination of grabbing points with the highest priority until the target combination of grabbing points is determined according to a preset grabbing parameter. In this technical solution, the sorted combinations of grabbing points are screened through the grabbing parameter, and the optimal grabbing mode indicated by the grabbing parameter can be obtained. The sorting based on the filtering priority and the screening based on the grabbing parameter can avoid the drawbacks of long cycle and low efficiency in determining the optimal grabbing mode in the prior art, and thus accurate control of the suction cups to grab the box based on the combination of grabbing points is also achieved.

Description

Technical Field

[0001] This disclosure relates to the field of machine vision technology, and in particular to a method and device for grasping objects. Background Technology

[0002] In typical cases of robotic depalletizing, there are many types of boxes and stack types, while the suction cups used by the robot are globally unique and cannot be replaced. To ensure that the suction cups effectively avoid other boxes besides the target box during the depalletizing process and prevent accidental grabbing, a suction cup offset method needs to be adopted during the robot's depalletizing path planning. This allows the areas where the suction cups are activated and have suction force to avoid non-target boxes.

[0003] In existing technologies, to avoid mis-grabbing, the conventional method is for the robot to test and record a set of fixed robot motion points in the robot's controller for each type of stack. This set of points records the robot motion points of all boxes in the stack being destacking, as well as the opening and closing states of each section of the suction cup, which can ensure that the suction cup is correctly offset and avoid collisions during the destacking process.

[0004] However, in the above implementation, the method of testing in advance is inefficient and has a long cycle. Summary of the Invention

[0005] This disclosure provides a method and apparatus for grasping objects to solve the technical problem of low efficiency during destacking in the prior art.

[0006] In a first aspect, embodiments of this disclosure provide a method for grasping an object, including:

[0007] Based on the size and position information of the object to be grasped, and the size information of the suction cups in the fixture, all possible gripping point combinations for grasping the object to be grasped are determined. The fixture includes: multiple suction cups that are adjacent to each other in pairs.

[0008] All crawl point combinations are sorted according to the preset filtering priority to obtain a crawl point combination sequence;

[0009] Based on preset capture parameters, filtering begins with the highest priority group from the capture point combination sequence until the target capture point combination is determined.

[0010] In one possible design of the first aspect, determining all possible combinations of gripping points for gripping the object based on the size and position information of the object to be gripped, and the size information of the suction cup in the fixture, includes:

[0011] Based on the size and position information of the object to be grasped, and the size information of the suction cup in the clamp, the target suction cup required for grasping the object to be grasped is determined;

[0012] Based on the different overlap patterns between the object to be grasped and the target suction cup, the grasping point corresponding to the overlapping area between the object to be grasped and the target suction cup is determined;

[0013] All the grab points corresponding to the overlapping areas under all the aforementioned overlapping methods are combined as a single grab point group, and finally all grab point combinations are obtained.

[0014] In one possible design of the first aspect, the step of sorting all crawl point combinations according to a preset filtering priority to obtain a crawl point combination sequence includes:

[0015] The filtering priority is obtained, and the filtering priority includes multiple suction cup alignment methods with different priorities;

[0016] Based on the filtering priority, the crawl point combinations are sorted according to the order in which they were filtered to obtain the crawl point combination sequence.

[0017] Optionally, the suction cup alignment method includes at least one of the following:

[0018] The center of the object to be grasped is aligned with the center of the suction cup performing the grasping action; one side of the object to be grasped is aligned with one side of the suction cup performing the grasping action; one corner of the object to be grasped is aligned with one corner of the suction cup performing the grasping action; and the preset corner number of the suction cup to be used is consistent with the corner number of the suction cup mapped by the combination of grasping points.

[0019] In one possible design of the first aspect, the step of filtering from the highest priority group of the grab point combination sequence according to preset grab parameters until the target grab point combination is determined includes:

[0020] Determine whether the group of crawl points with the highest filtering priority in the crawl point combination sequence matches the crawling parameters;

[0021] If the group of crawl points with the highest filtering priority in the crawl point combination sequence matches the crawling parameters, then that group of crawl points is determined as the target crawl point combination.

[0022] Otherwise, the process continues to check whether the next sequence of grab point combinations matches the grab parameters, until a set of grab point combinations that matches the grab parameters is determined as the target grab point combination.

[0023] Optionally, the fetching parameters include at least one of the following:

[0024] The distance between the suction cup corresponding to the gripping point combination and the preset point, the overlapping area between the suction cup corresponding to the gripping point combination and other objects adjacent to the object to be gripped, and the overlapping area between the suction cup corresponding to the gripping point combination and the object to be gripped.

[0025] In one possible design of the first aspect, the step of filtering from the highest priority group of the grab point combination sequence according to preset grab parameters until the target grab point combination is determined includes:

[0026] Determine the corner number group of the suction cup that performs the gripping action for each gripping point combination in the gripping point combination sequence;

[0027] Based on the capture parameters, the corner number groups are filtered according to priority order until a set of usable corner number groups is determined as the corner number group corresponding to the target capture point combination.

[0028] In one possible design of the first aspect, after determining the target grasp point combination, the method further includes:

[0029] Determine the suction cup corner number corresponding to the target gripping point combination;

[0030] Based on the determined suction cup corner number, the corresponding suction cup is activated to grasp the object to be grasped.

[0031] In one possible design of the first aspect, before obtaining the filtering priority, the crawling method further includes:

[0032] Obtain the priority setting order of multiple suction cup alignment methods;

[0033] Based on the obtained priority setting order, the multiple suction cup alignment methods are sequentially set to the filtering priority.

[0034] Secondly, embodiments of this disclosure provide an object grasping device, comprising:

[0035] The first processing module is used to determine all possible gripping point combinations for gripping the object based on the size and position information of the object to be gripped and the size information of the suction cups in the fixture. The fixture includes: multiple suction cups that are adjacent to each other in pairs.

[0036] The second processing module is used to sort all the crawl point combinations according to the preset filtering priority to obtain the crawl point combination sequence.

[0037] The third processing module is used to filter from the highest priority group in the sequence of grab point combinations according to preset grab parameters until the target grab point combination is determined.

[0038] In one possible design of the second aspect, the first processing module is specifically used for:

[0039] Based on the size and position information of the object to be grasped, and the size information of the suction cup in the clamp, the target suction cup required for grasping the object to be grasped is determined;

[0040] Based on the different overlap patterns between the object to be grasped and the target suction cup, the grasping point corresponding to the overlapping area between the object to be grasped and the target suction cup is determined;

[0041] All the grab points corresponding to the overlapping areas under all the aforementioned overlapping methods are combined as a single grab point group, and finally all grab point combinations are obtained.

[0042] In one possible design of the second aspect, the second processing module is specifically used for:

[0043] The filtering priority is obtained, and the filtering priority includes multiple suction cup alignment methods with different priorities;

[0044] Based on the filtering priority, the crawl point combinations are sorted according to the order in which they were filtered to obtain the crawl point combination sequence.

[0045] Optionally, the suction cup alignment method includes at least one of the following:

[0046] The center of the object to be grasped is aligned with the center of the suction cup performing the grasping action; one side of the object to be grasped is aligned with one side of the suction cup performing the grasping action; one corner of the object to be grasped is aligned with one corner of the suction cup performing the grasping action; and the preset corner number of the suction cup to be used is consistent with the corner number of the suction cup mapped by the combination of grasping points.

[0047] In one possible design of the second aspect, the third processing module is specifically used for:

[0048] Determine whether the group of crawl points with the highest filtering priority in the crawl point combination sequence matches the crawling parameters;

[0049] If the group of crawl points with the highest filtering priority in the crawl point combination sequence matches the crawling parameters, then that group of crawl points is determined as the target crawl point combination.

[0050] Otherwise, the process continues to check whether the next sequence of grab point combinations matches the grab parameters, until a set of grab point combinations that matches the grab parameters is determined as the target grab point combination.

[0051] Optionally, the fetching parameters include at least one of the following:

[0052] The distance between the suction cup corresponding to the gripping point combination and the preset point, the overlapping area between the suction cup corresponding to the gripping point combination and other objects adjacent to the object to be gripped, and the overlapping area between the suction cup corresponding to the gripping point combination and the object to be gripped.

[0053] In one possible design of the second aspect, the third determining module is specifically used for:

[0054] Determine the corner number group of the suction cup that performs the gripping action for each gripping point combination in the gripping point combination sequence;

[0055] Based on the capture parameters, the corner number groups are filtered according to priority order until a set of usable corner number groups is determined as the corner number group corresponding to the target capture point combination.

[0056] In one possible design of the second aspect, after the target grasping point combination is determined, the third determining module is further configured to:

[0057] Determine the suction cup corner number corresponding to the target gripping point combination;

[0058] Based on the determined suction cup corner number, the corresponding suction cup is activated to grasp the object to be grasped.

[0059] In one possible design of the second aspect, before obtaining the filtering priority, the first determining module is further configured to:

[0060] Obtain the priority setting order of multiple suction cup alignment methods;

[0061] Based on the obtained priority setting order, the multiple suction cup alignment methods are sequentially set to the filtering priority.

[0062] Thirdly, this disclosure provides an electronic device, including: a processor, and a memory communicatively connected to the processor;

[0063] The memory stores computer-executed instructions;

[0064] The processor executes computer execution instructions stored in the memory to implement the method as described in the first aspect above.

[0065] Fourthly, this disclosure provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, are used to implement the method of the first aspect described above.

[0066] Fifthly, this disclosure provides a computer program product, including a computer program that, when executed by a processor, implements the method described in the first aspect above.

[0067] The object grasping method and device disclosed herein determine all possible grasping point combinations for grasping the object based on the size and position information of the object to be grasped, as well as the size information of the suction cups in the fixture. The fixture includes multiple suction cups that are adjacent to each other. Then, all grasping point combinations are sorted according to a preset filtering priority to obtain a grasping point combination sequence. Finally, according to preset grasping parameters, filtering starts from the group with the highest filtering priority in the grasping point combination sequence until the target grasping point combination is determined. In this technical solution, multiple gripping point combinations are pre-determined based on the object's size, position, and suction cup size. By filtering the sorted gripping point combinations using gripping parameters, the optimal gripping method indicated by the gripping parameters can be obtained. The sorting based on filtering priority and the filtering of gripping parameters can avoid the drawbacks of existing technologies, such as long cycle, low efficiency, and waste of human resources in determining the optimal gripping method. In actual depalletizing, filtering multiple gripping point combinations based on gripping parameters can quickly determine the gripping point combination suitable for depalletizing the current pallet. There is no difficulty in managing depalletizing gripping point related files, and thus it also realizes accurate control of the suction cup to grip the box based on the gripping point combination. Attached Figure Description

[0068] The accompanying drawings, which are incorporated in and form a part of this specification, illustrate embodiments consistent with this disclosure and, together with the description, serve to explain the principles of this disclosure.

[0069] Figure 1 Flowchart of the object grasping method provided in the embodiments of this disclosure Figure 1 ;

[0070] Figure 2 This is a schematic diagram of a fixture structure;

[0071] Figure 3 This is an illustration of the alignment method. Figure 1 ;

[0072] Figure 4 This is an illustration of the alignment method. Figure 2 ;

[0073] Figure 5 This is an illustration of the alignment method. Figure 3 ;

[0074] Figure 6 Flowchart of the object grasping method provided in the embodiments of this disclosure Figure 2 ;

[0075] Figure 7 A schematic diagram illustrating the determination of a target suction cup;

[0076] Figure 8Flowchart of the object grasping method provided in the embodiments of this disclosure Figure 3 ;

[0077] Figure 9 Flowchart of the object grasping method provided in the embodiments of this disclosure Figure 4 ;

[0078] Figure 10 This is a schematic diagram of a corner numeral group;

[0079] Figure 11 Flowchart of the object grasping method provided in the embodiments of this disclosure Figure 5 ;

[0080] Figure 12 A schematic diagram of the structure of the object grasping device provided in the embodiments of this disclosure;

[0081] Figure 13 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this disclosure.

[0082] The accompanying drawings have illustrated specific embodiments of this disclosure, which will be described in more detail below. These drawings and descriptions are not intended to limit the scope of the concept in any way, but rather to illustrate the concepts of this disclosure to those skilled in the art through reference to particular embodiments. Detailed Implementation

[0083] To make the objectives, technical solutions, and advantages of the embodiments of this disclosure clearer, the technical solutions of the embodiments of this disclosure will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this disclosure, and not all embodiments. Based on the embodiments of this disclosure, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this disclosure.

[0084] Before introducing the embodiments of this disclosure, the application background of the embodiments of this disclosure will first be explained:

[0085] In typical cases of robotic depalletizing, there are many types of boxes and stack types, while the suction cups used by the robot are globally unique and cannot be replaced. To ensure that the suction cups effectively avoid other boxes besides the target box during the depalletizing process and prevent accidental grabbing, a suction cup offset method needs to be adopted during the robot's depalletizing path planning. This allows the areas where the suction cups are activated and have suction force to avoid non-target boxes.

[0086] In existing technologies, robotic depalletizing in this situation without machine vision is typically referred to as blind depalletizing. To avoid mis-grabbing, the conventional approach is for the robot to test and record a set of fixed robot motion points in its controller for each type of stack. This set of points records the robot motion points of all boxes in the stack being depalletized, as well as the opening and closing states of each section of the suction cups, ensuring proper suction cup offset and preventing collisions during depalletizing.

[0087] The problems existing in the prior art that this disclosure aims to solve are as follows:

[0088] 1. Blind dismantling requires testing each type of stack and recording a fixed set of gripping points, which is time-consuming and labor-intensive.

[0089] 2. Blind dismantling presents difficulties in managing the dismantling movement point files when there are many types of stacks.

[0090] 3. Blind dismantling requires that the stacking structure cannot rotate.

[0091] 4. For cases where the stack is not full, blind unpacking requires manual counting of the number of missing boxes and manual input into the robot program to achieve half-stack unpacking, which consumes a lot of manpower and is prone to errors.

[0092] 5. To achieve fully automated half-stack blind unstacking, it is necessary to cooperate with the automated warehouse management system to record the number of boxes unstacking on each pallet. The system is complex, has high construction costs, and a long debugging cycle.

[0093] To address the aforementioned technical problems, the technical solutions of this disclosure for solving these problems will be described in detail through specific embodiments. It should be noted that the following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described again in some embodiments.

[0094] It is worth noting that the application areas of the object grasping method and equipment disclosed herein are not limited.

[0095] The subject of this disclosure is an electronic device, which may be a robot, a computing device, a control unit in a robot, or a controller that controls a robot, etc.

[0096] Figure 1 Flowchart of the object grasping method provided in the embodiments of this disclosure Figure 1 ,like Figure 1 As shown, the method for grasping this object may include the following steps:

[0097] Step 11: Based on the size and position information of the object to be grasped, and the size information of the suction cup in the fixture, determine all possible combinations of gripping points that can grasp the object.

[0098] The clamps include multiple suction cups that are adjacent to each other.

[0099] In this step, before destacking, the size information of the objects in the stack is obtained, namely the size information of the object to be grasped, the position information of the object to be grasped, and the size information of the suction cup in the jig used for destacking.

[0100] Then, based on the information obtained above, the set of gripping points of the suction cup on the object to be gripped under different gripping methods is determined, that is, the gripping point combination.

[0101] For example, a combination of gripping points includes: at least one gripping point, which can be a grippable point on the object to be gripped (of course, a gripping point can also be an edge, region, etc. on the object to be gripped, depending on the actual situation).

[0102] Optionally, the size information of the object to be grasped can be the length and width values ​​of the object to be grasped; it should be understood that in the embodiments of this disclosure, the size of the object to be grasped and the size of the suction cup are arbitrary, and the stack of objects to be grasped can also be arranged arbitrarily.

[0103] Optionally, the clamp includes multiple suction cups that are adjacent to each other. When gripping an object, the opening and closing of each suction cup in the clamp is controlled to grip the object. For example, the clamp includes suction cup 21, suction cup 22, and suction cup 23. In this case, when it is necessary to grip an object, suction cup 21 and suction cup 22 can be opened and suction cup 23 can be closed to grip the object.

[0104] Optionally, the size information of the suction cup in the fixture can be the length and width of the suction cup.

[0105] As an example, Figure 2 This is a schematic diagram of a fixture structure, such as... Figure 2 As shown, the clamp includes: suction cup 21, suction cup 22, and suction cup 23.

[0106] Based on the above, let's assume the suction cup has a length of 10 and a width of 6, and the object to be grasped has a length of 14 and a width of 8.

[0107] Step 12: Sort all crawl point combinations according to the preset filtering priority to obtain a crawl point combination sequence;

[0108] In this step, since there is generally only one way to grab the object to be grabbed at a time when destacking, we can filter among all the grab point combinations. Before that, in order to improve the filtering efficiency, we can sort all the grab point combinations, that is, we can sort them using the preset filtering priority to obtain the grab point combination sequence.

[0109] Optionally, the order of the crawled points in the sequence can be either reverse or ascending. Taking ascending order as an example, filtering can be performed from beginning to end in subsequent filtering processes.

[0110] Optionally, step 12 can be implemented as follows:

[0111] Step 1: Obtain the filter priority; where the filter priority includes multiple suction cup alignment methods with different priorities;

[0112] In this implementation, the filtering priority is first obtained, which can be the system default filtering priority or the filtering priority set by the user.

[0113] The suction cup alignment method includes at least one of the following: the center of the object to be grasped is aligned with the center of the suction cup performing the grasping; one side of the object to be grasped is aligned with one side of the suction cup performing the grasping; one corner of the object to be grasped is aligned with one corner of the suction cup performing the grasping; and the preset corner number of the suction cup to be used is consistent with the corner number of the suction cup mapped by the combination of grasping points.

[0114] Specifically, Figure 3 This is an illustration of the alignment method. Figure 1 ,like Figure 3 As shown, this schematic diagram indicates that the center of the object 24 to be grasped is aligned with the center of the combination of suction cups 21 and 22; Figure 4 This is an illustration of the alignment method. Figure 2 ,like Figure 4 As shown in the diagram, this schematic indicates that one side of the object 24 to be grasped is aligned with one side of the combination of suction cups 21 and 22. Figure 5 This is an illustration of the alignment method. Figure 3 ,like Figure 5 As shown in the diagram, one corner of the object 24 to be grasped is aligned with one corner of the combination of suction cups 21 and 22.

[0115] Among them, the fact that the preset suction cup corner number and the suction cup corner number mapped by the gripping point combination are consistent can be: to support users to specify specific corners of the suction cup for gripping, to allow for fine configuration of robot depalletizing rules, and to cover a large number of special depalletizing needs.

[0116] in, Figures 3-5 In the diagram, the dashed lines represent the object to be grasped, and the solid lines represent the suction cups under the clamp.

[0117] Before this first step, you can also obtain the priority setting order of multiple suction cup alignment methods. Then, according to the obtained priority setting order, set the multiple suction cup alignment methods as filtering priorities in sequence.

[0118] For example, aligning the center of the object to be grasped with the center of the suction cup performing the grasp can be the first filtering priority; aligning one edge of the object to be grasped with one edge of the suction cup performing the grasp, or aligning one corner of the object to be grasped with one corner of the suction cup performing the grasp can be the second filtering priority; or only including the suction cup edge and corner numbers that are consistent with the preset intended suction cup edge and corner numbers mapped by the grasp point combination, etc.

[0119] It should be understood that: the fact that the preset suction cup corner number and the suction cup corner number mapped by the gripping point combination are consistent can be: support users to specify specific corner numbers of the suction cup for gripping, allow fine configuration of depalletizing rules, and cover a large number of special depalletizing needs.

[0120] Step 2: Sort the crawl point combinations according to the filtering priority and the order in which they were filtered to obtain the crawl point combination sequence.

[0121] In this implementation, according to the above filtering priority, the gripping point combination corresponding to the first filtering priority is first determined from all gripping point combinations, and then the gripping point combination corresponding to the second filtering priority is determined from the remaining gripping point combinations, until all gripping point combinations corresponding to the suction cup alignment method in the filtering priority are selected, thus obtaining the gripping point combination sequence.

[0122] Step 13: Based on the preset crawling parameters, start filtering from the highest priority group in the crawling point combination sequence until the target crawling point combination is determined.

[0123] In this step, the grasping parameters can be used to determine some constraints of the suction cup when grasping the object. From the grasping point combination sequence determined above (taking the above ascending order as an example), grasping point combinations that meet the grasping parameters are matched from front to back, and the grasping point combinations that meet the grasping parameters are taken as the target grasping point combinations.

[0124] Then, based on the target gripping point combination, the suction cup can be controlled to grip the object to be gripped. This can be done by: determining the suction cup corner number corresponding to the target gripping point combination, and activating the corresponding suction cup to grip the object to be gripped based on the determined suction cup corner number.

[0125] In this implementation, under the above-mentioned overlapping method, the corresponding suction cup corner numbers of the grasping combination are known. After determining the target grasping point combination, the corresponding suction cup corner numbers can also be mapped. Then, based on the suction cup corner numbers corresponding to the target grasping point combination, the suction cup can be activated so that the corresponding suction cup corner numbers are aligned with the target grasping point combination to grasp the object to be grasped.

[0126] In this embodiment, based on the size and position of the box, possible combinations of gripping points for the box can be determined, and then directly filtered to quickly obtain the gripping point combination suitable for the current destacking. This avoids the situation in the prior art where each type of stack needs to be tested to obtain a suitable gripping point combination when blindly destacking, which is time-consuming and laborious, and when there are many types of stacks to be destacking, the corresponding number of gripping point combinations is also large, making file management difficult.

[0127] Because there are cases where the stack is not full, the existing technology requires manual counting of the number of missing boxes and manual input into the program to achieve half-stack unpacking. This is labor-intensive and prone to errors. However, in this embodiment, the combination of gripping points is determined directly based on the boxes. Then, the gripping parameters are used to simulate cases such as incomplete stacks and different stack types in the stack. Possible gripping point combinations are filtered out, which can avoid the above problems. Moreover, it does not require the use of an automated storage and retrieval system to record the number of boxes unpacked on each pallet. It does not have the disadvantages of existing technologies such as system complexity, high construction cost, and long debugging cycle.

[0128] The object grasping method provided in this embodiment determines all possible grasping point combinations based on the size and position information of the object to be grasped, as well as the size information of the suction cups in the fixture. The fixture includes multiple suction cups that are adjacent to each other. Then, all grasping point combinations are sorted according to a preset filtering priority to obtain a grasping point combination sequence. Finally, according to preset grasping parameters, filtering starts from the group with the highest filtering priority in the grasping point combination sequence until the target grasping point combination is determined. In this technical solution, multiple gripping point combinations are pre-determined based on the object's size, position, and suction cup size. By filtering the sorted gripping point combinations using gripping parameters, the optimal gripping method that matches the parameters can be obtained. The sorting based on filtering priority and the filtering of gripping parameters can avoid the drawbacks of long cycles, low efficiency, and waste of human resources in determining the optimal gripping method. In actual depalletizing, filtering the gripping point combinations based on the gripping parameters can quickly determine the gripping point combinations suitable for depalletizing the current stack. This avoids the difficulty in managing depalletizing gripping point-related files when there are too many stack types, and also enables accurate control of the suction cup to grip boxes based on gripping point combinations.

[0129] Based on the above embodiments, Figure 6 Flowchart of the object grasping method provided in the embodiments of this disclosure Figure 2 ,like Figure 6 As shown, step 11 of the object grasping method may include the following steps:

[0130] Step 61: Based on the size and position information of the object to be grasped, and the size information of the suction cup in the fixture, determine the target suction cup required to grasp the object;

[0131] This solution is applicable to boxes of any size, stacking arrangements of any type, and rectangular multi-section suction cups of any size.

[0132] Combination Figure 7 This embodiment will be described below. Figure 7 A schematic diagram for determining the target suction cup, such as Figure 7 As shown in the diagram, the system includes: suction cup 21, suction cup 22, suction cup 23, and object to be grasped 24. The specific judgment is implemented as follows:

[0133] S1, control the first side of the object to be grasped to coincide with the second side of the suction cup;

[0134] For example, the first side 2401 of the object to be grasped 24 is controlled to coincide with the second side 2101 of the suction cup 21.

[0135] S2 controls the third side, which is perpendicular to the first side, and the fourth side, which is perpendicular to the second side, to coincide;

[0136] For example, the third side 2402 of the object to be grasped 24 is controlled to coincide with the fourth side 2102 of the suction cup 21.

[0137] S3, determine whether the suction cups corresponding to the second and fourth sides cover the center point information (one of the position information of the object to be grasped);

[0138] In suction cup 21, the length of suction cup 21 is 10, the width is 6, and the center point O is (7,4). Based on the example of the above edges, it is determined whether 6 is greater than 7 and whether 10 is greater than 4. If both conditions are met, it is determined that suction cup 21 covers the center point O. If either condition is not met, it is determined that suction cup 21 does not cover the center point O.

[0139] S4, when the suction cups corresponding to the second and fourth sides do not cover the center point, the number of suction cups is incremented by 1, and the fourth side is updated to the fourth side corresponding to the current number of suction cups, and steps S2-S4 are repeated until the suction cups corresponding to the second and fourth sides cover the center point.

[0140] As can be seen from the above, if suction cup 21 does not cover the center point O, then suction cup 22 is added, and the fourth side is updated to the fourth side 2102 of suction cup 21 and the fourth side 2202 of suction cup 22. That is, the width of the updated fourth side is 6+6=12.

[0141] Further, repeat the above steps to determine whether 12 is greater than 7 and whether 10 is greater than 4. If both conditions are met, determine that the combination of suction cups 21 and 22 covers the center point O. If either condition is not met, determine that the combination of suction cups 21 and 22 does not cover the center point O.

[0142] In this example, after adding suction cup 22, 12 is greater than 7 and 10 is greater than 4, so the combination of suction cup 21 and suction cup 22 covers the center point O.

[0143] In other examples, if the above conditions are still not met, a suction cup 23 is added, and the above steps are repeated.

[0144] S5, the suction cups corresponding to the second and fourth sides covering the center point are identified as the target suction cups.

[0145] Based on the above example, suction cups 21 and 22 are used as suction cups to grasp the object 24 to be grasped, i.e., target suction cups.

[0146] It should be understood that, under the above-mentioned determination method, the target suction cup can also be suction cup 23 and suction cup 22.

[0147] This implementation also represents the case where the box rotates as well when the suction cup is determined, i.e., the stack rotates accordingly.

[0148] Step 62: Based on the different overlapping patterns between the object to be grasped and the target suction cup, determine the grasping point corresponding to the overlapping area between the object to be grasped and the target suction cup;

[0149] In this step, after identifying the target suction cup for grasping the object, different overlapping methods between the object to be grasped and the target suction cup are used, such as the edge of the object to be grasped overlapping the edge of the target suction cup, the corner of the object to be grasped overlapping the corner of the target suction cup, the center of the object to be grasped overlapping the center of the target suction cup, or the corner of the object to be grasped overlapping the center of the edge of the target suction cup, etc.

[0150] For each type of overlap, there is a corresponding overlap area, under which the grab point corresponding to the object to be grabbed can be obtained.

[0151] Optionally, the corner number of the target suction cup can also be obtained at the gripping point corresponding to the object to be gripped in the overlapping area.

[0152] Step 63: Combine the grab points corresponding to the overlapping areas under all overlapping modes as a grab point group, and finally obtain all grab point combinations.

[0153] In this step, for each overlapping method, there is a corresponding overlapping area. The grab points involved in the overlapping area can be used as grab point combinations to obtain all grab point combinations.

[0154] The object grasping method provided in this disclosure determines the target suction cup required for grasping the object based on the size and position information of the object to be grasped and the size information of the suction cup in the fixture. Based on different overlap patterns between the object to be grasped and the target suction cup, it determines the grasping points corresponding to the overlapping areas between the object to be grasped and the target suction cup. It then combines the grasping points corresponding to the overlapping areas under all overlap patterns as a single grasping point combination, finally obtaining all possible grasping point combinations. In this technical solution, based on different overlap patterns between the object to be grasped and the suction cup grasping it, it can determine the grasping point combinations corresponding to the overlapping areas under different overlap patterns, thus exhausting all possible grasping point combinations, increasing the range and accuracy of the selection of grasping point combinations for subsequent grasping.

[0155] Figure 8 Flowchart of the object grasping method provided in the embodiments of this disclosure Figure 3 ,like Figure 8 As shown, step 13 in the object grasping method may include the following steps:

[0156] Step 81: Determine whether the group of crawl points with the highest filtering priority in the crawl point combination sequence matches the crawl parameters;

[0157] In this step, the crawling parameters are used to match the crawling point combination sequence (taking ascending order as an example) in order to determine whether the current crawling point combination matches the crawling parameters.

[0158] Optionally, the grasping parameters include at least one of the following: the distance between the suction cup corresponding to the grasping point combination and the preset point, the overlap area between the suction cup corresponding to the grasping point combination and other objects adjacent to the object to be grasped, and the overlap area between the suction cup corresponding to the grasping point combination and the object to be grasped.

[0159] As one implementation, the distance between the suction cup corresponding to the matching gripping point combination and the preset point can be: In some scenarios, the object to be gripped is close to obstacles such as walls or other objects. The suction cup corresponding to the gripping point combination needs to be far away from these positions in order to grip the object normally. In this case, the distance between the suction cup corresponding to the gripping point combination and the preset point (e.g., the location of the obstacle) can be set to be the maximum, or the distance between the suction cup and the preset point (e.g., far away from the location of the obstacle) can be set to be the minimum (where the maximum and minimum can also be replaced by the design of thresholds).

[0160] As an implementation, the overlapping area between the suction cup corresponding to the matching gripping point combination and other objects adjacent to the object to be gripped can be: In some scenarios, when the suction cup corresponding to the gripping point combination grips the object to be gripped, it may accidentally suck up other objects. In this case, the overlapping area between the suction cup and other objects adjacent to the object to be gripped can be limited to less than a certain area threshold to filter out gripping point combinations that may be accidentally sucked up.

[0161] As one implementation, the overlapping area between the suction cup corresponding to the matching gripping point combination and the object to be gripped can be: In some scenarios, it is necessary to ensure that the suction cup corresponding to the gripping point combination can pick up the object to be gripped. In this case, a certain area threshold can be set to filter out gripping point combinations that are smaller than the area threshold.

[0162] In the above implementation, at least one crawling parameter can be selected to select crawling point combinations in the crawling point combination sequence, and the crawling point combinations that match the at least one crawling parameter can be filtered out.

[0163] It should be understood that the capture parameters can simulate various scenarios that may occur in the capture scenario, and can also indicate any stack type.

[0164] Step 82: If the group of crawl points with the highest filtering priority in the crawl point combination sequence matches the crawl parameters, then the group of crawl points is determined as the target crawl point combination; otherwise, continue to check whether the crawl point combination of the next sequence matches the crawl parameters, until a group of crawl points that matches the crawl parameters is determined as the target crawl point combination.

[0165] In this step, the group of crawl points with the highest filtering priority in the crawl point combination sequence is matched with the set crawl parameters. When the group of crawl points with the highest filtering priority matches the crawl parameters, the group of crawl points is determined as the target crawl point combination.

[0166] Furthermore, if the set of crawl points with the highest filtering priority does not match the crawl parameters, the set of crawl points with the second highest filtering priority will be matched with the crawl parameters, and so on, until a set of crawl points that matches the crawl parameters is determined as the target set of crawl points.

[0167] The object grasping method provided in this disclosure determines whether the highest-priority grasping point combination in the grasping point combination sequence matches grasping parameters. If the highest-priority grasping point combination matches the grasping parameters, that grasping point combination is identified as the target grasping point combination. Otherwise, the method continues to check whether the grasping point combination in the next sequence matches the grasping parameters, until a grasping point combination matching the grasping parameters is identified as the target grasping point combination. This technical solution, by adding a grasping parameter matching method, obtains grasping point combinations that meet user expectations from the grasping point combination sequence, thereby increasing the accuracy and efficiency of palletizing / depalletizing.

[0168] Figure 9 Flowchart of the object grasping method provided in the embodiments of this disclosure Figure 4 ,like Figure 9 As shown, step 13 in the object grasping method may include the following steps:

[0169] Step 91: Determine the corner number group of the suction cup that performs the gripping action for each gripping point combination in the gripping point combination sequence;

[0170] In this step, when determining the gripping point corresponding to the overlapping area between the object to be gripped and the target suction cup based on the different overlapping methods of the object to be gripped and the target suction cup, the corresponding corner number group of the gripping point combination can be mapped out.

[0171] At this point, for each gripping point combination sequence, the corner number group of the suction cup that performs the gripping can be obtained respectively.

[0172] For example, Figure 10 This is a schematic diagram of a corner number group, such as... Figure 10 As shown, the corner numbers corresponding to the overlapping area are 217.218.227.228.

[0173] Step 92: Based on the capture parameters, filter the corner number groups according to their priority order until a set of usable corner number groups is determined as the corner number group corresponding to the target capture point combination.

[0174] In this step, the method of filtering the corner number groups according to the priority order based on the capture parameters is similar to the implementation in the above embodiment.

[0175] It can be based on the crawling parameters, starting from the highest priority group of crawling point combinations in the crawling point combination sequence and matching the corresponding corner number group, until a group of corner numbers that matches the crawling parameters is matched as the corner number group corresponding to the target crawling point combination.

[0176] The object grasping method provided in this disclosure determines the corner number group of the suction cup corresponding to each grasping point combination in the grasping point combination sequence, and filters the corner number groups according to the grasping parameters and priority order until a usable corner number group is determined as the corner number group corresponding to the target grasping point. In this technical solution, when all grasping point combinations are determined, each grasping point combination is mapped to a corresponding corner number. Then, based on the grasping parameters, each corner number is filtered to accurately determine the corner number that meets the user's expectations and can be used to grasp the object to be grasped, thereby enabling subsequent grasping operations.

[0177] Based on the above embodiments, Figure 11 Flowchart of the object grasping method provided in the embodiments of this disclosure Figure 5 ,like Figure 11 As shown, the methods for grasping this object include:

[0178] Step 1: Enter the location, dimensions, and suction cup dimensions of the box;

[0179] Step 2: Calculate the target suction cups (i.e., which suction cups to use for gripping);

[0180] Step 3: Calculate the distance between the center of the target suction cup and the center of the clamp;

[0181] Step 4: Determine all possible combinations for grabbing the box; (arbitrary combination, or the long side of the box is aligned with the long side of the suction cup, or the long side of the box is parallel or perpendicular to the long side of the suction cup);

[0182] Step 5: Determine the group of edge and corner points to be captured based on center alignment, edge alignment, and corner alignment;

[0183] Step 6: Arrangement of corner points (prioritize hierarchical sorting or default sorting);

[0184] Step 7: Delete the corner numbers of boxes that were mistakenly captured from other boxes;

[0185] Step 8: Determine whether the suction cup needs to be prioritized to the preset point; if yes, prioritize sorting and output the corner number group; otherwise, directly output the corner number group.

[0186] The object grasping method provided in this disclosure is a possible implementation of the above embodiments, and its technical effect is similar, so it will not be described again here.

[0187] The following are embodiments of the apparatus disclosed herein, which can be used to execute embodiments of the method disclosed herein. For details not disclosed in the apparatus embodiments of this disclosure, please refer to the embodiments of the method disclosed herein.

[0188] Figure 12 This is a schematic diagram of the structure of the object-grabbing device provided in an embodiment of this disclosure. Figure 6 As shown, the device includes:

[0189] The first processing module 121 is used to determine all possible gripping point combinations of the object to be gripped based on the size and position information of the object to be gripped and the size information of the suction cups in the fixture. The fixture includes: multiple suction cups that are adjacent to each other.

[0190] The second processing module 122 is used to sort all the grab point combinations according to the preset filtering priority to obtain the grab point combination sequence.

[0191] The third processing module 123 is used to filter from the highest priority group in the sequence of grab point combinations according to the preset grab parameters until the target grab point combination is determined.

[0192] In one possible design of this embodiment, the first processing module 121 is specifically used for:

[0193] Based on the size and position information of the object to be grasped, as well as the size information of the suction cup in the fixture, determine the target suction cup required for grasping the object;

[0194] Based on the different overlapping patterns between the object to be grasped and the target suction cup, the grasping point corresponding to the overlapping area between the object to be grasped and the target suction cup is determined.

[0195] All the grab points corresponding to the overlapping areas under all overlapping modes are combined as a single grab point group, and finally all grab point combinations are obtained.

[0196] In one possible design of this embodiment, the second processing module 122 is specifically used for:

[0197] Obtain the filter priority, which includes multiple suction cup alignment methods with different priorities;

[0198] Based on the filtering priority, the crawl point combinations are sorted according to the order in which they were filtered, resulting in a crawl point combination sequence.

[0199] Optionally, the suction cup alignment method includes at least one of the following:

[0200] The center of the object to be grasped is aligned with the center of the suction cup that performs the grasping action; one edge of the object to be grasped is aligned with one edge of the suction cup that performs the grasping action; one corner of the object to be grasped is aligned with one corner of the suction cup that performs the grasping action; and the preset corner numbers of the suction cup to be used are consistent with the corner numbers of the suction cup mapped by the combination of grasping points.

[0201] In one possible design of this embodiment, the third processing module 123 is specifically used for:

[0202] Determine whether the highest-priority combination of crawl points in the crawl point combination sequence matches the crawl parameters;

[0203] If the group of crawl points with the highest filtering priority in the crawl point combination sequence matches the crawl parameters, then that group of crawl points is determined as the target crawl point combination.

[0204] Otherwise, continue to check whether the next sequence of grab point combinations matches the grab parameters, until a set of grab point combinations that matches the grab parameters is determined as the target grab point combination.

[0205] Optionally, the fetching parameters may include at least one of the following:

[0206] The distance between the suction cup corresponding to the gripping point combination and the preset point, the overlap area between the suction cup corresponding to the gripping point combination and other objects adjacent to the object to be gripped, and the overlap area between the suction cup corresponding to the gripping point combination and the object to be gripped.

[0207] In one possible design of this disclosure embodiment, the third determining module is specifically used for:

[0208] Determine the corner group of the suction cup that performs the gripping action for each gripping point combination in the gripping point combination sequence;

[0209] Based on the capture parameters, the corner number groups are filtered according to their priority order until a set of usable corner number groups is determined as the corner number group corresponding to the target capture point combination.

[0210] In one possible design of this disclosure embodiment, after determining the target grasping point combination, the third determining module is further configured to:

[0211] Determine the suction cup corner number corresponding to the target gripping point combination;

[0212] Based on the determined suction cup corner number, the corresponding suction cup is activated to grasp the object to be grasped.

[0213] In one possible design of this disclosure embodiment, before obtaining the preset filtering priority, the first determining module is further configured to:

[0214] Get the priority setting order of multiple suction cup alignment methods;

[0215] Based on the obtained priority settings, the alignment methods of multiple suction cups are set as filtering priorities in sequence.

[0216] The object grasping device provided in this disclosure can be used to execute the object grasping method in any of the above embodiments. Its implementation principle and technical effect are similar, and will not be described again here.

[0217] It should be noted that the division of the various modules in the above device is merely a logical functional division. In actual implementation, they can be fully or partially integrated into a single physical entity, or they can be physically separated. Furthermore, these modules can be implemented entirely in software via processing element calls; they can be fully implemented in hardware; or some modules can be implemented by processing element calls to software, while others are implemented in hardware. Additionally, these modules can be fully or partially integrated together, or implemented independently. The processing element mentioned here can be an integrated circuit with signal processing capabilities. In the implementation process, each step of the above method or each of the above modules can be completed through the integrated logic circuits in the hardware of the processor element or through software instructions.

[0218] Figure 13 This is a schematic diagram of the structure of the electronic device provided in the embodiments of this disclosure, such as... Figure 13 As shown, the electronic device may include: a processor 131, a memory 132, and computer program instructions stored in the memory 132 and executable on the processor 131. When the processor 131 executes the computer program instructions, it implements the method provided in any of the foregoing embodiments.

[0219] Optionally, the various components of the electronic device can be connected via a system bus.

[0220] The memory 132 can be a separate memory unit or a memory unit integrated into the processor 131. The number of processors 131 can be one or more.

[0221] It should be understood that the processor 131 can be a Central Processing Unit (CPU), or other general-purpose processors 131, digital signal processors (DSPs), application-specific integrated circuits (ASICs), etc. The general-purpose processor 131 can be a microprocessor 131, or any conventional processor 131. The steps of the method disclosed in this disclosure can be directly manifested as being executed by the hardware processor 131, or being executed by a combination of hardware and software modules within the processor 131.

[0222] The system bus can be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus, etc. The system bus can be divided into address bus, data bus, control bus, etc. For ease of representation, only one thick line is used in the diagram, but this does not indicate that there is only one bus or one type of bus. Memory 132 may include random access memory (RAM) 132, and may also include non-volatile memory (NVM) 132, such as at least one disk storage device 132.

[0223] All or part of the steps of the above method embodiments can be implemented by hardware related to program instructions. The aforementioned program can be stored in a readable memory 132. When the program is executed, it performs the steps of the above method embodiments; and the aforementioned memory 132 (storage medium) includes: read-only memory 132 (ROM), RAM, flash memory 132, hard disk, solid-state hard disk, magnetic tape, floppy disk, optical disk, and any combination thereof.

[0224] The electronic device provided in this disclosure can be used to execute the object grasping method provided in any of the above method embodiments. Its implementation principle and technical effect are similar, and will not be described again here.

[0225] This disclosure provides a computer-readable storage medium storing computer instructions that, when executed on a computer, cause the computer to perform the object grasping method described above.

[0226] The aforementioned computer-readable storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory, electrically erasable programmable read-only memory, erasable programmable read-only memory, programmable read-only memory, read-only memory, magnetic storage, flash memory, magnetic disk, or optical disk. The readable storage medium can be any available medium accessible to a general-purpose or special-purpose computer.

[0227] Optionally, a readable storage medium can be coupled to a processor, enabling the processor to read information from and write information to the readable storage medium. Alternatively, the readable storage medium can be an integral part of the processor. Both the processor and the readable storage medium can reside in an Application Specific Integrated Circuit (ASIC). Alternatively, the processor and the readable storage medium can exist as discrete components within the device.

[0228] This disclosure also provides a computer program product, which includes a computer program stored in a computer-readable storage medium. At least one processor can read the computer program from the computer-readable storage medium, and when the at least one processor executes the computer program, it can implement the above-described object grasping method.

[0229] It should be understood that this disclosure is not limited to the precise structures described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of this disclosure is limited only by the appended claims.

Claims

1. A method for grasping an object, characterized in that, include: Based on the size and position information of the object to be grasped, and the size information of the suction cups in the fixture, all possible gripping point combinations for grasping the object to be grasped are determined. The fixture includes: multiple suction cups that are adjacent to each other in pairs. All crawl point combinations are sorted according to the preset filtering priority to obtain a crawl point combination sequence; According to the preset grasping parameters, the filtering starts from the highest priority group in the grasping point combination sequence until the target grasping point combination is determined. The step of filtering from the highest priority group in the sequence of grabbing points according to preset grabbing parameters until the target grabbing point combination is determined includes: Determine the corner number group of the suction cup that performs the gripping action for each gripping point combination in the gripping point combination sequence; Based on the capture parameters, the corner number groups are filtered according to priority order until a set of usable corner number groups is determined as the corner number group corresponding to the target capture point combination.

2. The method according to claim 1, characterized in that, The step of determining all possible gripping point combinations for gripping the object based on its size and position information, as well as the size information of the suction cup in the fixture, includes: Based on the size and position information of the object to be grasped, and the size information of the suction cup in the clamp, the target suction cup required for grasping the object to be grasped is determined; Based on the different overlap patterns between the object to be grasped and the target suction cup, the grasping point corresponding to the overlapping area between the object to be grasped and the target suction cup is determined; All the grab points corresponding to the overlapping areas under all the aforementioned overlapping methods are combined as a single grab point group, and finally all grab point combinations are obtained.

3. The method according to claim 1, characterized in that, The step of sorting all crawl point combinations according to a preset filtering priority to obtain a crawl point combination sequence includes: The filtering priority is obtained, and the filtering priority includes multiple suction cup alignment methods with different priorities; Based on the filtering priority, the crawl point combinations are sorted according to the order in which they were filtered to obtain the crawl point combination sequence.

4. The method according to claim 3, characterized in that, The suction cup alignment method includes at least one of the following: The center of the object to be grasped is aligned with the center of the suction cup performing the grasping action; one side of the object to be grasped is aligned with one side of the suction cup performing the grasping action; one corner of the object to be grasped is aligned with one corner of the suction cup performing the grasping action; and the preset corner number of the suction cup to be used is consistent with the corner number of the suction cup mapped by the combination of grasping points.

5. The method according to claim 1, characterized in that, The step of filtering from the highest priority group in the sequence of grabbing points according to preset grabbing parameters until the target grabbing point combination is determined includes: Determine whether the group of crawl points with the highest filtering priority in the crawl point combination sequence matches the crawling parameters; If the group of crawl points with the highest filtering priority in the crawl point combination sequence matches the crawling parameters, then that group of crawl points is determined as the target crawl point combination. Otherwise, continue to check whether the next sequence of grab point combinations matches the grab parameters, until a set of grab point combinations that matches the grab parameters is determined as the target grab point combination.

6. The method according to claim 5, characterized in that, The crawling parameters include at least one of the following: The distance between the suction cup corresponding to the gripping point combination and the preset point, the overlapping area between the suction cup corresponding to the gripping point combination and other objects adjacent to the object to be gripped, and the overlapping area between the suction cup corresponding to the gripping point combination and the object to be gripped.

7. The method according to claim 1, characterized in that, After determining the target grab point combination, the method further includes: Determine the suction cup corner number corresponding to the target gripping point combination; Based on the determined suction cup corner number, the corresponding suction cup is activated to grasp the object to be grasped.

8. The grasping method according to claim 3, characterized in that, Before obtaining the filtering priority, the crawling method further includes: Obtain the priority setting order of multiple suction cup alignment methods; Based on the obtained priority setting order, the multiple suction cup alignment methods are sequentially set to the filtering priority.

9. An electronic device, characterized in that, include: A processor, and a memory communicatively connected to the processor; The memory stores computer-executed instructions; The processor executes computer execution instructions stored in the memory to implement the method as described in any one of claims 1 to 8.

Images