Warehouse system and sorting method for picking work
The warehouse system optimizes picking operations by assigning tasks based on robot grasping success rates, addressing the inefficiencies in human-robot collaboration by ensuring that complex or difficult items are handled by the most capable worker or robot, thereby enhancing warehouse efficiency.
Patent Information
- Application Number
- PCT/JP2024/018473
- Authority / Receiving Office
- WO · WO
- Patent Type
- Applications
- Current Assignee / Owner
- Priority Date
- 2023-05-31
- Filing Date
- 2024-05-20
- Publication Date
- 2024-12-05
AI Technical Summary
Automated warehouses face inefficiencies in picking operations due to the differing capabilities of humans and robots, with robots being less effective on complex or soft products and humans being less efficient on heavy or complex items, necessitating a method to optimally allocate tasks between them.
A warehouse system that acquires the grasping success rate of robots and assigns picking tasks based on this rate, using a processor and memory to determine whether a robot or human should handle a task, with the option to adjust the grasping success rate based on product characteristics and operational conditions.
This approach improves the efficiency of picking operations by appropriately sorting tasks between humans and robots, ensuring that complex or difficult items are handled by the most capable worker or robot, enhancing overall warehouse productivity.
Smart Images

Figure JP2024018473_05122024_PF_FP_ABST
Abstract
Description
Warehouse system and sorting method for picking work
[0001] The present disclosure relates to a warehouse system and a method for sorting picking operations.
[0002] In recent years, automated warehouses for receiving and shipping packaged goods have become widespread. For example, Patent Literature 1 discloses a configuration for allocating tasks to individual workers in order to improve the efficiency of picking work by workers.
[0003] Japanese Patent Application Laid-Open No. 2020-128268
[0004] The present disclosure has been devised in view of the above-described conventional situation, and aims to achieve improved work efficiency related to picking work by workers and robots in warehouses.
[0005] The present disclosure provides a warehouse system having an acquisition unit that acquires a robot's gripping success rate for items that are the subject of a picking operation, and a sorting unit that assigns a worker for the picking operation to a person or the robot based on the gripping success rate.
[0006] The present disclosure also provides a method for sorting picking work, in which a processor and a memory work together to perform an acquisition process for acquiring a robot's gripping success rate for items that are the subject of a picking work, and a sorting process for assigning a worker for the picking work to a person or the robot based on the gripping success rate.
[0007] According to the present disclosure, it is possible to improve the efficiency of picking work by workers and robots in a warehouse.
[0008] FIG. 1 is a block diagram showing an example of a system configuration according to an embodiment of the present invention; FIG. 2 is a block diagram showing an example of a configuration of an information processing device that can be used in a system according to an embodiment of the present invention; FIG. 3 is a schematic diagram showing an example of a configuration inside a warehouse according to an embodiment of the present invention; FIG. 4 is a table showing an example of a data configuration according to an embodiment of the present invention; FIG. 5 is a table showing an example of a data configuration according to an embodiment of the present invention;
[0009] (Background to the Contents of Each Embodiment) Warehouses that handle receiving, storing, packaging, shipping, and the like of packages require automation using robots and the like to reduce the manual workload. With the recent increase in packages, further efficiency improvements in a series of operations are required. In such warehouses, items (hereinafter also referred to as "products") with various shapes, attributes, and other characteristics are handled, so it is necessary for people and robots to share and perform tasks while taking into consideration the characteristics of the products. One such task is picking, based on shipping instructions, from a storage unit where products are stored (hereinafter referred to as a "storage bin") to a storage unit (hereinafter referred to as a "shipping bin") that will store one or more products to be shipped.
[0010] Humans and robots, the main workers performing the picking work, have different strengths and weaknesses when it comes to picking work. For example, robots can handle products with simple shapes, but for products with complex shapes, such as products with few flat surfaces or products made of soft materials, picking by humans may be more efficient. On the other hand, for products that are above a certain weight or size, picking by robots may be more efficient.
[0011] Therefore, in the following embodiment, an example of a system and control method for assigning appropriate tasks to workers in order to perform picking work efficiently will be described.
[0012] Hereinafter, with reference to the drawings as appropriate, detailed descriptions of embodiments that specifically disclose systems and control methods according to the present disclosure will be provided. However, unnecessary detailed descriptions may be omitted. For example, detailed descriptions of well-known matters or redundant descriptions of substantially identical configurations may be omitted. This is to avoid unnecessary redundancy in the following description and to facilitate understanding by those skilled in the art. Note that the accompanying drawings and the following description are provided to enable those skilled in the art to fully understand the present disclosure, and are not intended to limit the subject matter recited in the claims.
[0013] <First Embodiment> [System Configuration] Fig. 1 is a block diagram showing an overall overview of a warehouse system 1 according to this embodiment. Note that the system configuration shown in Fig. 1 is an example, and one system may be divided into multiple systems, or multiple systems may be integrated into one system. Also, one system or device shown in Fig. 1 may be provided multiple times. Furthermore, the processing entities shown below are an example, and some of the functions of one system may be realized as functions of another system.
[0014] The warehouse system 1 includes a warehouse management system 100, a warehouse operations management system 200, warehouse control systems 300, 400, and 500, a robot 600, an automated warehouse 700, an automated guided vehicle 800, and an operation terminal 900. Each component of the warehouse system 1 is configured to be able to communicate with each other via a network. The warehouse management system 100 is a system that manages and controls logistics within a warehouse and is positioned at the highest level in the configuration example shown in FIG. 1 . The warehouse management system 100 manages, for example, inventory management of items within the warehouse, as well as the inflow and outflow (receiving and shipping) and movement of items. The warehouse management system is sometimes referred to as a WMS (Warehouse Management System). The warehouse management system 100 may be configured to be able to communicate with external systems not shown in FIG. 1 to acquire and manage instructions related to the inflow and outflow of goods, product information, information about warehouse equipment such as robots, and information about workers.
[0015] The warehouse operations management system 200 is a system that manages and controls work within a warehouse, and in the example configuration shown in Fig. 1, is positioned below the warehouse management system 100. The warehouse operations management system is sometimes referred to as a WES (Warehouse Execution System). The warehouse operations management system 200 comprehensively controls, for example, the work content of various work entities within the warehouse and the equipment within the warehouse.
[0016] The warehouse control systems 300, 400, and 500 manage and control various pieces of equipment in the warehouse. The warehouse control system may also be referred to as a WCS (warehouse control system). In the example configuration shown in FIG. 1 , the warehouse control systems 300, 400, and 500 manage and control the robot 600, the automated warehouse 700, and the automated guided vehicle 800, respectively. The robot 600 is equipped with, for example, a direct-travel mechanism or a multi-axis arm and is configured to be able to hold products at its tip. The tip of the robot 600 may have, for example, a suction mechanism or a multi-fingered gripping mechanism, but is not particularly limited thereto. Multiple types of robots 600 may be installed in the warehouse to accommodate picking operations for various products. Furthermore, a camera may be installed around the robot 600 to capture images of the surrounding area, particularly images of bins placed nearby.
[0017] The automated warehouse 700 is configured to be able to store multiple bins, and transports the bins using an automated guided vehicle 800 as required. Note that the method of transporting the bins is not limited to using the automated guided vehicle 800. For example, the bins may be transported using a belt conveyor or the like. The automated warehouse 700 is configured, for example, with a lattice frame so that multiple bins can be stored. Examples of bins stored in the automated warehouse 700 include storage bins for storing products. The storage bins may also include empty bins that do not contain any products, or bins for which no products have been determined to be stored. Note that the bins used in the automated warehouse 700 also include shipping bins for bundling products together before shipping. The shapes and dimensions of the storage bins and shipping bins may differ, but they are configured to be transportable by the automated guided vehicle 800, and will be described here as having the same rectangular box-shaped configuration.
[0018] Automated guided vehicle 800 is a vehicle for transporting bins to a predetermined location, and automatically moves or waits based on instructions. Automated guided vehicle 800 may be configured to detachably mount bins on its top, or may be configured to transport bins by pushing or pulling them. Automated guided vehicle 800 is configured to include, for example, a traveling unit for performing operations related to movement, sensors for acquiring peripheral information, and a communication unit for transmitting and receiving data to and from warehouse control system 300, etc.
[0019] The operation terminal 900 is an information processing device configured to be usable by workers both inside and outside the warehouse. The operation terminal 900 may be, for example, a stationary information processing device such as a PC (Personal Computer), or may be a mobile terminal such as a tablet terminal, POS terminal, handheld terminal, or smartphone. The operation terminal 900 transmits and receives data to and from the warehouse management system 100, warehouse operations management system 200, warehouse control systems 300, 400, and 500, and is used to receive notifications from each system and to configure and operate each system.
[0020] (Hardware Configuration Example) Each system shown in FIG. 1 may be configured as an on-premise server device at a base where a warehouse is located, or may be configured as a cloud-based system on a network. FIG. 2 is a diagram showing an example of the hardware configuration of an information processing device that can be used as a device constituting each system. Here, the devices constituting each system are described as having the same configuration, but some components may be omitted or other components may be added depending on the functions provided. An example of a component that may be added is a barcode reader used to acquire information from barcodes attached to products and bins in the warehouse.
[0021] The information processing device 10 includes a processing device 11, a storage device 12, a communication device 13, an input device 14, an image acquisition unit 15, an external interface 16, and a display device 17. Each component is configured to be able to communicate via an internal interface 18. The processing device 11 may be configured using, for example, a central processing unit (CPU), a graphic processing unit (GPU), a micro processing unit (MPU), a digital signal processor (DSP), or a field-programmable gate array (FPGA). The processing device 11 realizes various functions described below by, for example, referencing various databases (hereinafter, referred to as DBs) stored in the storage device 12 or reading programs. The storage device 12 is a storage unit for storing various data, programs, etc., and may be composed of volatile / non-volatile storage devices such as RAM (Random Access Memory), ROM (Read Only Memory), and HDD (Hard Disk Drive).
[0022] The communication device 13 is an interface for communicating with external devices via the network 35. There are no particular limitations on the communication standards that can be supported by the communication device 13, and the communication standards may be wired or wireless. The communication device 13 may also be capable of supporting multiple communication standards. Therefore, the network 35 may be configured by combining networks based on multiple communication standards.
[0023] The input device 14 accepts operations and instructions from warehouse users (e.g., managers and workers). The input device 14 may be composed of a mouse, a keyboard, a touch panel display, etc. The image acquisition unit 15 is an interface for acquiring images of the warehouse interior from cameras 30 installed in the warehouse. The external interface 16 is an interface for communicating with an external system 20. The external system 20 may be communicatively connected via the communication device 13 and a network 35. The external system 20 is not limited to the systems shown in FIG. 1 , and may be another system. The display device 17 displays various user interfaces to the user. The display device 17 may be composed of a liquid crystal display, a touch panel display, a lamp, etc.
[0024] 3 is a conceptual diagram showing an example of the configuration inside a warehouse of the warehouse system 1 according to this embodiment. An automated warehouse 700 and one or more robots 600 are installed inside the warehouse. Also, a plurality of automated guided vehicles 800 that transport bins are arranged in a drivable manner inside the warehouse.
[0025] A work area 830 is configured around the automated warehouse 700 where a worker 850, who will be the main operator of the picking work, will work. A work area is also provided where the robot 600 will work. A bin arrangement is determined to make it more efficient for the operator to move products from the storage bins to the shipping bins. Furthermore, from the perspective of improving the efficiency of the entire shipping work, if it is desirable to temporarily wait for a bin instead of moving it into the automated warehouse 700, a waiting area 840 is provided for waiting the bin. Hereinafter, the area where picking work is performed may be referred to as a picking station.
[0026] 3 shows an example in which one area for the human worker 850 to work and one area for the robot 600 to work are provided, but this is not limiting. Multiple areas of each type may be provided. Alternatively, only one area for the human worker or one area for the robot to work may be provided. Furthermore, although an example in which the robot 600 equipped with a direct mechanism is provided is shown, a robot equipped with a multi-axis arm may also be provided.
[0027] [Data Configuration Example] An example of the data configuration according to this embodiment will be described using Figures 4 and 5. Here, the description focuses on one shipping instruction. One shipping instruction, i.e., one shipping bin, can contain multiple products and multiple types of products. Since this information is included in one shipping instruction, one shipping instruction is divided into sections for each product.
[0028] 4A shows an example of the configuration of shipping information 40, which shows records for each product in a shipping instruction where three products, A, B, and C, are specified as products to be shipped in one shipping instruction. Each record includes the following fields: shipping destination 40a, shipping product ID 40b, quantity 40c, and scheduled shipping date 40d.
[0029] 4B shows shipping information 41 in which a field indicating the picking operator has been added to each record of the shipping information 40 shown in FIG. 4A. Each record includes a field for a shipping destination 41a, a shipping product ID 41b, a quantity 41c, a scheduled shipping date 41d, and a field for a picker 41e.
[0030] The picker 41e indicates a worker who picks products from storage bins to shipping bins. The picker 41e may further include information such as the picking station where the worker performs the work. In the example of FIG. 4(b), the picking work indicated in record 41f is assigned to "Robot A." The picking work indicated in record 41g is assigned to "Robot B." The picking work indicated in record 41h is assigned to "Worker," i.e., a person.
[0031] FIG. 5A shows an example of the data structure of product information, which is an example of product information. The product information 50 includes a product ID 50a, a product classification 50b, dimensions 50c, weight 50d, inventory quantity 50e, and a storage bin 50f. The product ID 50a is identification information for uniquely identifying a product. The product classification 50b indicates a predefined product classification. The product classification may indicate a commercial classification, such as food or furniture, or may be a classification defined in association with information related to picking work. Examples of information related to picking work include the product's surface shape, softness, and material. These attributes affect the product's slipperiness and the limit of force required to grasp the product without damaging it, thereby affecting the difficulty of grasping. The dimensions 50c indicate the product's dimensions. The inventory quantity 50e indicates the inventory quantity of the product in the warehouse. Note that the same product may be stored in different storage bins. In such cases, the total inventory quantity may be displayed. Alternatively, the inventory quantity may be displayed for each storage bin containing the same product. The storage bin 50f is identification information for uniquely identifying the storage bin in which the product is stored.
[0032] FIG. 5B shows an example of the data structure of station information related to a picking station where picking work is performed. The station information 51 includes a station ID 51a, a picker 51b, an arm configuration 51c, a tip configuration 51d, and an operating rate 51e. The station ID 51a is identification information for uniquely identifying the picking station. The picker 51b indicates the worker performing the picking work at the picking station. For example, if the worker is a human, "Worker" is set, and if the worker is a robot, the identification information is set. The arm configuration 51c indicates information related to the arm configuration if the worker at the picking station is a robot. Examples of the robot's arm configuration include an articulated arm and an orthogonal arm. The tip configuration 51d indicates information related to the configuration of the tip of the robot if the worker at the picking station is a robot. Examples of the robot's tip configuration include a suction arm and a multi-fingered hand. The operating rate 51e indicates the current operating rate of the picking station. The utilization rate may be calculated, for example, by calculating the ratio of the number of assigned picking operations to a preset number of picking operations (for example, the number that can be processed within a predetermined time).
[0033] FIG. 5C shows an example of the data structure of robot information in which a gripping success rate for each product or product category is specified for the robot 600 performing the picking operation. The robot information 52 includes a robot ID 52a, a product ID 52b, a product category 52c, and a gripping success rate 52d. The robot ID 52a is identification information for uniquely identifying the robot 600. The product ID 52b is identification information for uniquely identifying the product and corresponds to the product ID 50a in the product information 50 shown in FIG. 5A. The product category 52b indicates a predefined product category and corresponds to the product category 50b shown in FIG. 5A. The gripping success rate 52d indicates the probability that the robot 600 successfully grips the corresponding product or product category when attempting to grip it. The gripping success rate may be, for example, the probability that the robot 600 is successful after performing a predetermined number of gripping operations (e.g., one time). In this embodiment, it is assumed that the gripping success rate is set for either the product or the product category. That is, the gripping success rate of the robot 600 is set for each type of article or each classification of articles.
[0034] [Processing Flow] The sorting process for picking work according to this embodiment will be described below with reference to Fig. 6. Fig. 6 is a flowchart for explaining the flow of the sorting process for picking work at the time of shipping of products by the warehouse operations management system 200 in the warehouse system 1 according to this embodiment. Note that in this example, the processing is performed by the warehouse operations management system 200, but some functions may be performed by other systems.
[0035] The warehouse operations management system 200 receives a shipping instruction from the warehouse management system 100, which is a higher-level system (step S601).
[0036] The warehouse operations management system 200 breaks down the shipping instructions received in step S601 into individual products and registers the picking work for each product (step S602). As a result of this process, shipping information such as that shown in Figure 4(a) is generated.
[0037] The warehouse operations management system 200 focuses on unsorted products, i.e., products for which the allocation of picking work has not been completed, for the picking work for each product generated in step S602 (step S603).
[0038] The warehouse operations management system 200 acquires the grasping success rate of each robot for the product focused on in step S603 (step S604). The grasping success rate is acquired from the robot information 52 shown in FIG. 5(c). If the grasping success rate for the product corresponding to the robot information 52 is not registered, the warehouse operations management system 200 refers to the product information 50 shown in FIG. 5(a) to identify the product classification of the product. The warehouse operations management system 200 then acquires the grasping success rate of each robot for the product classification. This makes it possible to identify the grasping success rate by using the product classification, even if individual grasping success rates for a huge group of products are not registered. If multiple picking stations are installed in a warehouse, it is also possible to acquire only information from picking stations that are capable of sorting picking operations.
[0039] The warehouse operations management system 200 acquires shipping conditions for the target product (step S605). The shipping conditions here include, for example, conditions regarding the operation status of robots and humans picking operations, the time required for picking operations, the urgency of shipping instructions, etc. These conditions are assumed to be defined in advance and registered in the warehouse operations management system 200, etc.
[0040] The warehouse operations management system 200 determines a threshold value for the gripping success rate based on the shipping conditions acquired in step S605 (step S606). For example, if the shipping instruction is highly urgent, the threshold value for the gripping success rate is also determined to be high. Furthermore, if the picking work is performed during late night hours, for example, the system determines a low threshold value for the gripping success rate because it is desirable to have the robot perform as much of the work as possible rather than a human. Furthermore, by comparing the operating rates of the robot and the human picking work, if the operating rate of the robot appears to be lower, the system determines a low threshold value for the gripping success rate because it is desirable to have the robot perform as much of the work as possible rather than a human.
[0041] The warehouse operations management system 200 determines whether there is a robot 600 whose gripping success rate acquired in step S604 exceeds the threshold value set in step S606 (step S607). If there is a robot 600 whose gripping success rate exceeds the threshold value (step S607: YES), the processing of the warehouse operations management system 200 proceeds to step S609. On the other hand, if there is no robot 600 whose gripping success rate exceeds the threshold value (step S607: NO), the processing of the warehouse operations management system 200 proceeds to step S608.
[0042] The warehouse operations management system 200 assigns the picking work for the focused product to a person (step S608). If there are multiple picking stations where people are responsible for the work, the warehouse operations management system 200 may assign the picking work for the focused product to the picking station with the lowest operating rate, or to a picking station where a pre-designated worker is working. Then, the processing of the warehouse operations management system 200 proceeds to step S612.
[0043] The warehouse operations management system 200 determines whether there is one robot 600 with a gripping success rate exceeding the threshold (step S609). If there is one robot 600 (step S609: YES), the process of the warehouse operations management system 200 proceeds to step S610. On the other hand, if there are multiple robots 600 (step S609: NO), the process of the warehouse operations management system 200 proceeds to step S611.
[0044] The warehouse operations management system 200 assigns the picking work for the selected product to the robot 600 having a gripping success rate exceeding the threshold (step S610). Then, the process of the warehouse operations management system 200 proceeds to step S612.
[0045] The warehouse operations management system 200 assigns the picking task for the target product to the robot 600 with the lowest operating rate among the robots 600 with a gripping success rate exceeding the threshold (step S611). Then, the process of the warehouse operations management system 200 proceeds to step S612.
[0046] The warehouse operations management system 200 determines whether there are any unsorted products (step S612). If there are any unsorted products (step S612: YES), the warehouse operations management system 200 returns to step S603 and repeats the process focusing on the unsorted products. On the other hand, if there are no unsorted products (step S612: NO), this process flow ends.
[0047] After this processing flow is completed, the warehouse operations management system 200 will send picking work instructions to each robot or person who sorted the items.
[0048] As described above, the warehouse system (e.g., 1) according to this embodiment includes an acquisition unit (e.g., 200, 10, 11) that acquires the gripping success rate of a robot (e.g., 600) for items to be picked, and a sorting unit (e.g., 200, 10, 11) that assigns picking tasks to people or robots based on the gripping success rate. This configuration improves the efficiency of picking tasks performed by workers and robots in the warehouse. In particular, it enables more appropriate sorting of items for picking tasks for people and robots.
[0049] The warehouse system further includes a determination unit (e.g., 200, 10, 11) that determines a threshold value for the success rate of picking based on conditions related to the picking work, and the sorting unit assigns picking tasks to people or robots based on the success rate of picking and the threshold value. This enables more appropriate sorting of products for picking work for people or robots.
[0050] The acquisition unit acquires the gripping success rate for each of the plurality of robots for the item. This configuration enables sorting of picking work based on the gripping success rate for each robot for the item.
[0051] Furthermore, the gripping success rate is set for each robot, either for each type of product or for each category of product. This configuration allows the gripping success rate to be specified for each product type or category, enabling more flexible sorting.
[0052] Furthermore, if there is no robot with a gripping success rate exceeding the threshold, the sorting unit assigns the picking work to a human. With this configuration, it is possible to assign the picking work to a human for products that are difficult for a robot to pick.
[0053] The conditions are conditions for at least one of the operating status of the robot and human picking work, the time for the picking work, and the urgency of the shipping instruction. This configuration makes it possible to sort picking work based on conditions that assume the situation when the picking work is performed.
[0054] <Embodiment 2> Hereinafter, embodiment 2 will be described as another embodiment of the present invention. Note that description of configurations that overlap with embodiment 1 will be omitted, and the description will focus on the differences. Since the system configuration and the like are the same as embodiment 1, description thereof will be omitted.
[0055] In the first embodiment, sorting was performed using a threshold value for the gripping success rate. The robot's gripping success rate can vary depending on the condition of the products in the storage bin. For example, if the products in the storage bin are unevenly stored, the gripping success rate may decrease depending on the position of the products. Alternatively, the gripping success rate may vary depending on whether the products in the storage bin are standing or lying down. In this embodiment, a configuration is described in which the gripping success rate set for each product, etc., is corrected depending on the condition of the products in the storage bin, and then used for sorting.
[0056] (Correction Information Generation Process) FIG. 7 is a flowchart of the process for generating correction information for the grasping success rate according to this embodiment. In this embodiment, this process flow is described assuming that the warehouse operations management system 200 is the processing entity, but some functions may be configured to be executed by other systems. This process flow may be executed each time a picking operation is performed. Alternatively, this process flow may be executed at a predetermined timing for images of the inside of the storage bin and the results of the picking operation, which are associated and stored.
[0057] The warehouse operations management system 200 acquires an image of the storage bin in which the product to be picked is stored (step S701). The image of the storage bin may be acquired, for example, via a camera 30 installed near the robot 600 immediately before the robot 600 performs the picking operation.
[0058] The warehouse operations management system 200 analyzes the image acquired in step S701 and derives the state of the product in the storage bin (step S702). The state of the product derived here may be the position or orientation within the storage bin. Furthermore, it is not necessary to derive the state of all products stored in the storage bin from the image; the state of only the products that are the target of picking may be derived.
[0059] The warehouse operations management system 200 acquires the gripping result of the robot 600 for the product in the storage bin (step S703). The gripping result here may be information indicating how many times the robot 600 has performed a gripping operation on the product in the storage bin before successfully gripping the product.
[0060] The warehouse operations management system 200 determines correction information based on the gripping result acquired in step S703 (step S704). For example, if the gripping result indicates that the robot 600 can grip the product correctly on the first try, correction information may be determined as not requiring correction. On the other hand, if the robot 600 can grip the product correctly after multiple attempts, correction information may be determined based on the number of attempts.
[0061] The warehouse operations management system 200 stores the correction information determined in step S704 and the product status information derived in step S702 in association with each other (step S705), and then ends this processing flow.
[0062] (Sorting Process) Figure 8 is a flowchart for explaining the flow of sorting process for picking work at the time of shipping of products by the warehouse operations management system 200 in the warehouse system 1 according to this embodiment. This process flow differs from the sorting process flow shown in Figure 6 according to the first embodiment in steps S801 to S803. The same process steps are indicated by the same reference numbers.
[0063] After the process of step S604, the warehouse operations management system 200 acquires status information of the storage bin in which the target product is stored (step S801). The storage information may be information derived and managed from an image acquired when the previous picking operation for the storage bin was completed. Alternatively, the storage information may be acquired by taking a new image of the storage bin at that time and analyzing the image.
[0064] The warehouse operations management system 200 acquires correction information corresponding to the status information acquired in step S802 (step S802). Since the status information and correction information are associated and stored by the correction information generation process shown in Fig. 7, the correction information is acquired by referring to this. Note that if correction information corresponding to the status information is not stored, the process may proceed assuming that correction of the gripping success rate is not necessary.
[0065] The warehouse operations management system 200 corrects the grasping success rate of the robot 600 acquired in step S604 based on the correction information acquired in step S803 (step S803). Then, the processing of the warehouse operations management system 200 proceeds to step S605. The subsequent processing is performed using the grasping success rate corrected based on the correction information.
[0066] As described above, the warehouse system according to the present embodiment further includes a generation unit (e.g., 200, 10, 11) that generates correction information based on an image of a storage bin (e.g., 810) containing items to be picked and the results of the robot picking the items from the storage bin, and a correction unit (e.g., 200, 10, 11) that corrects a threshold value using the correction information. The sorting unit assigns workers using the threshold value corrected by the correction unit. This configuration makes it possible to adjust the gripping success rate depending on the situation when the picking operation is performed, enabling more appropriate sorting of the picking operation.
[0067] (Other Modifications) In the second embodiment, a configuration has been described in which the gripping success rate is corrected depending on the results of the picking operation. In this case, if it is detected that a robot has failed to grip a certain product after a predetermined number of picking operations, the robot may be controlled not to sort the product in subsequent sorting operations. In such a case, the configuration may be such that a user (manager or worker) is notified of the fact.
[0068] In the above embodiment, a configuration in which sorting processing is performed using a threshold value based on shipping conditions has been described. However, this configuration is not limited to this, and some functions may be realized using a trained model obtained through a learning process. For example, regarding setting a threshold value for the gripping success rate, a trained model obtained as a result of a certain learning process may be used, with the operating status of each picking station, the picking operation time, and the urgency of the shipping instruction as input data, and the threshold value for the gripping success rate as output data. Alternatively, instead of setting a gripping success rate in advance, a trained model may be used as a result of a certain learning process with images of the storage bin, product information, and robot information as input data, and the gripping success rate as output data.
[0069] It is assumed that the above-described learning process is executed in advance, and a trained model is generated so that it can be used at the time of sorting. Furthermore, in the warehouse system 1, the above-described process is intermittently repeated, and various data obtained during the process may be acquired as training data and used in the learning process to update the trained model. Furthermore, the learning algorithm used in the learning process is not particularly limited, and may be selected depending on the training data and process used.
[0070] In each of the above embodiments, individual workers may be assigned as pickers. In this case, the products to be assigned to each worker may be further assigned based on the worker's attributes. Examples of worker attributes include the worker's physical ability and years of work experience. In this case, the strengths and weaknesses of each worker may be estimated from their work history, and the products to be assigned to each worker may be determined based on the estimation results. This information can be collected, for example, by measuring the time required for each worker to perform each task for each product.
[0071] Furthermore, the data configuration examples of the product information in each of the above embodiments are merely examples, and each piece of information may be provided from a separate database. For example, information used primarily in the warehouse and information used outside the warehouse, such as in a retail store, may be provided from separate databases. An example of information used primarily in the warehouse is information about storage bins. An example of information used outside the warehouse is a product ID for uniquely identifying a product. Here, the information used outside the warehouse may be obtained from a database provided by an entity other than the entity operating the warehouse, such as a retail store or a product manufacturer.
[0072] In addition, in each of the above embodiments, warehouse users may be able to manually set the gripping success rate for each product. In this case, a predetermined meaning may be assigned to the value of the gripping success rate. For example, the gripping success rate for a product that must be handled by a human may be set to "0." This prevents a robot from being selected to handle that product. Similarly, for a product that must be handled by a specific robot, the gripping success rate for that robot may be set to "100." In other words, the gripping success rate does not necessarily reflect the success or failure of past gripping attempts, but may instead be the priority of the robot's gripping, which can be determined by the warehouse user's will. Note that in each of the above embodiments, the gripping success rate is set for each product. Therefore, this modification allows for detailed setting of whether the work of a worker or a robot should be prioritized for each product.
[0073] In each of the above embodiments, a warehouse user may be able to manually set the threshold value for the grasping success rate. In this case, for example, if a warehouse user wants all products to be handled by a worker, the threshold value may be set to "100," and if a warehouse user wants all products to be handled by a robot, the threshold value may be set to "0." In each of the above embodiments, a common threshold value is used for all products. Therefore, according to this modification, it is possible to adjust, for all products at once, whether the work of a worker or a robot is to be prioritized.
[0074] However, the ranges for setting the gripping success rate and threshold value in the above-described embodiment and modified examples are merely examples. That is, a threshold value may be set for each product, or the same gripping success rate may be set for all products. While the above-described embodiment describes a configuration in which the gripping success rate is used as an index for sorting, this is not limiting. For example, a configuration may be adopted in which sorting of picking work is performed using an evaluation value (e.g., sorting priority) or a threshold value for the combination of the robot 600 and the product.
[0075] Furthermore, in each of the above embodiments, picking tasks are assigned to humans or robots based on the results of comparing the robot's success rate in grasping each product with a threshold value based on the conditions related to the picking task. However, if control taking into account the conditions of the picking task is not necessary, a configuration without a threshold value may be used. In this case, whether to assign a product to a robot may be determined probabilistically based on the grasping success rate. For example, if the grasping success rate is "80%," 80% of the total number of products may be assigned to the robot, and the remaining 20% may be assigned to humans. In this case, the assignment of tasks between humans and robots can also be adjusted according to the grasping success rate.
[0076] Furthermore, in each of the above-described embodiments, the objects of the picking operation are not limited to "products" that are commercially distributed. The configurations of the above-described embodiments can be applied to the picking operation of general items that may not be classified as "products," such as non-sale items and parts.
[0077] The present disclosure also applies to programs and storage media that realize the functions of the devices of the above-mentioned embodiments, which are supplied to the device via a network or various storage media and that are read and executed by a computer within the device.
[0078] Although various embodiments have been described above with reference to the drawings, it goes without saying that the present disclosure is not limited to these examples. It is clear to those skilled in the art that various modifications, alterations, substitutions, additions, deletions, and equivalents may be made within the scope of the claims, and it is understood that these also fall within the technical scope of the present disclosure. Furthermore, the components of the various embodiments described above may be combined in any manner without departing from the spirit of the invention.
[0079] (Additional Notes) The above description of the embodiments discloses the following techniques.
[0080] (Technology 1) A warehouse system having: an acquisition unit that acquires a robot's gripping success rate for items that are the subject of a picking operation; and a sorting unit that assigns a worker for the picking operation to a person or the robot based on the gripping success rate.
[0081] This configuration improves the efficiency of picking work by workers and robots in the warehouse, and in particular enables more appropriate sorting of products for picking work by people and robots.
[0082] (Technology 2) The warehouse system described in Technology 1 further includes a determination unit that determines a threshold value for the grasping success rate based on conditions related to the picking work, and the sorting unit assigns a worker for the picking work to a person or the robot based on the grasping success rate and the threshold value.
[0083] This configuration enables more appropriate sorting of products for picking tasks by humans and robots.
[0084] (Technology 3) The warehouse system according to Technology 2, wherein the acquisition unit acquires a grasping success rate for each of the plurality of robots with respect to the item.
[0085] This configuration makes it possible to sort picking operations based on the success rate of each robot in grasping products.
[0086] (Technology 4) The warehouse system according to Technology 2 or Technology 3, wherein the grasping success rate is set in association with the robot for each type of item and / or each classification of items.
[0087] This configuration allows the gripping success rate to be defined for each type of product or each product category, making sorting more flexible.
[0088] (Technology 5) The warehouse system according to any one of Technology 2 to Technology 4, wherein the sorting unit assigns the picking work to a human if there is no robot having a gripping success rate exceeding the threshold.
[0089] With this configuration, it is possible to assign the picking work to humans for products that are difficult for robots to pick.
[0090] (Technology 6) The warehouse system according to any one of Technology 2 to Technology 5, wherein the condition is a condition regarding at least one of an operation status of a robot and a human picking operation, an execution time of the picking operation, and an urgency of a shipping instruction.
[0091] This configuration makes it possible to sort picking work based on conditions that anticipate the situation when picking work is performed.
[0092] (Technology 7) A warehouse system according to any one of Technology 2 to Technology 6, further comprising: a generation unit that generates correction information based on an image of a storage bin containing an item to be picked and a result of a robot picking the item from the storage bin; and a correction unit that corrects the threshold determined by the determination unit using the correction information generated by the generation unit, wherein the sorting unit assigns workers to work using the threshold corrected by the correction unit.
[0093] This configuration makes it possible to adjust the gripping success rate depending on the situation when performing the picking work, allowing for more appropriate sorting of the picking work.
[0094] (Technology 8) A method for sorting picking work, comprising: an acquisition process in which a processor and a memory cooperate to acquire a robot's gripping success rate for an item to be picked; and a sorting process in which a worker for the picking work is assigned to a person or the robot based on the gripping success rate.
[0095] This configuration improves the efficiency of picking work by workers and robots in the warehouse, and in particular enables more appropriate sorting of products for picking work by people and robots.
[0096] The present disclosure is useful for a warehouse system and a sorting method for picking work in a warehouse.
[0097] DESCRIPTION OF SYMBOLS 1...Warehouse system 10...Information processing device 11...Processing device 12...Storage device 13...Communication device 14...Input device 15...Image acquisition unit 16...External interface 17...Display device 18...Internal interface 20...External system 30...Camera 35...Network 100...Warehouse management system 200...Warehouse operation management system 300, 400, 500...Warehouse control system 600...Robot 700...Automated warehouse 800...Automated guided vehicle 900...Operation terminal
Claims
1. A warehouse system having an acquisition unit that acquires a robot's gripping success rate for items that are the subject of a picking operation, and a sorting unit that assigns work for the picking operation to a person or the robot based on the gripping success rate.
2. The warehouse system according to claim 1, further comprising a determination unit that determines a threshold value for the picking success rate based on conditions related to the picking work, and the sorting unit assigns a worker for the picking work to a person or the robot based on the picking success rate and the threshold value.
3. The warehouse system according to claim 2, wherein the acquisition unit acquires the grasping success rate for the item for each of the multiple robots.
4. The warehouse system of claim 2, wherein the grasping success rate is set for each type of item or each classification of item.
5. The warehouse system according to claim 2, wherein the sorting unit assigns the picking task to a human if there is no robot with a gripping success rate exceeding the threshold.
6. The warehouse system according to claim 2, wherein the conditions relate to at least one of the operating status of the robot and human picking operations, the time during which the picking operations are carried out, and the urgency of the shipping instructions.
7. The warehouse system of claim 2, further comprising: a generation unit that generates correction information based on an image of the storage bin in which the item to be picked is stored and a result of the robot picking the item from the storage bin; and a correction unit that uses the correction information generated by the generation unit to correct the threshold determined by the determination unit; and wherein the sorting unit assigns workers for the picking work using the threshold corrected by the correction unit.
8. A method for sorting a picking operation, comprising: an acquisition step in which a processor and a memory cooperate to acquire a robot's gripping success rate for an item to be picked; and a sorting step in which a worker for the picking operation is assigned to a person or the robot based on the gripping success rate.
Citation Information
Patent Citations
Information processing apparatus, picking robot system, information processing method and information processing program
JP2020040159A
Information processing device, information processing method, program, and control system
JP2022100437A
Information processing method, program and information processing device
JP2023017393A
