Method, device, robot and storage medium for destacking a magazine

Abstract

The application is suitable for the technical field of intelligent equipment, and provides a material box unstacking method, device, robot and storage medium. The method comprises: responding to an unstacking task, performing stack type identification, and obtaining stack type information of a material box stack; according to the stack type information, determining a current unstacking layer of the material box stack and an unstacking sequence of each material box in the current unstacking layer; positioning a target unstacking material box in the unstacking sequence to obtain positioning information of the target unstacking material box; determining a target grabbing strategy based on the positioning information; and controlling a grabbing device to perform an unstacking operation on the target unstacking material box in a grabbing pose corresponding to the target grabbing strategy. The application can realize adaptive and efficient grabbing of material boxes at different positions of the material box stack, and guarantee the stability and overall operation efficiency of the material box unstacking operation under complex working conditions.

Description

Technical Field

[0001] This application relates to the field of intelligent device technology, and in particular to a method, apparatus, robot, and storage medium for destacking bins. Background Technology

[0002] In warehousing and smart manufacturing material handling scenarios, stacked bins need to be dispersed and transferred using industrial automated depalletizing operations. In industrial automated depalletizing scenarios, bin stacks are usually formed by stacking multiple bins layer by layer, with each layer containing several bins. The positions, orientations, and spatial relationships of different bins within a layer vary.

[0003] The current method of destacking bins is relatively simple. Most of them use fixed gripping methods and positioning logic to process all bins in a uniform manner. This method is prone to problems such as gripping failure and collision with adjacent bins or pallets in space-constrained locations, which affects destacking efficiency and operational stability.

[0004] Therefore, how to achieve adaptive and efficient grasping of bins at different positions in the bin stack, and ensure the stability and overall efficiency of bin destacking operations under complex working conditions, is a problem that needs to be considered. Summary of the Invention

[0005] This application provides a method, apparatus, robot, and storage medium for destacking bins, which can adaptively and efficiently grasp bins at different positions in the bin stack, ensuring the stability and overall efficiency of the destacking operation under complex working conditions.

[0006] In a first aspect, embodiments of this application provide a method for destacking material bins, including: In response to the destacking task, the stack type is identified to obtain the stack type information of the material bin stack; Based on the stack type information, determine the current layer to be dismantled in the stack of material boxes, and the dismantling order of each material box in the current layer to be dismantled; The target bin to be unpacked in the destacking sequence is located to obtain its location information; Based on the location information, a target capture strategy is determined; The control gripping device performs a destacking operation on the target bin to be destacking using the gripping pose corresponding to the target gripping strategy.

[0007] Secondly, embodiments of this application provide a bin destacking device, comprising: The stack type recognition unit is used to recognize the stack type in response to the destacking task and obtain the stack type information of the material box stack; The unit for determining information to be dismantled is used to determine the current layer to be dismantled in the stack of material boxes and the dismantling order of each material box in the current layer to be dismantled, based on the stack type information. The unpacking bin positioning unit positions the target unpacking bin in the destacking sequence and obtains its positioning information. The grasping strategy determination unit is used to determine the target grasping strategy based on the positioning information; The destacking unit is used to control the gripping device to perform a destacking operation on the target bin to be destacking in the gripping pose corresponding to the target gripping strategy.

[0008] Thirdly, embodiments of this application provide a robot, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the bin destacking method as described in the first aspect above.

[0009] Fourthly, embodiments of this application provide a computer-readable storage medium storing a computer program that, when executed by a processor, implements the bin destacking method described in the first aspect above.

[0010] Fifthly, embodiments of this application provide a computer program product that, when run on a robot, causes the robot to perform the bin destacking method described in the first aspect above.

[0011] In this embodiment, the robot responds to the destacking task by recognizing the stack type and obtaining the stack type information of the bins. This allows the robot to understand the overall stacking structure of the bins and the spatial distribution of each bin. Then, based on the stack type information, the robot determines the current layer to be destacking and the destacking sequence of each bin in that layer. This enables a structured operation of destacking layer by layer from the top, avoiding mechanical motion redundancy caused by disordered grasping. Next, the robot locates the target bin in the destacking sequence, obtains its location information, and determines the target grasping strategy based on this location information. This allows for adaptive adjustment of the grasping method according to the specific position of the target bin in the stack, overcoming the limitations of a uniform grasping mode and achieving adaptive grasping of bins in different positions. By controlling the grasping device to perform the destacking operation with the grasping posture corresponding to the target grasping strategy, the robot can effectively improve the accuracy and fit of the grasping action, reduce the probability of grasping failure during the destacking process under complex conditions such as slight bin offset and stacking deviation, and effectively ensure the stability and overall efficiency of the bin destacking operation under complex conditions. Attached Figure Description

[0012] To more clearly illustrate the technical solutions in the embodiments of this application, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0013] Figure 1 This is a schematic diagram of the architecture of a material bin destacking control system provided in an embodiment of this application; Figure 2 This is a flowchart illustrating the implementation of a bin destacking method provided in an embodiment of this application. Figure 3 This is a flowchart illustrating a specific implementation of a bin destacking method for evaluating the reachability of navigation points, as provided in an embodiment of this application. Figure 4 This is a flowchart illustrating a specific implementation of step S204 in a bin destacking method provided in this application embodiment; Figure 4.1 This is a schematic diagram of a stack of material boxes to be disassembled in a method for disassembling material boxes provided in an embodiment of this application; Figure 5 This is a flowchart illustrating a specific implementation of step S205 in the bin destacking method provided in this application embodiment; Figure 6.1 This is a flowchart illustrating a specific implementation of secondary positioning in a bin destacking method provided in this application embodiment; Figure 6.2 This is a flowchart illustrating a specific implementation of virtual box determination and skipping processing in a bin destacking method provided in this application embodiment; Figure 7 This is a flowchart illustrating a specific implementation of a destacking method for a material box provided in this application, specifically the destacking operation performed on the next layer to be destacking. Figure 8 This is a structural block diagram of a bin destacking device provided in an embodiment of this application; Figure 9 This is a schematic diagram of the robot provided in an embodiment of this application. Detailed Implementation

[0014] In the following description, specific details such as particular system architectures and techniques are set forth for illustrative purposes and not for limitation, in order to provide a thorough understanding of the embodiments of this application. However, those skilled in the art will understand that this application may also be implemented in other embodiments without these specific details. In other instances, detailed descriptions of well-known systems, apparatuses, circuits, and methods have been omitted so as not to obscure the description of this application with unnecessary detail.

[0015] It should be understood that, when used in this application specification and the appended claims, the term "comprising" indicates the presence of the described features, integrals, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, integrals, steps, operations, elements, components and / or a collection thereof.

[0016] It should also be understood that the term “and / or” as used in this application specification and the appended claims means any combination of one or more of the associated listed items and all possible combinations, and includes such combinations.

[0017] As used in this application specification and the appended claims, the term "if" may be interpreted, depending on the context, as "when," "once," "in response to determination," or "in response to detection." Similarly, the phrase "if determined" or "if detected [the described condition or event]" may be interpreted, depending on the context, as meaning "once determined," "in response to determination," "once detected [the described condition or event]," or "in response to detection [the described condition or event]."

[0018] Furthermore, in the description of this application and the appended claims, the terms "first," "second," "third," etc., are used only to distinguish descriptions and should not be construed as indicating or implying relative importance.

[0019] References to "one embodiment" or "some embodiments" as described in this specification mean that one or more embodiments of this application include a specific feature, structure, or characteristic described in connection with that embodiment. Therefore, the phrases "in one embodiment," "in some embodiments," "in other embodiments," "in still other embodiments," etc., appearing in different parts of this specification do not necessarily refer to the same embodiment, but rather mean "one or more, but not all, embodiments," unless otherwise specifically emphasized. The terms "comprising," "including," "having," and variations thereof mean "including but not limited to," unless otherwise specifically emphasized.

[0020] By way of example and not limitation, the destacking method for tote boxes provided in this application can be applied to robots in scenarios such as warehousing and intelligent manufacturing. Specifically, it can include automated equipment such as destacking robots with robotic arms and mobile chassis, and fixed articulated robots capable of grasping and transferring stacked tote boxes. This application does not impose any restrictions on the specific type of robot.

[0021] The following describes in detail the application scenario of a material bin destacking method provided in the embodiments of this application, as detailed below: The bin destacking method provided in this application is applied to a bin destacking control system with visual perception and multi-system collaborative control capabilities. The control function of the bin destacking control system can be deployed on an independent control terminal or integrated into the robot.

[0022] Figure 1 A schematic diagram of a bin destacking control system provided in an embodiment of this application is shown. See also... Figure 1As shown, the destacking control system for the material bin includes at least a control terminal 10, a vision system 11, a navigation system 12, a motion control system 13, and a gripping execution system 14. The control terminal 10 is connected to the vision system 11, the navigation system 12, the motion control system 13, and the gripping execution system 14 via an industrial communication network.

[0023] The control terminal 10 can be used to execute the bin destacking method provided in this application embodiment. It receives the stack type information of the bin stack and the positioning information of the target bin to be destacking from the vision system 11. Based on the stack type information, it determines the current layer to be destacking and the destacking sequence. Based on the positioning information, it determines the target grasping strategy and grasping posture. It sends navigation commands to the navigation system 12 to control the robot to move to the navigation point corresponding to the target bin to be destacking, sends motion control commands to the motion control system 13 to control the grasping device to move to the grasping posture, and sends grasping and placement commands to the grasping execution system 14 to drive the grasping device to complete the destacking of the target bin to be destacking. The vision system 11 is used to collect images or point cloud data of the bin stack and may include a 3D camera fixedly installed above the bin stack or a 2D camera installed at the end of the robot. The navigation system 12 is used to control the robot chassis to move to a designated position and may include a lidar, odometer, and path planning module. The motion control system 13 is a motion control system used to control the posture adjustment and motion trajectory planning of the grasping device and may include a multi-axis motion controller and servo driver. The gripping execution system 14 is used to drive the gripping device to complete the clamping and releasing of the hopper, and may include an end effector and its drive control unit. The gripping device is an automated execution device used to complete the clamping, gripping, and transfer of the hopper.

[0024] Figure 2 The implementation flow of the destacking method for material bins provided in this application embodiment is illustrated. This method includes steps S201 to S205. The specific implementation principles of each step are as follows: Step S201: In response to the destacking task, perform stack type identification and obtain the stack type information of the material bin stack.

[0025] The destacking task is the execution command that triggers the automated destacking operation of the bin stack. It serves as a prerequisite for the entire destacking process and can be automatically issued by the control terminal or manually triggered. A bin stack is an integral stack structure formed by the orderly stacking of multiple layers and rows of bins, and it is the object processed in the automated destacking operation. Stack type information is a set of basic parameters characterizing the stacking state of the bin stack. Stack type information reflects the stacking structure of the entire bin stack and the spatial distribution of each bin.

[0026] In one possible implementation, the stack type information may include, but is not limited to, the total number of stacked layers of the bins, the layer height, the number of bins contained in a single layer, the arrangement of each bin within the layer, and the relative spatial relationship between the bins.

[0027] The process of stack type recognition can be triggered by the control terminal to execute the vision system.

[0028] In one possible implementation, upon receiving the destacking task, the vision system immediately initiates a full-area scan of the stack of boxes placed on the pallet to acquire image data or point cloud data of the stack. This data is then matched against a pre-stored stack type template to determine the stack type information corresponding to the current stack. If stack type recognition fails due to factors such as lighting conditions, stack deformation, or occlusion, the scanning parameters of the vision system, such as the scanning angle and acquisition accuracy, can be automatically adjusted before attempting recognition again. If multiple retries still fail, a manual intervention mechanism can be triggered, such as prompting the operator to manually mark reference points or confirm the stack type to assist in recognition, until the stack type recognition is completed and complete stack type information is obtained.

[0029] This application embodiment identifies the stack type and obtains the stack type information of the material box stack by responding to the destacking task. It can accurately grasp the overall stacking status and structural characteristics of the material box stack, and provide reliable data support for subsequent layered disassembly and orderly operation.

[0030] Step S202: Based on the stack type information, determine the current layer to be dismantled in the stack of material boxes, and the dismantling sequence of each material box in the current layer to be dismantled.

[0031] The current layer to be destabilized refers to the stack of bins in the bin pile that currently requires destabilization. In this embodiment, the destabilization process follows the principle of starting from the top layer and proceeding downwards layer by layer. Therefore, the current layer to be destabilized is generally initialized to the top layer indicated by the stack type information. As the destabilization task progresses, after each layer is destabilized, the next layer becomes the new current layer to be destabilized.

[0032] The destacking sequence refers to the order in which each bin within the current layer to be destacking is grabbed, and is used to standardize the sequential operation logic of a single layer of bins.

[0033] In one possible implementation, based on the total number of stacked layers and the stacking status of each layer in the acquired stack type information, the top layer of the stack is prioritized as the first layer to be dismantled. The dismantling order is then determined based on the layout of the boxes in this current layer, the box status of each box, or preset operational efficiency requirements. For example, for a stack type with six boxes per layer, the boxes can be dismantled sequentially from the edge to the middle, and from open space to confined space, to reduce the adjustment movements of the gripping device in confined areas and lower the risk of collision.

[0034] In this embodiment of the application, by determining the current layer to be destabilized and the destabilization sequence, an orderly layer-by-layer destabilization plan is established, so that the destabilization operation proceeds layer by layer according to the preset logic, which can avoid mechanical motion redundancy and efficiency loss caused by disordered grasping.

[0035] Step S203: Locate the target bin to be unpacked in the destacking sequence and obtain its location information.

[0036] The target bin to be unpacked refers to the single bin currently being processed according to the unpacking sequence; it is the object to be processed in a single grabbing operation. Positioning information refers to data that characterizes the actual position and orientation of the target bin in space, such as the bin's six-dimensional pose, including three-dimensional spatial coordinates and three rotation angles.

[0037] In one possible implementation, the positioning process of the target bin to be disassembled can be performed by a vision system: the vision system acquires the actual reference point of the bin stack, the pallet position, or the edge of the disassembled bin as a reference, and uses a vision algorithm to calculate the actual spatial pose of the target bin relative to the reference object, which serves as its positioning information. The actual reference point can be a corner point of the bin stack or a marked point on the pallet; the edge of the disassembled bin refers to the boundary of the position vacated by the bins that have been grabbed and moved, which can provide a new reference for the positioning of adjacent bins. By accurately positioning the target bin through the vision system, interference from surrounding bins and stack structures is eliminated, effectively ensuring the uniqueness and accuracy of the positioning information of a single bin.

[0038] This application embodiment accurately obtains the positioning information of the target bin to be disassembled, enabling the control terminal to grasp the actual spatial state of the target bin to be disassembled. This solves the problem of position ambiguity caused by stacking of stacks and slight displacement of bins, and provides core data support for subsequent matching and adaptation of grasping strategies and accurate execution of grasping actions.

[0039] As one possible implementation of this application, before entering the depalletizing cycle, the gripping poses and corresponding navigation points of all boxes in the current layer to be depalletized can be pre-evaluated to ensure that the robot can smoothly reach each gripping position during actual execution.

[0040] Figure 3 This application illustrates a specific implementation flow for evaluating the reachability of navigation points corresponding to each gripping pose in the bin destacking method provided in this embodiment, detailed below: A1: Synchronously calculate the grasping pose of each bin in the current layer to be disassembled, and evaluate whether the navigation point corresponding to each grasping pose is reachable. The navigation point is the position that the robot needs to reach when grasping the corresponding bin.

[0041] The navigation point is determined based on the grasping pose of the corresponding bin and the robot's kinematic model. It is usually a stopping position of the robot chassis (such as the base of an autonomous mobile robot with a robotic arm or a stationary robot) in front of the bin stack. The navigation point can be represented by the coordinates of the projection of the robot chassis center onto the ground.

[0042] In one possible implementation, after the control terminal identifies the stack type of the bins and determines the current layer to be dismantled and the dismantling order of each bin in that layer based on the stack type information, it performs pre-planned operations on all bins in that layer. Specifically, the control terminal synchronously calculates the spatial pose that the robotic arm end effector needs to reach when each bin is grasped, based on the preset position of each bin in the layer recorded in the stack type information (e.g., the coordinate range of bin position 1 to bin position 6) and the actual reference point of the bin stack obtained through the vision system (e.g., the corner point of the pallet or the edge of the dismantled bin). This spatial pose is the grasping pose. Synchronous calculation means that the pose calculation is performed in parallel or sequentially for all bins in the current layer to be dismantled, rather than only calculating the target bin to be dismantled in the current dismantling sequence. The grasping pose includes at least the three-dimensional spatial coordinates of the robotic arm end effector in the robot coordinate system and three rotation angles, i.e., a six-dimensional pose.

[0043] The control terminal assesses the reachability of the navigation point corresponding to each grasping pose based on the grasping posture of each bin and the robot's kinematic model (e.g., the workspace range of the robotic arm and the motion constraints of the mobile chassis). The assessment process includes: determining whether the robot can safely and without collision move from its current position to the navigation point based on the stack type information and the positioning information of each bin, combined with the robot's workspace range and path planning algorithm; and whether the posture of the grasping device at the navigation point is within the kinematic constraints. When the robot chassis is located at the navigation point corresponding to a bin, and the robotic arm can move to the grasping pose of that bin and complete the grasping action without collision or exceeding joint limits, the navigation point is considered reachable; otherwise, it is considered unreachable.

[0044] A2: If there are unreachable navigation points, adjust the unreachable navigation points and re-evaluate the navigation points for each grab pose until all navigation points are reachable.

[0045] When the assessment finds that one or more navigation points are deemed unreachable, the control terminal adjusts these unreachable navigation points.

[0046] One possible implementation is to adjust the navigation point's coordinates automatically based on the constraints of the robot's kinematic model (e.g., moving the navigation point a preset distance closer to the toy box, or changing the navigation point's orientation angle), or to control the mobile chassis to move within a small range to find a better docking position, thereby changing the relative positional relationship between the robot and the toy box stack, making previously unreachable navigation points reachable. After adjustment, the control terminal re-evaluates the reachability of the adjusted navigation points and their corresponding grasping poses, i.e., repeats the evaluation operation in step A1. If there are still unreachable navigation points, the adjustment and re-evaluation continue until all navigation points corresponding to toy boxes in the current layer to be removed are determined to be reachable.

[0047] In this embodiment, before the actual depalletizing is performed, potential navigation point unreachability issues are identified in advance through pre-calculation and evaluation, avoiding grasping failures or robot collisions due to improper navigation point settings during the actual depalletizing process; the grasping risk caused by improper navigation point settings is eliminated through a closed-loop adjustment mechanism, ensuring that each bin has at least one feasible robot docking position and corresponding grasping pose, thereby improving the reliability and automation of the depalletizing task.

[0048] Step S204: Determine the target capture strategy based on the location information.

[0049] The target grasping strategy is a grasping operation plan determined based on the positioning information of the target bin to be disassembled. It includes the clamping method and offset parameters. The clamping method defines the way the grasping device clamps the bin, such as clamping with both hands along the long side, clamping with both hands along the short side, or grasping with one hand. The offset parameters define the offset distance of the grasping device in the grasping direction.

[0050] In one possible implementation, the target grasping strategy can be one of a first type of strategy, a second type of strategy, or a third type of strategy. The first type of strategy includes grasping the material box with one hand in an offset manner; the second type of strategy includes holding the material box with both hands along the short side in a non-offset manner; and the third type of strategy includes holding the material box with both hands along the long side in a non-offset manner.

[0051] Because the spatial constraints faced by bins vary depending on their location within the bin stack, for example, bins located at the edge of the stack may be adjacent to other bins or pallet boundaries, while bins in the middle or open areas may have more space. Based on the positioning information of the target bin to be disassembled, the system determines its arrangement position and real-time offset posture within the current stack. Based on this, a corresponding target grasping strategy is matched from multiple grasping strategies, allowing the grasping method to adaptively adjust according to the actual spatial position of the target bin within the stack. Differentiated and adaptive matching of target grasping strategies for bins in different areas and with different placement states within the stack can improve grasping adaptability and success rate at the operational strategy level.

[0052] As one possible implementation of this application, the positioning information includes the pose of the target bin to be disassembled; the bin pose refers to the six-dimensional pose of the target bin to be disassembled in three-dimensional space, including three-dimensional spatial coordinates and three rotation angles.

[0053] Figure 4 A specific implementation flow of step S204 in the destacking method of the material bins provided in the embodiments of this application is shown below: B1: Determine the box number of the target box to be dismantled. The box number is a logical number determined by matching the box's position with a preset box stack layout template. The box number identifies the box's position within the stack and is not physically marked on the box's surface. The box stack layout template is a pre-configured data model describing the theoretical arrangement of each box in each stack. For example, for a stack with six boxes per stack, the layout template can define the theoretical coordinate range of each box's position within the stack.

[0054] Specifically, the control terminal matches the target bin's pose (i.e., actual spatial coordinates) with the theoretical coordinate range of each bin position in the layout template within the bin stack. The corresponding bin number is determined based on the theoretical coordinate range into which the actual coordinates fall. For example, if the actual coordinates of the target bin are within the coordinate range corresponding to bin position number "1" in the layout template, then the bin number is determined to be 1; if they are within the range of bin position number "6", then it is determined to be 6.

[0055] In one possible implementation, the layout template within the bin stack layer can be generated by a vision system during bin stacking. Specifically, after stacking is completed, the actual placement pose of each bin is saved; the layout template within the layer is constructed based on the saved actual placement pose. This layout template can be stored in a designated storage unit for retrieval during destacking, and is used to match the bin pose of the target bin to be destacking to determine the bin number.

[0056] B2: Retrieve the grabbing strategy corresponding to the box number of the target box to be disassembled from the preset strategy mapping table as the target grabbing strategy.

[0057] The pre-configured strategy mapping table is a data structure that stores the binding relationship between each box number and its corresponding grasping strategy. This pre-configured strategy mapping table is pre-configured before the depalletizing task is executed, with different box numbers corresponding to different grasping strategies.

[0058] For example, such as Figure 4.1 As shown, for bin positions surrounded by other bins and only operable with one hand (such as bin positions 1 or 3), the corresponding strategy can be configured to use an offset method for one-handed gripping, with an offset distance of 20 cm; for bin positions with open space on both sides (such as bin positions 5 or 6), the corresponding strategy can be configured to use a non-offset method for gripping along the long side with both hands; for bin positions with limited space in the short side direction (such as bin positions 2 or 4), the corresponding strategy can be configured to use a non-offset method for gripping along the short side with both hands.

[0059] In this embodiment, by matching the actual spatial position of the material box with the preset template, the physical position is converted into a logical number, and then the corresponding grasping strategy is retrieved from the preset mapping table. This allows the grasping method to be adaptively adjusted according to the specific position of the material box in the layer, thus overcoming the limitations of the uniform grasping mode and improving the adaptability and stability of the destabilization operation.

[0060] Step S205: Control the gripping device to perform a destacking operation on the target bin to be destacking in the gripping pose corresponding to the target gripping strategy.

[0061] Grasping pose refers to the spatial position and orientation that a gripping device needs to reach when performing a gripping operation. In one possible implementation, the gripping pose is determined based on the clamping method and offset parameters in the target gripping strategy, as well as the positioning information of the target bin to be unloaded.

[0062] The destacking operation includes grabbing the target bins to be destacking and transferring them after successful grabbing, thereby transferring the target bins from the bin stack to the target conveyor line or other designated locations.

[0063] As one possible implementation of this application Figure 5 A specific implementation flow of step S205 in the destacking method for material boxes provided in this application embodiment is shown below: C1: Control the robot to move to the navigation point corresponding to the target bin to be unloaded. The navigation point is the position the robot needs to reach when grasping the corresponding bin. There is a correspondence between the navigation point and the target bin; that is, each bin has a pre-set navigation point based on its position in the layer and its corresponding grasping posture.

[0064] The control terminal sends a navigation command to the navigation system to navigate to the navigation point, and the navigation system controls the robot chassis to move to that position. Once the robot reaches the navigation point, its gripping device is within its effective working range, capable of performing gripping operations on the target bin. By guiding the robot to a suitable working position, a correct spatial relationship is established between the gripping device and the target bin, providing a positional basis for subsequent gripping operations.

[0065] C2: Determine the grasping pose based on the clamping method and offset parameters in the target grasping strategy, as well as the pose of the target box to be disassembled.

[0066] The control terminal uses the target bin's orientation as a reference, combined with the relative orientation relationship between the gripping device and the bin determined by the clamping method, and the offset in the gripping direction determined by the offset parameter, to calculate the target position and orientation of the gripping device in space, that is, to determine the gripping orientation.

[0067] For example, when the target gripping strategy is to grip with one hand using an offset method with an offset parameter of 20 cm, the gripping posture is based on the target bin's bin posture, offset 20 cm along the gripping direction, and adopts a preset posture for one-handed gripping. When the target gripping strategy is to grip with both hands along the long sides without offset, the gripping posture is based on the target bin's bin posture, adopting a preset posture for gripping with both hands along the long sides, without offset. By converting the gripping method at the strategy level into an executable and precise spatial posture, the gripping device can accurately align with the target bin to be gripped.

[0068] C3: At the navigation point, control the gripping device to perform a gripping operation on the target box to be disassembled in the gripping posture.

[0069] After the robot reaches the navigation point and the grasping posture is determined, the control terminal sends a command to the motion control system to move to the grasping posture. The motion control system then controls the grasping device to adjust its attitude and move to the grasping posture. The control terminal then sends a grasping command to the grasping execution system, which drives the grasping device to perform a clamping or grasping action on the target box to be unloaded. By performing the grasping action in the correct working position and with the correct posture, the physical grasping of the target box to be unloaded is completed.

[0070] C4: Perform target transfer and placement operation on the target bins that have been successfully grabbed and are awaiting dismantling.

[0071] The target transfer and placement operation refers to the operation of transferring the successfully grabbed target unpacked box from the grabbing position and placing it at a designated target location, which can be a target conveyor line or other designated location.

[0072] The control terminal sends motion control commands to the motion control system, instructing the gripping device to lift the target destacking box from the gripping position to the transfer height and move it towards the target position. Upon reaching the target position, the control terminal sends a placement command to the gripping execution system, instructing the gripping device to release the target destacking box, thus completing the placement. By transferring the successfully gripped box to the subsequent workstation, a complete destacking task loop is completed.

[0073] In this embodiment, the robot first moves to the navigation point to establish the basic working position, then determines the precise grasping posture according to the target grasping strategy and the position of the bin, then performs the grasping operation, and finally completes the transfer and placement, forming a complete action chain from movement, positioning, grasping to placement, ensuring the accuracy and reliability of each destacking operation.

[0074] As one possible implementation of this application Figure 6.1 The following is a detailed implementation process of the secondary positioning in the destacking method for material boxes provided in this application embodiment: D1: Obtain feedback information indicating the depalletizing operation result. This feedback information refers to a status signal reflecting the result of the depalletizing operation. This status signal can be generated by sensors configured on the gripping device, such as the clamping force value detected by a force sensor, the air pressure change signal detected by a vacuum suction cup, or the gripping confirmation image acquired by a vision sensor. The feedback information is used to objectively determine whether the gripping was successful, rather than relying on preset logical inferences. Judging the gripping result through objective feedback signals acquired by sensors provides an accurate decision-making basis for whether to trigger subsequent secondary positioning.

[0075] In one possible implementation, when the gripping device is a clamping fixture, the force sensor detects the actual clamping force after the clamp is closed; when the clamping force reaches a preset clamping force threshold, feedback information indicates successful gripping; when the clamping force is lower than the preset clamping force threshold or is zero, feedback information indicates failed gripping.

[0076] In one possible implementation, when the gripping device is a vacuum suction cup, a pressure sensor detects the air pressure inside the suction cup; when the air pressure value is lower than a preset vacuum threshold, feedback information indicates successful gripping; when the air pressure value fails to reach the preset vacuum threshold, feedback information indicates failed gripping.

[0077] D2: When the feedback information indicates that the grasping has failed, the positioning information of the target box to be disassembled is reacquired through the vision system, and the grasping pose is updated according to the reacquired positioning information.

[0078] When feedback indicates a grasping failure, it means the grasping process was incomplete. At this point, the control terminal triggers a secondary positioning, sending a command to the vision system to reposition the target bin to be disassembled. The process of re-acquiring positioning information is the same as the initial positioning process and will not be elaborated here. Using the re-acquired bin pose as a reference, and combining the clamping method and offset parameters in the target grasping strategy, the control terminal recalculates the target pose of the grasping device to update the previously used grasping pose.

[0079] Grabbing failure may be caused by a deviation between the actual pose of the bin and the initial positioning result. This deviation may stem from factors such as slight slippage of the bin during stacking, disturbance of adjacent bins during destacking, or visual errors during the initial positioning. By re-acquiring the real-time pose of the bin through the vision system, any potential positioning deviations can be corrected, providing a more accurate grasping pose for subsequent grasping.

[0080] D3: Based on the updated gripping pose, re-control the gripping device to perform a destacking operation on the target bin to be destacking.

[0081] After completing the gripping pose update, the control terminal sends corresponding instructions to the navigation system, motion control system and gripping execution system again according to the updated gripping pose, and controls the gripping device to perform gripping on the target unpacked box again and the transfer and placement operation after successful gripping.

[0082] In this embodiment, when the first grasping fails, a secondary positioning is triggered based on the objective feedback signal from the sensor. The vision system is used to reacquire the position of the bin and update the grasping position before the destacking operation is performed again. This can effectively deal with grasping failures caused by bin position deviation, improve the overall success rate of the destacking task, and ensure the continuity and robustness of the destacking process.

[0083] As one possible implementation of this application, some box positions may be empty due to missing boxes during stacking or box displacement during destacking. For such box positions, a virtual box determination can be performed before grabbing to skip empty box positions and avoid invalid operations.

[0084] Figure 6.2 The following is a detailed implementation flow of the virtual box determination and skipping process in the destacking method for material boxes provided in this application embodiment: E1: Based on the stack type information or real-time visual feedback from the vision system, determine whether the target unpacked bin's corresponding bin location is a virtual bin. A virtual bin indicates that there is no bin at the corresponding bin location.

[0085] In this embodiment, the determination of virtual boxes can be carried out in two stages: First, in the stack type recognition stage, when the vision system performs an overall scan of the stack of boxes, if it detects that a certain box position is missing a box, it marks the box position as a virtual box, and the marking information is included in the stack type information; Second, in the process of unstacking box by box, the vision system detects the actual state of the box position corresponding to the target box to be unstacking through real-time visual feedback. If it finds that the box position originally had a box but has been moved or tilted, it determines the box position as a virtual box.

[0086] In one possible implementation, the control terminal first checks whether the stack type information already contains a virtual box marker for that box location. If so, it is directly determined to be a virtual box; otherwise, it further obtains real-time visual feedback through the vision system and determines whether a box exists based on the depth information or image features of that box location in the real-time visual feedback. When the depth information shows that there is no valid point cloud data at that box location, or the image features do not match the preset box features, the box location is determined to be a virtual box.

[0087] E2: If it is determined that the target unpacked bin is a virtual bin, then skip the target unpacked bin and process the next bin according to the unpacking sequence.

[0088] When the location corresponding to the target bin to be unpacked is determined to be a virtual bin, it means that there is actually no bin available for grabbing at that location. In this case, the control terminal does not perform the location, target grabbing strategy determination, or grabbing operation for the target bin; it skips it and treats the next bin in the destacking sequence as the new target bin to be unpacked, continuing the destacking process. The processing flow for the next bin is the same as for a normal bin, i.e., location, target grabbing strategy determination, and destacking operation are performed sequentially.

[0089] In this embodiment of the application, by executing the virtual box determination and skip processing flow, empty box positions in the box stack can be automatically identified and skipped, maintaining the continuity and efficiency of the destacking operation, avoiding invalid operations and equipment waiting caused by empty box positions, and improving the robustness of the overall destacking process.

[0090] As one possible implementation of this application, during the destacking process, after processing each box, it is necessary to determine whether the current layer has been completely destacking, and after the current layer has been completely destacking, switch to the next layer to be destacking to continue the operation. Figure 7 The following is a detailed implementation flow of the destacking method for material bins provided in this application, which involves performing a destacking operation on the next layer to be destacking: F1: After the target bin to be dismantled has been processed, determine whether all bins in the current layer to be dismantled have been processed.

[0091] The completion of the processing of the target bin means that the destacking operation has been completed for the bin, including successful grabbing and transfer, or it has been determined that it is a virtual bin and has been skipped. When all bins in the current layer have been processed as target bins in the destacking sequence, it is determined that all bins in the current layer have been processed; otherwise, it is determined that they have not been processed.

[0092] F2: If all the boxes in the current layer to be dismantled have not been processed, then the next box to be dismantled will be processed according to the dismantling sequence.

[0093] When it is determined that there are still unprocessed boxes in the current layer to be dismantled, the control terminal takes the next box as the new target box to be dismantled according to the dismantling sequence, and performs positioning, strategy determination and dismantling operations in sequence. Its processing flow is consistent with the aforementioned processing flow of the target box to be dismantled.

[0094] F3: If all the bins in the current layer to be dismantled have been processed, then determine whether there is a next layer to be dismantled in the bin stack based on the layer sequence to be dismantled determined by the stack type information.

[0095] The destabilization sequence refers to the sequence of all layers to be destabilized in the stack, determined based on the stack type information and arranged in the destabilization order. The destabilization process starts from the top layer and proceeds downwards layer by layer; therefore, the destabilization sequence is usually arranged from the top to the bottom layer. After all bins in the current destabilization layer have been processed, the control terminal checks whether there is a layer following the current destabilization layer in the sequence. If there is a layer following the current destabilization layer, it is determined that there is a next destabilization layer; if the current destabilization layer is the last layer in the sequence, it is determined that there is no next destabilization layer, and the entire destabilization task of the bin stack is completed.

[0096] F4: If there is a next layer to be removed, obtain the height information of the next layer to be removed.

[0097] When it is determined that there is a next layer to be removed, the control terminal needs to obtain the height information of the next layer to be removed. The height information refers to the height value of the next layer to be removed relative to the robot's reference coordinate system. This height information can be obtained and stored in the stack type information by the vision system during the stack type recognition stage, or it can be obtained in real time by the vision system when switching layers.

[0098] F5: Based on the height information of the next layer to be removed, adjust the height of the gripping device to the working height corresponding to the next layer to be removed, and then perform a destacking operation on the next layer to be removed.

[0099] Based on the height information of the next layer to be dismantled, the control terminal sends a height adjustment command to the motion control system. The motion control system then controls the gripping device to rise and fall to the working height corresponding to the next layer to be dismantled. This working height refers to the range within which the gripping device can effectively grip each box in the current layer to be dismantled, and can be determined with reference to the gripping posture height of each box in the current layer to be dismantled. After the height adjustment is completed, the control terminal takes the next layer to be dismantled as the new current layer to be dismantled, and sequentially performs positioning, strategy determination, and dismantling operations on each box in that layer according to the dismantling sequence. The processing flow is consistent with the previous layer.

[0100] In this embodiment, the destacking process proceeds layer by layer from top to bottom: each layer is processed one box at a time according to the destacking sequence, and after each layer is completed, the process automatically switches to the next layer and adjusts the working height until all layers of the stack have been processed. This process achieves complete automated destacking of multi-layer stacks of boxes, avoiding manual intervention in layer switching, and effectively ensuring the continuity and overall efficiency of the destacking operation.

[0101] As can be seen from the above, in this embodiment, by recognizing the stack type in response to the destacking task, the robot obtains the stack type information of the bin stack, thereby grasping the overall stacking structure of the bin stack and the spatial distribution of each bin. Then, based on the stack type information, the current layer to be destacking and the destacking sequence of each bin in the layer to be destacking are determined, enabling a structured operation of destacking layer by layer from the top, avoiding mechanical motion redundancy caused by disordered grasping. Next, the target bin to be destacking in the destacking sequence is located to obtain its positioning information, and a target grasping strategy is determined based on the positioning information. This allows for adaptive adjustment of the grasping method according to the specific position of the target bin to be destacking in the bin stack, overcoming the limitations of a uniform grasping mode and realizing adaptive grasping operation for bins in different positions. Then, by controlling the grasping device to perform the destacking operation with the grasping posture corresponding to the target grasping strategy, the accuracy and fit of the grasping action can be effectively improved, reducing the probability of grasping failure during the destacking process under complex working conditions such as slight bin offset and stacking deviation, effectively ensuring the stability and overall efficiency of the bin destacking operation under complex working conditions.

[0102] It should be understood that the sequence number of each step in the above embodiments does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0103] Corresponding to the destacking method of the material bins described in the above embodiments, Figure 8 A structural block diagram of the destacking device for material boxes provided in an embodiment of this application is shown. For ease of explanation, only the parts related to the embodiment of this application are shown.

[0104] Reference Figure 8 The bin destacking device includes: a stack type recognition unit 81, a bin to be destacking information determination unit 82, a bin to be destacking positioning unit 83, a gripping strategy determination unit 84, and a bin destacking unit 85, wherein: The stack type identification unit 81 is used to identify the stack type in response to the destacking task and obtain the stack type information of the material box stack; The unit 82 for determining information to be dismantled is used to determine the current layer to be dismantled in the stack of material boxes and the dismantling order of each material box in the current layer to be dismantled, based on the stack type information. The unpacking bin positioning unit 83 positions the target unpacking bin in the destacking sequence and obtains its positioning information. The grasping strategy determination unit 84 is used to determine the target grasping strategy based on the positioning information; The destacking unit 85 is used to control the gripping device to perform a destacking operation on the target bin to be destacking in the gripping pose corresponding to the target gripping strategy.

[0105] As one possible implementation of this application, the positioning information includes the pose of the target bin to be disassembled; the grasping strategy determination unit 84 is specifically used for: The box number of the target box to be dismantled is determined. The box number is a logical number determined by matching the position of the target box to be dismantled with the preset layout template of the box stack layer. The grabbing strategy corresponding to the box number of the target box to be unpacked is retrieved from the preset strategy mapping table and used as the target grabbing strategy.

[0106] As one possible implementation of this application, the bin destacking device further includes: The depalletizing feedback acquisition unit is used to acquire feedback information indicating the result of the depalletizing operation. The grasping pose update unit is used to reacquire the positioning information of the target box to be disassembled through the vision system when the feedback information indicates that the grasping has failed, and update the grasping pose according to the reacquired positioning information. The destacking unit 85 is also used to re-control the gripping device to perform destacking operation on the target destacking bin based on the updated gripping posture.

[0107] As one possible implementation of this application, the bin destacking device further includes a virtual bin processing unit, used for: Based on the stacking information or the real-time visual feedback from the vision system, it is determined whether the box position corresponding to the target box to be unloaded is a virtual box. The virtual box indicates that there is no box in the corresponding box position. If it is determined that the target bin to be unpacked corresponds to a virtual bin, then the target bin to be unpacked is skipped, and the next bin is processed according to the unpacking sequence.

[0108] As one possible implementation of this application, the bin destacking unit 85 is specifically used for: Control the robot to move to the navigation point corresponding to the target bin to be disassembled, the navigation point being the position the robot needs to reach when grabbing the corresponding bin; The grasping pose is determined based on the gripping method and offset parameters in the target grasping strategy, as well as the pose of the target box to be disassembled. At the navigation point, the gripping device is controlled to perform a gripping operation on the target box to be disassembled in the gripping pose; Perform target transfer and placement operations on the target bins that have been successfully grabbed and are awaiting dismantling.

[0109] As one possible implementation of this application, the navigation point evaluation processing unit is used for: Before locating the target bin in the destacking sequence, the grasping pose of each bin in the current layer to be destacking is calculated synchronously, and the navigation point corresponding to each grasping pose is evaluated as reachable. The navigation point is the position that the robot needs to reach when grasping the corresponding bin. If any navigation point is unreachable, adjust the unreachable navigation point and re-evaluate the navigation points for each grab pose until all navigation points are reachable.

[0110] As one possible implementation of this application, the bin destacking unit 85 is further used for: After the target bin to be dismantled has been processed, determine whether all bins in the current layer to be dismantled have been processed. If all the bins in the current layer to be dismantled have not been processed, then the next bin to be dismantled shall be processed in the dismantling order. If all the bins in the current layer to be dismantled have been processed, then based on the layer to be dismantled sequence determined by the stack type information, it is determined whether there is a next layer to be dismantled in the bin stack. If there is a next layer to be removed, then obtain the height information of the next layer to be removed; Based on the height information of the next layer to be removed, the height of the gripping device is adjusted to the working height corresponding to the next layer to be removed, and then the destacking operation is performed on the next layer to be removed.

[0111] As can be seen from the above, in this embodiment, by recognizing the stack type in response to the destacking task, the robot obtains the stack type information of the bin stack, thereby grasping the overall stacking structure of the bin stack and the spatial distribution of each bin. Then, based on the stack type information, the current layer to be destacking and the destacking sequence of each bin in the layer to be destacking are determined, enabling a structured operation of destacking layer by layer from the top, avoiding mechanical motion redundancy caused by disordered grasping. Next, the target bin to be destacking in the destacking sequence is located to obtain its positioning information, and a target grasping strategy is determined based on the positioning information. This allows for adaptive adjustment of the grasping method according to the specific position of the target bin to be destacking in the bin stack, overcoming the limitations of a uniform grasping mode and realizing adaptive grasping operation for bins in different positions. Then, by controlling the grasping device to perform the destacking operation with the grasping posture corresponding to the target grasping strategy, the accuracy and fit of the grasping action can be effectively improved, reducing the probability of grasping failure during the destacking process under complex working conditions such as slight bin offset and stacking deviation, effectively ensuring the stability and overall efficiency of the bin destacking operation under complex working conditions.

[0112] It should be noted that the information interaction and execution process between the above-mentioned devices / units are based on the same concept as the method embodiments of this application. For details on their specific functions and technical effects, please refer to the method embodiments section, and they will not be repeated here.

[0113] This application embodiment also provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements... Figures 2 to 7 The steps of any method for destacking material bins are represented.

[0114] This application also provides a robot, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements... Figures 2 to 7 The steps of any method for destacking material bins are represented.

[0115] This application also provides a computer program product that, when run on a robot, causes the robot to perform actions such as... Figures 2 to 7 The steps of any method for destacking material bins are represented.

[0116] Figure 9 This is a schematic diagram of a robot provided in one embodiment of this application. Figure 9 As shown, the robot 9 in this embodiment includes a processor 90, a memory 91, and a computer program 92 stored in the memory 91 and executable on the processor 90. When the processor 90 executes the computer program 92, it implements the steps in the various bin destacking method embodiments described above, for example... Figure 1 Steps S201 to S205 are shown. Alternatively, when the processor 90 executes the computer program 92, it implements the functions of each module / unit in the above-described device embodiments, for example... Figure 8 The functions of units 81 to 85 shown.

[0117] For example, the computer program 92 may be divided into one or more modules / units, which are stored in the memory 91 and executed by the processor 90 to complete this application. The one or more modules / units may be a series of computer-readable instruction segments capable of performing a specific function, which describe the execution process of the computer program 92 in the robot 9.

[0118] The robot 9 may include, but is not limited to, a processor 90 and a memory 91. Those skilled in the art will understand that... Figure 9 This is merely an example of robot 9 and does not constitute a limitation on robot 9. It may include more or fewer parts than shown, or combine certain parts, or different parts. For example, robot 9 may also include input / output devices, network access devices, buses, etc.

[0119] The processor 90 can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or any conventional processor.

[0120] The memory 91 can be an internal storage unit of the robot 9, such as a hard drive or memory. The memory 91 can also be an external storage device of the robot 9, such as a plug-in hard drive, smart media card (SMC), secure digital (SD) card, flash card, etc., equipped on the robot 9. Furthermore, the memory 91 can include both internal and external storage units of the robot 9. The memory 91 is used to store the computer program and other programs and data required by the robot. The memory 91 can also be used to temporarily store data that has been output or will be output.

[0121] It should be noted that the information interaction and execution process between the above-mentioned devices / units are based on the same concept as the method embodiments of this application. For details on their specific functions and technical effects, please refer to the method embodiments section, and they will not be repeated here.

[0122] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described division of functional units and modules is merely an example. In practical applications, the above functions can be assigned to different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiments can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit. Furthermore, the specific names of the functional units and modules are only for easy differentiation and are not intended to limit the scope of protection of this application. The specific working process of the units and modules in the above system can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0123] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the methods of the above embodiments of this application can be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include at least: any entity or device capable of carrying computer program code to a device / robot / smart device, a recording medium, a computer memory, a read-only memory (ROM), a random access memory (RAM), an electrical carrier signal, a telecommunication signal, and a software distribution medium. Examples include USB flash drives, portable hard drives, magnetic disks, or optical disks. In some jurisdictions, according to legislation and patent practice, computer-readable media cannot be electrical carrier signals or telecommunication signals.

[0124] In the above embodiments, the descriptions of each embodiment have different focuses. For parts that are not described in detail or recorded in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0125] The above-described embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application, and should all be included within the protection scope of this application.

Claims

1. A magazine de-stacking method, characterized by, include: In response to the destacking task, the stack type is identified to obtain the stack type information of the material bin stack; Based on the stack type information, determine the current layer to be dismantled in the stack of material boxes, and the dismantling order of each material box in the current layer to be dismantled; The target bin to be unpacked in the destacking sequence is located to obtain its location information; Based on the location information, a target capture strategy is determined; The control gripping device performs a destacking operation on the target bin to be destacking using the gripping pose corresponding to the target gripping strategy.

2. The method of claim 1, wherein, The positioning information includes the pose of the target bin to be disassembled; the step of determining the target grasping strategy based on the positioning information includes: The box number of the target box to be dismantled is determined. The box number is a logical number determined by matching the position of the target box to be dismantled with the preset layout template of the box stack layer. The grabbing strategy corresponding to the box number of the target box to be unpacked is retrieved from the preset strategy mapping table and used as the target grabbing strategy.

3. The method of claim 1, wherein, After the control gripping device performs a destacking operation on the target bin to be destacking in the gripping pose corresponding to the target gripping strategy, the method further includes: Obtain feedback information to indicate the results of the depalletizing operation; When the feedback information indicates that the grasping has failed, the positioning information of the target box to be disassembled is reacquired through the vision system, and the grasping pose is updated according to the reacquired positioning information. Based on the updated gripping pose, the gripping device is re-controlled to perform a destacking operation on the target bin to be destacking.

4. The method of claim 1, wherein, Before the control gripping device performs a destacking operation on the target bin to be destacking in the gripping pose corresponding to the target gripping strategy, the method further includes: Based on the stacking information or the real-time visual feedback from the vision system, it is determined whether the box position corresponding to the target box to be unloaded is a virtual box. The virtual box indicates that there is no box in the corresponding box position. If it is determined that the target bin to be unpacked corresponds to a virtual bin, then the target bin to be unpacked is skipped, and the next bin is processed according to the unpacking sequence.

5. The method of claim 1, wherein, The positioning information includes the bin's pose; the control gripping device performs a destacking operation on the target bin to be destacking using the gripping pose corresponding to the target gripping strategy, including: Control the robot to move to the navigation point corresponding to the target bin to be disassembled, the navigation point being the position the robot needs to reach when grabbing the corresponding bin; The grasping pose is determined based on the gripping method and offset parameters in the target grasping strategy, as well as the pose of the target box to be disassembled. At the navigation point, the gripping device is controlled to perform a gripping operation on the target box to be disassembled in the gripping pose; Perform target transfer and placement operations on the target bins that have been successfully grabbed and are awaiting dismantling.

6. The method according to any one of claims 1 to 5, characterized in that, Before locating the target bin to be unpacked in the destacking sequence, the process also includes: The grasping poses of each bin in the current layer to be disassembled are calculated synchronously, and the navigation point corresponding to each grasping pose is evaluated as reachable. The navigation point is the position that the robot needs to reach when grasping the corresponding bin. If any navigation point is unreachable, adjust the unreachable navigation point and re-evaluate the navigation points for each grab pose until all navigation points are reachable.

7. The method according to any one of claims 1 to 5, characterized in that, The method further includes: After the target bin to be dismantled has been processed, determine whether all bins in the current layer to be dismantled have been processed. If all the bins in the current layer to be dismantled have not been processed, then the next bin to be dismantled shall be processed in the dismantling order. If all the bins in the current layer to be dismantled have been processed, then based on the layer to be dismantled sequence determined by the stack type information, it is determined whether there is a next layer to be dismantled in the bin stack. If there is a next layer to be removed, then obtain the height information of the next layer to be removed; Based on the height information of the next layer to be removed, the height of the gripping device is adjusted to the working height corresponding to the next layer to be removed, and then the destacking operation is performed on the next layer to be removed.

8. A magazine de-stacking apparatus characterized by, include: The stack type recognition unit is used to recognize the stack type in response to the destacking task and obtain the stack type information of the material box stack; The unit for determining information to be dismantled is used to determine the current layer to be dismantled in the stack of material boxes and the dismantling order of each material box in the current layer to be dismantled, based on the stack type information. The unpacking bin positioning unit positions the target unpacking bin in the destacking sequence and obtains its positioning information. The grasping strategy determination unit is used to determine the target grasping strategy based on the positioning information; The destacking unit is used to control the gripping device to perform a destacking operation on the target bin to be destacking in the gripping pose corresponding to the target gripping strategy.

9. A robot comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the bin destacking method as described in any one of claims 1 to 7.

10. A computer-readable storage medium storing a computer program, the computer program comprising instructions that, when executed by a computer, cause the computer to perform the method of any one of claims 1 to 9. When the computer program is executed by the processor, it implements the bin destacking method as described in any one of claims 1 to 7.

Images