Collision detection method, control method, grasping system and computer storage medium

Abstract

The present invention provides a collision detection method, a control method for a gripping device, a material gripping system and a computer-readable storage medium, wherein the collision detection method comprises: obtaining a gripping model of an object to be gripped; correcting the gripping model, clipping the boundary of the gripping model, and obtaining a collision model; and performing collision detection according to the collision model. The embodiment of the present invention corrects the gripping model, obtains the collision model by clipping the boundary of the gripping model, and performs collision detection using the obtained collision model, which can overcome the problem that the gripping device cannot pass the collision detection in some cases, causing the gripping device to shut down. In other embodiments of the present invention, the control method of the gripping device and the material gripping system using the control method utilize the aforementioned collision detection method to control the gripping device to grip the object to be gripped after collision detection, thereby improving the efficiency of the material gripping system in transferring and destacking.

Description

Technical Field

[0001] The present invention generally relates to the technical field of intelligent devices and control methods, and in particular to a collision detection method, a control method, a gripping system and a computer-readable storage medium. Background Art

[0002] With the development of technology, in the fields of industrial production, warehousing and transportation, especially high-precision processing, it is usually necessary to disassemble and transport objects and workpieces. In order to prevent the grasping device and the object to be grasped from colliding, causing structural damage or safety accidents, collision detection is required before executing the grasping action, and grasping is performed after the collision detection passes. However, in actual applications, especially in disordered grasping scenarios, because the object to be grasped deviates from its position due to other reasons, the collision detection cannot pass, the grasping action is suspended, the grasping device is shut down, and the work efficiency is reduced. The existing collision detection method and the control method of the grasping device cannot effectively solve this problem, so it needs to be improved.

[0003] The contents of the background technology section are merely the technologies known to the inventors and do not necessarily represent the prior art in the field. Summary of the invention

[0004] In view of one or more defects in the prior art, the present invention provides a collision detection method, comprising:

[0005] Obtain a grasping model of the object to be grasped;

[0006] Correcting the grasping model, clipping the boundary of the grasping model, and obtaining a collision model;

[0007] Collision detection is performed according to the collision model.

[0008] According to one aspect of the present invention, the step of acquiring a grasping model of the object to be grasped includes acquiring point cloud data of the object to be grasped.

[0009] According to one aspect of the present invention, there are a plurality of objects to be grasped, and the step of clipping the boundary of the grasping model comprises:

[0010] cropping the entire boundary of the captured model; or

[0011] The boundary of the grasping model adjacent to the free position of the carrying platform of the object to be grasped is cut.

[0012] According to one aspect of the present invention, the step of clipping the boundary of the grasping model includes: independently clipping the portion of the grasping model corresponding to each object to be grasped.

[0013] According to one aspect of the present invention, wherein a plurality of the objects to be grasped have an overall boundary, in the step of cropping the boundary of the grasping model, the size of any boundary cropped to the grasping model is not greater than a first preset size, and the sum of the sizes of the plurality of boundaries cropped to the grasping model is not greater than a second preset size.

[0014] According to one aspect of the present invention, the value range of the first preset size is 2-10 mm.

[0015] According to one aspect of the present invention, the present invention also includes a control method for a gripping device, the control method comprising:

[0016] Execute the collision detection method as described above;

[0017] After passing the collision detection, the grasping device is controlled to grasp the object to be grasped.

[0018] According to one aspect of the present invention, the control method further comprises: when the collision detection fails, reselecting the object to be grasped and repeating the collision detection step.

[0019] According to one aspect of the present invention, the control method further comprises: when the object to be grasped includes a plurality of mutually independent objects,

[0020] Determining whether the relative position relationship of the plurality of objects meets a preset value, wherein the preset value includes a maximum distance between the objects;

[0021] When the relative position relationship of the multiple objects does not meet the preset value, the object to be grasped is reselected.

[0022] According to one aspect of the present invention, the present invention also provides a material grabbing system, the material grabbing system comprising:

[0023] A grasping device, wherein the grasping device is configured to be driven to grasp an object to be grasped and transport the object to be grasped to a target location;

[0024] An image acquisition device, wherein the image acquisition device is configured to acquire image information of an object to be grasped; and

[0025] A control system, wherein the control system communicates with the gripping device and the image acquisition device and is capable of executing the control method as described above.

[0026] According to one aspect of the present invention, the gripping device is a suction gripping mechanism.

[0027] According to one aspect of the present invention, the image acquisition module includes a 3D camera, and the image information includes point cloud data of the object to be grasped.

[0028] According to one aspect of the present invention, the present invention also includes a computer-readable storage medium, including computer executable commands stored thereon, and when the executable commands are executed by a processor, the collision detection method and / or the control method as described above are implemented.

[0029] Compared with the prior art, an embodiment of the present invention provides a collision detection method, which modifies a grasping model, obtains a collision model by clipping the boundaries of the grasping model, and uses the obtained collision model to perform collision detection, which can overcome the problem that the grasping device cannot pass the collision detection in some cases, resulting in shutdown of the grasping device. The present invention also includes a control method for a grasping device and a material grasping system using the control method, which uses the aforementioned collision detection method to control the grasping device to grasp the object to be grasped after collision detection, thereby improving the efficiency of the material grasping system in transferring and destacking. The present invention also includes an embodiment of a computer-readable storage medium that can be executed by a computer processor to implement the aforementioned collision detection method and / or grasping device control method. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0031] Figure 1 is a schematic flow chart of a collision detection method in one embodiment of the present invention;

[0032] Figure 2A is a schematic diagram of a grasping model in one embodiment of the present invention;

[0033] Figure 2B is a schematic diagram of a preset placement position of an object to be grasped on a carrying platform in one embodiment of the present invention;

[0034] Figure 3A-3C is a schematic diagram of clipping and grabbing models to obtain collision models in different embodiments of the present invention;

[0035] Figure 4 is a flow chart of a control method of a grabbing device in one embodiment of the present invention;

[0036] Figure 5 is a flow chart of a control method including a process of determining the relative position relationship of grasped objects in one embodiment of the present invention;

[0037] Figure 6 is a structural block diagram of a material grabbing system in one embodiment of the present invention;

[0038] Figure 7 It is a schematic diagram of interference between an object to be grasped and an existing object in the prior art. DETAILED DESCRIPTION

[0039] In the following, only some exemplary embodiments are briefly described. As those skilled in the art will appreciate, the described embodiments may be modified in various ways without departing from the spirit or scope of the present invention. Therefore, the drawings and descriptions are considered to be exemplary and non-restrictive in nature.

[0040] In the description of the present invention, it should be understood that the terms "center", "longitudinal", "lateral", "length", "width", "thickness", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", "clockwise", "counterclockwise" and the like indicate positions or positional relationships based on the positions or positional relationships shown in the accompanying drawings, which are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as limiting the present invention. In addition, the terms "first" and "second" are only used for descriptive purposes, and cannot be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. In the description of the present invention, the meaning of "multiple" is two or more, unless otherwise clearly and specifically defined.

[0041] In the description of the present invention, it should be noted that, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection, an electrical connection, or can communicate with each other; it can be directly connected, or indirectly connected through an intermediate medium, it can be the internal connection of two elements or the interaction relationship between two elements. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0042] In the present invention, unless otherwise clearly specified and limited, a first feature being "above" or "below" a second feature may include that the first and second features are in direct contact, or may include that the first and second features are not in direct contact but are in contact through another feature between them. Moreover, a first feature being "above", "above" and "above" a second feature includes that the first feature is directly above and obliquely above the second feature, or simply means that the first feature is higher in level than the second feature. A first feature being "below", "below" and "below" a second feature includes that the first feature is directly above and obliquely above the second feature, or simply means that the first feature is lower in level than the second feature.

[0043] The disclosure below provides many different embodiments or examples to realize different structures of the present invention. In order to simplify the disclosure of the present invention, the parts and settings of specific examples are described below. Of course, they are only examples, and the purpose is not to limit the present invention. In addition, the present invention can repeat reference numbers and / or reference letters in different examples, and this repetition is for the purpose of simplicity and clarity, which itself does not indicate the relationship between the various embodiments and / or settings discussed. In addition, the present invention provides various specific examples of processes and materials, but those of ordinary skill in the art can be aware of the application of other processes and / or the use of other materials.

[0044] The preferred embodiments of the present invention are described below in conjunction with the accompanying drawings. It should be understood that the preferred embodiments described herein are only used to illustrate and explain the present invention, and are not used to limit the present invention.

[0045] Figure 1 FIG. 1 shows a specific process of a collision detection method 100 in one embodiment of the present invention. Figure 2A-Figure 3C They are the specific forms of the grabbing model and the collision model in the embodiment of the present invention. Figure 1-3C Detailed description.

[0046] like Figure 1 As shown, in the collision detection method 100, in step S101, a grasping model of the object to be grasped is obtained. According to a specific embodiment of the present invention, the grasping model may be the actual placement form of the object to be grasped, such as a specific posture, or the relative position relationship of multiple objects to be grasped. Preferably, in some embodiments of the present invention, the step of obtaining the grasping model of the object to be grasped includes obtaining point cloud data of the object to be grasped, which may be obtained through sensors on a grasping device or a grasping system, such as a binocular lens, a 3D camera such as a 3D structured light, or a laser radar is provided in the working scene of the grasping device or the grasping operation to obtain the actual placement form of the object to be grasped.

[0047] In step S102, the grasping model is corrected and the boundary of the grasping model is clipped to obtain a collision model. In this step, the boundary of the grasping model is clipped. The specific clipping process and clipping method are described in detail in the subsequent embodiments. In step S103, collision detection is performed according to the collision model. In this embodiment, compared with the grasping model, the boundary of the collision model has been clipped. When performing collision detection, the boundary size is smaller, which improves the pass rate of collision detection.

[0048] In the specific production process, collision detection is an essential procedure for the grasping operation, which is used to determine whether the grasping device and the object to be grasped will collide with other objects to be grasped and other obstacles in the working environment when grasping and placing the object to be grasped. Only after collision detection will the grasping device perform the grasping action to prevent production safety accidents. In the control system that performs collision detection, the information of existing obstacles is pre-stored, and the information of other objects to be grasped can be collected in real time through sensors. One or more objects to be grasped during each grasping process have a preset placement position on the carrying platform that is feasible after the target stack type matching operation. Under normal circumstances, the grasping device transfers the object to be grasped to the top of the preset placement position that is feasible after the matching operation, until the object to be grasped is placed at the preset placement position, completing a grasping and placement process.

[0049] For example Figure 2A The figure shows the size and position of the object to be grasped at the loading station when grasping multiple objects in a single beat. The initial preset position of the object to be grasped is shown by a dotted line, and one grasping action will grasp all the objects in the figure. Of course, in one grasping process, when grasping one object to be grasped, the size and position of the object to be grasped can also be reflected by the grasping model, and the position and angle of the object to be grasped may also deviate from the initial preset position. When the object to be grasped does not deviate, the grasping device grasps the object to be grasped and places it at the preset placement position on the carrying platform, for example Figure 2B As shown, the next beat of the grasping action is continued. However, due to the influence of external factors, in the actual production process, the actual placement of the object to be grasped usually deviates from the initial preset posture. Figure 2A The solid line in the figure indicates that there may be a difference between the posture of the object to be grasped at the incoming material and the posture of the feasible placement position in the target stack after the target stack matching operation. The object to be grasped may be displaced or rotated, or the relative position relationship of multiple objects to be grasped may change. When grasping multiple objects to be grasped at one time, the boundary formed by the multiple objects to be grasped as a whole may be different from their placement posture at the target posture. In the existing collision detection method, collision detection is performed based on the grasping model, that is, the actual posture state of the object to be grasped. Since the posture of the object to be grasped is different from the posture of the place where it should be placed in the target stack, when the displacement of the object to be grasped is large, in the final placement stage, the object to be grasped may have geometric interference with the objects that have been placed in the previous stacking process, for example Figure 7As shown in the figure, collision detection is performed directly with the grasping model. Since the object to be grasped deviates from the initial preset position, the stacking path cannot pass the collision detection, and the grasping device stops, affecting work efficiency. However, in actual situations, in order to ensure safe production, a safe distance is reserved between the preset placement position of the object to be grasped and obstacles and other objects to be grasped. In some cases, even if the existing collision detection method fails, a collision accident may still not occur. The traditional collision detection method has defects.

[0050] In this embodiment, by cropping the boundaries of the grasping model and correcting it to obtain a collision model, collision detection is performed using the collision model, which enables some objects to be grasped that can be placed normally to pass the collision detection method of this embodiment, thereby reducing the downtime of the grasping device and improving work efficiency.

[0051] Further, according to a preferred embodiment of the present invention, the step of clipping the boundary of the grasping model further includes clipping the entire boundary of the grasping model; or clipping the boundary of the grasping model adjacent to the empty position of the carrying platform of the object to be grasped. Figure 3A-3C As shown, different cutting methods can be flexibly selected in different embodiments of the present invention or different grabbing processes. Figure 3A-3C , describing in detail the different cropping methods.

[0052] like Figure 3A As shown, in a grasping process, there are multiple objects to be grasped, and the grasping model can be a whole composed of multiple objects to be grasped, or it can be a whole boundary composed of the boundaries of multiple objects to be grasped. In this embodiment, the whole boundary composed of multiple objects to be grasped is cut to a suitable size, for example Figure 3A The collision model shown in the implementation is overall smaller than the grasping model shown by the dotted line, and is easier to pass the collision detection so that the grasping device continues to operate normally.

[0053] like Figure 3B As shown, the objects to be grasped are multiple independent objects. According to a preferred embodiment of the present invention, only one side or part of the side of the overall boundary formed by the multiple objects to be grasped can be cut. Specifically, the boundary adjacent to the empty position of the carrying platform of the objects to be grasped in the grasping model is cut, such as Figure 3B As shown by the solid line in , for the boundaries that do not require collision detection, the grasping model is used as the standard, that is, the actual acquired position and posture of the object to be grasped is used as the standard, and for the boundaries of the object to be grasped that require collision detection, the overall boundary of the grasping model is cropped to obtain a collision model with a corrected boundary for collision detection to pass the collision detection. In this embodiment, the overall boundary of the grasping model is cropped, and the obtained collision model has a flush boundary. According to other preferred embodiments of the present invention, the boundaries of each object to be grasped can also be cropped separately.

[0054] like Figure 3C As shown, the objects to be grasped are multiple independent objects, preferably boxes with clear boundaries. Under default conditions, multiple objects to be grasped are arranged neatly, but in actual production, some or all of the objects to be grasped may deviate from the preset position, which may be the whole protrusion caused by translation, or the protrusion of some corners caused by rotation, or a mixture of the two. When cutting the grasping model, the whole boundary or part of the boundary can be cut by the method in the above embodiment, or the whole boundary can be cut by the method in the above embodiment. Figure 3C As shown, the portion corresponding to each object to be grasped in the grasped object is independently cropped. And the specific cropping method can also be adjusted according to the posture of the object to be grasped, for example, cropping is performed in a form parallel to the boundary of each object to be grasped. The boundaries of multiple objects to be grasped after cropping may be non-parallel according to the different postures of the objects to be grasped, for example Figure 3C As shown, a parallel cropping method (not shown in the figure) may also be used for the boundaries of multiple objects to be grasped, and the positions and parts of the multiple objects to be grasped are different.

[0055] To prevent collisions, in a preferred embodiment of the present invention, the clipping size of the grasping model is also limited. When grasping multiple objects to be grasped at one time, the multiple objects to be grasped have an overall boundary. In the step of clipping the boundary of the grasping model, the size of any boundary of the grasping model clipped is not greater than the first preset size. Preferably, the value range of the first preset size is 2-10 mm, for example, 5 mm, that is, when clipping the boundary of the object to be grasped, only a distance of 5 mm is clipped inward from the boundary position of the grasping model, and a new boundary is formed to obtain a collision model. When clipping multiple boundaries of the grasping model, the sum of the clipping sizes of the multiple boundaries is not greater than the second preset size, and the clipping size of each boundary should not be greater than the first preset size. The second preset size can be appropriately relaxed on the basis of the first preset size to improve the pass rate of collision detection. According to a preferred embodiment of the present invention, the first preset size and the second preset size are set according to actual conditions, and the border of the grasping model is clipped to pass the collision detection according to the safety distance between the object to be grasped and the obstacle and other objects to be grasped, for example, the safety distance is 5-20 mm. When the clipping size of the grasping model border exceeds the safety distance, for example, the safety distance is 10 mm and the clipping size is 12 mm, although the collision model size is smaller after clipping and can pass the collision detection, in the actual grasping and transportation process, it may cause the object to be grasped to collide with the obstacle or other objects to be grasped, increasing the possibility of collision and posing a safety hazard. Preferably, the first preset size and the second preset size can be set to half of the safety distance to ensure a margin for clipping the border of the grasping model in the next grasping cycle.

[0056] like Figure 4As shown, the present invention also provides an embodiment of a control method 200 for a grasping device. Specifically, in step S201, the collision detection method in the aforementioned embodiment is executed, and the collision detection is performed using the corrected collision model. In step S202, it is determined whether the collision detection is passed. If the collision detection is passed, in step S203, the grasping device is controlled to grasp the object to be grasped and perform the grasping action. If the collision detection is not passed, the grasping device is controlled to stop and stop executing the grasping action. Or according to a preferred embodiment of the present invention, in step S204, the object to be grasped is reselected, and the collision detection step is repeated to continue the grasping operation.

[0057] For some situations that cannot pass the collision detection in the prior art, the collision detection method in the aforementioned embodiment is used to crop the boundaries of the grasping model so that the objects to be grasped that will not collide during the actual grasping process can pass the collision detection, thereby reducing the number of shutdowns of the grasping device, improving the working efficiency of the grasping device, and ensuring that the grasping device can perform grasping actions continuously.

[0058] Figure 5 The control method 300 including the process of judging the posture of the object to be grasped according to the preferred embodiment of the present invention is shown, wherein steps S303-S305 correspond to steps S201-S203 in the control method 200 of the grasping device one by one, and are basically the same, and are not repeated here. In step S301, it is judged whether the relative position relationship of the object to be grasped meets the preset value. In this embodiment, the object to be grasped is a plurality of independent objects, and in one grasping beat, a plurality of objects to be grasped are grasped at the same time, and the relative position relationship of the plurality of objects to be grasped has a theoretical value. For example, when the object to be grasped is a box, the theoretical value of the relative position relationship of the plurality of objects to be grasped is as follows: Figure 2A As shown, they are arranged neatly with each other, but as mentioned above, in the actual production process, the positional relationship between the multiple boxes will deviate. When the deviation distance of one of the boxes or multiple boxes is too large, for example, the multiple boxes are too far apart, or the lateral offset is large, in this case, by trimming the grasping model, the collision model obtained still cannot pass the collision detection and cannot be grasped. Therefore, in this embodiment, in step S302, when the relative positional relationship of the multiple objects does not meet the preset value, the objects to be grasped are reselected. According to a preferred embodiment of the present invention, the relative positional relationship between the reselected objects to be grasped can be judged until the objects to be grasped whose relative positional relationship meets the preset value are obtained.

[0059] In this embodiment, the preset value of the relative position relationship of the objects to be grasped includes at least the maximum distance between the objects to be grasped. Preferably, the preset value may also include the angle relationship between the objects to be grasped or the numerical value of the objects to be grasped exceeding the theoretical value. Of course, according to the preferred embodiment of the present invention, the grasping model is the actual arrangement form of the objects to be grasped, preferably point cloud data. Therefore, the judgment of the position relationship between the objects to be grasped can be obtained through the grasping model. The order of step S301 can be after obtaining the grasping model of the objects to be grasped. The step of judging the relative position relationship of the objects to be grasped is not limited to before the collision detection, and can also be performed before the grasping model is cropped.

[0060] The present invention also includes an embodiment of a material grabbing system 400, such as Figure 6 As shown, the material grabbing system 400 includes a grabbing device 401, an image acquisition device 402 and a control system 403, wherein the grabbing device 401 is used to be driven to grab the object to be grabbed and transport the object to be grabbed to the target position. In different embodiments of the present invention, the grabbing device 401 can be various existing structures with grabbing functions, such as a clamping claw grabbing mechanism, a magnetic grabbing mechanism or a vacuum adsorption grabbing mechanism, etc. Preferably, it can be an adsorption grabbing structure. The use of an adsorption grabbing mechanism can prevent the position of the object to be grabbed from changing again during the grabbing process, so as to ensure that the acquired grabbing model is the actual position relationship of the object to be grabbed, especially when multiple objects to be grabbed are grabbed in one grabbing cycle, so as to avoid displacement or loosening and scattering due to squeezing between the objects to be grabbed. In addition, the adsorption grabbing mechanism is preferably adsorbed on the top position of the object to be grabbed. When performing collision detection, the side boundary of the collision model is the boundary of the modified grabbing model, and there is no need to reserve additional gaps for the structure of the grabbing device, so that the arrangement between the objects to be grabbed is tighter and the result of collision detection is more accurate.

[0061] The image acquisition device 402 is used to obtain image information of the object to be grasped. According to a preferred embodiment of the present invention, the image acquisition device 402 can be set on the grasping device 401 and move with the grasping device 401, or it can be set at other positions in the grasping operation working environment to obtain the actual placement form of the object to be grasped, that is, the grasping model. Preferably, the image acquisition device 402 can be a 3D camera, and the image information of the object to be grasped obtained includes point cloud data of the object to be grasped, which is used to obtain the grasping model.

[0062] The control system 403 communicates with the gripping device 401 and the image acquisition device 402, and the control system 403 can execute the control method of the gripping device in the above-mentioned embodiment. Figure 6As shown, the control system 403 includes a task management module 4031, an information interaction module 4032 and a system management module 4033, wherein the information interaction module 4032 communicates with the grasping device 401 and the image acquisition device 402 respectively, the system management module 4033 is used to execute the control method of the grasping device and realize other control functions, and the task management module 4031 is used to manage the grasping tasks, in which information such as the number of objects to be grasped, the grasping order, and the target position, placement method, etc. of the objects to be grasped can be stored.

[0063] The present invention also includes an embodiment of a computer-readable storage medium, which includes computer executable commands stored thereon, and when the executable commands are executed by a processor, they implement the collision detection method described in the aforementioned embodiments and / or the control method of the gripping device described in the aforementioned embodiments.

[0064] Finally, it should be noted that the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art can still modify the technical solutions described in the aforementioned embodiments or replace some of the technical features therein by equivalents. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A collision detection method, comprising: Obtain a grasping model of the object to be grasped; The grasping model is modified, and the boundary of the grasping model is clipped to obtain a collision model, wherein the size of any boundary of the grasping model clipped is not greater than a first preset size; Collision detection is performed according to the collision model. 2 . The collision detection method according to claim 1 , wherein the step of obtaining a grasping model of the object to be grasped comprises obtaining point cloud data of the object to be grasped.

3. The collision detection method according to claim 1, wherein there are a plurality of objects to be grasped, and the step of clipping the boundary of the grasping model comprises: cropping the entire boundary of the captured model; or The boundary of the grasping model adjacent to the free position of the carrying platform of the object to be grasped is cut.

4. The collision detection method according to claim 3, wherein the step of clipping the boundary of the grab model comprises: The portion of the grasping model corresponding to each object to be grasped is independently cut.

5. The collision detection method according to claim 3, wherein the plurality of objects to be grasped have an integral boundary, and in the step of clipping the boundary of the grasping model, the sum of the sizes of the plurality of boundaries clipped is not greater than a second preset size. 6 . The collision detection method according to claim 5 , wherein the value range of the first preset size is 2-10 mm.

7. A method for controlling a gripping device, comprising: Execute the collision detection method according to any one of claims 1 to 6; After passing the collision detection, the grasping device is controlled to grasp the object to be grasped.

8. The control method according to claim 7, further comprising: When the collision detection fails, the object to be grasped is reselected and the collision detection step is repeated.

9. The control method according to claim 7, further comprising: When the object to be grasped includes multiple independent objects, Determining whether the relative position relationship of the plurality of objects meets a preset value, wherein the preset value includes a maximum distance between the objects; When the relative position relationship of the multiple objects does not meet the preset value, the object to be grasped is reselected.

10. A material grabbing system, comprising: A grasping device, wherein the grasping device is configured to be driven to grasp an object to be grasped and transport the object to be grasped to a target location; An image acquisition device, wherein the image acquisition device is configured to acquire image information of an object to be grasped; and A control system, wherein the control system communicates with the gripping device and the image acquisition device and is capable of executing the control method as described in any one of claims 7-9. The material grabbing system according to claim 10 , wherein the grabbing device is an adsorption-type grabbing mechanism.

12. The material grasping system according to claim 10 or 11, wherein the image acquisition device comprises a 3D camera, and the image information comprises point cloud data of the object to be grasped.

13. A computer-readable storage medium, comprising computer executable commands stored thereon, wherein the executable commands, when executed by a processor, implement the collision detection method according to any one of claims 1 to 6 and / or the control method according to any one of claims 7 to 9.

Images