Warehouse robot control method, device, robot, and warehouse system
The warehouse robot control method addresses the limitations of conventional systems by using a position and orientation identification algorithm to handle various container types, enhancing efficiency and automation in smart warehouses.
Patent Information
- Application Number
- JP2022574777
- Authority / Receiving Office
- JP · JP
- Patent Type
- Patents
- Current Assignee / Owner
- Priority Date
- 2020-06-12
- Filing Date
- 2021-06-29
- Publication Date
- 2024-11-06
- Estimated Expiration
- 2041-06-29
AI Technical Summary
Conventional smart warehouse systems can only handle standard containers with consistent specifications, requiring users to purchase or lease standard containers and perform additional packing operations, increasing costs and reducing efficiency and user experience.
The warehouse robot control method employs a position and orientation identification algorithm to automatically identify and retrieve containers of different types based on their dimensions, surface characteristics, and material, allowing for the use of various container types without additional packing.
This method enhances warehouse efficiency and expands the application scope of warehouse robots by enabling the automatic handling of diverse containers, reducing costs and improving automation levels.
Smart Images

Figure 0007578727000001 
Figure 0007578727000002 
Figure 0007578727000003
Abstract
Description
[Technical field]
[0001] This application claims priority to a Chinese patent application filed with the China Patent Office on June 12, 2020, application number 202010536391.4, entitled "Warehouse robot control method, apparatus, robot and warehouse system," the entire contents of which are incorporated by reference into this application.
[0002] The present application relates to the technical field of smart warehouses, and in particular to a control method, device, robot, and warehouse system for warehouse robots. [Background technology]
[0003] Warehouse robots use smart operation systems that enable them to automatically pick up and store luggage according to system commands. They can also operate continuously 24 hours a day, thereby replacing human management and operation to improve warehouse efficiency, and are therefore widely used and well-received. Summary of the Invention [Problem to be solved by the invention]
[0004] However, conventional smart warehouse systems can only automatically take out and store standard containers that are completely consistent in specifications, which means that users need to purchase or lease standard containers and then pack the items into them when storing their luggage, which increases costs and processing steps, resulting in a poor user experience. In addition, the scope of application of smart warehouse systems is limited.
[0005] The warehouse robot control method, device, robot, and warehouse system provided in the embodiments of the present application target different types of containers and automatically obtain the positions and postures of different types of containers based on a position and posture identification algorithm, thereby improving warehouse efficiency and the application range of the warehouse robot.
[0006] As a first aspect, a control method for a warehouse robot provided in an embodiment of the present application includes the steps of obtaining a container scheduling command for a first target container, including a container type of the first target container; determining a container posture identification algorithm based on the container type of the first target container, and identifying posture information of the first target container based on the container posture identification algorithm; and controlling the warehouse robot to remove the first target container based on the posture information.
[0007] Optionally, the step of determining a container posture identification algorithm based on the container type of the first target container includes a step of pre-establishing a correspondence relationship between each container type and a container posture identification algorithm, and a step of determining a container posture identification algorithm for the first target container based on the correspondence relationship and the container type of the first target container.
[0008] Optionally, the container type is classified into at least one of a smooth surface type container, a rough surface type container, and a type of container including an identification design on the surface based on surface characteristics, or the container type is classified into at least one of a large container, a standard container, and a small container based on dimensional characteristics, or the container type is classified into at least one of a paper container and a plastic container based on material characteristics.
[0009] Optionally, the step of determining a container posture identification algorithm based on the container type includes a step of determining the container posture identification algorithm of the first target container to a smooth-surface type posture identification algorithm if the container type of the first target container is a smooth-surface type, and accordingly, the step of identifying posture information of the first target container based on the smooth-surface type posture identification algorithm includes a step of acquiring a point cloud image and a predetermined reference image of the first target container, a step of registering the point cloud image and the predetermined reference image, and a step of identifying posture information of the first target container based on a result of the registration.
[0010] Optionally, determining a container posture identification algorithm based on the container type, and identifying posture information of the first target container based on the container posture identification algorithm includes determining the container posture identification algorithm of the first target container to a surface unevenness type posture identification algorithm if the container type of the first target container is a surface unevenness type, and correspondingly, identifying the posture information of the first target container based on the surface unevenness type posture identification algorithm includes identifying an uneven portion of a surface of the first target container, and determining the posture information of the first target container based on physical information of the uneven portion, and the physical information includes one or more of the length, width, height, depth, angle, contour, and quantity of the uneven portion.
[0011] Optionally, the step of determining a container posture identification algorithm based on the container type, and identifying posture information of the first target container based on the container posture identification algorithm includes a step of determining the container posture identification algorithm of the first target container to a surface-marked type posture identification algorithm if the container type of the first target container is a type including an identification design on its surface, and accordingly, the step of identifying posture information of the first target container based on the surface-marked type posture identification algorithm includes a step of identifying an identification design of the first target container, and a step of determining posture information of the first target container based on the posture of the identification design.
[0012] Optionally, prior to the step of identifying posture information of the first target container based on the container posture identification algorithm, the step further includes a step of identifying storage location identification information of a target storage location corresponding to the first target container, and accordingly, the step of identifying posture information of the first target container based on the container posture identification algorithm includes a step of identifying posture information of the first target container based on the container posture identification algorithm if identification of the storage location identification information is successful.
[0013] Optionally, the container scheduling command further includes container position information of the first target container, and before determining a container posture identification algorithm based on the container type of the first target container, the method further includes a step of moving the warehouse robot to a target position and moving a luggage removal device of the warehouse robot to a set height based on the container position information.
[0014] Optionally, when the container type of the first target container is a paper container, the step of controlling the luggage removal device of the warehouse robot to remove the first target container includes the steps of obtaining a paper container removal command and controlling the luggage removal device of the warehouse robot to remove the first target container based on the paper container removal command, wherein the paper container removal command includes a first stage removal command and a second stage removal command, the removal speed of the first stage removal command is lower than the removal speed of the second stage removal command, the first stage corresponds to a stage before the luggage removal device contacts the first target container, and the second stage corresponds to a stage after the luggage removal device contacts the first target container.
[0015] Optionally, the step of controlling the warehouse robot to pick up the first target container based on the posture information includes a step of determining a positional relationship between an item removal device of the warehouse robot and the first target container based on the posture information, a step of moving and / or rotating the warehouse robot based on the positional relationship, and a step of controlling the item removal device of the warehouse robot to pick up the first target container.
[0016] Optionally, the posture information includes a distance between the first target container and the warehouse robot, and dimensional information and position / posture information of the first target container, and the container scheduling command further includes standard dimensions of the first target container, and the step of determining a positional relationship between the luggage picking device of the warehouse robot and the first target container based on the posture information includes a step of determining whether the first target container exists based on the distance, and if the first target container exists, a step of determining whether the first target container is valid based on the standard dimensions and the dimensional information of the first target container, and if the first target container is valid, a step of determining a positional relationship between the luggage picking device of the warehouse robot and the first target container based on the posture information.
[0017] Optionally, after moving and / or rotating the warehouse robot based on the positional relationship, the method further includes the steps of obtaining a pick-up distance between the warehouse robot and the first target container, determining whether the pick-up distance satisfies a pick-up condition of the warehouse robot, and if so, controlling a luggage pick-up device of the warehouse robot to pick up the first target container.
[0018] Optionally, the control method for the warehouse robot further includes the steps of: acquiring a container storage command for a second target container on a luggage removal device of the warehouse robot, the container storage command including a storage location location of a storage location corresponding to the second target container; moving the warehouse robot to the storage location of the second target container based on the storage location location; acquiring storage location identification information of the storage location; determining a second positional relationship between the warehouse robot and the storage location based on the storage location identification information of the storage location; moving and / or rotating the warehouse robot based on the second positional relationship; determining whether a third container is present in the storage location; and if not, storing the second target container in the storage location.
[0019] In a second aspect, the present application further provides a control device for a warehouse robot, the control device including: a scheduling command acquisition module for acquiring a container scheduling command for a first target container, the container scheduling command including a container type of the first target container; a container posture identification module for determining a container posture identification algorithm based on the container type of the first target container and identifying posture information of the first target container based on the container posture identification algorithm; and a container removal module for controlling the warehouse robot to remove the first target container based on the posture information.
[0020] Optionally, the container posture identification module includes a correspondence relationship establishment means for pre-establishing a correspondence relationship between each container type and a container posture identification algorithm, a posture identification algorithm determination means for determining a container posture identification algorithm for the first target container based on the correspondence relationship and the container type of the first target container, and a container posture identification means for identifying posture information of the first target container based on the container posture identification algorithm.
[0021] Optionally, the container type is classified into at least one of a smooth surface type, an uneven surface type, and a type including an identification design on the surface according to surface characteristics, and into at least one of a large container, a standard container, and a small container according to dimensional characteristics, and the container type is classified into at least one of a paper container and a plastic container according to material characteristics.
[0022] Optionally, the posture identification algorithm determination means specifically determines the container posture identification algorithm of the first target container to be a smooth surface type posture identification algorithm when the container type of the first target container is a smooth surface type, and accordingly, the container posture identification means specifically acquires a point cloud image and a predetermined reference image of the first target container, registers the point cloud image and the predetermined reference image, and identifies the posture information of the first target container based on the registration result.
[0023] Optionally, the orientation identification algorithm determining means specifically determines the container orientation identification algorithm of the first target container to be an orientation identification algorithm of the surface unevenness type when the container type of the first target container is a surface unevenness type, and accordingly, the container orientation identifying means specifically identifies the uneven parts of the surface of the first target container and determines the orientation information of the first target container based on the physical information of the uneven parts, where the physical information includes one or more of the length, width, height, depth, angle, contour, and quantity of the uneven parts.
[0024] Optionally, the posture identification algorithm determination means specifically determines the container posture identification algorithm of the first target container to a surface marked type posture identification algorithm when the container type of the first target container is a type including an identification design on its surface, and accordingly, the container posture identification means specifically identifies the identification design of the first target container and determines posture information of the first target container based on the posture of the identification design.
[0025] Optionally, the control device of the warehouse robot further includes a rack identification mark identification module that identifies storage location identification information of a target storage location corresponding to the first target container before identifying the posture information of the first target container based on the container posture identification algorithm; accordingly, the container posture identification module specifically determines a container posture identification algorithm based on the container type of the first target container when the identification of the storage location identification information is successful, and identifies the posture information of the first target container based on the container posture identification algorithm.
[0026] Optionally, the container scheduling command further includes container position information of the first target container, and the control device of the warehouse robot further includes a robot movement module for moving the warehouse robot to a target position and moving a luggage removal device of the warehouse robot to a set height based on the container position information before determining a container posture identification algorithm based on the container type of the first target container.
[0027] Optionally, the container removal module includes a positional relationship determination means for determining a positional relationship between the luggage removal device of the warehouse robot and the first target container based on the posture information, a robot movement means for moving and / or rotating the warehouse robot based on the positional relationship, and a container removal means for controlling the luggage removal device of the warehouse robot to remove the first target container.
[0028] Optionally, when the container type of the first target container is a paper container, the container picking means specifically obtains the paper container picking command, and controls the luggage picking device of the warehouse robot to pick up the first target container according to the paper container picking command, the paper container picking command includes a first stage picking command and a second stage picking command, the picking speed of the first stage picking command is lower than the picking speed of the second stage picking command, the first stage corresponds to a stage before the luggage picking device contacts the first target container, and the second stage corresponds to a stage after the luggage picking device contacts the first target container.
[0029] Optionally, the posture information includes a distance between the first target container and the warehouse robot, and dimensional information and position / posture information of the first target container, and the container scheduling command further includes standard dimensions of the first target container, and the positional relationship identification means specifically determines whether the first target container exists based on the distance, and if exists, determines whether the first target container is valid based on the standard dimensions and the dimensional information of the first target container, and if valid, identifies the positional relationship between the luggage removal device of the warehouse robot and the first target container based on the posture information.
[0030] Optionally, the control device of the warehouse robot further includes a distance determination module for obtaining a pick-up distance between the warehouse robot and the first target container after moving and / or rotating the warehouse robot based on the positional relationship, and determining whether the pick-up distance meets the pick-up condition of the warehouse robot, and accordingly, the container pick-up means specifically controls the luggage pick-up device of the warehouse robot to pick up the first target container if the pick-up distance meets the pick-up condition of the warehouse robot.
[0031] Optionally, the control device of the warehouse robot further includes a storage control module, which is used to obtain a container storage command for a second target container on an item picking device of the warehouse robot, the container storage command including a storage location position of a storage location corresponding to the second target container, move the warehouse robot to the storage location of the second target container based on the storage location position, obtain storage location identification information of the storage location, identify a second positional relationship between the warehouse robot and the storage location based on the storage location identification information of the storage location, move and / or rotate the warehouse robot based on the second positional relationship, determine whether a third container exists in the storage location, and if not, store the second target container in the storage location.
[0032] In a third aspect, the present application provides a warehouse robot including a memory and at least one processor, wherein the memory stores computer-executable instructions, and the at least one processor executes the computer-executable instructions stored in the memory, thereby causing the at least one processor to perform the warehouse robot control method provided in any embodiment of the present disclosure.
[0033] As a fourth aspect, the present application provides a warehouse system including a warehouse robot provided in an embodiment corresponding to the third aspect of the present application, a rack, and a warehouse management module, the warehouse robot being connected to the warehouse management module and moving to a position where a target container is located according to a command from the warehouse management module, and picking up and / or storing the target container placed on the rack. conduct .
[0034] In a fifth aspect, the present application provides a computer-readable storage medium having stored thereon computer-executable instructions that, when executed by a processor, are used to implement a warehouse robot control method provided in any embodiment of the present application.
[0035] The warehouse robot control method, device, robot, and warehouse system provided in the embodiments of the present application move the warehouse robot to a target position and move its baggage picking device to a set height based on the container position information in the container scheduling command, and at the same time, determine a corresponding container posture identification algorithm based on the container type in the container scheduling command to identify the posture information, and then pick up the container based on the posture information. This can realize automatic picking of various types of containers with different sizes, materials, and shapes, reduce the difficulty and cost of storing different types of luggage, expand the application range of the warehouse robot, and improve the automation level and efficiency of the warehouse system. [Brief description of the drawings]
[0036] The following drawings are incorporated in and constitute a part of this specification, illustrate preferred embodiments of the present application, and together with the description serve to explain the principles of the present application.
[0037] [Figure 1] FIG. 1 is a diagram showing an application scenario of the warehouse robot control method provided in the embodiment of the present application. [Diagram 2] FIG. 2 is a flowchart of a method for controlling a warehouse robot provided in an embodiment of the present application. [Diagram 3] FIG. 3 is a flowchart of a control method for a warehouse robot provided in another embodiment of the present application. [Figure 4] FIG. 4 is a flow chart of step S304 in the embodiment shown in FIG. 3 of the present application. [Diagram 5] FIG. 5 is a flow chart of step S306 in the embodiment shown in FIG. 3 of the present application. [Figure 6] FIG. 6 is a flow chart of step S308 in the embodiment shown in FIG. 3 of the present application. [Figure 7] FIG. 7 is a flowchart of a control method for a warehouse robot provided in yet another embodiment of the present application. [Figure 8]FIG. 8 is a flow chart of step S411 in the embodiment shown in FIG. [Figure 9] FIG. 9 is a flowchart of a control method for a warehouse robot provided in another embodiment of the present application. [Figure 10] FIG. 10 is a structural schematic diagram of a controller for a warehouse robot provided in one embodiment of the present application. [Figure 11] FIG. 11 is a structural schematic diagram of a warehouse robot provided in one embodiment of the present application. [Figure 12] FIG. 12 is a structural schematic diagram of a warehouse system provided in one embodiment of the present application. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS
[0038] The figures above show clear examples of the present application, which will be described in more detail below. These figures and written description are not intended to limit the scope of the concept of the present application in any way, but to explain the concept of the present application to those skilled in the art by referring to specific examples.
[0039] Exemplary embodiments are now described in detail, examples of which are also illustrated in the drawings. When referring to the drawings in the following description, the same reference numerals in different drawings refer to the same or similar elements unless otherwise indicated. The embodiments described in the following exemplary embodiments are not representative of all embodiments consistent with the present application. Rather, they are merely illustrative of apparatus and methods consistent with certain aspects of the present application as recited in the claims.
[0040] The following specific examples will be used to describe in detail the technical solution of the present application and how the technical solution of the present application solves the above technical problems. Some of the following specific examples can be combined, and the same or similar concepts or processes may not be described repeatedly in the examples. The following examples will be described in conjunction with the drawings. First, the application scenarios of the embodiments of the present application will be described.
[0041] 1 is a diagram of an application scene of the warehouse robot control method provided in the embodiment of the present application. As shown in FIG. 1, the smart warehouse system 100 uses the warehouse robot 110 to pick up and store a target container on the rack 120, and uses the warehouse management module 130 to control the warehouse robot 110 to move to a set position and pick up and store the target container. The warehouse management module 130 further stores storage information of each storage location on the rack 120 and basic information of the target container to facilitate warehouse management.
[0042] In a scene where a warehouse robot retrieves a target container, the warehouse robot of the smart warehouse system provided by the conventional technology can only automatically retrieve completely identical containers. However, in actual operation, there may be situations where the target containers are of different types, such as mismatched dimensions, mismatched shapes, and mismatched materials. In conventional warehouse systems, it is often necessary to add additional standard containers for storage, which increases warehouse costs and reduces the efficiency of storing and retrieving cargo. Conventional warehouse systems cannot directly automatically retrieve containers of different container types. In order to solve this problem, the control method of the warehouse robot provided in the embodiment of the present application targets a warehouse system including multiple types of containers, determines an appropriate identification algorithm based on the container type of the container, identifies the posture information of the container, and further causes the warehouse robot to automatically retrieve the different types of containers based on the posture information. This improves the application range of the warehouse robot and the smart level, automation level, and efficiency of the warehouse system.
[0043] 2 is a flowchart of a control method for a warehouse robot provided in an embodiment of the present application. The control method for a warehouse robot can be executed by a warehouse robot, a warehouse system, a processor, a server, etc. As shown in FIG. 2, the control method for a warehouse robot provided in this embodiment includes the following steps:
[0044] In step S201, a container scheduling command for a first target container is obtained, the container scheduling command including a container type of the first target container.
[0045] Specifically, the first target container may be any one or more containers in a warehouse of the warehousing system, and is identified by a container scheduling command. The container scheduling command may be issued from a warehouse management module of the warehousing system, or may be a command input by a responsible operator through an operation interface. The container type may be identified from the aspects of the container's dimensions, contour, material, surface characteristics, etc. The surface characteristics include, for example, surface pattern, color, whether or not it includes an identification design, whether or not it includes a protrusion or a depression, etc.
[0046] Specifically, the container scheduling command may further include container location information of the first target container, which may be the number of the storage location where the first target container is located or the storage location coordinate value.
[0047] Furthermore, container types may be classified into large containers, standard containers, and small containers according to their dimensions, or into regular-contour containers and irregular-contour containers according to their contours, for example, rectangular containers are classified as regular-contour containers and those with protrusions or depressions on the surface are classified as irregular-contour containers. Irregular-contour containers may be further divided into contour-contour ...
[0048] Specifically, a type number corresponding to each container type can be set, and the type of the first target container can be identified based on the number. Expressed as a four-digit hexadecimal code, for example, 2010, the first digit is a parameter for representing the dimensions, where 2 indicates that it is a large container; the second digit is a parameter for representing the contour, where 0 indicates that it is a regular contour type container; the third digit is a parameter for representing the material, where 1 indicates that it is a plastic type container; the fourth digit is a parameter for representing the surface characteristics, where 0 indicates that it is a type of container without an identification mark on the surface. In other words, 2010 indicates that the first target container is a large plastic container with a regular contour and without an identification mark on the surface.
[0049] Of course, the container type may be classified in other aspects, or may be described in other ways, such as a decimal code or a character string, and the present application is not limited thereto.
[0050] For example, if the container scheduling command is "1, N0053, 3", the first parameter 1 indicates that the action corresponding to the command is removal, and 0 indicates storage. The second parameter indicates the storage location number. The third parameter indicates that the target container type is 3. The specific content of the command is "remove the container whose storage location number is N0053 and whose container type is 3."
[0051] Additionally, the container scheduling instructions may include information such as dimensional information of the first target container including length, width, height, weight, type of cargo contained therein, and the like.
[0052] In step S202, a container posture identification algorithm is determined based on the container type of the first target container, and posture information of the first target container is identified based on the container posture identification algorithm.
[0053] The orientation information may include position and orientation information and dimensional information of the first target container, such as the dimensions of the first target container, its angle relative to the baggage unloading device, its depth, and the like.
[0054] Specifically, different container posture identification algorithms can be set for different container types, so that the corresponding container posture identification algorithm can be determined based on the container type.
[0055] Optionally, determining a container posture identification algorithm based on the container type of the first target container includes pre-establishing a correspondence between each container type and a container posture identification algorithm, and determining a container posture identification algorithm for the first target container based on the correspondence and the container type of the first target container.
[0056] Specifically, the container posture identification algorithm can identify the posture information of the first target container by identifying the quantity, positional relationship, or figure of certain key points of the first target container.Furthermore, the identification information of the first target container can be identified based on a deep learning algorithm, and the posture information of the first target container can be determined based on the identification information.
[0057] In step S203, the warehouse robot is controlled to pick up the first target container based on the posture information.
[0058] Specifically, after identifying the posture information of the first target container, the position of the warehouse robot and the position or angle of the luggage removal device are adjusted based on the posture information, and after the adjustment is completed, the first target container can be removed via the luggage removal device.
[0059] Specifically, when adjusting the position of the warehouse robot and the position or angle of the load picking device based on the posture information, the center of the load picking device must be reliably aligned with the center of the first target container.
[0060] The control method for the warehouse robot provided in this embodiment moves the warehouse robot to a target position according to the container position information in the container scheduling command, moves its luggage picking device to a set height, and at the same time determines a corresponding container posture identification algorithm according to the container type in the container scheduling command to identify its posture information, and then picks up the container according to the posture information. This can realize automatic picking up of various types of containers with different sizes, materials, or shapes, reduce the cost of picking up different types of luggage, expand the application range of the warehouse robot, and improve the automation level and efficiency of luggage picking.
[0061] Figure 3 is a flowchart of a control method for a warehouse robot provided in another embodiment of the present application. As shown in Figure 3, the control method for a warehouse robot provided in this embodiment is based on the control method for a warehouse robot provided in the embodiment shown in Figure 2, with steps S202 and S203 subdivided and a step of moving the warehouse robot and a step of identifying the identification mark on the rack added after step S201. The control method for a warehouse robot provided in this embodiment includes the following steps.
[0062] In step S301, a container scheduling command for a first target container is obtained, the container scheduling command including container location information of the first target container and a container type of the first target container.
[0063] Optionally, the container type is classified into at least one of a smooth surface type, a rough surface type, and a type including an identification pattern on the surface according to a surface characteristic, and is classified into at least one of a large container, a standard container, and a small container according to a dimensional characteristic, and the container type is classified into at least one of a paper container and a plastic container according to a material characteristic.
[0064] Specifically, a container with a smooth surface means that the container surface does not have an identification pattern and does not have any protrusions or depressions, for example, a rectangular parallelepiped container with a smooth surface and no identification pattern. A container with an identification pattern on its surface means that the container surface includes one or more identification patterns, or includes an identification pattern or shape consisting of multiple key points, and the identification pattern can be a barcode, a QR code, a product mark, a product code, etc. The identification pattern can also be information such as letters, numbers, and special codes. A container with a convex or concave surface means that the container surface includes protrusions or depressions, that is, the container surface includes a curved surface such as a concave or convex surface.
[0065] In step S302, the warehouse robot is moved to a target position based on the container position information, and the baggage picking device of the warehouse robot is moved to a set height.
[0066] The load removal device is used to remove or grip containers and can be a fork, a robotic arm, a gripping device, etc.
[0067] Specifically, the container position information may be coordinate information of the storage location where the first target container is placed. For example, (2,3,5) represents the storage location of the third row and fifth column of the second rack in the warehouse. Furthermore, based on the coordinate information, the warehouse robot is moved to the target column of the target rack corresponding to the coordinate information, and the baggage picking device of the warehouse robot is moved to a set height according to the target row of the target rack corresponding to the coordinate information.
[0068] Furthermore, the warehouse robot may include a path planning module, and after receiving the container position information, move to a target position corresponding to the container position information by auto-cruise, and move the luggage removal device to a set height.
[0069] The method may further include a step of rotating the luggage removal device to a direction directly facing the first target container after moving the luggage removal device to the set height, or rotating the luggage removal device to a direction directly facing the first target container while moving the luggage removal device to the set height.
[0070] In step S303, if the container type of the first target container is a smooth surface type, the container posture identification algorithm of the first target container is determined to be a smooth surface type posture identification algorithm.
[0071] In step S304, the posture information of the first target container is identified based on the surface smoothing type posture identification algorithm.
[0072] Specifically, the surface smoothing type posture identification algorithm may be an identification algorithm based on laser distance measurement, that is, the distance of each key point of the first target container is scanned with a laser, the distance is obtained by moving the warehouse robot left and right, and the posture information of the first target container can be identified based on the distance of each key point.
[0073] Specifically, the surface smoothing type attitude identification algorithm may be an identification algorithm based on point cloud data. That is, a laser radar collects point cloud data of the front surface of the first target container. The laser radar attached to the baggage removal device is moved to obtain the point cloud data, and key points in the point cloud data are identified, and attitude information of the first target container can be identified based on coordinate information of each key point. Furthermore, association information of each key point may be identified based on the coordinate information of each key point, and attitude information of the first target container may be identified based on the dimensional information of the first target container in the container scheduling command.
[0074] Furthermore, the contour of the first target container, for example, the contour line segments, may be identified based on the point cloud data, and the position and orientation information of the first target container relative to the warehouse robot may be specified based on the contour.
[0075] Optionally, FIG. 4 is a flowchart of step S304 in the embodiment shown in FIG. 3 of the present application. As shown in FIG. 4, step S304 includes the following steps:
[0076] In step S3041, a point cloud image of the first target container and a predetermined reference image are obtained.
[0077] The point cloud image, also referred to as point cloud data, can be collected by a radar or a depth camera. The point cloud image can be point cloud data of the entire container or a specific area of the first target container. The predetermined reference image can be an image collected or taken when the first target container is placed in storage.
[0078] In step S3042, registration is performed between the point cloud image and the predetermined reference image.
[0079] Specifically, the point cloud image is registered with the predetermined reference image based on predetermined key points, which may be vertices or the center of the first target container.
[0080] In step S3043, pose information of the first target container is determined based on the result of the registration.
[0081] Specifically, based on the result of the registration, information such as the angle and depth at which the first target container is placed can be identified.
[0082] In step S305, if the container type of the first target container is a surface irregularity type, the container posture identification algorithm of the first target container is determined to be a surface irregularity type posture identification algorithm.
[0083] In step S306, the posture information of the first target container is identified based on the surface irregularity type posture identification algorithm.
[0084] Specifically, by identifying information about the protrusions of the protruding portions, the posture information of the first target container can be identified based on information about the height, length, width, number, shape, angle, etc. of the protrusions.
[0085] Optionally, FIG. 5 is a flowchart of step S306 in the embodiment shown in FIG. 3 of the present application. As shown in FIG. 5, step S306 includes the following steps:
[0086] In step S3061, uneven portions of the surface of the first target container are identified.
[0087] Specifically, point cloud data of the first target container is collected, and the uneven parts of the first target container are identified based on the coordinate information of the point cloud data. Also, image information of the first target container at each angle may be captured, and the uneven parts of the surface of the first target container may be identified based on the image information at each angle.
[0088] In step S3062, posture information of the first target container is determined based on the physical information of the uneven portion.
[0089] The physical information includes one or more of the length, width, height, depth, angle, contour, and quantity of the irregularities.
[0090] In step S307, if the container type of the first target container is a type containing an identification pattern on the surface, the container posture identification algorithm of the first target container is determined to be a posture identification algorithm of the type with a surface mark.
[0091] In step S308, the attitude information of the first target container is identified based on the surface marked type attitude identification algorithm.
[0092] Optionally, FIG. 6 is a flowchart of step S308 in the embodiment shown in FIG. 3 of the present application. As shown in FIG. 6, step S308 includes the following steps:
[0093] In step S3081, an identification design of the first target container is identified.
[0094] Specifically, the distinguishing design of the first target container can be identified based on a deep learning algorithm, a speed up robust feature (SURF) algorithm, or other algorithms.
[0095] In step S3082, the orientation information of the first target container is determined based on the orientation of the identification design.
[0096] Specifically, the container scheduling command includes a standard identification mark of the identification design that is input in advance, and the posture of the identification design can be identified based on the standard identification mark and the identified identification design.
[0097] Furthermore, if the container scheduling command does not include container material characteristics, i.e., if it is not clear that the first target container is a paper container or a plastic container, an image of the first target container can be acquired, the color and / or pattern of the first target container can be identified based on the image of the first target container, and the container type can be determined to be a paper container or a plastic container based on the color and / or pattern.
[0098] Furthermore, when the container type of the first target container is a large container, a standard container or a small container, feature extraction or image recognition can be performed on a specified area of the image of the first target container to identify the dimensional information, position and orientation information of the first target container, i.e., the above-mentioned orientation information. The predetermined area is a set range area in the center of the image.
[0099] In step S309, a positional relationship between the baggage picking device of the warehouse robot and the first target container is identified based on the posture information.
[0100] The positional relationship is the relative position between the two, and includes the relative angle and the relative distance.
[0101] Specifically, the angle at which the first target container is currently placed and the distance from the warehouse robot can be identified based on the posture information of the first target container, and the dimensions of the first target container can also be obtained. Furthermore, the relative angle and relative distance between the baggage picking device of the warehouse robot and the first target container can be identified based on the angle at which the first target container is placed and the distance from the warehouse robot.
[0102] In step S310, the warehouse robot is moved and / or rotated based on the positional relationship.
[0103] The warehouse robot and its luggage picking device are connected via a connection part, and the luggage picking device can be moved or rotated by moving or rotating the warehouse robot.
[0104] Specifically, the warehouse robot is rotated based on the relative angle, and the warehouse robot is moved based on the relative distance.
[0105] Furthermore, a standard distance and a standard angle for the work of the warehouse robot may be obtained, the warehouse robot may be rotated based on the result of comparing the relative angle with the standard angle, and the warehouse robot may be moved based on the result of comparing the relative distance with the standard distance.
[0106] In step S311, the baggage picking device of the warehouse robot is controlled to pick up the first target container.
[0107] Specifically, a luggage pick-up command is sent to the warehouse robot, and the warehouse robot controls its luggage pick-up device to pick up the first target container.
[0108] Furthermore, the luggage removal command may limit the speed of the luggage removal device to a low speed in the first stage and a high speed in the second stage when the luggage removal device removes the luggage. The first stage is a stage before the luggage removal device contacts the first target container, and the second stage is a stage after the luggage removal device contacts the first target container. The advantage of setting in this way is that in the case of a paper container, the luggage removal device can avoid hitting the paper container at a high speed, which may cause damage to the container, thereby extending the usable life of the container.
[0109] In this embodiment, three different container posture identification algorithms are provided for three types of containers, namely, a smooth-surface type, a rough-surface type, and a type with an identification pattern on the surface. The posture information of the corresponding types of containers is automatically identified based on the algorithms, and automatic removal of different types of containers is realized based on the posture information, thereby reducing the cost of removing different types of cargo, expanding the application range of warehouse robots, and improving the automation level and efficiency of cargo removal.
[0110] 7 is a flow chart of a control method for a warehouse robot provided in another embodiment of the present application. The control method for a warehouse robot provided in this embodiment is based on the control method for a warehouse robot provided in the embodiment shown in FIG. 3, and further subdivides step S309, adds a step of identifying a rack identification mark after step S302, and adds a step of determining a removal distance after step S310. As shown in FIG. 7, the control method for a warehouse robot includes the following steps:
[0111] In step S401, a container scheduling command for a first target container is obtained, the container scheduling command including container location information of the first target container and a container type of the first target container.
[0112] In step S402, the warehouse robot is moved to a target position based on the container position information, and the baggage picking device of the warehouse robot is moved to a set height.
[0113] In step S403, the storage location identification information of the target storage location corresponding to the first target container is identified.
[0114] The storage location identification information may be a barcode or QR code of the rack, or may be a tag number, a reference number, a serial number, or the like of the target storage location.
[0115] Specifically, the identification may be performed based on an image identification algorithm, and further, the identification information of the storage location may be identified based on wireless technology, infrared technology, or the like.
[0116] Specifically, first, the storage location identification information of the target storage location corresponding to the first target container is obtained, and then the storage location identification information is identified.
[0117] In step S404, if the storage location identification information is successfully identified, a container posture identification algorithm is determined based on the container type, and posture information of the first target container is identified based on the container posture identification algorithm.
[0118] The posture information includes a distance between the first target container and the warehouse robot, and dimensional information and position / posture information of the first target container, and the container scheduling command includes standard dimensions of the first target container.
[0119] Furthermore, if the identification fails, the warehouse robot moves the baggage picking device within a set range and repeats the identification in step S403. An upper limit on the number of repetitions may be set, and if the identification is not successful even after reaching the upper limit, the warehouse robot returns to a standby state and generates a warning message indicating failure to read the storage location identification information.
[0120] Specifically, there are two types of identification failures. The first is a case where storage location identification information is not set for the target storage location, and the second is a case where storage location identification information is set for the target storage location but is invalid. If the warehouse robot was able to collect storage location identification information in step S403 but is unable to identify the information, the current identification failure is the second case, and if the storage location identification information is unable to be collected, the current identification failure is the first case.
[0121] By adding a step of identifying the identification mark on the rack, the accuracy of the parcels retrieved can be effectively guaranteed.
[0122] In step S405, it is determined whether the first target container exists based on the distance.
[0123] Specifically, the presence or absence of the first target container is determined based on the result of comparing the distance between the first target container and the warehouse robot with a predetermined distance threshold. If the distance is greater than the predetermined distance threshold, it indicates that the first target container is not placed in the target storage location, i.e., does not exist, and if the distance is smaller, it indicates that the first target container exists. The predetermined distance threshold may be set based on the depth of the storage location.
[0124] Furthermore, this step may be replaced with a step of determining whether or not a first target container is present by identifying whether or not a container is present at a specified position in a collected image of the first target container, which may be an image collected by a 2D camera or a point cloud image collected by a depth camera.
[0125] In step S406, if present, it is determined whether the first target container is valid based on the standard dimensions and the dimension information of the first target container.
[0126] Specifically, if the difference between the dimension information and the standard dimension is large, for example, greater than a predetermined error, it indicates that the first target container is invalid, i.e., the current first target container is not the container specified in the container scheduling command.
[0127] In step S407, if the posture information is valid, a positional relationship between the baggage picking device of the warehouse robot and the first target container is determined based on the posture information.
[0128] If the first target container is invalid, indicating that the first target container and the container scheduling command do not match, the warehouse robot is controlled to execute a standby mode. If the first target container is invalid, container unmatched warning information may be generated to facilitate verification of the first target container.
[0129] By making a further determination as to whether the first target container to be retrieved exists and whether it is a valid container, the accuracy of the container to be retrieved can be further ensured, and the phenomenon of an error in placement or an error in system information registration leading to an error in retrieving luggage, thereby causing an error in delivery of the luggage, can be avoided.
[0130] In step S408, the warehouse robot is moved and / or rotated based on the positional relationship.
[0131] In step S409, the pick-up distance between the warehouse robot and the first target container is obtained.
[0132] Specifically, the pick-up distance between the warehouse robot and the first target container can be obtained by a depth camera or a radar.
[0133] In step S410, it is determined whether the picking distance satisfies the picking condition of the warehouse robot.
[0134] The pick-up condition refers to a condition that must be met for the warehouse robot's baggage picking device to pick up luggage, and may be a minimum distance threshold for the pick-up distance.
[0135] By determining the pick-up distance, it is possible to effectively avoid the occurrence of a situation in which the warehouse robot's baggage picking device, for example, hits a rack when extending a fork to pick up a baggage, thereby ensuring the safety of the pick-up operation.
[0136] In step S411, if the condition is met, control the baggage picking device of the warehouse robot to pick up the first target container.
[0137] 8 is a flow chart of step S411 in the embodiment shown in FIG 7 of the present application, in which the container type of the first target container in this embodiment is a paper container. As shown in FIG 8, step S411 includes the following steps:
[0138] In step S4111, if the conditions are met, a paper container removal command is obtained.
[0139] In step S4112, the baggage picking device of the warehouse robot is controlled to pick up the first target container based on the paper container picking command.
[0140] The paper container removal command includes a first stage removal command and a second stage removal command, the first stage removal command has a lower removal speed than the second stage removal command, the first stage corresponds to a stage before the load removal device contacts the first target container, and the second stage corresponds to a stage after the load removal device contacts the first target container.
[0141] Furthermore, if the conditions are not satisfied, the warehouse robot is adjusted based on the pick-up distance and the pick-up condition so that the pick-up distance satisfies the pick-up condition of the warehouse robot. Furthermore, an upper limit value for the number of adjustments may be set, and if the pick-up distance cannot be adjusted to satisfy the pick-up condition of the warehouse robot within the upper limit value, the warehouse robot may be returned to a standby state.
[0142] In this embodiment, the target storage location is identified, and the first target container is checked to see whether it exists and is valid, thereby ensuring the accuracy of the container to be removed. In addition, the picking distance is checked to see whether it meets the picking condition before picking, which can improve the safety of the picking operation and effectively prevent the baggage picking device from hitting the rack.
[0143] Fig. 9 is a flowchart of a control method for a warehouse robot provided in another embodiment of the present application. The control method for a warehouse robot provided in this embodiment is based on the control method for a warehouse robot provided in the embodiment shown in Figs. 2 to 8, and adds a step of storing a second target container after removing a first target container, during removing the first target container, or before removing the first target container. As shown in Fig. 9, storing the second target container specifically includes the following steps:
[0144] In step S501, a container storage command for the second target container is obtained.
[0145] The container storage command includes a storage location location of a storage location corresponding to the second target container, and the second target container is on a baggage picking device of the warehouse robot.
[0146] The warehouse robot according to this embodiment may be the same as the warehouse robot in the container removal embodiment (the embodiment corresponding to Figs. 2 to 7), or may be a different warehouse robot. Specifically, the second target container may be the same as the first target container, or may be a different container.
[0147] In step S502, the warehouse robot is moved to the storage location of the second target container based on the storage location location.
[0148] In step S503, storage location identification information of the storage location is obtained.
[0149] The storage location may be the same as the target storage location in the above embodiment, or may be a different storage location in the same warehouse.
[0150] In step S504, a second positional relationship between the warehouse robot and the storage location is determined based on the storage location identification information of the storage location.
[0151] In step S505, the warehouse robot is moved and / or rotated based on the second positional relationship.
[0152] In step S506, it is determined whether a third container is present in the storage location.
[0153] In step S507, if the second target container does not exist, the second target container is stored in the storage location.
[0154] In this embodiment, a step of storing the second target container is added, specifically, the warehouse robot is moved based on the storage location position in the container storage command, the positional relationship between the storage location and the warehouse robot is specified by identifying the storage location identification information, the robot is automatically adjusted based on the positional relationship, and after the adjustment is completed, it is determined whether there is another container in the storage location, and if not, the second target container is automatically stored. This realizes automatic storage of containers by the warehouse robot, increases the automation level and efficiency of container storage, and reduces labor costs.
[0155] FIG. 10 is a structural schematic diagram of the warehouse robot control device provided in one embodiment of the present application. As shown in FIG. 10, the warehouse robot control device provided in this embodiment includes a scheduling command acquisition module 610, a container posture identification module 620, and a container removal module 630.
[0156] The scheduling command acquisition module 610 is used for acquiring a container scheduling command for a first target container. The container scheduling command includes a container type of the first target container. The container posture identification module 620 is used for determining a container posture identification algorithm based on the container type of the first target container, and identifying posture information of the first target container based on the container posture identification algorithm. The container removal module 630 is used for controlling the warehouse robot to remove the first target container based on the posture information.
[0157] Optionally, the container posture identification module 620 includes a correspondence establishment means for pre-establishing a correspondence between each container type and a container posture identification algorithm, a posture identification algorithm determination means for determining a container posture identification algorithm for the first target container based on the correspondence and the container type of the first target container, and a container posture identification means for identifying posture information of the first target container based on the container posture identification algorithm.
[0158] Optionally, the container type is classified according to surface characteristics into at least one of a smooth surface type, a rough surface type, and a type including a distinguishing pattern on the surface.
[0159] Optionally, the posture identification algorithm determination means specifically determines the container posture identification algorithm of the first target container to be a smooth surface type posture identification algorithm when the container type of the first target container is a smooth surface type, and accordingly, the container posture identification means specifically acquires a point cloud image and a predetermined reference image of the first target container, registers the point cloud image and the predetermined reference image, and identifies the posture information of the first target container based on the registration result.
[0160] Optionally, the orientation identification algorithm determining means specifically determines the container orientation identification algorithm of the first target container to be an orientation identification algorithm of the surface unevenness type when the container type of the first target container is a surface unevenness type, and accordingly, the container orientation identifying means specifically identifies the uneven parts of the surface of the first target container and determines the orientation information of the first target container based on the physical information of the uneven parts, where the physical information includes one or more of the length, width, height, depth, angle, contour, and quantity of the uneven parts.
[0161] Optionally, the posture identification algorithm determination means specifically determines the container posture identification algorithm of the first target container to a surface marked type posture identification algorithm when the container type of the first target container is a type including an identification design on its surface, and accordingly, the container posture identification means specifically identifies the identification design of the first target container and determines posture information of the first target container based on the posture of the identification design.
[0162] Optionally, the control device of the warehouse robot further includes a rack identification mark identification module that identifies storage location identification information of a target storage location corresponding to the first target container before identifying the posture information of the first target container based on the container posture identification algorithm; accordingly, the container posture identification module specifically determines a container posture identification algorithm based on the container type of the first target container when the identification of the storage location identification information is successful, and identifies the posture information of the first target container based on the container posture identification algorithm.
[0163] Optionally, the container scheduling command further includes container position information of the first target container, and the control device of the warehouse robot further includes a robot movement module for moving the warehouse robot to a target position and moving a luggage removal device of the warehouse robot to a set height based on the container position information before determining a container posture identification algorithm based on the container type of the first target container.
[0164] Optionally, the container removal module 630 includes a positional relationship determination means for determining a positional relationship between the luggage removal device of the warehouse robot and the first target container based on the posture information, a robot movement means for moving and / or rotating the warehouse robot based on the positional relationship, and a container removal means for controlling the luggage removal device of the warehouse robot to remove the first target container.
[0165] Optionally, when the container type of the first target container is a paper container, the container picking means specifically obtains the paper container picking command, and controls the luggage picking device of the warehouse robot to pick up the first target container according to the paper container picking command, the paper container picking command includes a first stage picking command and a second stage picking command, the picking speed of the first stage picking command is lower than the picking speed of the second stage picking command, the first stage corresponds to a stage before the luggage picking device contacts the first target container, and the second stage corresponds to a stage after the luggage picking device contacts the first target container.
[0166] Optionally, the posture information includes a distance between the first target container and the warehouse robot, and dimensional information and position / posture information of the first target container, and the container scheduling command further includes standard dimensions of the first target container, and the positional relationship identification means specifically determines whether the first target container exists based on the distance, and if exists, determines whether the first target container is valid based on the standard dimensions and the dimensional information of the first target container, and if valid, identifies the positional relationship between the luggage removal device of the warehouse robot and the first target container based on the posture information.
[0167] Optionally, the control device of the warehouse robot further includes a distance determination module for obtaining a pick-up distance between the warehouse robot and the first target container after moving and / or rotating the warehouse robot based on the positional relationship, and determining whether the pick-up distance meets the pick-up condition of the warehouse robot, and accordingly, the container pick-up means specifically controls the luggage pick-up device of the warehouse robot to pick up the first target container if the pick-up distance meets the pick-up condition of the warehouse robot.
[0168] Optionally, the control device of the warehouse robot further includes a storage control module, which is used to obtain a container storage command for a second target container on an item picking device of the warehouse robot, the container storage command including a storage location position of a storage location corresponding to the second target container, move the warehouse robot to the storage location of the second target container based on the storage location position, obtain storage location identification information of the storage location, identify a second positional relationship between the warehouse robot and the storage location based on the storage location identification information of the storage location, move and / or rotate the warehouse robot based on the second positional relationship, determine whether a third container exists in the storage location, and if not, store the second target container in the storage location.
[0169] FIG. 11 is a structural schematic diagram of a warehouse robot provided in an embodiment of the present application. As shown in FIG. 11, the warehouse robot includes a memory 710, a processor 720, and a computer program.
[0170] The computer program is stored in the memory 710 and is configured to be executed by the processor 720 to realize the warehouse robot control method provided in any one of the embodiments corresponding to Figures 2 to 9 of the present application.
[0171] The memory 710 and the processor 720 are connected via a bus 730 .
[0172] Descriptions that can be understood by referring to the related descriptions and effects corresponding to the steps in FIGS. 2 to 9 will be omitted here.
[0173] FIG. 12 is a structural schematic diagram of a warehouse system provided in an embodiment of the present application. As shown in FIG. 12 , the warehouse system includes a warehouse robot 810, a rack 820, and a warehouse management module 830.
[0174] The target container 821 is placed on the rack 820 or needs to be placed on the rack 820, the warehouse robot 810 is the warehouse robot provided in the embodiment corresponding to FIG. 11 of the present application, the warehouse robot 810 is connected to the warehouse management module 830, receives a command from the warehouse management module including information of the target container that needs to be picked up or stored, and moves to a set position based on the command from the warehouse management module 830 to pick up and / or store the target container.
[0175] A computer-readable storage medium provided in one embodiment of the present application stores a computer program, and when the computer program is executed by a processor, it realizes a warehouse robot control method provided in any one of the embodiments corresponding to Figures 2 to 9 of the present application.
[0176] The computer readable storage medium may be a ROM, a random access memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, and so on.
[0177] It is understood that the disclosed apparatus and method may be realized in other ways in some embodiments provided in the present application. For example, the above-described apparatus embodiments are merely exemplary, and the division of modules is merely a division according to a kind of logical function, and other division methods may be used in actual implementation. For example, multiple modules or units may be combined or integrated into another system, or some features may be omitted or not implemented. In addition, the couplings, direct couplings, or communication connections shown or discussed between each other may be indirect couplings or communication connections via interfaces, devices, or modules, or may be electrical, mechanical, or other forms.
[0178] Those skilled in the art will be able to readily devise other embodiments of the present application from consideration of the specification and practice of the present application. Any modifications, uses, and variations of the present application that conform to the general principles disclosed herein and that incorporate common knowledge or customary technical means in the art that are not applied for in the present application are within the scope of the present application. It is intended that the specification and examples be considered as merely exemplary, with the true and original scope and spirit of the present application being indicated by the following claims.
[0179] It is to be understood that the present application is not limited to the exact structure described above and shown in the drawings, and various modifications and variations can be made without departing from the scope of the present application, which is limited only by the appended claims.
Claims
1. obtaining container scheduling instructions for a first target container, the scheduling instructions including a container type of the first target container; determining a container attitude identification algorithm based on the container type of the first target container, and identifying attitude information of the first target container based on the container attitude identification algorithm; and controlling a warehouse robot to retrieve the first target container based on the posture information. A method for controlling a warehouse robot, comprising: The step of controlling the warehouse robot to pick up a first target container based on the posture information includes: determining a positional relationship between a baggage picking device of the warehouse robot and the first target container based on the posture information; moving and / or rotating the warehouse robot based on the positional relationship; and controlling a load picking device of the warehouse robot to pick up the first target container; The method for controlling a warehouse robot comprises: After moving and / or rotating the warehouse robot based on the positional relationship, obtaining a pick-up distance between the warehouse robot and the first target container; determining whether the picking distance satisfies a picking condition of the warehouse robot; If so, controlling a load picking device of the warehouse robot to pick up the first target container. How to control warehouse robots.
2. The step of determining a container attitude identification algorithm based on the container type of the first target container, A step of establishing a correspondence between each container type and a container posture identification algorithm in advance; determining a container posture identification algorithm for the first target container based on the correspondence and a container type of the first target container. The method for controlling a warehouse robot according to claim 1 .
3. The container type is classified according to surface characteristics into at least one of a smooth surface type container, a rough surface type container, and a type container having an identification pattern on the surface; or The container types are classified according to dimensional characteristics into at least one of large containers, standard containers, and small containers; or The container type is classified into at least one of a paper container and a plastic container according to material characteristics; A method for controlling a warehouse robot according to claim 1 or 2.
4. determining a container attitude identification algorithm based on the container type, If the container type of the first target container is a smooth surface type, determining a container posture identification algorithm of the first target container to be a smooth surface type posture identification algorithm; Accordingly, identifying the orientation information of the first target container based on the surface smoothing type orientation identification algorithm includes: acquiring a point cloud image of the first target container and a predetermined reference image; performing registration between the point cloud image and the predetermined reference image; determining pose information of the first target container based on a result of the registration. The method for controlling a warehouse robot according to claim 3.
5. determining a container attitude identification algorithm based on the container type; and identifying attitude information of the first target container based on the container attitude identification algorithm, If the container type of the first target container is a surface irregularity type, determining a container posture identification algorithm of the first target container to be a surface irregularity type posture identification algorithm; Accordingly, identifying the posture information of the first target container based on the surface irregularity type posture identification algorithm includes: identifying irregularities on a surface of the first target container; determining attitude information of the first target container based on physical information of the uneven portion; The physical information includes one or more of a length, a width, a height, a depth, an angle, a contour, and a quantity of the irregularities; The method for controlling a warehouse robot according to claim 3.
6. determining a container attitude identification algorithm based on the container type; and identifying attitude information of the first target container based on the container attitude identification algorithm, If the container type of the first target container is a type having an identification pattern on a surface, a container posture identification algorithm of the first target container is determined to be a posture identification algorithm of a type having a surface mark; Accordingly, the step of identifying the attitude information of the first target container based on the surface marked type attitude identification algorithm includes: identifying an identification design of the first target container; and determining attitude information of the first target container based on the attitude of the identification design. The method for controlling a warehouse robot according to claim 3.
7. After obtaining a container scheduling command for the first target container, acquiring an image of a first target container; identifying a color and / or pattern of the first target container based on the image of the first target container; and identifying a container type of the first target container as a paper container or a plastic container based on a color and / or pattern of the first target container. A method for controlling a warehouse robot according to any one of claims 3 to 6.
8. prior to identifying the attitude information of the first target container based on the container attitude identification algorithm, identifying a location identification for a target location corresponding to the first target container; Accordingly, the step of identifying the attitude information of the first target container based on the container attitude identification algorithm further comprises: if the identification of the storage location identification information is successful, identifying the attitude information of the first target container based on the container attitude identification algorithm; A method for controlling a warehouse robot according to any one of claims 1 to 7.
9. the container scheduling command further includes container location information for the first target container; prior to determining a container pose identification algorithm based on the container type of the first target container; a step of moving the warehouse robot to a target position and moving a baggage picking device of the warehouse robot to a set height based on the container position information; A method for controlling a warehouse robot according to any one of claims 1 to 8.
10. The method includes a step of rotating the luggage picking device of the warehouse robot to a direction directly facing the first target container after moving the luggage picking device of the warehouse robot to a set height, or rotating the luggage picking device to a direction directly facing the first target container while moving the luggage picking device of the warehouse robot to a set height. The method for controlling a warehouse robot according to claim 9.
11. When the container type of the first target container is a paper container, the step of controlling a baggage picking device of the warehouse robot to pick up the first target container includes: obtaining a paper container removal command; and controlling a baggage picking device of the warehouse robot to pick up the first target container based on the paper container picking command; The paper container removal command includes a first stage removal command and a second stage removal command, the removal speed of the first stage removal command is lower than the removal speed of the second stage removal command, the first stage corresponds to a stage before the load removal device contacts the first target container, and the second stage corresponds to a stage after the load removal device contacts the first target container. The method for controlling a warehouse robot according to claim 1 .
12. the posture information includes a distance between the first target container and the warehouse robot, and dimensional information and position / posture information of the first target container; the container scheduling directive further includes standard dimensions of the first target container; The step of determining a positional relationship between the luggage picking device of the warehouse robot and the first target container based on the posture information includes: determining whether the first target container is present based on the distance; if so, determining whether the first target container is valid based on the standard dimensions and the dimensional information of the first target container; If the posture information is valid, determining a positional relationship between the baggage picking device of the warehouse robot and the first target container based on the posture information. The method for controlling a warehouse robot according to claim 1 .
13. obtaining a container storage command for a second target container on a load picking device of the warehouse robot, the container storage command including a storage location location of a storage location corresponding to the second target container; moving the warehouse robot to a storage location of the second target container based on the storage location location; obtaining storage location identification information for the storage location; determining a second positional relationship between the warehouse robot and the storage location based on storage location identification information of the storage location; moving and / or rotating the warehouse robot based on the second positional relationship; determining whether a third container is present at the storage location; if not, storing a second target container in the storage location. A method for controlling a warehouse robot according to any one of claims 1 to 12.
14. a scheduling command acquisition module for acquiring container scheduling commands for the first target container, the scheduling command including a container type of the first target container; a container posture identification module for determining a container posture identification algorithm based on the container type of the first target container, and identifying posture information of the first target container based on the container posture identification algorithm; and a container retrieval module for controlling a warehouse robot to retrieve the first target container based on the pose information. A control device for a warehouse robot, Controlling the warehouse robot to pick up a first target container based on the posture information includes: Identifying a positional relationship between a baggage picking device of the warehouse robot and the first target container based on the posture information; moving and / or rotating the warehouse robot based on the positional relationship; and controlling a load picking device of the warehouse robot to pick up the first target container; The warehouse robot control device includes: After moving and / or rotating the warehouse robot based on the positional relationship, a distance determination module for obtaining a pick-up distance between the warehouse robot and the first target container and determining whether the pick-up distance satisfies a pick-up condition of the warehouse robot; and a container removal means for controlling a load removal device of the warehouse robot to remove the first target container if the load removal device is satisfied. Warehouse robot control device.
15. A memory and at least one processor, The memory stores computer executable instructions, The at least one processor executes the computer-executable instructions stored in the memory, whereby the at least one processor executes the warehouse robot control method according to any one of claims 1 to 13. Warehouse robot.
16. A warehouse robot comprising: a rack; and a warehouse management module, The warehouse robot is connected to the warehouse management module, and moves to a position where a target container is located according to a command from the warehouse management module, and picks up and / or stores the target container placed on the rack. Warehouse system.
17. A computer-executable instruction is stored which, when executed by a processor, is used to implement the warehouse robot control method according to any one of claims 1 to 13. A computer-readable storage medium.
18. A computer program for implementing the warehouse robot control method according to any one of claims 1 to 13 when executed by a processor. Computer program products.
Citation Information
Patent Citations
JPP7015031B
