Picking control method, picking control device, and automatic picking system

Abstract

The application discloses a picking control method, a picking control device and an automatic picking system, and relates to the technical field of logistics and warehousing. A specific embodiment of the picking control method comprises the following steps: based on a received picking task, determining a storage box corresponding to target materials in the picking task and a target picking path; according to the target picking path, controlling a mobile chassis to move to a rack where the storage box is located, and controlling a lifting module and a mechanical arm to move cooperatively, so that an end effector arranged at the end of the mechanical arm extends into the interior of the storage box to grasp the target materials, and a grasping result is obtained; performing image detection processing on the grasping result, and determining a picking result corresponding to the picking task based on the image detection result; the embodiment can complete high-precision picking work without manual intervention, reduces the cost of manual picking, and improves picking efficiency and picking accuracy.

Description

Technical Field

[0001] This invention relates to the field of logistics and warehousing technology, and in particular to picking control methods, picking control devices, and automatic picking systems. Background Technology

[0002] With the rapid growth in order volume in industries such as e-commerce and retail, warehouse picking operations are characterized by numerous batches, diverse product types, and fragmented orders. The existing picking method is mainly manual picking, in which operators push picking carts through warehouse aisles, search for corresponding materials on shelves according to the picking list, and pick them one by one. This method is characterized by high labor costs, low picking efficiency, and a high risk of errors. Summary of the Invention

[0003] In view of this, embodiments of the present invention provide a picking control method, a picking control device, and an automatic picking system. By converting the received picking task into a target picking path and combining the coordinated control of a mobile chassis, a lifting module, and a robotic arm, the system achieves automatic lateral gripping of target materials in storage boxes located on both sides of the shelf aisle. At the same time, an image recognition-based gripping result detection mechanism is introduced to verify the gripping process in real time, thereby completing high-precision picking operations without human intervention, reducing manual picking costs, and improving picking efficiency and accuracy.

[0004] To achieve the above objectives, according to one aspect of the present invention, a picking control method is provided, comprising: Based on the received picking task, determine the storage box corresponding to the target material in the picking task and the target picking path; According to the target picking path, the mobile chassis moves to the shelf where the storage box is located, and the lifting module and the robotic arm move together so that the end effector set at the end of the robotic arm can extend into the inside of the storage box to grab the target material and obtain the grab result. The captured results are processed for image detection, and the picking results corresponding to the picking task are determined based on the image detection results.

[0005] Optionally, based on the received picking task, the storage box corresponding to the target material in the picking task and the target picking path are determined, including: Based on the analysis results of the picking task, determine the order material information and storage location information; Based on the order material information and storage location address information, determine the target material corresponding to the picking task and the storage box corresponding to the target material; Based on the storage location address information, path planning is performed to generate the target picking path corresponding to the storage location box.

[0006] Optionally, controlling the coordinated movement of the lifting module and the robotic arm includes: Control the lifting module to move along the height direction, so as to move the robotic arm base installed on the lifting module to the target height corresponding to the storage box; The storage box is identified using a first vision recognition camera mounted on the robotic arm base; In response to a successful identification process, the robotic arm is controlled to extend and rotate so that the end effector faces the storage box.

[0007] Optionally, the end effector located at the end of the robotic arm extends into the interior of the storage box to grasp the target material, and the grasping result includes: The control robot arm drives the end effector to move horizontally toward the storage box, so that the end effector extends into the interior of the storage box from the aisle side of the shelf; The end effector is controlled to perform adsorption, clamping, or a combination of adsorption and clamping operations on the target material to obtain a grasping result.

[0008] Optionally, image detection processing is performed on the grasping results, and the picking result corresponding to the picking task is determined based on the image detection results, including: Turn on the second light source mounted on the robotic arm, and use the second vision recognition camera mounted on the robotic arm to acquire images of the target area corresponding to the end effector; Based on the target area image corresponding to the end effector, determine whether the end effector has grasped the target material; In response to the end effector grabbing the target material and meeting the preset grabbing posture conditions, the picking result is determined to be a successful picking; If the end effector fails to grasp the target material or does not meet the preset grasping posture conditions, the picking result is determined to be a picking failure.

[0009] Optionally, after determining that the picking result is successful, the following steps are also included: The robotic arm is controlled to move the target material to the hopper mounted on the mobile chassis, and the end effector is controlled to release the target material. Turn on the second light source and control the second vision recognition camera to acquire images of the target area corresponding to the material box; The target area image corresponding to the material bin is compared with the preset area image, and the comparison result is used to determine whether the target material has entered the material bin. In response to the target material entering the bin, record the picking quantity corresponding to the target material and confirm that the target material has been successfully discharged; In response to the failure of the target material to enter the hopper, it is determined that the material feeding has failed, and a feeding failure prompt message is generated.

[0010] Optionally, the method further includes: In response to a picking failure or a failure to release the target material, the system acquires a real-time video stream captured by the first vision recognition camera and / or the second vision recognition camera. Send real-time video streams to a pre-configured remote control terminal and receive control commands sent by remote operators based on the remote control terminal; According to the control instructions, the robotic arm and end effector are controlled to re-perform the gripping or unloading process of the target material.

[0011] Optionally, the method further includes: In response to the fact that all target materials corresponding to the picking task have been successfully placed into the bin, the mobile chassis is moved to the packing station set up in the warehouse. The robotic arm is controlled to transfer the target material in the bin to the packaging table for packaging.

[0012] According to a second aspect of the present invention, a picking control device is provided, comprising: The determination module is used to determine the storage box corresponding to the target material in the picking task and the target picking path based on the received picking task; The gripping module is used to control the mobile chassis to move to the shelf where the storage box is located according to the target picking path, and to control the lifting module and the robotic arm to move in coordination so that the end effector set at the end of the robotic arm can extend into the interior of the storage box to grip the target material and obtain the gripping result. The detection module is used to perform image detection processing on the grasping results and determine the picking result corresponding to the picking task based on the image detection results.

[0013] According to a third aspect of the present invention, an automatic picking system is provided, comprising: an automatic picking mechanism and a picking control device; The shelves located on both sides of the warehouse aisle are equipped with multiple partitions inside, and each partition has multiple storage boxes for storing the target materials. The automatic picking mechanism includes a mobile chassis, a lifting module on the top of the mobile chassis, a robotic arm mounted on the lifting module, and an end effector fixedly mounted at the end of the robotic arm away from the lifting module. Based on the received picking task, the picking control device determines the storage box corresponding to the target material in the picking task and the target picking path; according to the target picking path, it controls the mobile chassis to move to the shelf where the storage box is located, and controls the lifting module and the robotic arm to move in coordination, so that the end effector set at the end of the robotic arm extends into the interior of the storage box to grab the target material and obtain the grabbing result; the grabbing result is processed by image detection, and the picking result corresponding to the picking task is determined based on the image detection result.

[0014] Optionally, the automated picking mechanism also includes a bin, which is fixedly or detachably mounted on a mobile chassis, and an end effector can release the picked material into the bin.

[0015] Optionally, the upper surface of the mobile chassis is provided with an installation platform, and the lifting module is vertically fixed to the installation platform; and / or, the robotic arm includes a robotic arm base, and the robotic arm base is mounted on the lifting module.

[0016] Optionally, the lifting module includes a lifting column and a slider that slides with the lifting column, with a robotic arm mounted on the slider.

[0017] Optionally, the automated picking system also includes a packing station located in the warehouse, which is used to receive boxes transported by a mobile chassis; The packaging station includes: a station frame, a support platform installed on the top of the station frame, a barcode scanning and identification device installed above the support platform for identifying the material box, and a weighing device installed inside or below the support platform for weighing the material box.

[0018] According to a fourth aspect of the present invention, an electronic device is provided, comprising: One or more processors; Memory, used to store one or more programs. When one or more programs are executed by one or more processors, the one or more processors implement the methods of any of the above embodiments.

[0019] According to a fifth aspect of the present invention, a computer-readable medium is provided having a computer program stored thereon, which, when executed by a processor, implements the method of any of the above embodiments.

[0020] According to a sixth aspect of the present invention, a computer program product is provided, including a computer program that, when executed by a processor, implements the method of any of the above embodiments.

[0021] One embodiment of the above invention has the following advantages or beneficial effects: Based on the received picking task, the storage box corresponding to the target material in the picking task and the target picking path are determined; according to the target picking path, the mobile chassis is controlled to move to the shelf where the storage box is located, and the lifting module and the robotic arm are controlled to move in coordination so that the end effector set at the end of the robotic arm extends into the interior of the storage box to grab the target material and obtain the grabbing result; the grabbing result is processed by image detection, and the picking result corresponding to the picking task is determined based on the image detection result; this embodiment converts the received picking task into a target picking path, and combines the coordinated control of the mobile chassis, the lifting module and the robotic arm to realize the automatic lateral grabbing of the target material in the storage box located on both sides of the shelf aisle. At the same time, an image recognition-based grabbing result detection mechanism is introduced to verify the grabbing process in real time, thereby completing high-precision picking operations without human intervention, reducing the cost of manual picking, and improving picking efficiency and picking accuracy. An automated picking system includes: an automated picking mechanism and a picking control device; multiple partitions are installed inside the shelves on both sides of the warehouse aisle, and each partition has multiple storage boxes for storing materials; the automated picking mechanism includes a mobile chassis, a lifting module is installed on the top of the mobile chassis, a robotic arm is installed on the lifting module, and an end effector is fixedly installed at the end of the robotic arm away from the lifting module; the picking control device determines the storage box corresponding to the target material in the picking task and the target picking path based on the received picking task; according to the target picking path, it controls the mobile chassis to move to the shelf where the storage box is located, and controls the lifting module and the robotic arm to move in coordination so that the end effector at the end of the robotic arm extends into the interior of the storage box to grab the target material, and obtain the grab result; the grab result is processed by image detection, and the picking result corresponding to the picking task is determined based on the image detection result. In this embodiment, multiple storage boxes for storing materials are installed on the shelves on both sides of the warehouse aisle. The mobile chassis of the automatic picking mechanism can move autonomously in the aisle and, with the cooperation of the lifting module, enable the robotic arm and end effector to reach the corresponding storage box, thereby realizing automatic lateral picking of materials and improving picking efficiency.

[0022] The further effects of the aforementioned unconventional alternative methods will be explained below in conjunction with specific implementation methods. Attached Figure Description

[0023] The accompanying drawings are provided to better understand the invention and are not intended to unduly limit the scope of the invention. Wherein: Figure 1 This is a schematic diagram of the main flow of the picking control method according to an embodiment of the present invention; Figure 2 This is one of the structural schematic diagrams of an automated picking system according to an embodiment of the present invention; Figure 3This is a second schematic diagram of the structure of an automatic picking system according to an embodiment of the present invention; Figure 4 This is one of the structural schematic diagrams of an automatic picking mechanism according to an embodiment of the present invention; Figure 5 This is a second schematic diagram of the structure of the automatic picking mechanism according to an embodiment of the present invention; Figure 6 This is a schematic diagram of the structure of a robotic arm according to an embodiment of the present invention; Figure 7 This is a schematic diagram of the packing station according to an embodiment of the present invention; Figure 8 This is a schematic diagram of the main modules of the picking control device according to an embodiment of the present invention; Figure 9 This is an exemplary system architecture diagram in which embodiments of the present invention can be applied; Figure 10 This is a schematic diagram of the structure of a computer system suitable for implementing terminal devices or servers of the present invention.

[0024] Reference numerals: 100-Shelf; 110-Divider; 120-Storage box; 200-Automatic picking mechanism; 210-Mobile chassis; 211-Mounting platform; 220-Lifting module; 221-Lifting column; 230-Robotic arm; 240-End effector; 250-Bin; 260-Packing table; 800-Picking control device; 801-Determination module; 802-Grabbing module; 803-Detection module. Detailed Implementation

[0025] The following description, in conjunction with the accompanying drawings, illustrates exemplary embodiments of the present invention, including various details to aid understanding. These details should be considered merely exemplary. Therefore, those skilled in the art will recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of the invention. Similarly, for clarity and brevity, descriptions of well-known functions and structures are omitted in the following description.

[0026] Furthermore, it should be noted that, in the description of this invention, unless otherwise explicitly specified and limited, the terms "installation," "connection," and "linking" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; and they can refer to the internal connection of two components. Those skilled in the art can understand the specific meaning of the above terms in this invention according to the specific circumstances.

[0027] It should be noted that the acquisition, storage, and application of personal information involved in the embodiments of the present invention comply with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0028] With the rapid growth in order volume in industries such as e-commerce and retail, warehouse picking operations are characterized by numerous batches, diverse product types, and fragmented orders. The existing picking method is mainly manual picking, in which operators push picking carts through warehouse aisles, search for corresponding materials on shelves according to the picking list, and pick them one by one. This method is characterized by high labor costs, low picking efficiency, and a high risk of errors.

[0029] In view of this, according to one aspect of the present invention, a picking control method is provided.

[0030] Figure 1 This is a schematic diagram of the main flow of the picking control method according to an embodiment of the present invention. Figure 1 As shown, a picking control method includes the following steps S101 to S103.

[0031] Step S101: Based on the received picking task, determine the storage box 120 corresponding to the target material in the picking task and the target picking path.

[0032] In this embodiment, the picking task can be a set of task data generated by the warehouse management system (WMS) based on customer orders, used to instruct the automated picking mechanism 200 to complete the outbound operation of specified materials. The picking task includes at least order identifier, target material information, storage location address information (such as shelf number, layer number, and storage location number), and packing station location information. The target material refers to the specific inventory unit item that needs to be picked from the warehouse and transferred to the material box 250, usually uniquely identified in the form of SKU. The storage box 120 is a standardized storage unit set on the partitions 110 of each shelf 100, used to store the corresponding target material. The target picking path refers to the optimal or suboptimal travel path planned by the mobile chassis 210 as it moves sequentially from its current position to each target storage box 120 within the warehouse aisle.

[0033] Specifically, when determining the target storage box 120 based on the received picking task, the code of the target material in the picking task is parsed, and the shelf 100 position, layer information, and spatial coordinate information of the corresponding storage box 120 are directly obtained through the WMS storage location mapping relationship, thereby determining the storage box 120 corresponding to each target material. Further, based on the spatial coordinates of each storage box 120 and the current position information of the mobile chassis 210, a path planning algorithm is used to optimize the order of each storage box 120, generating an access sequence path covering all storage boxes 120 corresponding to the target materials. In another implementation, a reinforcement learning or heuristic sorting strategy can also be used to dynamically rearrange the storage boxes 120 according to the distance matrix and access cost between them to generate a target picking path, thereby reducing the movement distance and improving picking efficiency.

[0034] In step S102, the mobile chassis 210 is moved to the shelf 100 where the storage box 120 is located according to the target picking path, and the lifting module 220 and the robotic arm 230 are controlled to move in coordination so that the end effector 240 set at the end of the robotic arm 230 extends into the interior of the storage box 120 to grab the target material and obtain the grabbing result.

[0035] In this embodiment, the grasping result refers to the actual interaction state between the end effector 240 and the target material after the control of the mobile chassis 210, lifting module 220, and robotic arm 230 to coordinately perform the grasping action. This state characterizes whether the target material has been successfully separated from the storage box 120 and stably clamped or adsorbed onto the end effector 240. The grasping result can be expressed as different states such as the target material being completely clamped, partially clamped, or unsuccessfully clamped, and serves as the basis for subsequent successful picking judgments.

[0036] In one embodiment, the mobile chassis 210 can be controlled to move along the target picking path to the shelf 100 aisle position corresponding to the storage box 120, and the current position can be calibrated by the positioning sensor. After calibration, the lifting module 220 is controlled to drive the robotic arm 230 to rise or fall as a whole according to the level height corresponding to the storage box 120, so that the end effector 240 on the robotic arm 230 is vertically aligned with the storage box 120. Then, the robotic arm 230 is further controlled to adjust its posture and extend in the horizontal plane, so that the end effector 240 extends from the side of the shelf aisle into the storage box 120 to perform adsorption or clamping actions, thereby forming a grasping result.

[0037] In another implementation, after the mobile chassis 210 approaches the shelf 100, it first performs a secondary fine positioning of the storage box 120 based on the first vision recognition camera. Then, the lifting module 220 and the robotic arm 230 perform decoupled step-by-step control. That is, the lifting module 220 first completes the coarse positioning of the height, and then the robotic arm 230 completes the fine-tuning extension action through end trajectory planning. This reduces error accumulation and improves grasping stability, thereby obtaining a more reliable grasping result.

[0038] Step S103: Perform image detection processing on the grabbing result, and determine the picking result corresponding to the picking task based on the image detection result.

[0039] The image detection results specifically include information such as whether the target material exists within the gripping area of ​​the end effector 240, the integrity of the target material's outline, the degree of pose matching, and the gripping stability score, which are used to characterize whether the gripping is successful and its reliability. The picking result is a comprehensive judgment output of the picking task execution status, including at least picking success or picking failure, and can be further subdivided into states such as partial success, need for retry, or need for remote operation intervention.

[0040] Specifically, after the controller completes the grasping action, it controls the second light source to light up, and the second vision recognition camera captures images of the end effector 240 and the target material. The target material in the image is identified and the bounding box is extracted by a pre-trained target detection model. The image is then fused and judged by combining the gripper opening and closing state or adsorption pressure data to generate an image detection result. Based on the presence of the target material and the pose threshold in the image detection result, the picking result is determined to be either successful or unsuccessful.

[0041] In another implementation, the image before and after grabbing is compared differentially, and background modeling analysis is performed in combination with the change characteristics of the internal area of ​​the storage box 120. At the same time, multiple consecutive images are introduced to judge the temporal stability, so as to reduce the risk of misjudgment in a single frame. When the target material is detected to disappear from the storage box 120 area and there is a stable target matching in the end effector 240 area, the image detection result is determined to be valid, and the picking result corresponding to the picking task is further determined to be successful. Otherwise, it is determined to be a picking failure or trigger an abnormal handling process.

[0042] This embodiment determines the storage box 120 corresponding to the target material in the picking task and the target picking path based on the received picking task. According to the target picking path, the mobile chassis 210 is controlled to move to the shelf 100 where the storage box 120 is located, and the lifting module 220 and the robotic arm 230 are controlled to move collaboratively so that the end effector 240 at the end of the robotic arm 230 extends into the storage box 120 to grasp the target material, obtaining a grasping result. Image detection processing is performed on the grasping result, and the picking result corresponding to the picking task is determined based on the image detection result. This embodiment converts the received picking task into a target picking path and, combined with the collaborative control of the mobile chassis 210, lifting module 220, and robotic arm 230, achieves automatic lateral grasping of the target material in the storage boxes 120 located on both sides of the aisle of the shelf 100. Simultaneously, an image recognition-based grasping result detection mechanism is introduced to verify the grasping process in real time, thereby completing high-precision picking operations without human intervention, reducing manual picking costs, and improving picking efficiency and accuracy.

[0043] Optionally, based on the received picking task, the storage box 120 corresponding to the target material in the picking task and the target picking path are determined, including: determining the order material information and storage location address information based on the parsing result of the picking task; determining the target material corresponding to the picking task and the storage box 120 corresponding to the target material based on the order material information and storage location address information; and performing path planning processing based on the storage location address information to generate the target picking path corresponding to the storage box 120.

[0044] In this embodiment, the picking task is first processed through structured parsing to extract order identifiers, target material information, and corresponding storage location address information. The target material information represents the type and quantity of the target material to be picked, while the storage location address information represents the spatial location mapping of the target material within the shelf 100. Based on the target material information and storage location address information, an association matching process is performed to bind each target material to its corresponding storage box 120, thereby determining the storage box 120 corresponding to each target material in the picking task. On this basis, path planning is performed based on the storage location address information. Preferably, a graph search algorithm or a heuristic cost function model is used to optimize the spatial distribution of each storage box 120, and the access order is generated by combining the current pose of the mobile chassis 210, thus obtaining the target picking path. In another embodiment, dynamic path optimization can also be performed based on historical picking data. A machine learning model can be used to predict the access cost of different storage locations to generate a better target picking path. By using the above processing methods, the accuracy of target material positioning can be improved and the movement path can be minimized, thereby improving picking efficiency and reducing the ineffective travel distance of the mobile chassis 210.

[0045] Optionally, controlling the lifting module 220 and the robotic arm 230 to move in coordination includes: controlling the lifting module 220 to move along the height direction to move the robotic arm base mounted on the lifting module 220 to the target height corresponding to the storage box 120; using a first vision recognition camera mounted on the robotic arm base to recognize the storage box 120; and in response to a successful recognition result, controlling the robotic arm 230 to extend and rotate so that the end effector 240 faces the storage box 120.

[0046] In this embodiment, when controlling the lifting module 220 and the robotic arm 230 to move in coordination, firstly, the lifting module 220 is driven to adjust its position vertically according to the layer height information of the storage box 120 in the shelf 100, so that the robotic arm base mounted on the lifting module 220 moves to the target height position corresponding to the storage box 120, thereby completing the coarse positioning in the height dimension. Then, the first vision recognition camera mounted on the robotic arm base is used to acquire and recognize images of the storage box 120, and the position deviation of the storage box 120 is corrected and judged by the target detection algorithm, and the recognition processing result is output. In response to the recognition processing result being successful, the robotic arm 230 is controlled to perform posture adjustment and joint extension movements in the horizontal plane, so that the end effector 240 faces the target storage box 120 and completes spatial alignment. Through the above-mentioned hierarchical control method, the coordination of coarse height adjustment and fine vision positioning is achieved, which improves the alignment accuracy and grasping success rate of the end effector 240 to the storage box 120, while reducing the accumulation of end trajectory error of the robotic arm 230 and improving the overall picking stability.

[0047] Optionally, to allow the end effector 240 located at the end of the robotic arm 230 to extend into the storage box 120 to grasp the target material and obtain a grasping result, the following steps are taken: controlling the robotic arm 230 to move the end effector 240 horizontally toward the storage box 120 so that the end effector 240 extends into the storage box 120 from the aisle side of the shelf 100; controlling the end effector 240 to perform an adsorption operation, a clamping operation, or a combination of adsorption and clamping operation on the target material to obtain a grasping result.

[0048] In this embodiment, the control robot arm 230, based on the spatial position information of the storage box 120, drives the end effector 240 to perform a horizontal trajectory planning movement, causing the end effector 240 to gradually approach and align with the opening area of ​​the storage box 120 from the aisle side of the shelf 100. After horizontal alignment is completed, the control robot arm 230 continues to perform fine-tuning insertion actions, allowing the end effector 240 to stably enter the target grasping area inside the storage box 120. Further, based on the morphological characteristics of the target material and the grasping strategy, the control robot arm 230 performs adsorption operations, clamping operations, or a combination of adsorption and clamping operations to achieve stable acquisition of the target material, thereby forming a grasping result. In another embodiment, the grasping contact force can also be controlled in a closed loop using force sensor feedback to dynamically adjust the adsorption pressure or clamping force of the end effector 240, thereby improving the adaptability and grasping success rate of target materials of different specifications and reducing the risk of falling or damage.

[0049] Optionally, image detection processing is performed on the grasping result, and the picking result corresponding to the picking task is determined based on the image detection result, including: turning on the second light source installed on the robotic arm 230, and using the second vision recognition camera installed on the robotic arm 230 to acquire the target area image corresponding to the end effector 240; based on the target area image corresponding to the end effector 240, determining whether the end effector 240 has grasped the target material; in response to the end effector 240 grasping the target material and meeting the preset grasping posture conditions, determining the picking result as successful; in response to the end effector 240 not grasping the target material or not meeting the preset grasping posture conditions, determining the picking result as failed.

[0050] In this embodiment, a second light source mounted on the robotic arm 230 is activated to provide a stable lighting environment for the target area where the end effector 240 is located. A second vision recognition camera mounted on the robotic arm 230 is used to acquire images containing the end effector 240 and its target area; the target area can be understood as the end effector 240 and the area in front of it. Image preprocessing and target recognition analysis are performed on the target area images. Specifically, the end effector 240 area can be located, features of the target material can be extracted, and the material contour can be detected, etc., to determine whether the end effector 240 has stably gripped or adsorbed the target material. When the detection result indicates that the end effector 240 has successfully grasped the target material and meets the preset grasping posture conditions, the picking result is determined to be successful; when the detection result indicates that the target material was not grasped or the preset grasping posture conditions are not met, the picking result is determined to be unsuccessful. The preset grasping posture conditions refer to the spatial posture of the end effector 240 after grasping meeting pre-set constraints, including the positional stability of the end effector 240, the gripping angle or adsorption contact angle, the relative positional deviation with the target material, and the offset amplitude of the material after grasping not exceeding a threshold, thereby ensuring that the target material has been reliably attached to the end effector 240. Through this method, automated visual verification of the grasping status can be achieved, improving picking accuracy and operational reliability.

[0051] Optionally, after determining that the picking result is successful, the process further includes: controlling the robotic arm 230 to move the target material to the hopper 250 set on the mobile chassis 210, and controlling the end effector 240 to release the target material; turning on the second light source and controlling the second vision recognition camera to capture the target area image corresponding to the hopper 250; comparing the target area image corresponding to the hopper 250 with the preset area image, and determining whether the target material has entered the hopper 250 based on the comparison result; in response to the target material entering the hopper 250, recording the picking quantity corresponding to the target material, and determining that the target material has been successfully released; in response to the target material not entering the hopper 250, determining that the target material release has failed, and generating a release failure prompt message.

[0052] In this embodiment, after determining that the picking result is successful, the robotic arm 230 is controlled to move the target material to above the hopper 250 set on the mobile chassis 210, and the end effector 240 is controlled to perform a release action, placing the target material into the hopper 250. The second light source mounted on the robotic arm 230 is turned on, and a second vision recognition camera is used to capture an image of the target area corresponding to the hopper 250 to obtain real-time visual information after material placement. Then, the target area image is compared and analyzed with a preset empty hopper area image or a standard material placement area model. Target detection and area matching are used to determine whether the target material has actually entered the hopper 250. If the detection result indicates that the target material has entered the hopper 250, the corresponding picking quantity is recorded and the material placement is confirmed as successful; if it has not entered or there is an offset, the material placement is determined to have failed, and a corresponding failure message is generated for subsequent corrective processing or manual intervention. Through the above method, automatic verification of the material placement process can be achieved, improving the accuracy of the picking closed-loop and the reliability of the operation.

[0053] Optionally, the method further includes: in response to a picking failure or a target material unloading failure, acquiring a real-time video stream captured by a first visual recognition camera and / or a second visual recognition camera; sending the real-time video stream to a pre-configured remote operation terminal and receiving control commands sent by a remote operator based on the remote operation terminal; and controlling the robotic arm 230 and the end effector 240 to re-execute the picking or unloading process on the target material according to the control commands.

[0054] In this embodiment, when the picking result is a picking failure or a target material unloading failure, the controller acquires real-time video streams from the first and / or second visual recognition cameras. The first visual recognition camera captures a macroscopic view of the vicinity of the robotic arm base, while the second visual recognition camera captures a close-up view of the gripping area of ​​the end effector 240 on the robotic arm 230, enabling multi-angle perception of abnormal scenarios. The controller transmits the real-time video stream to a pre-configured remote operation terminal via a wireless communication unit, allowing remote operators to view the current picking and unloading status in real time. The remote operator generates control commands based on the screen information from the remote operation terminal and sends them back to the controller. The controller then controls the robotic arm 230 and the end effector 240 to re-execute the gripping or unloading process of the target material according to the control commands, thereby providing manual correction for abnormal picking processes. Through this method, human-machine collaboration can be achieved under complex or abnormal working conditions, improving the success rate of operations.

[0055] Optionally, the method further includes: in response to the fact that all target materials corresponding to the picking task have been successfully placed into the bin 250, controlling the mobile chassis 210 to move to the packing table 260 set in the warehouse; controlling the robotic arm 230 to transfer the target materials in the bin 250 to the packing table 260 for packing.

[0056] In this embodiment, after all target materials corresponding to the picking task have been successfully placed into the bin 250, a task completion identifier is first generated. Based on this identifier, the mobile chassis 210 is controlled to move from its current aisle position to the pre-set packing station 260 within the warehouse along a preset or optimal path. During the movement, navigation sensors can be used to correct the position in real time to ensure accuracy. After the mobile chassis 210 reaches the packing station 260, the robotic arm 230 is controlled to perform a transfer action, picking up the target materials from the bin 250 one by one and placing them into the carrying area of ​​the packing station 260, thus completing the transfer of materials from the picking container to the packing station. Finally, the barcode scanning or weighing equipment at the packing station 260 can confirm the transferred target materials to support subsequent packing processing and order verification. Through the above method, centralized transfer and standardized packing of picking results are achieved, improving the overall continuity and automation level of warehousing operations.

[0057] A preferred embodiment of the present invention provides a picking control method. In this preferred embodiment, the warehouse management system generates picking tasks based on customer orders. Each picking task includes an order number, one or more SKU codes, a corresponding quantity, and storage location address information. The storage location address information includes the shelf number, layer number, and storage box number 120, and may also include the location information of the packing station 260. The warehouse management system sends the picking tasks to an idle mobile chassis 210 via a wireless network, where the onboard controller receives and executes subsequent control processes.

[0058] After receiving the picking task, the vehicle controller performs path planning and controls the mobile chassis 210 to travel from its current location to the aisle of the target shelf 100, and then travels along the aisle to the corresponding position of the target storage box 120. During the journey, navigation, positioning and obstacle avoidance control are performed through lidar, QR code landmarks or visual sensors to ensure that the mobile chassis 210 can stably reach the target work area.

[0059] After the mobile chassis 210 reaches the target shelf 100, the vehicle controller controls the lifting module 220 to adjust the robotic arm base of the robotic arm 230 to the corresponding height according to the shelf height of the target storage box 120. At the same time, the robotic arm 230 rotates and extends in the horizontal plane, so that the end effector 240 faces the interior of the target storage box 120. Under the condition of visual positioning, the position of the storage box 120 can be identified and accurately calibrated by the second visual recognition camera set on the robotic arm 230 or the first visual recognition camera set on the robotic arm base 31, thereby improving the alignment accuracy.

[0060] The on-board controller controls the end effector 240 to extend horizontally from the center of the channel into the target storage box 120 to grab or pick up the target SKU. The end effector 240 can adopt a vacuum adsorption type or a gripper type structure, and the SKU can be grabbed by suction cup negative pressure adsorption or gripper closing method. The robotic arm 230 then removes the grabbed SKU from the storage box 120 along the reverse path.

[0061] After the end effector 240 completes the grasping, the control system illuminates the second light source, and the second vision recognition camera captures an image containing the end effector 240 and the area in front of it. The vehicle controller performs target recognition and contour detection on the image to determine whether there is a target SKU between the grippers or in the adsorption area of ​​the end effector 240. If the preset grasping posture conditions are met, the picking is determined to be successful; otherwise, the picking is determined to be a failure, and the robot arm 230 can be automatically adjusted to re-grab, or the abnormal information can be sent to the remote operation terminal.

[0062] Once the picking is successful, the onboard controller controls the robotic arm 230 to move the grabbed SKU above the bin 250 and perform the unloading action. At the same time, the second light source is turned on again, and the second vision recognition camera captures images of the inside of the bin 250 or the entrance area. The current image is compared with the image before unloading or the preset model to determine whether the SKU has successfully entered the bin 250. If the unloading is successful, the quantity of the SKU is recorded and the process proceeds to the next SKU picking process. If it fails or is uncertain, a corrective action is performed or a remote operation intervention is prompted.

[0063] When the picking task is a collection order, the vehicle controller plans the optimal or suboptimal picking path based on the target storage box 120 address, relative spatial position, and current position information of the mobile chassis 210 for multiple SKUs. Then, it executes the path planning, lifting and positioning, lateral gripping, and placement into the material box 250 operations in sequence until all SKUs in the order have been successfully picked and confirmed to be placed into the material box 250 before triggering the action of going to the packing station 260.

[0064] When the system detects multiple consecutive picking failures or unloading failures for the same SKU, or abnormal stacking of the target storage box 120, the mobile chassis 210 sends the real-time video streams from the first vision recognition camera on the robotic arm base and, if necessary, the second vision recognition camera at the end effector to the remote operation terminal via a wireless network. The remote operator then guides the robotic arm 230's movements based on the video feed or directly controls the end effector 240 to complete the picking and unloading operations. After the remote operation is completed, the system returns to automatic operation mode to continue executing the remaining tasks.

[0065] Once it is confirmed that all SKUs in the task have been successfully placed into the bin 250, the vehicle controller controls the mobile chassis 210 to drive away from the aisle of the shelf 100 and head to the preset packing station 260. Upon arrival, the SKUs in the bin 250 can be transferred to the packing station 260 for packing by the robotic arm 230 or by manual labor. At the same time, the order picking completion information is fed back to the warehouse management system, thus completing the entire automated picking process of the collection order.

[0066] Through the above preferred embodiments, the automated picking system can achieve fully automated control of the entire process from task generation, path planning, lateral grasping, visual detection to multi-SKU sequential picking and packaging feedback, thereby improving picking efficiency and accuracy. At the same time, the combination of visual recognition and remote operation mechanisms enhances the system's robustness and adaptability in complex warehousing environments.

[0067] According to another aspect of the present invention, an automated picking system is provided.

[0068] like Figure 2 , Figure 3 and Figure 8 As shown, the automated picking system includes: an automated picking mechanism 200 and a picking control device 800; multiple shelves 110 are installed inside the shelves 100 located on both sides of the warehouse aisle, and each shelf 110 has multiple storage boxes 120 for storing target materials; the automated picking mechanism 200 includes a mobile chassis 210, a lifting module 220 is installed on the top of the mobile chassis 210, a robotic arm 230 is installed on the lifting module 220, and an end effector 240 is fixedly installed at the end of the robotic arm 230 away from the lifting module 220; the picking control device 800... Based on the received picking task, the 800 determines the storage box 120 corresponding to the target material in the picking task and the target picking path; according to the target picking path, it controls the mobile chassis 210 to move to the shelf 100 where the storage box 120 is located, and controls the lifting module 220 and the robotic arm 230 to move in coordination, so that the end effector 240 set at the end of the robotic arm 230 extends into the interior of the storage box 120 to grab the target material and obtain the grabbing result; the grabbing result is processed by image detection, and the picking result corresponding to the picking task is determined based on the image detection result.

[0069] In this embodiment, the automated picking system is applied to a warehouse aisle scenario. The warehouse aisle scenario includes shelves 100 arranged on both sides of the aisle, and a picking control device 800 controls the movement of the automated picking mechanism 200 within the aisle. The shelves 100 extend along the aisle direction, and their interiors are divided into multiple storage spaces by multiple partitions 110. Each partition 110 has multiple storage boxes 120 arranged horizontally at intervals, and each storage box 120 is used to store a corresponding type of target material. Through the above structure, the shelves 100 form a high-density, multi-level storage layout within a limited space.

[0070] An automated picking mechanism 200 is installed in the aisles between shelves 100. It includes a movable chassis 210 that can travel along the aisle and stop near the target storage location. A lifting module 220 is mounted on top of the movable chassis 210, extending vertically to move a mounted robotic arm 230 between different heights, thus adapting to different levels of storage boxes 120 on the shelves 100. The robotic arm 230 is mounted on the lifting module 220 and its overall height is adjusted as the lifting module 220 moves. An end effector 240 is located at the end of the robotic arm 230 furthest from the lifting module 220, directly contacting the material and performing a gripping action. Through the multi-degree-of-freedom movement of the robotic arm 230, it can align with the target storage location horizontally and drive the end effector 240 to extend into the corresponding storage box 120 to complete the material gripping. The specific implementation details of the picking control device 800 have already been explained in detail in the picking control method above, so they will not be repeated here.

[0071] In the specific operation, after the mobile chassis 210 travels to the aisle of the target shelf 100, the lifting module 220 adjusts its height according to the level of the target storage box 120, so that the robotic arm 230 is at a height matching the target storage location. Then, the robotic arm 230 adjusts its posture through joint movement, so that the end effector 240 is aligned with the opening of the target storage box 120 and extends horizontally into the storage box 120 to grab the target material. After grabbing, the robotic arm 230 drives the end effector 240 to exit the storage box 120, thus completing one picking action. Through the mobility of the mobile chassis 210 and the coordinated movement of the lifting module 220 and the robotic arm 230, it is possible to access and retrieve materials from storage boxes 120 at different locations on the shelf 100 one by one.

[0072] In other embodiments, the shelf 100 can be a standard shelf structure arranged in a regular array, and the storage box 120 is an open container of uniform specifications to facilitate the stable insertion of the end effector 240; the lifting module 220 can adopt different forms of vertical motion structure to achieve smooth lifting, and the robotic arm 230 can be selected in different degrees of freedom according to the actual application, but all of them maintain the basic structural relationship of being installed in the lifting module 220 and being able to drive the end effector 240 to complete spatial positioning and grasping actions.

[0073] Through the above structural design, the automated picking system can automatically access and pick up materials in the multi-layer storage box 120 without changing the original layout of the shelf 100. By utilizing the mobility of the mobile chassis 210 and the height adaptability of the lifting module 220, the robotic arm 230 is able to complete multi-position picking in a limited aisle space, thereby improving warehouse picking efficiency and reducing the degree of human intervention.

[0074] like Figures 2 to 5 As shown, the automatic picking mechanism 200 also includes a bin 250, which is fixedly or detachably mounted on the mobile chassis 210. The end effector 240 can release the grabbed material into the bin 250.

[0075] In this embodiment, the automatic picking mechanism 200 further includes a material bin 250, which is fixedly or detachably mounted on the mobile chassis 210 and located within the working range of the robotic arm 230. This arrangement allows the end effector 240 to directly move the grabbed material above the material bin 250 and release it after grasping the material in the storage box 120, thus achieving centralized temporary storage of the material. The material bin 250 is preferably arranged on the upper surface of the mobile chassis 210 and matches the spatial position of the lifting module 220 and the robotic arm 230, enabling the robotic arm 230 to complete the material transfer from the storage box 120 to the material bin 250 without complex path adjustments.

[0076] Specifically, the material bin 250 can be a fixed installation structure to ensure good stability during the movement of the mobile chassis 210; the material bin 250 can also be detachable for quick replacement after a batch of picking tasks is completed or for the entire bin to be transferred to a subsequent processing station. The material bin 250 can be an open box structure to allow the end effector 240 to release materials directly, or it can have a protective structure of a certain height at its edges to prevent materials from slipping during movement; the interior of the material bin 250 can also be simply partitioned according to the characteristics of the materials to meet the needs of temporary storage of different types of materials.

[0077] In the specific implementation process, after completing the grasping action, the robotic arm 230 uses joint movement to retract the end effector 240 from the storage box 120 and adjusts its posture in space to transfer the material to the area above the hopper 250. Then, it controls the end effector 240 to release the material, causing it to fall into the hopper 250 for storage. By integrating the hopper 250 onto the mobile chassis 210, the automatic picking mechanism 200 does not need to return to a fixed position for unloading each time it performs multiple picking tasks, thus enabling it to continuously complete picking operations of multiple storage boxes 120 within the aisle.

[0078] This embodiment, by setting a material bin 250 on the automatic picking mechanism 200, allows the picking and temporary storage processes to be completed on the same equipment, thereby forming a continuous operation flow of "grab-transfer-temporary storage," reducing the intermediate transfer links of materials in the warehouse and lowering the overall system uptime. Simultaneously, this structure enables the mobile chassis 210 to have a higher continuous operation capability when performing multi-SKU material picking tasks, helping to improve overall picking efficiency and reduce dependence on external conveying equipment.

[0079] like Figure 4 and Figure 5 As shown, the upper surface of the mobile chassis 210 is provided with an installation platform 211, and the lifting module 220 is vertically fixed to the installation platform 211.

[0080] In this embodiment, the mounting platform 211 provides a stable mounting base for the lifting module 220. The lifting module 220 is vertically fixed on the mounting platform 211, enabling the lifting module 220 to maintain a stable vertical posture during the movement of the mobile chassis 210, thus avoiding adverse effects on the working accuracy of the robotic arm 230 caused by tilting or vibration due to chassis movement. The mounting platform 211 can be a one-piece molded structure or fixed to the mobile chassis 210 via connectors. Its surface can be provided with mounting holes or reinforcing ribs according to the installation requirements of the lifting module 220 to improve overall rigidity and load-bearing capacity.

[0081] In practical implementation, the lifting module 220 is reliably connected to the mobile chassis 210 via the mounting platform 211, ensuring that its vertical lifting motion is stably transmitted to the robotic arm 230, thereby guaranteeing the positioning accuracy of the end effector 240 when grasping at different heights. Furthermore, the mounting platform 211 can be customized according to the structure of the mobile chassis 210, for example, it can be centrally located or slightly offset to one side to optimize the working space coverage of the robotic arm 230. Simultaneously, the mounting platform 211 can also be arranged in conjunction with components such as the material bin 250, enabling the robotic arm 230 to transfer materials to the material bin 250 via a shorter path after grasping. In further embodiments, the mounting platform 211 can also integrate vibration damping or reinforcement structures to adapt to stability requirements under different working conditions.

[0082] By setting up an installation platform 211 between the mobile chassis 210 and the lifting module 220, not only is a structural transition and stable connection between the two achieved, but the stability and reliability of the whole machine during dynamic travel and picking operations are also improved, which is conducive to improving the working accuracy of the robotic arm 230 and the overall operating performance of the system.

[0083] Optionally, the robotic arm 230 includes a robotic arm base, which is mounted on the lifting module 220. A first visual recognition camera and a first light source for illuminating the first visual recognition camera are mounted on the robotic arm base.

[0084] In this embodiment, the robotic arm 230 includes a robotic arm base, which is mounted on the lifting module 220, allowing the robotic arm 230 to move vertically along with the lifting module 220 to adapt to different storage locations on the shelf 100. A first visual recognition camera and a first light source for illuminating the first visual recognition camera are mounted on the robotic arm base. This arrangement ensures that the field of view of the first visual recognition camera covers the main working space of the robotic arm 230 and the target storage area, enabling the acquisition of macroscopic image information during operation. The first light source works in conjunction with the first visual recognition camera to provide stable illumination, allowing it to acquire clear images under different ambient light conditions, thereby assisting the robotic arm 230 in locating the target area and monitoring operations.

[0085] The first visual recognition camera can be configured with different field of view or resolution to adapt to monitoring needs in different ranges; the first light source can be set to fixed brightness or adjustable brightness according to the application scenario to ensure recognition effect while taking energy consumption control into account. In a further embodiment, the first visual recognition camera can also be connected to the control system to transmit the acquired image information to an external terminal to support remote monitoring or auxiliary operation.

[0086] By setting a first vision recognition camera and a first light source at the base of the robotic arm, the system adds a layer of macroscopic perception capability in addition to fine end-effector recognition. This not only improves the visualization of the overall operation process, but also enhances the ability to identify and monitor target areas in complex environments, thereby improving the stability and reliability of the automated picking system.

[0087] like Figure 4 and Figure 5 As shown, the lifting module 220 includes a lifting column 221 and a slider that slides with the lifting column 221, and a robotic arm 230 is mounted on the slider.

[0088] In this embodiment, the robotic arm 230 can move smoothly vertically along the lifting column 221 with the slider, thereby achieving height adaptation of storage boxes 120 at different levels of the shelf 100. The lifting column 221 is preferably a guide structure with high rigidity, which can be a single-column structure or a multi-column combination structure. A stable guiding relationship is formed between the slider and the lifting column 221 to ensure that no significant deviation or shaking occurs during the lifting process, thereby improving the positioning accuracy of the robotic arm 230. After the robotic arm 230 is mounted on the slider, its entire structure rises and falls with the slider, enabling the end effector 240 to complete the alignment and insertion operation of the storage box 120 at different height positions.

[0089] Specifically, the lifting column 221 can be configured as a hollow structure or with a guide rail structure to further improve the smoothness of the slider movement; the slider and the robotic arm 230 can be rigidly connected to ensure the stability of the robotic arm 230 during lifting. The cooperation between the lifting column 221 and the slider can be equipped with a limiting structure or a buffer structure to prevent the slider from impacting at extreme positions and improve the safety of equipment operation.

[0090] Through the above structural design, the lifting module 220 can not only provide the robotic arm 230 with stable vertical movement capability, but also achieve rapid switching access to multiple storage locations within a limited space. Combined with the horizontal movement capability of the mobile chassis 210, it forms a three-dimensional operation capability within the spatial range, thereby improving the adaptability of the automatic picking system to different storage locations and the overall picking efficiency.

[0091] Optionally, the lifting module 220 is a linear motion mechanism, which can be any of the following structures: a lead screw drive structure, a synchronous belt drive structure, and a chain drive structure.

[0092] In this embodiment, the lifting module 220 is a linear motion mechanism used to drive the robotic arm 230 to move controllably in the vertical direction, thereby achieving height adaptation to different levels of storage boxes 120. The linear motion mechanism can be any one of a screw drive structure, a synchronous belt drive structure, or a chain drive structure. The screw drive structure uses a motor to rotate the screw, thereby driving the slider to move precisely along the lifting direction, resulting in high positioning accuracy and stable control. The synchronous belt drive structure uses a pulley and a synchronous belt to achieve transmission, resulting in fast response and smooth operation. The chain drive structure is suitable for scenarios with large strokes or high loads, offering reliable structure and strong load-bearing capacity. By selecting the above different drive forms, the lifting module 220 can achieve a balance between accuracy, speed, and load-bearing capacity according to actual application requirements.

[0093] By setting the lifting module 220 to various optional linear motion mechanism forms, the system has strong versatility and expandability in design. It can not only meet different accuracy and efficiency requirements, but also achieve rapid lifting response of the robotic arm 230 while ensuring structural stability, thereby improving the efficiency and reliability of the overall picking operation.

[0094] like Figure 6 As shown, the robotic arm 230 is a multi-degree-of-freedom collaborative robot robotic arm that includes at least 4 to 7 rotational joints.

[0095] In this embodiment, the robotic arm 230, through the linkage of multiple rotary joints, possesses high flexibility and accessibility in space, thereby driving the end effector 240 to complete the alignment, insertion, and grasping actions of storage boxes 120 at different locations. Preferably, the robotic arm 230 has 6 or 7 rotary joints to provide sufficient posture adjustment capability while ensuring a compact structure, enabling the end effector 240 to bypass obstacles and adjust to a suitable grasping posture within a limited aisle space. In cooperation with the lifting module 220, the robotic arm 230 can not only extend and retract horizontally but also adapt to different storage locations vertically, thereby achieving continuous access to more than 100 storage boxes 120 on the shelf.

[0096] In another embodiment, the robotic arm 230 can also be a multi-degree-of-freedom structure with four or five rotary joints to simplify the structure and reduce costs while meeting basic picking requirements, making it suitable for application scenarios with relatively low requirements for posture flexibility.

[0097] By setting the robotic arm 230 as a multi-degree-of-freedom collaborative robot robotic arm, it has strong spatial operation capabilities and posture adjustment capabilities in a limited space, and can flexibly cope with the positional changes of different storage boxes 120, thereby improving the grasping success rate and operational adaptability of the end effector 240, and thus improving the efficiency and stability of the entire automatic picking system.

[0098] Optionally, such as Figure 4 and Figure 6 As shown, the end effector 240 can be any of the following structures: vacuum suction type, gripper type, and suction-grip combination type.

[0099] In this embodiment, the vacuum adsorption end effector 240 grips materials by negative pressure adsorption, which is suitable for materials with relatively flat surfaces and light weight; the gripper end effector 240 grips materials by mechanical clamping structure, which is suitable for materials with regular shapes or clampable edges; the suction-clamp combination end effector 240 combines adsorption and clamping methods, which improves the adaptability to different types of materials through synergistic effect.

[0100] In another embodiment, the end effector 240 can also be structurally optimized according to material characteristics, for example, by setting up a multi-suction cup array to improve adsorption stability, or by adjusting the opening and closing range of the grippers to adapt to materials of different sizes. The end effector 240 can also integrate a flexible contact structure to reduce the impact of gripping fragile materials.

[0101] This embodiment enables the automated picking system to adapt to materials of different shapes and characteristics by setting the end effector 240 to various optional structural forms, thereby improving the success rate of picking and the stability of operation, while enhancing the versatility and flexibility of the system in multi-SKU scenarios, thus improving the overall picking efficiency.

[0102] Optionally, a second visual recognition camera and a second light source for illuminating the second visual recognition camera are installed around the periphery of the robotic arm 230 near the end effector 240. The second light source is a ring light or a strip light.

[0103] In this embodiment, by positioning the second visual recognition camera close to the end effector 240, its field of view covers the gripping area of ​​the end effector 240, thereby acquiring real-time image information of the target material and its surrounding environment during the picking process performed by the robotic arm 230. A second light source is positioned around the end effector 240 and works in conjunction with the second visual recognition camera to provide stable local illumination conditions for the gripping area, thus enabling clear images to be obtained under different lighting conditions and improving recognition accuracy. When the robotic arm 230 completes the alignment and gripping of materials in the storage box 120, the second visual recognition camera can simultaneously acquire image information, providing a basis for subsequent gripping status judgment or position correction.

[0104] The second visual recognition camera can be arranged at different angles depending on the structure of the end effector 240, such as a single-camera structure or a multi-camera combination structure, to expand the field of view or improve recognition accuracy. The second light source can also be selected in different shapes or arrangements according to application requirements, such as using a ring distribution to provide uniform illumination, or using a strip distribution to enhance the light intensity in a certain direction. In a further embodiment, the second light source can be controlled according to the picking action, such as automatically lighting up when performing gripping or unloading operations, thereby reducing energy consumption while ensuring recognition effect.

[0105] By integrating a second vision recognition camera and a second light source into the end effector region of the robotic arm 230, the system is equipped with real-time perception capabilities of the gripping area. This improves the accuracy of target material identification and the reliability of gripping in complex warehousing environments, while reducing the impact of external ambient light on system performance, thereby enhancing the stability and adaptability of the automated picking system.

[0106] like Figure 7 As shown, the automated picking system also includes a packing station 260 installed in the warehouse. The packing station 260 is used to receive the boxes 250 transported by the mobile chassis 210. The packing station 260 includes: a platform frame, a support platform installed on the top of the platform frame, a barcode scanning device installed above the support platform for identifying the boxes 250, and a weighing device installed inside or below the support platform for weighing the boxes 250.

[0107] In this embodiment, the automated picking system also includes a packing station 260 located within the warehouse. The packing station 260 receives the boxes 250 transported by the mobile chassis 210 and serves as a material handling node after picking. The packing station 260 includes a frame supporting the overall structure, with a support platform on its top for holding the boxes 250 or materials removed from them. A barcode scanner is installed above the support platform to identify the markings on the boxes 250, thereby enabling the reading and confirmation of order or material information. Simultaneously, a weighing device is installed inside or below the support platform to measure the weight of the boxes 250, verifying whether the quantity or weight of the materials meets the expected requirements. This structure enables the packing station 260 to complete identification and verification operations after receiving the boxes 250. In the specific implementation process, the mobile chassis 210 transports the picking bins 250 to the packing table 260 and places the bins 250 on the support platform. The barcode scanning and identification device identifies the bins 250 to obtain relevant information, and the weighing device simultaneously detects the weight of the bins 250, thereby realizing the automatic verification of the picking results.

[0108] In another embodiment, the barcode scanning and identification device can be configured as a fixed installation structure or an adjustable installation structure according to application requirements to adapt to different positions or different sizes of bins 250; the weighing device can be configured as an embedded structure or an external structure to meet different accuracy or installation space requirements.

[0109] By setting up a packing station 260 in the automated picking system, the system has a unified receiving and processing node after completing the picking operation. It can identify information and verify the weight of the bins 250, thereby improving the accuracy and traceability of the picking results. At the same time, it provides a basis for subsequent packing processing, which helps to improve the continuity and efficiency of the entire warehousing operation process.

[0110] According to a preferred embodiment of the present invention, a mobile composite robot system for SKU lateral picking in a material warehouse is provided. The system includes a mobile chassis 210, a lifting module 220, a robotic arm 230, an end effector 240, a material bin 250, a shelf 100 and storage boxes 120 thereon, a packing table 260, and a control system.

[0111] The mobile chassis 210 is preferably an autonomous mobile robot chassis, equipped with drive wheels, driven wheels, and onboard navigation sensors. The onboard navigation sensors include a lidar, a QR code recognition device, and a vision sensor, used to achieve autonomous positioning and navigation in the warehouse environment. The upper surface of the mobile chassis 210 is provided with a mounting platform 211 for mounting the lifting module 220, the material bin 250, and the control unit, thereby providing a stable mounting foundation for each component.

[0112] The lifting module 220 is fixedly connected to the mounting platform 211 and is a vertically arranged linear motion mechanism. This linear motion mechanism can employ a lead screw drive structure, a synchronous belt drive structure, or a chain drive structure. The lifting module 220 includes a lifting column 221 and a slider that slides in conjunction with the lifting column 221. A robotic arm 230 and components such as a base light source are mounted on the slider, enabling the robotic arm 230 to move vertically along with the lifting module 220. The travel of the lifting module 220 covers the entire height of the shelf 100, allowing the robotic arm 230 to perform picking operations at the corresponding storage boxes 120 positions on each shelf level of the shelf 100.

[0113] A robotic arm 230 is mounted on a slider, preferably a multi-degree-of-freedom collaborative robot arm, comprising at least 4 to 7 rotary joints. The robotic arm 230 includes a robotic arm base, which is mounted on and synchronously raised and lowered with the lifting module 220 to accommodate storage boxes 120 at different heights. The coordinated movement of each rotary joint of the robotic arm 230 enables the end effector 240 to translate, extend, and adjust its posture in space, allowing the end effector 240 to accurately align with the target storage box 120 and complete the grasping action. The end effector 240 is fixed to the end of the robotic arm 230 and is used to grasp or extract target SKUs from the storage box 120. Its structure can be vacuum suction type, gripper type, or a combination of suction and gripping, and distance or pressure sensors can be configured as needed to improve grasping stability.

[0114] The hopper 250 is fixedly or detachably mounted on the mobile chassis 210 for temporarily storing picked SKUs during the picking process. The hopper 250 is within the reach of the robotic arm 230, allowing the end effector 240 to release the material into the hopper 250 after gripping. The hopper 250 can be an open container or equipped with protective baffles, spill-proof edges, or a compartmentalized structure to adapt to the temporary storage needs of different materials.

[0115] The shelving 100 is arranged along both sides of the warehouse aisle. It has multiple partitions 110 inside, and each partition 110 has multiple front-opening storage boxes 120. Each storage box 120 is used to store one or more SKUs and corresponds to a unique storage location code so that it can be managed by address mapping in the warehouse management system.

[0116] The packing station 260 is located in a fixed position within the warehouse to receive the tote boxes 250 transported by the mobile chassis 210 and to perform subsequent processing on the picked SKUs. The packing station 260 includes a frame, a support platform mounted on top of the frame, a barcode scanner mounted above the support platform to identify the markings on the tote boxes 250, and a weighing device located inside or below the support platform to measure the weight of the tote boxes 250, thereby verifying the picking results.

[0117] The control system includes a robot vehicle controller and a warehouse management system. The vehicle controller is connected to the mobile chassis 210, lifting module 220, robotic arm 230, end effector 240, vision recognition camera and light source, etc., to realize path planning, posture control and picking action control. The warehouse management system is used for order management, SKU information management and task distribution, and communicates with the robot through a wireless network.

[0118] In terms of visual recognition and light source configuration, a first visual recognition camera and a first light source are installed on the robotic arm base of the robotic arm 230. The first light source is mounted on a bracket integrated with the slider of the lifting module 220 or the robotic arm base, and rises and falls synchronously with the lifting module 220, thereby providing stable lighting for the working area at different heights. The field of view of the first visual recognition camera covers the working space of the robotic arm 230 and the target shelf 100 area, used to output macroscopic operation images and support remote operation. A second visual recognition camera and a second light source are installed around the robotic arm 230 near the end effector 240. The second light source is a ring light or a strip light, used to provide local lighting for the second visual recognition camera, so that its field of view covers the gripping area of ​​the end effector 240 and the area above the material box 250, used to collect image information of the picking and unloading processes. Through the above configuration, the system can still achieve effective lighting of the working area by relying on the first and second light sources even when the warehouse ambient lighting is reduced or even turned off, enabling the first and second visual recognition cameras to reliably complete image acquisition, thereby adapting to the dark warehouse environment and achieving continuous operation.

[0119] In terms of structure and relative position, the lateral dimension of the mobile chassis 210 is smaller than the width of the aisle between the shelves 100, allowing it to move freely within the aisle. The lifting module 220 is positioned approximately at the center of the aisle or slightly off-center. The robotic arm 230 has sufficient working radius and joint degrees of freedom, enabling the end effector 240 to cover all storage boxes 120 on the shelves 100 on both sides of the aisle. The robotic arm 230 can rotate around the centerline of the lifting module 220 through the rotation of its base and the coordinated movement of its joints, thereby achieving lateral picking of the shelves 100 on both sides of the aisle. The hopper 250 is positioned below the lifting module 220 and within the reach of the robotic arm 230, allowing the robotic arm 230 to place the SKU into the hopper 250 simply by rotating it after picking. Through the above structural design, the system achieves efficient access and automatic picking of multi-layer storage boxes 120 without changing the existing shelf layout, and possesses good spatial adaptability and continuous operation capability.

[0120] Figure 8 This is a schematic diagram of the main modules of a picking control device according to an embodiment of the present invention. Figure 8 As shown, the picking control device 800 includes: The determination module 801 is used to determine the storage box 120 corresponding to the target material in the picking task and the target picking path based on the received picking task. The gripping module 802 is used to control the mobile chassis 210 to move to the shelf 100 where the storage box 120 is located according to the target picking path, and to control the lifting module 220 and the robotic arm 230 to move together so that the end effector 240 set at the end of the robotic arm 230 extends into the interior of the storage box 120 to grip the target material and obtain the gripping result. The detection module 803 is used to perform image detection processing on the grasping results and determine the picking result corresponding to the picking task based on the image detection results.

[0121] Optionally, the determining module 801 is also used for: Based on the analysis results of the picking task, determine the order material information and storage location information; Based on the order material information and storage location address information, determine the target material corresponding to the picking task and the storage box 120 corresponding to the target material; Based on the storage location address information, path planning is performed to generate the target picking path corresponding to storage box 120.

[0122] Optionally, the grasping module 802 is also used for: Control the lifting module 220 to move along the height direction, so as to move the robotic arm base installed on the lifting module 220 to the target height corresponding to the storage box 120; The storage box 120 is identified using a first vision recognition camera mounted on the robotic arm base; In response to a successful identification process, the robotic arm 230 is controlled to extend and rotate so that the end effector 240 is directed toward the storage box 120.

[0123] Optionally, the grasping module 802 is also used for: The control robot arm 230 drives the end effector 240 to move horizontally toward the storage box 120, so that the end effector 240 extends into the interior of the storage box 120 from the aisle side of the shelf 100. The end effector 240 is controlled to perform adsorption, clamping, or a combination of adsorption and clamping operations on the target material to obtain a grasping result.

[0124] Optionally, the detection module 803 is also used for: The second light source mounted on the robotic arm 230 is turned on, and the second vision recognition camera mounted on the robotic arm 230 is used to acquire the target area image corresponding to the end effector 240; Based on the target area image corresponding to the end effector 240, determine whether the end effector 240 has grasped the target material; In response to the end effector 240 grasping the target material and meeting the preset grasping posture conditions, the picking result is determined to be a successful picking; If the end effector 240 fails to grasp the target material or does not meet the preset grasping posture conditions, the picking result is determined to be a picking failure.

[0125] Optionally, the detection module 803 is also used for: The robotic arm 230 is controlled to move the target material to the hopper 250 set on the mobile chassis 210, and the end effector 240 is controlled to release the target material. Turn on the second light source and control the second vision recognition camera to acquire images of the target area corresponding to the material box 250; The target area image corresponding to the material bin 250 is compared with the preset area image, and the target material is determined to enter the material bin 250 based on the comparison result. In response to the target material entering the bin 250, the picking quantity of the target material is recorded, and the successful dispensing of the target material is confirmed. In response to the fact that the target material has not entered the hopper 250, it is determined that the material feeding has failed and a feeding failure prompt message is generated.

[0126] Optionally, the picking control device 800 also includes a remote operation module, which is further used for: In response to a picking failure or a failure to release the target material, the system acquires a real-time video stream captured by the first vision recognition camera and / or the second vision recognition camera. Send real-time video streams to a pre-configured remote control terminal and receive control commands sent by remote operators based on the remote control terminal; According to the control instructions, the robotic arm 230 and the end effector 240 are controlled to re-perform the gripping or unloading process of the target material.

[0127] Optionally, the picking control device 800 also includes a transfer module, which is further used for: In response to the fact that all target materials corresponding to the picking task have been successfully placed into the bin 250, the mobile chassis 210 is controlled to move to the packing table 260 set in the warehouse. The robotic arm 230 is controlled to transfer the target material in the hopper 250 to the packaging table 260 for packaging.

[0128] It should be noted that the specific implementation details of the picking control device in the embodiments of the present invention have been described in detail in the picking control method above, so the details will not be repeated here.

[0129] According to a fourth aspect of the present invention, an electronic device is provided, comprising: One or more processors; Storage device for storing one or more programs. When one or more programs are executed by one or more processors, the one or more processors implement the method provided in the first aspect of the embodiments of the present invention.

[0130] According to a fifth aspect of the present invention, a computer-readable medium is provided having a computer program stored thereon, which, when executed by a processor, implements the method provided in the first aspect of the present invention.

[0131] According to a sixth aspect of the present invention, a computer program product is provided, including a computer program that, when executed by a processor, implements the method provided in the first aspect of the present invention.

[0132] Figure 9 An exemplary system architecture 900 is shown that can be applied to the picking control method or picking control device of the present invention.

[0133] like Figure 9 As shown, system architecture 900 may include terminal devices 901, 902, and 903, network 904, and server 905. Network 904 is used as a medium to provide a communication link between terminal devices 901, 902, and 903 and server 905. Network 904 may include various connection types, such as wired or wireless communication links or fiber optic cables, etc.

[0134] Users can use terminal devices 901, 902, and 903 to interact with server 905 via network 904 to receive or send messages, etc. Various communication client applications can be installed on terminal devices 901, 902, and 903, such as shopping applications, web browser applications, search applications, instant messaging tools, email clients, social media platform software, etc. (for example only).

[0135] Terminal devices 901, 902, and 903 can be various electronic devices with displays that support web browsing, including but not limited to smartphones, tablets, laptops, and desktop computers.

[0136] Server 905 can be a server providing various services, such as a back-end management server supporting shopping websites browsed by users using terminal devices 901, 902, and 903 (for example only). The back-end management server can analyze and process data such as received picking control requests, and feed back the processing results (such as picking results - for example only) to the terminal devices.

[0137] It should be noted that the picking control method provided in the embodiments of the present invention is generally run by server 905, and correspondingly, the picking control device is generally set in server 905.

[0138] It should be understood that Figure 9 The number of terminal devices, networks, and servers shown is merely illustrative. Depending on implementation needs, any number of terminal devices, networks, and servers can be included.

[0139] The following is for reference. Figure 10 It shows a schematic diagram of the structure of a computer system 1000 suitable for implementing a terminal device of the present invention. Figure 7 The terminal device shown is merely an example and should not impose any limitations on the functionality and scope of use of the embodiments of the present invention.

[0140] like Figure 10 As shown, the computer system 1000 includes a central processing unit (CPU) 1001, which can perform various appropriate actions and processes based on programs stored in read-only memory (ROM) 1002 or programs loaded from storage section 708 into random access memory (RAM) 1003. The RAM 1003 also stores various programs and data required for the operation of the system 1000. The CPU 1001, ROM 1002, and RAM 1003 are interconnected via a bus 1004. An input / output (I / O) interface 1005 is also connected to the bus 1004.

[0141] The following components are connected to I / O interface 1005: an input section 1006 including a keyboard, mouse, etc.; an output section 1007 including a cathode ray tube (CRT), liquid crystal display (LCD), etc., and speakers, etc.; a storage section 1008 including a hard disk, etc.; and a communication section 1009 including a network interface card such as a LAN card, modem, etc. The communication section 1009 performs communication processing via a network such as the Internet. A drive 1010 is also connected to I / O interface 1005 as needed. A removable medium 1011, such as a disk, optical disk, magneto-optical disk, semiconductor memory, etc., is installed on drive 1010 as needed so that computer programs read from it can be installed into storage section 1008 as needed.

[0142] In particular, according to the embodiments disclosed in this invention, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments disclosed in this invention include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via communication section 1009, and / or installed from removable medium 1011. When the computer program is run by the central processing unit (CPU) 1001, it performs the functions defined above in the system of this invention.

[0143] It should be noted that the computer-readable medium shown in this invention can be a computer-readable signal medium, a computer-readable storage medium, or any combination thereof. A computer-readable storage medium can be, for example,—but not limited to—an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this invention, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In this invention, a computer-readable signal medium can include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. Computer-readable signal media can also be any computer-readable medium other than computer-readable storage media, which can send, propagate, or transmit programs for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to: wireless, wire, optical fiber, RF, etc., or any suitable combination thereof.

[0144] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of the present invention. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more operable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually operate substantially in parallel, and they may sometimes operate in reverse order, depending on the functions involved. It should also be noted that each block in a block diagram or flowchart, and combinations of blocks in a block diagram or flowchart, may be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0145] The modules described in the embodiments of the present invention can be implemented in software or hardware. The described modules can also be housed in a processor; for example, a processor can be described as including a determining module, a grasping module, and a detection module. The names of these modules do not necessarily limit the module itself; for example, the detection module can also be described as "a module for performing image detection processing on the grasping results and determining the picking result corresponding to the picking task based on the image detection results."

[0146] In another aspect, the present invention also provides a computer-readable medium, which may be included in the device described in the above embodiments; or it may exist independently and not assembled into the device. The computer-readable medium carries one or more programs that, when executed by the device, cause the device to include: determining, based on a received picking task, the storage box 120 corresponding to the target material in the picking task and the target picking path; controlling the mobile chassis 210 to move to the shelf 100 where the storage box 120 is located according to the target picking path, and controlling the lifting module 220 and the robotic arm 230 to move collaboratively, so that the end effector 240 disposed at the end of the robotic arm 230 extends into the interior of the storage box 120 to grasp the target material, obtaining a grasping result; performing image detection processing on the grasping result, and determining the picking result corresponding to the picking task based on the image detection result.

[0147] The computer program product provided in this embodiment of the invention includes a computer program that, when executed by a processor, implements the automatic picking method in this embodiment of the invention.

[0148] According to the technical solution of the present invention, the following advantages or beneficial effects are achieved: based on the received picking task, the storage box 120 corresponding to the target material in the picking task and the target picking path are determined; according to the target picking path, the mobile chassis 210 is controlled to move to the shelf 100 where the storage box 120 is located, and the lifting module 220 and the robotic arm 230 are controlled to move in coordination, so that the end effector 240 set at the end of the robotic arm 230 extends into the interior of the storage box 120 to grab the target material and obtain the grabbing result; image detection processing is performed on the grabbing result. Based on image detection results, the picking result corresponding to the picking task is determined; the received picking task is converted into a target picking path, and combined with the coordinated control of the mobile chassis 210, lifting module 220 and robotic arm 230, the target material in the storage box 120 located on both sides of the aisle of the shelf 100 is automatically grasped laterally. At the same time, an image recognition-based grasping result detection mechanism is introduced to verify the grasping process in real time, thereby completing high-precision picking operations without human intervention, reducing manual picking costs and improving picking efficiency and accuracy.

[0149] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can occur depending on design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

[0150] It should be noted that the acquisition, storage, and application of user personal information involved in the technical solution disclosed herein comply with the provisions of relevant laws and regulations and do not violate public order and good morals.

Claims

1. A picking control method, characterized in that, include: Based on the received picking task, determine the storage box (120) corresponding to the target material in the picking task and the target picking path; According to the target picking path, the mobile chassis (210) is moved to the shelf (100) where the storage box (120) is located, and the lifting module (220) and the robotic arm (230) are controlled to move in coordination so that the end effector (240) set at the end of the robotic arm (230) extends into the interior of the storage box (120) to grab the target material and obtain the grabbing result; The grasping result is subjected to image detection processing, and the picking result corresponding to the picking task is determined based on the image detection result.

2. The method according to claim 1, characterized in that, Based on the received picking task, determine the storage box (120) corresponding to the target material in the picking task and the target picking path, including: Based on the analysis results of the picking task, the order material information and storage location address information are determined; Based on the order material information and storage location address information, determine the target material corresponding to the picking task and the storage box (120) corresponding to the target material. Based on the storage location address information, path planning is performed to generate the target picking path corresponding to the storage location box (120).

3. The method according to claim 1, characterized in that, Controlling the coordinated movement of the lifting module (220) and the robotic arm (230) includes: Control the lifting module (220) to move along the height direction, so as to drive the robotic arm base installed on the lifting module (220) to move to the target height corresponding to the storage box (120); The storage box (120) is identified using a first vision recognition camera mounted on the robotic arm base; In response to a successful identification process, the robotic arm (230) is controlled to extend and rotate so that the end effector (240) is directed toward the storage box (120).

4. The method according to claim 1, characterized in that, To allow the end effector (240) located at the end of the robotic arm (230) to extend into the storage box (120) to grasp the target material, and to obtain the grasping result, including: Control the robotic arm (230) to drive the end effector (240) to move horizontally toward the storage box (120), so that the end effector (240) extends into the interior of the storage box (120) from the aisle side of the shelf (100); The end effector (240) is controlled to perform an adsorption operation, a clamping operation, or a combination of adsorption and clamping operation on the target material to obtain a grasping result.

5. The method according to claim 4, characterized in that, The grasping result is subjected to image detection processing, and the picking result corresponding to the picking task is determined based on the image detection result, including: Turn on the second light source installed on the robotic arm (230), and use the second vision recognition camera installed on the robotic arm (230) to acquire the target area image corresponding to the end effector (240); Based on the target area image corresponding to the end effector (240), it is determined whether the end effector (240) has grasped the target material; In response to the end effector (240) grasping the target material and meeting the preset grasping posture conditions, the picking result is determined to be a successful picking; In response to the end effector (240) failing to grasp the target material or not meeting the preset grasping posture conditions, the picking result is determined to be a picking failure.

6. The method according to claim 5, characterized in that, After determining that the picking result is successful, the process also includes: The robotic arm (230) is controlled to move the target material to the hopper (250) set on the mobile chassis (210), and the end effector (240) is controlled to release the target material. Turn on the second light source and control the second visual recognition camera to acquire the target area image corresponding to the material box (250); The target area image corresponding to the material bin (250) is compared with the preset area image, and the target material is determined to enter the material bin (250) based on the comparison result. In response to the target material entering the bin (250), the picking quantity corresponding to the target material is recorded, and the successful dispensing of the target material is confirmed. In response to the fact that the target material has not entered the hopper (250), it is determined that the material feeding has failed, and a feeding failure prompt message is generated.

7. The method according to claim 6, characterized in that, The method further includes: In response to the picking result being a picking failure or the target material feeding failure, a real-time video stream captured by the first visual recognition camera and / or the second visual recognition camera is acquired; The real-time video stream is sent to a pre-configured remote operation terminal, and control commands sent by a remote operator based on the remote operation terminal are received. According to the control instructions, the robotic arm (230) and the end effector (240) are controlled to re-execute the gripping or unloading process on the target material.

8. The method according to claim 6, characterized in that, The method further includes: In response to the fact that all target materials corresponding to the picking task have been successfully placed into the bin (250), the mobile chassis (210) is controlled to move to the packing station (260) set in the warehouse. The robotic arm (230) is controlled to transfer the target material in the hopper (250) to the packing table (260) for packing.

9. A picking control device (800), characterized in that, include: The determination module (801) is used to determine the storage box (120) corresponding to the target material in the picking task and the target picking path based on the received picking task; The gripping module (802) is used to control the mobile chassis (210) to move to the shelf (100) where the storage box (120) is located according to the target picking path, and to control the lifting module (220) and the robotic arm (230) to move together so that the end effector (240) set at the end of the robotic arm (230) extends into the interior of the storage box (120) to grip the target material and obtain the gripping result; The detection module (803) is used to perform image detection processing on the grasping result and determine the picking result corresponding to the picking task based on the image detection result.

10. An automated picking system, characterized in that, include: Automatic picking mechanism (200) and picking control device (800); The shelves (100) located on both sides of the warehouse aisle are equipped with multiple partitions (110), and each partition (110) is equipped with multiple storage boxes (120) for storing target materials. The automatic picking mechanism (200) includes a mobile chassis (210), a lifting module (220) is provided on the top of the mobile chassis (210), a robotic arm (230) is installed on the lifting module (220), and an end effector (240) is fixedly provided at the end of the robotic arm (230) away from the lifting module (220). The picking control device (800) determines the storage box (120) corresponding to the target material in the picking task and the target picking path based on the received picking task; according to the target picking path, it controls the mobile chassis (210) to move to the shelf (100) where the storage box (120) is located, and controls the lifting module (220) and the robotic arm (230) to move together so that the end effector (240) set at the end of the robotic arm (230) extends into the interior of the storage box (120) to grab the target material and obtain the grabbing result; it performs image detection processing on the grabbing result and determines the picking result corresponding to the picking task based on the image detection result.

11. The automatic picking system according to claim 10, characterized in that, The automatic picking mechanism (200) also includes a bin (250), which is fixedly or detachably installed on the mobile chassis (210), and the end effector (240) can release the grabbed material into the bin (250).

12. The automatic picking system according to claim 10, characterized in that, The upper surface of the mobile chassis (210) is provided with an installation platform (211), and the lifting module (220) is vertically fixed to the installation platform (211); and / or, the robotic arm (230) includes a robotic arm base, and the robotic arm base is installed on the lifting module (220).

13. The automatic picking system according to claim 12, characterized in that, The lifting module (220) includes a lifting column (221) and a slider that slides with the lifting column (221), and the robotic arm (230) is mounted on the slider.

14. The automatic picking system according to claim 11, characterized in that, The automated picking system also includes a packing station (260) located in the warehouse, which is used to receive boxes (250) transported by a mobile chassis (210). The packaging table (260) includes: a table frame, a support platform installed on the top of the table frame, a barcode scanning device installed above the support platform, the barcode scanning device being used to identify the material box (250), and a weighing device being provided inside or below the support platform, the weighing device being used to detect the weight of the material box (250).

15. An electronic device, characterized in that, include: One or more processors; Storage device for storing one or more programs. When the one or more programs are executed by the one or more processors, the one or more processors implement the method as described in any one of claims 1-8.

16. A computer-readable medium having a computer program stored thereon, characterized in that, When the program is executed by the processor, it implements the method as described in any one of claims 1-8.

17. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the method as described in any one of claims 1-8.

Images