Grasping method, device, actuator, storage medium and computer product

Abstract

The present disclosure discloses a grasping method, device, actuator, storage medium, and computer product. The method comprises: generating a grasping plan based on the current grasping state of the grasping area, the current stacking state of the items in the stacking area, and the maximum grasping quantity of the actuator, wherein the grasping plan includes a grasping position plan for grasping items from the grasping area multiple times; and performing a grasping action according to the grasping plan. The grasping method of the present disclosure generates a grasping plan including a grasping position plan for grasping items from the grasping area multiple times. Thus, even if the items in the grasping area are scattered, the number of grasped items is not limited, thereby reducing the number of stacking times and improving the overall efficiency of item stacking.

Description

Technical Field

[0001] The present disclosure relates to the field of intelligent machine technology, and in particular to a grasping method, device, actuator, storage medium, and computer product. Background Art

[0002] When measuring the efficiency of a palletizing system, cycle time is an important parameter. Cycle time is generally defined as the time required to palletize one item. The lower the cycle time, the more items can be palletized in the same amount of time.

[0003] The current method of stacking items allows multiple items to be grasped and stacked at once, reducing the motion time of actuators (such as robotic arms and palletizers), thereby reducing the average cycle time. However, the number of items stacked with this method depends on the distribution of items in the grasping area. If the items are scattered, the number of items that can be grasped will be limited, resulting in lower overall stacking efficiency.

[0004] Therefore, the current method of grabbing items leads to low overall efficiency of item stacking. Summary of the Invention

[0005] The present disclosure provides a grasping method, device, actuator, storage medium, and computer product to solve the problem of low overall efficiency of item stacking caused by current item grasping methods.

[0006] In a first aspect, the present disclosure provides a grasping method, wherein the method is used for an actuator to grasp an object from a grasping area, comprising:

[0007] generating a grasping plan according to a current grasping state of the grasping area, a current stacking state of the stacking area, and a maximum grasping quantity of the actuator, wherein the grasping plan includes a grasping position plan for grasping items from the grasping area multiple times;

[0008] The grasping action is performed according to the grasping plan.

[0009] In a possible implementation, the current item grabbing state includes the number of remaining items and the positions of the remaining items in the grabbing area, and the current item stacking state includes the number of empty spaces;

[0010] The generating of the grabbing plan according to the current grabbing state of the grabbing area, the current stacking state of the stacking area, and the maximum grabbing quantity of the actuator includes:

[0011] The grasping position plan is generated according to the number of remaining items, the positions of the remaining items, the maximum grasping quantity of the actuator and the number of vacancies.

[0012] In a possible implementation, generating the grabbing position plan according to the number of remaining items, the positions of the remaining items, the maximum grabbing quantity of the actuator, and the number of vacant positions includes:

[0013] Obtaining the number of items to be grabbed based on the number of remaining items, the number of empty spaces, and the maximum grabbing number of the actuator; wherein the number of items to be grabbed is the minimum value among the number of remaining items, the number of empty spaces, and the maximum grabbing number of the actuator;

[0014] The grabbing position plan is determined according to the number of items grabbed and the positions of the remaining items; wherein the grabbing position plan includes the number of items grabbed each time, the items grabbed each time, and the position of each grab.

[0015] In a possible implementation, the grasping scheme further includes: a grasping path scheme corresponding to the grasping position scheme;

[0016] The generating of the grasping plan according to the current grasping state of the grasping area, the current grasping state of the grasping area and the maximum grasping quantity of the actuator further includes:

[0017] According to the grasping position plan, generating at least one grasping path plan corresponding thereto;

[0018] The carrying out of the grabbing action according to the grabbing scheme includes:

[0019] Screening at least one grasping solution based on first environmental information to generate a final grasping solution; wherein the first environmental information includes: position information of a first potential collision object between the grasping area and the actuator;

[0020] Implement the grasping action according to the final grasping plan.

[0021] In a possible implementation, there are multiple grabbing schemes;

[0022] The step of screening at least one crawling solution according to the first environment information to generate a final crawling solution includes:

[0023] Sorting the grasping position solutions corresponding to the grasping solutions;

[0024] Performing collision detection on the grasping path solutions corresponding to the grasping position solutions one by one according to the position information of the first potential collision objects in the sorted order;

[0025] The grasping path plan that passes the collision detection and the corresponding grasping position plan are determined as the final grasping plan.

[0026] In a possible implementation, sorting the grasping position solutions corresponding to the grasping solutions includes:

[0027] Determine the total number of grasping times and the total grasping position distance corresponding to each grasping position scheme; the total grasping position distance is the sum of the distances between the grasping positions of the items to be grasped;

[0028] Performing weighted processing on the total number of grasping times and the corresponding total distance of the grasping position to generate a grasping score corresponding to the grasping position solution;

[0029] The grasping position solutions are sorted in descending order of grasping scores.

[0030] In one possible implementation, if there is no grasping path solution that passes the collision detection, the method further includes:

[0031] A new grasping plan is regenerated according to the current item grasping status of the grasping area, the current item stacking status of the stacking area and the maximum grasping quantity of the actuator; the item grasping quantity in the new grasping plan is the difference between the item grasping quantity in the previous grasping plan and the preset value.

[0032] In a possible implementation, the current item stacking status further includes: an empty position;

[0033] Before performing the grabbing action according to the grabbing scheme, the method further includes:

[0034] Generate a stacking plan based on the number of items grabbed and the empty positions;

[0035] After the grabbing action is performed according to the grabbing scheme, the method further includes:

[0036] Perform stacking actions according to the stacking plan.

[0037] In a possible implementation, the stacking plan includes a stacking position plan of stacking the multiple grasped items in the stacking area in multiple times;

[0038] Generating a stacking plan according to the number of items grabbed and the empty positions includes:

[0039] A stacking location plan is generated according to the number of items grabbed and the empty position; wherein the stacking location plan includes the number of items stacked each time, the items stacked each time, and the position of each stacking.

[0040] In a possible implementation, generating a stacking plan based on the number of items grabbed and the empty positions further includes:

[0041] generating at least one stacking path plan corresponding to the stacking position plan according to the stacking position plan;

[0042] The performing of the stacking action according to the stacking scheme includes:

[0043] Screening at least one stacking solution based on the second environmental information to generate a final stacking solution; wherein the second environmental information includes: position information of a second potential collision object between the stacking area and the actuator;

[0044] Implement stacking actions according to the final stacking plan.

[0045] In a possible implementation, there are multiple stacking schemes;

[0046] The screening of at least one stacking scheme according to the second environment information to generate a final stacking scheme includes:

[0047] sorting the stacking position schemes corresponding to the stacking schemes;

[0048] performing collision detection on the stacking path plans corresponding to the stacking position plans one by one according to the position information of the second potential collision objects in the sorted order;

[0049] The stacking path plan and the corresponding stacking position plan that pass the collision detection are determined as the final stacking plan.

[0050] In a possible implementation, sorting the stacking position schemes corresponding to the stacking schemes includes:

[0051] Determine the total number of stacking times and the total stacking distance corresponding to each stacking position scheme; the total stacking distance is the sum of the distances between the stacking positions of each grasped object;

[0052] Performing weighted processing on the total number of stacking times and the corresponding total distance of the stacking positions to generate a stacking score for the corresponding stacking position solution;

[0053] The stacking position solutions are sorted in descending order of stacking scores.

[0054] In a possible implementation, if there is no stacking path solution that passes the collision detection, the method further includes:

[0055] A new grasping plan is regenerated according to the current item grasping status of the grasping area, the current item stacking status of the stacking area and the maximum grasping quantity of the actuator; the item grasping quantity in the new grasping plan is the difference between the item grasping quantity in the previous grasping plan and the preset value.

[0056] In a second aspect, the present disclosure provides a grasping device, wherein the device is used to execute a mechanism to grasp an object from a grasping area, comprising:

[0057] a generation module, configured to generate a grabbing plan based on a current item grabbing state of the grabbing area, a current item stacking state of the stacking area, and a maximum grabbing quantity of the actuator, wherein the grabbing plan includes a grabbing position plan for grabbing items from the grabbing area multiple times;

[0058] The grabbing module is used to perform a grabbing action according to the grabbing scheme.

[0059] In a possible implementation, the current item grabbing state includes the number of remaining items and the positions of the remaining items in the grabbing area, and the current item stacking state includes the number of empty spaces;

[0060] The generation module is specifically used to:

[0061] The grasping position plan is generated according to the number of remaining items, the positions of the remaining items, the maximum grasping quantity of the actuator and the number of vacancies.

[0062] In a possible implementation, when generating the grabbing position plan based on the number of remaining items, the positions of the remaining items, the maximum grabbing quantity of the actuator, and the number of vacancies, the generation module is specifically configured to:

[0063] The number of items to be grasped is obtained based on the number of remaining items, the number of empty spaces, and the maximum grasping number of the actuator; wherein the number of items to be grasped is the minimum value among the number of remaining items, the number of empty spaces, and the maximum grasping number of the actuator; and the grasping position plan is determined based on the number of items to be grasped and the positions of the remaining items; wherein the grasping position plan includes the number of items to be grasped each time, the items to be grasped each time, and the position of each grasp.

[0064] In a possible implementation, the grasping scheme further includes: a grasping path scheme corresponding to the grasping position scheme;

[0065] The generating module is further configured to:

[0066] According to the grasping position plan, generating at least one grasping path plan corresponding thereto;

[0067] The crawling module is specifically used for:

[0068] At least one grasping scheme is screened according to first environmental information to generate a final grasping scheme; wherein the first environmental information includes: position information of a first potential collision object between the grasping area and the actuator; and a grasping action is performed according to the final grasping scheme.

[0069] In a possible implementation, there are multiple grabbing schemes;

[0070] When the crawling module screens at least one crawling solution according to the first environment information and generates a final crawling solution, it is specifically configured to:

[0071] The grasping position schemes corresponding to each grasping scheme are sorted; collision detection is performed on the grasping path schemes corresponding to the grasping position schemes one by one according to the posture information of the first potential collision object in the sorted order; and the grasping path scheme and the corresponding grasping position scheme that pass the collision detection are determined as the final grasping scheme.

[0072] In a possible implementation, when sorting the grasping position schemes corresponding to the grasping schemes, the grasping module is specifically configured to:

[0073] Determine the total number of grasping times and the total grasping position distance corresponding to each grasping position scheme; the total grasping position distance is the sum of the distances between the grasping positions of the items to be grasped; perform weighted processing on each of the total number of grasping times and the corresponding total grasping position distances to generate a grasping score for the corresponding grasping position scheme; and sort the grasping position schemes in descending order according to the grasping score.

[0074] In a possible implementation, if there is no grasping path solution that passes the collision detection, the grasping module is further configured to:

[0075] A new grasping plan is regenerated according to the current item grasping status of the grasping area, the current item stacking status of the stacking area and the maximum grasping quantity of the actuator; the item grasping quantity in the new grasping plan is the difference between the item grasping quantity in the previous grasping plan and the preset value.

[0076] In a possible implementation, the current item stacking status further includes: an empty position;

[0077] The generation module is further configured to:

[0078] Generate a stacking plan based on the number of items grabbed and the empty positions;

[0079] The device further comprises:

[0080] The stacking module is used to implement stacking actions according to the stacking plan.

[0081] In a possible implementation, the stacking plan includes a stacking position plan of stacking the multiple grasped items in the stacking area in multiple times;

[0082] When generating a stacking plan based on the number of items grabbed and the empty positions, the generating module is specifically configured to:

[0083] A stacking location plan is generated according to the number of items grabbed and the empty position; wherein the stacking location plan includes the number of items stacked each time, the items stacked each time, and the position of each stacking.

[0084] In a possible implementation, the generating module is further configured to:

[0085] generating at least one stacking path plan corresponding to the stacking position plan according to the stacking position plan;

[0086] The stacking module is specifically used for:

[0087] At least one stacking solution is screened based on the second environmental information to generate a final stacking solution, wherein the second environmental information includes: position information of a second potential collision object between the stacking area and the actuator; and a stacking action is performed based on the final stacking solution.

[0088] In a possible implementation, there are multiple stacking schemes;

[0089] When the stacking module screens at least one stacking scheme according to the second environment information and generates a final stacking scheme, it is specifically configured to:

[0090] The stacking position schemes corresponding to each stacking scheme are sorted; collision detection is performed on the stacking path schemes corresponding to the stacking position schemes one by one according to the posture information of the second potential collision object in the sorted order; and the stacking path scheme and the corresponding stacking position scheme that pass the collision detection are determined as the final stacking scheme.

[0091] In a possible implementation, when sorting the stacking position schemes corresponding to the stacking schemes, the stacking module is specifically configured to:

[0092] Determine the total number of stacking times and the total stacking position distance corresponding to each of the stacking position schemes; the total stacking position distance is the sum of the distances between the stacking positions of each grasped item; perform weighted processing on each of the total number of stacking times and the corresponding total stacking position distance to generate a stacking score for the corresponding stacking position scheme; and sort the stacking position schemes in descending order of the stacking score.

[0093] In a possible implementation, if there is no stacking path solution that passes the collision detection, the stacking module is further configured to:

[0094] A new grasping plan is regenerated according to the current item grasping status of the grasping area, the current item stacking status of the stacking area and the maximum grasping quantity of the actuator; the item grasping quantity in the new grasping plan is the difference between the item grasping quantity in the previous grasping plan and the preset value.

[0095] In a third aspect, the present disclosure provides an execution mechanism, comprising: a processor, a memory, and an execution component;

[0096] The processor, the memory and the execution component circuits are interconnected;

[0097] The memory stores computer-executable instructions; the execution component is used to grab or stack items under the control of the processor;

[0098] The processor executes the computer-executable instructions stored in the memory to implement the crawling method provided by the first aspect or any possible implementation manner of the first aspect.

[0099] In a fourth aspect, the present disclosure provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, are used to implement the capture method provided in the first aspect or any possible implementation method of the first aspect.

[0100] In a fifth aspect, the present disclosure provides a chip, comprising:

[0101] processor and memory;

[0102] The memory stores a computer program;

[0103] When the processor executes the computer program stored in the memory, the crawling method provided by the first aspect or any possible implementation manner of the first aspect is implemented.

[0104] In a sixth aspect, the present disclosure provides a computer program product, comprising a computer program, which, when executed by a processor, implements the crawling method provided by the above-mentioned first aspect or any possible implementation method of the first aspect.

[0105] The present disclosure provides a grasping method, device, actuator, storage medium, and computer product. The method includes: generating a grasping plan based on the current grasping state of items in the grasping area, the current stacking state of items in the stacking area, and the maximum grasping quantity of the actuator, wherein the grasping plan includes a grasping position plan for grasping items from the grasping area multiple times; and performing a grasping action based on the grasping plan. The grasping method of the present disclosure generates a grasping plan including a grasping position plan for grasping items from the grasping area multiple times. Thus, even if the items in the grasping area are scattered, the number of grasped items is not limited, thereby reducing the number of stacking times and improving the overall efficiency of item stacking. BRIEF DESCRIPTION OF THE DRAWINGS

[0106] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present disclosure and, together with the description, serve to explain the principles of the present disclosure.

[0107] Figure 1 An example diagram of an application scenario provided by an embodiment of the present disclosure;

[0108] Figure 2 This is a schematic diagram of the crawling method provided by the present disclosure. Figure 1 ;

[0109] Figure 3 The schematic diagram of the actuator and remaining items of the grabbing method provided by the present invention is as follows: Figure 1 ;

[0110] Figure 4 This is a schematic diagram of the crawling method provided by the present disclosure. Figure 2 ;

[0111] Figure 5 This is a schematic diagram of the crawling method provided by the present disclosure. Figure 3 ;

[0112] Figure 6 This is a schematic diagram of the crawling method provided by the present disclosure. Figure 4 ;

[0113] Figure 7 Schematic diagram of the actuator and remaining items of the grasping method provided by the present invention Figure 2 ;

[0114] Figure 8 This is a schematic diagram of the crawling method provided by the present disclosure. Figure 5 ;

[0115] Figure 9 This is a schematic diagram of the crawling method provided by the present disclosure. Figure 6 ;

[0116] Figure 10This is a schematic diagram of the grasped items and their placement in the grasping method provided by the present disclosure. Figure 1 ;

[0117] Figure 11 This is a schematic diagram of the grasped items and their placement in the grasping method provided by the present disclosure. Figure 2 ;

[0118] Figure 12 This is a schematic diagram of the crawling method provided by the present disclosure. Figure 7 ;

[0119] Figure 13 This is a schematic diagram of the structure of the gripping device provided by the present invention. Figure 1 ;

[0120] Figure 14 This is a schematic diagram of the structure of the gripping device provided by the present invention. Figure 2 ;

[0121] Figure 15 It is a schematic diagram of the internal structure of the actuator provided by the present disclosure.

[0122] The above drawings illustrate specific embodiments of the present disclosure, which will be described in more detail below. These drawings and textual descriptions are not intended to limit the scope of the present disclosure in any way, but rather to illustrate the concepts of the present disclosure to those skilled in the art by reference to specific embodiments. DETAILED DESCRIPTION

[0123] In order to enable those skilled in the art to better understand the solutions of the present disclosure, the technical solutions in the embodiments of the present disclosure will be clearly and completely described below in conjunction with the drawings in the embodiments of the present disclosure. Obviously, the embodiments described are only part of the embodiments of the present disclosure, not all of the embodiments. Based on the embodiments of the present disclosure, all other embodiments obtained by ordinary technicians in this field without making creative efforts should fall within the scope of protection of the present disclosure.

[0124] It should be noted that the terms "first", "second", etc. in the specification, claims, and drawings of the present disclosure are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present disclosure described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product, or smart device that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products, or smart devices.

[0125] In order to clearly understand the technical solution of the present disclosure, the solution of the prior art is first introduced in detail.

[0126] Currently, when stacking items, multiple items are typically grabbed and stacked all at once. This approach requires selecting appropriate grabbing and stacking strategies based on the current incoming material stack configuration and the target stack configuration. The incoming material stack is located in the grabbing area, while the target stack is located in the stacking area. Because items are grabbed in a single grab, if the incoming material stack is scattered and the items are scattered within the grabbing area, the number of items that can be grabbed can be limited, resulting in the actuator failing to reach its maximum capacity, leading to lower overall stacking efficiency.

[0127] Therefore, in order to address the problem of low overall efficiency of item stacking in the above-mentioned method, the inventors discovered in their research that in order to solve this problem, the core is to reduce the overall number of stacking times, generate a grabbing plan based on the current item grabbing status of the grabbing area, the current item stacking status of the stacking area, and the maximum grabbing number of the actuator, and improve the overall efficiency of item stacking through multiple grabbing.

[0128] Specifically, a grabbing plan is generated based on the current item grabbing status in the grabbing area, the current item stacking status in the stacking area, and the maximum number of items that can be grabbed by the actuator. The grabbing plan includes a grabbing position plan for multiple item grabs from the grabbing area. Grabbing actions are performed according to the grabbing plan. This eliminates the need to limit the number of items that can be grabbed, even if items are scattered in the grabbing area. This reduces the number of stacking attempts and improves overall item stacking efficiency.

[0129] Based on the above creative findings, the inventors proposed the technical solution of the present disclosure.

[0130] Figure 1 This is an example diagram of an application scenario provided by the embodiment of the present disclosure. Figure 1 As shown, the application scenario includes an actuator 1, a gripping area 2 and a stacking area 3.

[0131] The actuator 1 is a mechanical device capable of simultaneously grasping multiple objects. In some embodiments, the actuator 1 is implemented as a robotic arm 11 and a suction cup 12, with six suction cups 12 shown in the figure as an example. Multiple objects are placed in the grasping area 2, with five currently displayed as an example. Multiple objects are already stacked in the stacking area 3, with four already stacked as an example.

[0132] The actuator 1 can identify the current item grabbing status in the grabbing area and the current item stacking status in the stacking area. For example, it can obtain the current item grabbing status and the current item stacking status by setting a camera or a camera to perform image recognition and other operations. At the same time, a grabbing plan is generated in combination with the maximum grabbing number in the actuator 1. The maximum grabbing number in the actuator 1 is related to the number of suction cups 12. For example, if the number of suction cups 12 in the figure is 6, the maximum grabbing number is 6. If the actuator 1 uses a gripper, the maximum grabbing number is related to the number of grippers. After generating the grabbing plan, the actuator 1 controls the movement of the robot arm 11 according to the grabbing plan, and controls the suction cup 12 to perform the grabbing action, such as the items grabbed each time, the grabbing position, etc., to complete the grabbing process of the items. After completing the grabbing process, the grabbed items can be stacked in the stacking area in a one-time stacking manner.

[0133] In some embodiments, the actuator 1 may also employ multiple grippers, the number of which can be adjusted based on the actual application. For example, in this application scenario, the number of grippers is five. Given that the number of items placed in the gripping area 2 and the number of items stacked in the stacking area 3 are the same as in the previous application scenario, the specific gripping process in this application scenario is similar to that in the previous application scenario and will not be detailed here. Furthermore, the end of the gripper may also include multiple small grippers, allowing each gripper to grasp multiple items, further improving gripping efficiency.

[0134] The embodiments of the present invention are described below with reference to the accompanying drawings.

[0135] Figure 2 This is a schematic diagram of the crawling method provided by the present disclosure. Figure 1 .like Figure 2 As shown, in this embodiment, the execution subject of the embodiment of the present invention is a grasping device, which can be integrated into the actuator or set in other control equipment, and is used by the actuator to grasp objects from the grasping area. The method includes:

[0136] S101. Generate a grabbing plan based on a current item grabbing state in a grabbing area, a current item stacking state in a stacking area, and a maximum grabbing quantity of an actuator, wherein the grabbing plan includes a grabbing position plan for grabbing items from the grabbing area multiple times.

[0137] The current item grasping status of the grasping area includes the number of remaining items and their locations. The current item stacking status of the stacking area includes the number of stacked items and the status of available slots. The available slot status includes the number of available slots and their locations. An available slot is a position not occupied by an item. While occupying this position, an item will not collide with other stacked items. The actuator can be a robotic arm, palletizer, etc., and can grasp items multiple times, grasping one or more items at a time. After grasping an item, it can be stacked in the stacking area. The maximum grasping quantity refers to the maximum number of items that the actuator can grasp, which is related to the type and model of the actuator.

[0138] The grasping location plan includes the quantity grasped each time, the items grasped each time, and the location of each grasp.

[0139] S102: Implement the grasping action according to the grasping plan.

[0140] In this embodiment, after determining the grasping plan, the actuator may implement a grasping action, such as grasping objects from the grasping area multiple times.

[0141] For example, Figure 3 As shown, in this embodiment, the actuator grabs the items by means of suction cups. The actuator includes 4 suction cups, namely suction cup A, suction cup B, suction cup C and suction cup D. The number of remaining items in the grabbing area is 5, namely item a, item b, item c, item d and item e. In the generated grabbing plan, there can be one or more grabbing position plans. For example, in a certain grabbing position plan, two items are grabbed for the first time and two items are grabbed for the second time. Then the actuator can grab two items from item a, item b, item c, item d and item e through suction cup A and suction cup B for the first time, such as item a and item b, item b and item c, item c and item d, and so on. The actuator grabs two of the remaining three items through suction cup C and suction cup D for the second time. If item a and item b are grabbed for the first time, item c and item d, item c and item e, or item d and item e can be grabbed for the second time.

[0142] At the same time, based on the grasping method provided in the previous embodiment of the present invention, the solution of the present invention can be further refined. Figure 4 As shown, Figure 4 This is a schematic diagram of the crawling method provided by the present disclosure. Figure 2 In this embodiment, the current item grabbing status includes the number of remaining items in the grabbing area and the positions of the remaining items, and the current item stacking status includes the number of empty spaces.

[0143] The number of remaining items and the actuator's maximum grasping capacity are related to the upper limit of the number of items that can be grasped, while the number of empty slots is related to the number of items that need to be grasped. A grasping position plan is generated based on the number of remaining items, the positions of remaining items, the actuator's maximum grasping capacity, and the number of empty slots. This grasping position plan includes information related to multiple grasps. At the same time, the process of generating a grasping plan can be further refined, as follows:

[0144] S201: Obtain the number of items to be grabbed based on the number of remaining items, the number of empty slots, and the maximum grabbing number of the actuator, wherein the number of items to be grabbed is the minimum value among the number of remaining items, the number of empty slots, and the maximum grabbing number of the actuator.

[0145] In this embodiment, the number of items to be grabbed corresponds to three application scenarios. For example, in the first application scenario, the number of remaining items in the grabbing area is 8, the number of empty spaces in the stacking area is 8, and the maximum grabbing capacity of the actuator is 6. In this case, the current number of items to be grabbed is the minimum of 6. In this application scenario, the number of remaining items in the grabbing area and the number of empty spaces in the stacking area are sufficient, so the actuator can grab items according to the maximum grabbing capacity.

[0146] In the second application scenario, the number of remaining items in the grasping area is 3, the number of empty spaces in the stacking area is 8, and the maximum grasping capacity of the actuator is 6. Therefore, the current grasping capacity is the minimum of the three values, 3. In this application scenario, the number of remaining items in the grasping area is relatively small, so grasping is performed based on the remaining number of items.

[0147] In the third application scenario, the number of remaining items in the grasping area is 8, the number of empty spaces in the stacking area is 3, and the maximum number of grasps for the actuator is 6. Therefore, the current number of grasped items is the minimum of 3. In this application scenario, there are fewer empty spaces in the stacking area, so grasping is performed based on the number of empty spaces.

[0148] In actual applications, the first application scenario is the main application scenario. Therefore, the grabbing method of this embodiment can usually enable the actuator to grab items according to the maximum grabbing quantity of the actuator, reducing the overall stacking times and thus improving the overall stacking efficiency.

[0149] S202: Determine a grabbing location plan based on the number of items grabbed and the positions of the remaining items, wherein the grabbing location plan includes the number of items grabbed each time, the items grabbed each time, and the position of each grab.

[0150] After determining the number of items to be grabbed, we can further determine the number of items to be grabbed each time, the items to be grabbed each time, and the location of each grab. Figure 3As shown in the grabbing area, there are five remaining items: item a, item b, item c, item d, and item e. If the number of items to be grabbed is three, then one item can be grabbed in the first grab and two items in the second grab. Alternatively, one item can be grabbed in the first grab, one item in the second grab, and one item in the third grab. Furthermore, multiple grabbing position plans can be generated based on the number of items to be grabbed and the number of items remaining.

[0151] After the grasping position plans are generated, the grasping position plans may be screened to select a grasping position plan with higher grasping efficiency, or one of the grasping position plans may be randomly selected, which is not limited in this embodiment.

[0152] S203: Implement the grasping action according to the grasping position plan.

[0153] In this embodiment, the implementation of S203 is similar to the implementation of S102 in the previous embodiment of the present invention, and will not be described in detail here.

[0154] like Figure 5 As shown, Figure 5 This is a schematic diagram of the crawling method provided by the present disclosure. Figure 3 The grasping method provided in this embodiment includes a grasping scheme further comprising: a grasping path scheme corresponding to the grasping position scheme. The method of this embodiment includes the following steps:

[0155] S301: Generate a grabbing position plan according to the current grabbing state of the grabbing area, the current stacking state of the stacking area, and the maximum grabbing quantity of the actuator.

[0156] In this embodiment, the implementation of S301 is similar to the implementation of S201 and S202 in the previous embodiment of the present invention, and will not be described in detail here.

[0157] S302: Generate at least one corresponding grasping path plan according to the grasping position plan.

[0158] After determining the grasping position plan, there can be one or more possible movement paths between the actuator and the grasping area. Therefore, at least one grasping path plan can be generated. Because the generated grasping path plans may not have the same path distance and movement efficiency, if there are too many grasping path plans generated, further screening is required.

[0159] S303: Screen at least one grasping solution according to the first environmental information to generate a final grasping solution, wherein the first environmental information includes: position information of a first potential collision object between the grasping area and the actuator.

[0160] The first environmental information refers to information about the area between the grasping area and the actuator, such as whether there is a first potential collision object between the grasping area and the actuator. The first potential collision object refers to an object that may collide with the actuator and affect the implementation of the grasping. During the process of the actuator implementing the grasping, the area between the grasping area and the actuator will gradually become smaller until it overlaps. When the actuator is in the initial position area, the area between the actuator and the grasping area is the largest. Therefore, it is necessary to determine the first environmental information within the area composed of the grasping area, the initial position area of ​​the actuator, and the area between the grasping area and the initial position area of ​​the actuator.

[0161] Because a grasping plan includes a grasping position plan and at least one grasping path plan corresponding to the grasping position plan, and there can be one or more grasping plans, the grasping plans can be screened based on the first environment information to select a final, implementable grasping plan. For example, collision detection can be performed on the at least one grasping path plan corresponding to the grasping position plan based on the first environment information, with the grasping path plan that passes the collision detection being the implementable grasping path plan.

[0162] At the same time, the final grasping solution with high grasping efficiency can also be further screened. For example, the number of grasps, the number of grasps per grasp, and the grasping location in the grasping location solution can be weighted to screen out the grasping location solution with the highest score. Then, the feasible path solutions can be further screened. For example, the moving distance and moving time in the grasping path solution can be weighted to generate a grasping path solution score. The grasping path solution with the highest score and the corresponding grasping location solution can be selected as the final grasping solution.

[0163] It is also possible to immediately determine the high-scoring grasping position plan and the corresponding feasible grasping path plan as the final grasping plan when it is determined that the grasping position plan with a high score has an implementable grasping path plan, without further screening the grasping path plan, thereby improving the efficiency of generating the final grasping plan and further improving the overall stacking efficiency.

[0164] S304: Implement the grasping action according to the final grasping plan.

[0165] In this embodiment, the implementation of S304 is similar to the implementation of S203 in the previous embodiment of the present invention, and will not be described in detail here.

[0166] like Figure 6 As shown, Figure 6 This is a schematic diagram of the crawling method provided by the present disclosure. Figure 4 This embodiment is based on the previous embodiment and is further refined. There are multiple grasping schemes and corresponding grasping position schemes. The method of this embodiment includes the following steps:

[0167] S401: Generate a grabbing position plan according to the current grabbing state of the grabbing area, the current stacking state of the stacking area, and the maximum grabbing quantity of the actuator.

[0168] In this embodiment, the implementation of S401 is similar to the implementation of S301 in the previous embodiment of the present invention, and will not be described in detail here.

[0169] S402: Generate at least one corresponding grasping path plan according to the grasping position plan.

[0170] In this embodiment, the implementation of S402 is similar to the implementation of S302 in the previous embodiment of the present invention, and will not be described in detail here.

[0171] S403: Sort the grabbing position solutions.

[0172] In this embodiment, the sorting can be based on the grabbing efficiency, the number of grabbing times, or the grabbing distance, which is not limited in this embodiment.

[0173] If the grasping position solutions are sorted according to grasping efficiency, the specific process of S403 may include the following steps:

[0174] S4031: Determine the total number of grasping times and the total grasping distance corresponding to each grasping position scheme. The total grasping distance is the sum of the distances between the grasping positions of each object to be grasped.

[0175] S4032: Perform weighted processing on the total number of grasping times and the total distance of the corresponding grasping position to generate a grasping score for the corresponding grasping position solution.

[0176] S4033. Sort the grasping position solutions in descending order of grasping scores.

[0177] In some embodiments, the grasp score is derived based on the total number of grasps and the total grasp distance.

[0178] The number of grabbing times can be selected from once to the number of items to be grabbed, that is, from grabbing once to grabbing one item each time.

[0179] The total grasping distance can refer to the distance the clamp moves between multiple grasping positions. The clamp can be a gripper, a suction cup, etc.

[0180] When considering only one condition, a greater number of grasps results in lower grasping efficiency, and a longer total grasping distance also results in lower grasping efficiency. However, when considering both the number of grasps and the total grasping distance, the two factors have different impacts on grasping efficiency. Therefore, a grasping score generated by weighting the total number of grasps and the total grasping distance more accurately reflects grasping efficiency. Location solutions with high grasping scores have higher grasping efficiency. Meanwhile, location solutions with low grasping scores have lower grasping efficiency.

[0181] For example, Figure 7 As shown, the actuator of this embodiment uses six suction cups, namely suction cup E, suction cup F, suction cup G, suction cup H, suction cup I, and suction cup J. The dotted boxes in the grasping area represent grasped items, and the solid boxes represent remaining items. In the figure, the remaining items include 10 items, namely item f, item g, item h, item i, item j, item k, item l, item m, item n, and item o. In grasping position scheme 1, the number of grasps is two, and three items are grasped each time. The first items grasped are item f, item g, and item h, and the second items grasped are item m, item n, and item o. In grasping position scheme 2, the number of grasps is three, and two items are grasped each time. The first items grasped are item i and item j, the second items grasped are item k and item l, and the third items grasped are item m and item n.

[0182] Of the two grasping position schemes, grasping position scheme one requires two grasps, with fewer grasping times, but the distance between the two grasps is longer, from the upper left corner of the grasping area to the lower right corner of the grasping area. Grasping position scheme two requires three grasps, with more grasping times than grasping position scheme one, but the distance of each grasp is shorter. If the area of ​​the grasping area is large, the impact of the total grasping distance is greater, and the impact of the number of grasping times is relatively small. The grasping efficiency of grasping position scheme one may be lower than that of grasping position scheme two. If the area of ​​the grasping area is small, the impact of the total grasping distance is smaller, and the impact of the number of grasping times is relatively large. The grasping efficiency of grasping position scheme one may be higher than that of grasping position scheme two. The weights of the total grasping distance and the number of grasping times can be set according to the actual application environment, and this embodiment does not limit this.

[0183] S404 : performing collision detection on the grasping path solutions corresponding to the grasping position solutions one by one according to the position information of the first potential collision object in the sorted order.

[0184] S405: Determine whether there is a grasping path solution that passes the collision detection. If so, execute step S406; if not, execute step S408.

[0185] S406: Determine the grasping path solution that passes the collision detection and the corresponding grasping position solution as the final grasping solution.

[0186] S407: Implement the grasping action according to the final grasping plan.

[0187] S408: The number of items captured is reduced by one, and S401 is executed again.

[0188] In this embodiment, starting with the grabbing position solution with the highest grabbing score, a collision check is performed on the grabbing path solution corresponding to the grabbing position solution. If the collision check passes, it means that the grabbing path solution is feasible. If a feasible grabbing path solution exists for the grabbing position solution with the highest grabbing score, the grabbing position solution with the highest grabbing score and the grabbing path solution are determined as the final grabbing solution, and the grabbing operation is performed. If no feasible grabbing path solution exists for the grabbing position solution with the highest grabbing score, a collision check is performed on the grabbing path solution corresponding to the next grabbing position solution in order.

[0189] If none of the grabbing position plans pass the collision detection, S408 is executed, where the current number of items to be grabbed is reduced by one, and a new grabbing plan is generated. The value obtained by reducing the current number of items to be grabbed by one serves as the number of items to be grabbed for the newly generated grabbing plan. In this embodiment, the value to be reduced from the current number of items to be grabbed can be pre-set based on actual needs, and can also be set to two, three, etc.

[0190] In order to better understand the grabbing method of this embodiment, the entire grabbing process will be further illustrated below. First, the actuator generates a grabbing position plan based on the current item grabbing status of the grabbing area, the current item stacking status of the stacking area, and the maximum grabbing quantity of the actuator. Exemplarily, three grabbing position plans are generated in this embodiment, namely grabbing position plan A, grabbing position plan B, and grabbing position plan C. For each grabbing position plan, a corresponding grabbing path plan is generated. The grabbing path plans corresponding to position plan A are grabbing path plan a1, grabbing path plan a2, and grabbing path plan a3. The grabbing path plans corresponding to grabbing position plan B are grabbing path plan b1, grabbing path plan b2, and grabbing path plan b3. The grabbing path plans corresponding to grabbing position plan C are grabbing path plan c1, grabbing path plan c2, and grabbing path plan c3.

[0191] At this time, the grasping position plan A, grasping position plan B, and grasping position plan C are sorted. Assuming that the sorted order is grasping position plan C, grasping position plan B, and grasping position plan A, the grasping path plan c1, grasping path plan c2, and grasping path plan c3 are first subjected to collision detection. If the grasping path plan c1 is a feasible grasping path plan, the grasping position plan C and the grasping path plan c1 can be directly determined as the final grasping plan. If the collision detection result shows that the grasping path plan c1, the grasping path plan c2, and the grasping path plan c3 are all infeasible, then the grasping path plans b1, the grasping path plan b2, and the grasping path plan b3 corresponding to the grasping position plan B are subjected to collision detection one by one. The processing flow and processing logic are similar to those of the grasping position plan C, and will not be repeated here. After determining the final grasping plan, the grasping action can be implemented according to the final grasping plan.

[0192] Figure 8 This is a schematic diagram of the crawling method provided by the present disclosure. Figure 5 This embodiment is a further refinement of the above embodiment. The current item stacking state of this embodiment also includes: an empty position. The method of this embodiment includes the following steps:

[0193] S501. Obtain the number of items to be grasped according to the number of remaining items, the number of empty spaces, and the maximum grasping number of the actuator.

[0194] In this embodiment, the implementation of S501 is similar to the implementation of S201 in the embodiment of the present invention, and will not be described in detail here.

[0195] S502: Determine a grabbing plan based on the number of items to be grabbed and the locations of the remaining items.

[0196] In this embodiment, the implementation of S502 is similar to the implementation of S202 in the embodiment of the present invention, and will not be described in detail here.

[0197] S503: Generate a stacking plan based on the number of items picked up and the location of empty spaces.

[0198] The meaning of the empty slot position is the same as in the previous embodiment and will not be repeated here. The number of items to be picked is the same as the number of items to be stacked in the stacking area, and the empty slot position is related to the stacking position of the items. Therefore, a corresponding stacking plan can be generated based on the number of items to be picked and the empty slot position in the stacking area.

[0199] In this embodiment, the stacking plan includes a stacking position plan for stacking multiple grabbed items in a stacking area, and the stacking times can be one or more times. At the same time, at least one stacking path plan can be generated based on the stacking position plan to provide a basis for subsequent stacking actions. If the stacking times is fixed to once, when generating the grabbing plan, the number of items grabbed will be affected differently depending on the distribution of the vacant positions. For example, if the vacant positions are scattered, the number of items grabbed may be reduced. If the stacking times is one or more, when the number of vacancies in the stacking area is sufficient and the number of remaining items in the grabbing area is sufficient, the number of items grabbed is the maximum grabbing number of the actuator. By stacking multiple times, even if the items are scattered in the grabbing area and / or the vacancies in the stacking area are scattered, the number of items grabbed will not be limited, thereby improving the overall efficiency of item stacking.

[0200] S504: Implement the grabbing action according to the grabbing plan.

[0201] In this embodiment, the implementation of S503 is similar to the implementation of S203 in the embodiment of the present invention, and will not be described in detail here.

[0202] S505: Implement stacking actions according to the stacking plan.

[0203] When implementing stacking actions according to a stacking plan, stacking efficiency can be further considered. For example, similar to the aforementioned crawling plan screening process, parameters in the stacking plan that affect stacking efficiency, such as the number of stacking attempts and the stacking distance, can be determined. Furthermore, a comprehensive score is performed on each parameter in the stacking plan to determine the stacking score corresponding to the stacking plan. A high stacking score indicates high stacking efficiency, while a low stacking score also indicates low stacking efficiency.

[0204] At the same time, based on the grabbing method provided in the previous embodiment of the present invention, the stacking process can be further explained. Figure 9 As shown, Figure 9 This is a schematic diagram of the crawling method provided by the present disclosure. Figure 6 Among them, a stacking location plan is generated based on the number of items grabbed and the empty position. The stacking location plan includes the number of items to be stacked each time, the items to be stacked each time, and the location of each stacking. At the same time, the process of generating the stacking location plan can be further refined, as follows:

[0205] S601: Generate a stacking location plan based on the number of items picked up and the location of the empty space, wherein the stacking location plan includes the number of items to be stacked each time, the items to be stacked each time, and the location of each stacking.

[0206] For example, Figure 10As shown, the actuator grasps four items: item A, item B, item C, and item D. There can be one or more stacking location schemes. For example, in a certain stacking location scheme, item A and item B are stacked for the first time, and item C and item D are stacked for the second time. The actuator then first stacks item A and item B to the corresponding stacking locations, which are two of positions a, b, c, d, and e (possibly positions b and c, d and e, a and b, etc.). The actuator then stacks item C and item D to the remaining available stacking locations. If the first stacking locations are positions a and b, the second stacking location selects two positions from positions c, d, and e (possibly positions d and e, c and d, etc.).

[0207] S602: Generate at least one corresponding stacking path plan according to the stacking position plan.

[0208] The movement path from the actuator to the stacking area is usually not unique. Therefore, at least one corresponding stacking path plan can be generated based on the stacking position plan. If there are multiple stacking path plans, the stacking path plans can be further screened to determine the most efficient one, thereby improving overall stacking efficiency.

[0209] S603: Screen at least one stacking solution according to the second environmental information to generate a final stacking solution, wherein the second environmental information includes: position information of a second potential collision object between the stacking area and the actuator.

[0210] In this embodiment, the second environmental information is similar to the first environmental information, and refers to relevant information of the area between the stacking area and the actuator, such as whether there is a second potential collision object between the stacking area and the actuator. The second potential collision object is similar to the first potential collision object, and refers to an object that may collide with the actuator, affecting the implementation of stacking. The second environmental information is different from the first environmental information in that they are located in different areas. During the stacking process implemented by the actuator, the area between the stacking area and the actuator will change. After grabbing the item, the area between the actuator and the stacking area is the largest, and can be regarded as consisting of the grabbing area, the stacking area, and the area between the grabbing area and the stacking area. Therefore, it is necessary to determine the second environmental information within the area consisting of the grabbing area, the stacking area, and the area between the grabbing area and the stacking area.

[0211] Since a stacking plan includes a stacking position plan and at least one stacking path plan corresponding to the stacking position plan, and there can be one or more stacking plans, the stacking plans can be screened based on the second environment information to select a final, implementable stacking plan. For example, similar to collision detection for a grasping plan, collision detection can be performed on at least one stacking path plan corresponding to the stacking position plan based on the second environment information, with the stacking path plan that passes the collision detection being considered an implementable stacking path plan.

[0212] At the same time, the final stacking plan with high stacking efficiency can be further screened. For example, the stacking times and stacking positions in the stacking position plan can be weighted to screen out the stacking position plan with the highest score. Then, the feasible stacking path plans can be further screened. For example, the moving distance and moving time in the stacking path plan can be weighted to generate a score for the stacking path plan. The stacking path plan with the highest score and the corresponding stacking position plan can be selected as the final stacking plan.

[0213] Alternatively, when it is determined that a highly scored location solution has an implementable stacking path solution, the highly scored location solution and the corresponding implementable stacking path solution can be immediately determined as the final stacking solution without further screening the path solution, thereby improving the efficiency of generating the final stacking solution and further improving the overall stacking efficiency.

[0214] Optionally, in this embodiment, S603 may specifically be:

[0215] Sort the stacking position plans corresponding to each stacking plan.

[0216] Collision detection is performed on the stacking path plans corresponding to the stacking position plans one by one according to the position information of the second potential collision object in the sorted order.

[0217] The stacking path plan and the corresponding stacking position plan that pass the collision detection are determined as the final stacking plan.

[0218] In this embodiment, collision detection can start with the top-ranked stacking position solution and perform collision detection on the stacking path solution corresponding to the top-ranked stacking position solution. If the collision detection passes, it indicates that the stacking path solution is feasible. If a feasible stacking path solution exists for the top-ranked stacking position solution, the top-ranked stacking position solution and the stacking path solution are determined as the final stacking solution, and the stacking operation is performed.

[0219] At the same time, when sorting, it can be sorted by stacking efficiency, stacking times, or stacking distance, which is not limited in this embodiment. Each stacking plan corresponds to a stacking position plan, and each stacking position plan corresponds to at least one stacking path plan.

[0220] If the stacking position plans are sorted according to stacking efficiency, the following steps are included:

[0221] Determine the total number of stacking times and total stacking distance for each stacking location plan. The total stacking distance is the sum of the distances between the stacking locations of each grasped item.

[0222] The total number of stacking times and the total distance of the corresponding stacking positions are weighted to generate a stacking score for the corresponding stacking position solution.

[0223] Sort the stacking location plans in descending order of stacking scores.

[0224] In some embodiments, the stacking score is derived based on the total number of stacking times and the total stacking distance.

[0225] The number of stacking times can be selected from once to the number of items to be grabbed, that is, from stacking all items at once to stacking one item at a time.

[0226] The total stacking distance refers to the distance the fixture moves between multiple stacking positions.

[0227] When considering only one condition, the greater the number of stacking operations, the lower the stacking efficiency, and the longer the total stacking distance, the lower the stacking efficiency. However, when considering both the number of stacking operations and the total stacking distance, the two factors have different impacts on stacking efficiency. Therefore, a stacking score generated by weighting the total number of stacking operations and the corresponding total stacking distance can more accurately reflect stacking efficiency. Stacking solutions with high stacking scores have higher stacking efficiency. Meanwhile, stacking solutions with low stacking scores have lower stacking efficiency.

[0228] For example, Figure 11 As shown, the actuator currently grasps items E, F, G, H, I, and J. Dashed boxes in the stacking area represent empty locations, while solid boxes represent already stacked items. Stacking location plan 1 involves two stacking operations, each involving three items. The first stacking operation is at positions f, g, and h, and the second at positions m, n, and o. Stacking location plan 2 involves three stacking operations, each involving two items. The first stacking operation is at positions i and j, the second at positions k and l, and the third at positions m and n.

[0229] Of the two stacking position schemes, stacking position scheme one requires stacking twice, with fewer stacking times, but the distance between the two stackings is longer, from the upper left corner of the stacking area to the lower right corner of the stacking area. Stacking position scheme two requires stacking three times, with more stacking times than stacking position scheme one, but the distance of each stacking is shorter. If the area of ​​the stacking area is large, the impact of the total stacking distance is greater, and the impact of the number of stacking times is relatively small. The stacking efficiency of stacking position scheme one may be lower than that of stacking position scheme two. If the area of ​​the stacking area is small, the impact of the total stacking distance is smaller, and the impact of the number of stacking times is relatively large. The stacking efficiency of stacking position scheme one may be higher than that of stacking position scheme two. The weights of the total stacking distance and the number of stacking times can be set according to the actual application environment, and this embodiment does not limit this.

[0230] S604: Implement stacking operations according to the final stacking plan.

[0231] In this embodiment, the implementation of S604 is similar to the implementation of S505 in the previous embodiment of the present invention, and will not be described in detail here.

[0232] like Figure 12 As shown, Figure 12 This is a schematic diagram of the crawling method provided by the present disclosure. Figure 7 Based on the above embodiment, this embodiment further describes the entire process of grabbing and stacking. The method of this embodiment includes the following steps:

[0233] S701: Generate a grasping position plan and a grasping path plan according to the current grasping state of the grasping area, the current stacking state of the stacking area, and the maximum grasping quantity of the actuator.

[0234] S702: Perform collision detection on the grasping path solutions corresponding to the grasping position solutions one by one according to the posture information of the first potential collision object.

[0235] S703: Determine whether there is a grasping path solution that passes the collision detection. If so, execute step S704; if not, execute S710.

[0236] S704: Determine the grasping path solution that passes the collision detection and the corresponding grasping position solution as the final grasping solution.

[0237] In this embodiment, the implementation of S701 to S704 is similar to the implementation of S401 to S407 in the embodiment of the present invention, and will not be described in detail here.

[0238] S705: Generate a stacking location plan and a stacking path plan based on the number of items to be grabbed and the empty positions in the final grabbing plan.

[0239] S706 : Perform collision detection on the stacking path solutions corresponding to the stacking position solutions one by one according to the posture information of the second potential collision object.

[0240] S707 , determining whether there is a stacking path solution that passes the collision detection, if so, executing step S708 , if not, executing step S710 .

[0241] S708: Determine the stacking path plan that passes the collision detection and the corresponding stacking position plan as the final stacking plan.

[0242] In this embodiment, the implementation of S705 to S708 is similar to the implementation of S601 to S603 in the embodiment of the present invention, and will not be described in detail here.

[0243] S709: Implement the grabbing action according to the final grabbing plan, and implement the stacking action according to the final stacking plan.

[0244] S710: Subtract one from the number of items captured, and execute S701.

[0245] In this embodiment, the entire process of grabbing and stacking is carried out in the order of grabbing first and stacking last. The final grabbing plan generated includes a grabbing position plan and a grabbing path plan. If there is an implementable final grabbing plan, the stacking plan generation process continues. Since the stacking plan is based on the number of items to be grabbed in the grabbing plan, if there is no implementable final stacking plan, it is necessary to re-determine the new number of items to be grabbed. In this embodiment, the new number of items to be grabbed is the previous number of items to be grabbed minus one. The specific number can also be set to the previous number of items to be grabbed minus two or three, etc. When the number of items to be grabbed changes, the grabbing plan will also change accordingly, and therefore, a new grabbing plan needs to be regenerated.

[0246] Figure 13 This is a schematic diagram of the structure of the gripping device provided by the present invention. Figure 1 .like Figure 13 As shown, the grabbing device 800 can be located in an actuator or in other electronic devices, and the grabbing action is performed by controlling the actuator. The grabbing device 800 includes:

[0247] The generation module 801 is used to generate a grasping plan based on the current grasping status of the grasping area, the current item stacking status of the stacking area and the maximum grasping quantity of the actuator, wherein the grasping plan includes a grasping position plan for multiple grasping of items from the grasping area.

[0248] The grabbing module 802 is used to perform a grabbing action according to the grabbing plan.

[0249] Figure 13The provided grasping device can execute the aforementioned corresponding method embodiments, and its implementation principles and technical effects are similar, which will not be repeated here.

[0250] at the same time, Figure 14 This is a schematic diagram of the structure of the grabbing device provided by the present invention. Figure 2 ,like Figure 14 As shown, the grasping device provided in the present disclosure is further refined on the basis of the grasping device provided in the previous embodiment. For the convenience of description, the grasping device of this embodiment is described using the grasping device 900, as follows:

[0251] In a possible implementation, the current item grabbing status includes the number of remaining items and the positions of the remaining items in the grabbing area, and the current item stacking status includes the number of empty spaces.

[0252] The generation module 801 is specifically configured to:

[0253] Generate a grasping position plan based on the number of remaining items, the positions of the remaining items, the maximum grasping quantity of the actuator, and the number of empty positions.

[0254] In one possible implementation, when generating a grabbing position plan based on the number of remaining items, the positions of the remaining items, the maximum grabbing quantity of the actuator, and the number of empty positions, the generation module 801 is specifically configured to:

[0255] The number of items to be grasped is determined based on the number of remaining items, the number of available slots, and the maximum grasping capacity of the actuator. The number of items to be grasped is the minimum of the number of remaining items, the number of available slots, and the maximum grasping capacity of the actuator. A grasping position plan is determined based on the number of items to be grasped and the positions of the remaining items. The grasping position plan includes the number of items to be grasped each time, the items to be grasped each time, and the position of each grasp.

[0256] In a possible implementation, the grasping solution further includes: a grasping path solution corresponding to the grasping position solution.

[0257] The generating module 801 is further configured to:

[0258] At least one corresponding grasping path plan is generated according to the grasping position plan.

[0259] The crawling module 802 is specifically used to:

[0260] At least one grasping solution is screened based on the first environmental information to generate a final grasping solution. The first environmental information includes position information of a first potential collision object between the grasping area and the actuator. A grasping action is performed based on the final grasping solution.

[0261] In a possible implementation, there are multiple crawling schemes.

[0262] When the crawling module 802 screens at least one crawling solution according to the first environment information and generates a final crawling solution, it is specifically configured to:

[0263] Sort the grasping position solutions corresponding to each grasping solution. Perform collision checks on the grasping path solutions corresponding to each grasping position solution, one by one, based on the position information of the first potential collision object in the sorted order. The grasping path solution and its corresponding grasping position solution that pass the collision check are determined as the final grasping solution.

[0264] In a possible implementation, when sorting the grasping position solutions corresponding to the grasping solutions, the grasping module 802 is specifically configured to:

[0265] Determine the total number of grasps and total grasp distance for each grasping location plan. The total grasp distance is the sum of the distances between the grasping locations of each object to be grasped. Weight the total number of grasps and the corresponding total grasp distance to generate a grasp score for the grasping location plan. Rank the grasping location plans in descending order of their grasp scores.

[0266] In a possible implementation, if there is no grasping path solution that passes the collision detection, the grasping module 802 is further configured to:

[0267] A new grabbing plan is generated based on the current state of the grabbing area, the current state of the stacking area, and the maximum number of items that can be grabbed by the actuator. The number of items that can be grabbed in the new grabbing plan is the difference between the number of items that can be grabbed in the previous grabbing plan and the preset value.

[0268] In a possible implementation, the current item stacking status also includes: an empty position.

[0269] The generation module 801 is further used for:

[0270] Generate a stacking plan based on the number of items grabbed and the location of empty spaces.

[0271] The gripping device 900 further includes:

[0272] The stacking module 901 is configured to perform stacking operations according to a stacking plan.

[0273] In a possible implementation, the stacking plan includes a stacking position plan for stacking the multiple grasped objects in the stacking area in multiple times.

[0274] When generating a stacking plan based on the number of items grabbed and the location of the empty space, the generation module 801 is specifically used to:

[0275] Generate a stacking location plan based on the number of items picked and the available locations. The stacking location plan includes the number of items to be stacked each time, the items to be stacked each time, and the location of each stacking.

[0276] In a possible implementation, the generating module 801 is further configured to:

[0277] At least one corresponding stacking path plan is generated according to the stacking position plan.

[0278] The stacking module 901 is specifically used for:

[0279] At least one stacking solution is screened based on the second environmental information to generate a final stacking solution. The second environmental information includes position information of a second potential collision object between the stacking area and the actuator. Stacking actions are performed based on the final stacking solution.

[0280] In a possible implementation, there are multiple stacking schemes.

[0281] When the stacking module 901 screens at least one stacking scheme according to the second environment information and generates a final stacking scheme, it is specifically configured to:

[0282] Sort the stacking position plans corresponding to each stacking plan. Perform collision checks on the stacking path plans corresponding to each stacking position plan based on the position information of the second potential collision object in the sorted order. Determine the stacking path plan and the corresponding stacking position plan that pass the collision check as the final stacking plan.

[0283] In a possible implementation, when sorting the stacking position schemes corresponding to the stacking schemes, the stacking module 901 is specifically configured to:

[0284] Determine the total number of stacking attempts and total stacking distance for each stacking location plan. The total stacking distance is the sum of the distances between the stacking locations of each grasped item. Weight each total number of stacking attempts and the corresponding total stacking distance to generate a stacking score for the corresponding stacking location plan. Sort the stacking location plans in descending order of their stacking scores.

[0285] In a possible implementation, if there is no stacking path solution that passes the collision detection, the stacking module 901 is further configured to:

[0286] A new grabbing plan is generated based on the current state of the grabbing area, the current state of the stacking area, and the maximum number of items that can be grabbed by the actuator. The number of items that can be grabbed in the new grabbing plan is the difference between the number of items that can be grabbed in the previous grabbing plan and the preset value.

[0287] Figure 15Schematic diagram of the internal structure of the actuator provided in the present disclosure. Figure 15 As shown, the execution mechanism includes: a processor 1001, a memory 1002, and an execution component 1003. Memory 1002 stores a computer program. Processor 1001 executes the computer program stored in the memory to implement the steps of the grasping method in the above-mentioned method embodiment. Execution component 1003 is used to grasp or place items under the control of processor 1001.

[0288] In the above-mentioned execution mechanism, the processor 1001, memory 1002 and execution component 1003 are directly or indirectly electrically connected to each other to realize data transmission or interaction. For example, these components can be electrically connected to each other through one or more communication buses or signal lines, such as through a bus connection. The memory 1002 stores computer-executable instructions for implementing the data access control method, including at least one software function module that can be stored in the memory 1002 in the form of software or firmware. The processor 1001 executes various functional applications and data processing by running the software programs and modules stored in the memory 1002.

[0289] The memory 1002 may be, but is not limited to, a random access memory (RAM), a read-only memory (ROM), a programmable read-only memory (PROM), etc. Furthermore, the software programs and modules in the memory 1002 may also include an operating system, which may include various software components and / or drivers for managing system tasks (e.g., memory management, storage device control, power management, etc.), and may communicate with various hardware or software components to provide an operating environment for other software components.

[0290] Processor 1001 can be an integrated circuit chip with signal processing capabilities. The processor 1001 can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc. It can implement or execute the various methods, steps, and logic diagrams disclosed in the embodiments of the present disclosure. The general-purpose processor can be a microprocessor or any conventional processor.

[0291] An embodiment of the present disclosure further provides a chip including a processor and a memory. The memory stores a computer program, and when the processor executes the computer program stored in the memory, the steps of the crawling method in the above method embodiment are implemented.

[0292] An embodiment of the present disclosure further provides a computer-readable storage medium, in which computer-executable instructions are stored. When the computer-executable instructions are executed by a processor, they are used to implement the steps of the crawling method in the above method embodiment.

[0293] An embodiment of the present disclosure further provides a computer program product, including a computer program, which is used to implement the steps of the crawling method in the above method embodiment when executed by a processor.

[0294] Those skilled in the art will appreciate that all or part of the processes in the above-mentioned embodiment methods can be implemented by instructing the relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided by the present disclosure can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0295] Thus far, the technical solutions of the present disclosure have been described in conjunction with the preferred embodiments shown in the accompanying drawings. However, it will be readily understood by those skilled in the art that the scope of protection of the present disclosure is clearly not limited to these specific embodiments. Without departing from the principles of the present disclosure, those skilled in the art may make equivalent changes or substitutions to the relevant technical features, and the technical solutions after such changes or substitutions will fall within the scope of protection of the present disclosure.

[0296] Other embodiments of the present disclosure will readily occur to those skilled in the art after considering the specification and practicing the invention disclosed herein. The present invention is intended to cover any variations, uses, or adaptations of the present disclosure that follow the general principles of the present disclosure and include common knowledge or customary techniques in the art not disclosed herein. The description and examples are to be considered as exemplary only, with the true scope and spirit of the present disclosure being indicated by the claims.

[0297] It should be understood that the present disclosure is not limited to the exact structures that have been described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present disclosure is limited only by the appended claims.

Claims

1. A grasping method for grasping an object from a grasping area by an actuator, characterized in that: include: generating a grasping plan based on the current grasping state of the grasping area, the current stacking state of the items in the stacking area, and the maximum grasping quantity of the actuator, wherein the grasping plan includes a grasping position plan for grasping items from the grasping area multiple times, the current grasping state of the items includes the number of remaining items and the positions of the remaining items in the grasping area, and the current stacking state of the items includes the number of vacant positions; Implementing a grasping action according to the grasping plan; Generating a grabbing plan based on the current grabbing state of the grabbing area, the current stacking state of the stacking area, and the maximum grabbing quantity of the actuator includes: obtaining the number of items to be grabbed based on the number of remaining items, the number of empty spaces, and the maximum grabbing quantity of the actuator; wherein the number of items to be grabbed is the minimum value among the number of remaining items, the number of empty spaces, and the maximum grabbing quantity of the actuator; The grabbing position plan is determined according to the number of items grabbed and the positions of the remaining items; wherein the grabbing position plan includes the number of items grabbed each time, the items grabbed each time, and the position of each grab.

2. The method according to claim 1, characterized in that The grasping scheme further includes: a grasping path scheme corresponding to the grasping position scheme; The generating of the grasping plan according to the current grasping state of the grasping area, the current grasping state of the grasping area and the maximum grasping quantity of the actuator further includes: According to the grasping position plan, generating at least one grasping path plan corresponding thereto; The carrying out of the grabbing action according to the grabbing scheme includes: Screening at least one grasping solution based on first environmental information to generate a final grasping solution; wherein the first environmental information includes: position information of a first potential collision object between the grasping area and the actuator; Implement the grasping action according to the final grasping plan.

3. The method according to claim 2, characterized in that There are multiple grabbing schemes; The step of screening at least one crawling solution according to the first environment information to generate a final crawling solution includes: Sorting the grasping position solutions corresponding to the grasping solutions; Performing collision detection on the grasping path solutions corresponding to the grasping position solutions one by one according to the position information of the first potential collision objects in the sorted order; The grasping path plan that passes the collision detection and the corresponding grasping position plan are determined as the final grasping plan.

4. The method according to claim 3, characterized in that The sorting of the grasping position schemes corresponding to the grasping schemes includes: Determine the total number of grasping times and the total grasping position distance corresponding to each grasping position scheme; the total grasping position distance is the sum of the distances between the grasping positions of the items to be grasped; Performing weighted processing on the total number of grasping times and the corresponding total distance of the grasping position to generate a grasping score corresponding to the grasping position solution; The grasping position solutions are sorted in descending order of grasping scores.

5. The method according to claim 4, characterized in that If there is no grasping path solution that passes the collision detection, the method further includes: A new grasping plan is regenerated according to the current item grasping status of the grasping area, the current item stacking status of the stacking area and the maximum grasping quantity of the actuator; the item grasping quantity in the new grasping plan is the difference between the item grasping quantity in the previous grasping plan and the preset value.

6. The method according to any one of claims 1 to 5, characterized in that The current item stacking status also includes: empty position; Before performing the grabbing action according to the grabbing scheme, the method further includes: Generate a stacking plan based on the number of items grabbed and the empty positions; After the grabbing action is performed according to the grabbing scheme, the method further includes: Perform stacking actions according to the stacking plan.

7. The method according to claim 6, characterized in that The stacking plan includes a stacking position plan for stacking the multiple items that have been grabbed in the stacking area in multiple times; Generating a stacking plan according to the number of items grabbed and the empty positions includes: A stacking location plan is generated according to the number of items grabbed and the empty position; wherein the stacking location plan includes the number of items stacked each time, the items stacked each time, and the position of each stacking.

8. The method according to claim 7, characterized in that Generating a stacking plan according to the number of items grabbed and the empty positions also includes: generating at least one stacking path plan corresponding to the stacking position plan according to the stacking position plan; The performing of the stacking action according to the stacking scheme includes: Screening at least one stacking solution based on the second environmental information to generate a final stacking solution; wherein the second environmental information includes: position information of a second potential collision object between the stacking area and the actuator; Implement stacking actions according to the final stacking plan.

9. The method according to claim 8, characterized in that There are multiple stacking schemes; The screening of at least one stacking scheme according to the second environment information to generate a final stacking scheme includes: sorting the stacking position schemes corresponding to the stacking schemes; performing collision detection on the stacking path plans corresponding to the stacking position plans one by one according to the position information of the second potential collision objects in the sorted order; The stacking path plan and the corresponding stacking position plan that pass the collision detection are determined as the final stacking plan.

10. The method according to claim 9, characterized in that The sorting of the stacking position schemes corresponding to the stacking schemes includes: Determine the total number of stacking times and the total stacking distance corresponding to each stacking position scheme; the total stacking distance is the sum of the distances between the stacking positions of each grasped object; Performing weighted processing on the total number of stacking times and the corresponding total distance of the stacking positions to generate a stacking score for the corresponding stacking position solution; The stacking position solutions are sorted in descending order of stacking scores.

11. The method according to claim 10, characterized in that If there is no stacking path solution that passes the collision detection, the method further includes: A new grasping plan is regenerated according to the current item grasping status of the grasping area, the current item stacking status of the stacking area and the maximum grasping quantity of the actuator; the item grasping quantity in the new grasping plan is the difference between the item grasping quantity in the previous grasping plan and the preset value.

12. A gripping device, used for an actuator to grip an object from a gripping area, characterized in that: include: a generation module, configured to generate a grabbing plan based on a current item grabbing state of the grabbing area, a current item stacking state of the stacking area, and a maximum grabbing quantity of the actuator, wherein the grabbing plan includes a grabbing position plan for grabbing items from the grabbing area multiple times, the current item grabbing state includes the number of remaining items and the positions of the remaining items in the grabbing area, and the current item stacking state includes the number of empty positions; A grasping module, configured to implement a grasping action according to the grasping scheme; The generating module is specifically configured to obtain a grab number of items based on the number of remaining items, the number of empty spaces, and the maximum grab number of the actuator; wherein the grab number of items is the minimum value among the number of remaining items, the number of empty spaces, and the maximum grab number of the actuator; The grabbing position plan is determined according to the number of items grabbed and the positions of the remaining items; wherein the grabbing position plan includes the number of items grabbed each time, the items grabbed each time, and the position of each grab.

13. An actuator, characterized in that: include: Processor, memory and execution components; The processor, the memory and the execution component circuits are interconnected; The memory stores computer-executable instructions; the execution component is used to grab or place items under the control of the processor; The processor executes the computer-executable instructions stored in the memory to implement the grasping method according to any one of claims 1 to 11.

14. A computer-readable storage medium, characterized in that The computer-readable storage medium stores computer-executable instructions, which are used to implement the crawling method according to any one of claims 1 to 11 when executed by a processor.

15. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the crawling method according to any one of claims 1 to 11 is implemented.

Images