Warehouse system and data collection method

Abstract

This warehouse system for collecting data pertaining to picking work by a picking robot comprises: an identification unit for identifying a time zone in which a free time in a work schedule of the picking robot in the warehouse system coincides with a free time in a work schedule of at least one of an operator or an unmanned carrier; a determination unit for determining a commodity for which data pertaining to the picking work is collected in the time zone; and an instruction unit for instructing the picking robot and at least one of the operator or the unmanned carrier to collect the data in the time zone by adjusting a control parameter of the picking work and performing the picking work for the commodity.

Description

Warehouse system and data collection method

[0001] The present disclosure relates to a warehouse system and a data collection method.

[0002] In recent years, automated warehouses for receiving and shipping packages containing packaged goods have become widespread. Furthermore, methods for adjusting the control parameters of robots operating in automated warehouses to allow the robots to perform picking tasks more appropriately have been studied. For example, Patent Literature 1 discloses a configuration for predicting the gripping point position of an item and parameters for trajectory planning when a robot arm grips a product by performing machine learning using collected data.

[0003] Japanese Patent Application Laid-Open No. 2018-202550

[0004] The present disclosure has been devised in view of the above-described conventional situation, and aims to realize more efficient collection of data related to robot picking operations in a warehouse.

[0005] The present disclosure provides a warehouse system that collects data related to picking work by a picking robot, the warehouse system having an identification unit that identifies a time period in which an available time in the work schedule of the picking robot in the warehouse system coincides with an available time in the work schedule of at least one of a worker and an automated guided vehicle; a determination unit that determines products for which the data will be collected during the time period; and an instruction unit that instructs at least one of the worker and the automated guided vehicle, and the picking robot, to collect the data by adjusting control parameters for the picking work and attempting the picking work on the products during the time period.

[0006] The present disclosure also provides a data collection method in which a processor and a memory work together to collect data related to picking work by a picking robot, the data collection method including: an identifying step of identifying a time period in which an available time in the work schedule of the picking robot in a warehouse system coincides with an available time in the work schedule of at least one of a worker and an automated guided vehicle; a determining step of determining products for which the data will be collected during the time period; and an instructing step of instructing at least one of the worker and the automated guided vehicle, and the picking robot, to collect the data by adjusting control parameters for the picking work and attempting the picking work on the products during the time period.

[0007] According to the present disclosure, it is possible to improve the efficiency of collecting data related to robot picking operations 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 flowchart of overall processing according to an embodiment of the present invention;

[0009] (Background to the Contents of Each Embodiment) Warehouses that handle receiving, storing, packing, 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") of various shapes and attributes 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 of the tasks performed in a warehouse 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] When a robot performs picking work, it is necessary to adjust the control parameters related to picking depending on the characteristics of the product. Products have a wide variety of characteristics, such as shape, and new products may be added one after another to be picked. In light of this situation, data is collected by repeatedly trying out picking work using various parameters to accommodate each product. The collected data is then used during actual shipping work to improve the performance of the robot's picking work.

[0011] On the other hand, because actual receiving and shipping work is being carried out on-site, it is desirable to collect data at a time that does not interfere with this work. Furthermore, because data collection requires coordination between people, robots, automated guided vehicles, and other workers in the automated warehouse, data collection must be carried out after properly understanding their schedules.

[0012] Therefore, in the following embodiments, an example of a warehouse system and a data collection method that can efficiently collect data related to picking work in an automated warehouse will be described.

[0013] Hereinafter, with reference to the drawings as appropriate, detailed descriptions of embodiments specifically disclosing the warehouse system and data collection method 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.

[0014] <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.

[0015] 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.

[0016] 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.

[0017] 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 configuration example 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 a picking robot equipped with, for example, a direct-travel mechanism or a multi-axis arm and configured 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 various product picking tasks. A camera may also be installed around the robot 600 to capture images of the surrounding area, particularly images of bins placed nearby.

[0018] 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 provided in the automated warehouse 700. 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. Storage bins may also include empty bins that do not contain products, or bins for which a product to be stored has not yet been determined. 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.

[0019] The automated guided vehicle 800 is a vehicle for transporting bins to a predetermined location and is also referred to as an AGV (Automatic Guided Vehicle). The automated guided vehicle 800 automatically moves, waits, and so on, based on instructions. The 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. The 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 the warehouse control system 300, etc.

[0020] 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.

[0021] (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.

[0022] 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).

[0023] 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.

[0024] 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.

[0025] The warehouse according to this embodiment is equipped with an automated warehouse 700 and one or more robots 600. In addition, a plurality of automated guided vehicles 800 for transporting bottles are arranged in the warehouse so that they can travel.

[0026] A work area (not shown) is configured around the automated warehouse 700 where workers, who act as the main workers in the warehouse, can perform their work. A work area (not shown) is also provided where the robot 600 can perform its work. In the work area, the workers perform picking work by moving products from storage bins to shipping bins, and people, the robot 600, the automated warehouse 700, and the automated guided vehicle 800 work in coordination. Hereinafter, the area where picking work is performed may be referred to as a picking station.

[0027] The work area for data collection, which will be described later, may be the same as or different from the work area for picking work related to actual warehousing and shipping. Furthermore, multiple work areas may be set up depending on the number of people and robots 600. Here, the description will be given assuming that the work area for picking work for data collection and the work area for picking work related to warehousing are the same.

[0028] [Schedule] A data collection schedule according to this embodiment will be described with reference to Fig. 3. Schedule 301 shown in the upper part of Fig. 3 is an example of conventional data collection. Conventionally, actual shipping work is performed in a certain work area, and data collection related to picking work is performed during times when actual shipping work is not being performed. In the example of schedule 301, shipping work is assigned from 9:00 to 18:00, and data collection is assigned from 18:00 to 5:00.

[0029] When data collection is performed, the control parameters of the robot 600 are adjusted and repeated trials are performed, which may result in the robot 600 dropping products, malfunctioning, or damaging products during the picking operation. Human monitoring and response are required to anticipate such situations. For example, if only the data collection time period, such as schedule 301, were to be performed, the workload of humans late at night would increase. In an actual work site, shipping operations are not always being performed, and there will be idle time for the warehouse staff, the robot 600, and the automated guided vehicle 800.

[0030] Therefore, in this embodiment, free time in the schedules of the parties that should cooperate to perform the picking work is captured, and data collection is performed efficiently. Schedule 302 shown in the lower part of Fig. 3 shows an example of data collection according to this embodiment. In particular, the timing during the time period from 9:00 to 18:00 when data collection is possible without affecting the actual shipping work is captured, and data collection is performed at this timing.

[0031] For example, the time period from 11:00 to 13:00 indicates a time period in which no worker is performing shipping work. Furthermore, the time period from 14:00 to 16:30 indicates a time period in which only some robots 600 are performing shipping work, and no other robots 600 or humans are performing shipping work. In such a time period, a schedule can be set that allows for data collection by the robots 600 during the free time in parallel with shipping work, and for human monitoring of the data collection. Note that human monitoring here also includes taking measures such as moving or sorting the product if the robot 600 performs a picking work and collects data while adjusting parameters, and the target product falls out of the bin or is damaged.

[0032] [Processing Flow] The data collection process according to this embodiment will be described below with reference to FIGS.

[0033] (Overall Processing) Fig. 4 is a flowchart for explaining the flow of data collection processing 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 executed by other systems in the configuration example shown in Fig. 1. Furthermore, this processing flow may be executed for each work area where a robot 600 is installed, or may be executed collectively for multiple work areas.

[0034] The warehouse operations management system 200 receives shipping instructions for a certain period of time from the warehouse management system 100 (step S401). The shipping instructions here may be, for example, shipping instructions for one day. Before specifying the schedule for data collection, it is assumed that the schedule and allocation related to the shipping instructions for products have already been generated and are available for reference.

[0035] The warehouse operations management system 200 calculates the idle time of the robot 600 based on the shipping instruction acquired in step S401 (step S402). The idle time corresponds to a time period when the robot 600 is not performing a series of picking operations. As described above, data collection according to this embodiment is performed during a time period that does not interfere with shipping operations.

[0036] The warehouse operations management system 200 calculates the time required to collect data on the products that are the subject of data collection (step S403). The products that are the subject of data collection here may be products for which the robot 600 has attempted to pick them a predetermined number of times or less, or products for which picking has failed based on past operation history. These products may be managed using a list, etc. An example of this list will be described later using Table 1. The time required to collect data may be set taking into consideration not only the series of picking operations of the robot 600, but also the movement time of the storage bins containing the products and the movement time of the supervisor. The time may be determined in advance depending on the configuration of the robot 600 performing the picking operation.

[0037] The warehouse operations management system 200 determines whether a time is available for data collection by the robot 600 based on the available time calculated in step S402 and the time calculated in step S403 (step S404). Here, the warehouse operations management system 200 may determine whether time is available for data collection by one robot 600 in the schedule defined based on the shipping instruction, or may determine whether data collection is available by any of multiple robots 600. Furthermore, the warehouse operations management system 200 may determine that data collection is available during a certain time period by taking into account the processing load of the robot 600 during that time period if the shipping task itself is included but the workload of the robot 600 is low. If a time is available for data collection (step S404: YES), the warehouse operations management system 200 proceeds to step S405. On the other hand, if a time is not available for data collection (step S404: NO), the warehouse operations management system 200 proceeds to step S420.

[0038] The warehouse operations management system 200 determines whether or not to use an automated guided vehicle 800 to transport the products for which data is to be collected (step S405). Transporting the products here corresponds to transporting storage bins and bins to which the products will be moved. If the automated guided vehicle 800 will be used (step S405: YES), the processing of the warehouse operations management system 200 proceeds to step S406. On the other hand, if the automated guided vehicle 800 will not be used (step S405: NO), the processing of the warehouse operations management system 200 proceeds to step S414.

[0039] The warehouse operations management system 200 compares the free time of the robot 600 calculated in step S402 with the free time of the automated guided vehicles 800 that can transport the products that are the subject of data collection (step S406). If there are multiple automated guided vehicles 800 that can transport the products that are the subject of data collection, the free time is identified from the operation schedule of at least one of the automated guided vehicles 800 and compared.

[0040] As a result of the comparison process in step S406, the warehouse operations management system 200 determines whether there are any time slots with matching free times in the schedules of the robot 600 and the automated guided vehicle 800 (step S407). If there are any matching free times (step S407: YES), the processing of the warehouse operations management system 200 proceeds to step S408. On the other hand, if there are no matching free times (step S407: NO), the processing of the warehouse operations management system 200 proceeds to step S414.

[0041] The warehouse operations management system 200 calculates the amount of time each item requires manual supervision based on the data collection status (step S408). For example, for items that have a high probability of being picked successfully based on historical information about past picking operations, the amount of time that manual supervision is required may be set to zero or a predetermined short time. The historical information used for this determination may be the same as the information used in step S403, and an example of this information will be described later in Table 1.

[0042] The warehouse operations management system 200 calculates available free time in the worker's schedule as monitoring time based on the time calculated in step S408 (step S409). Note that if it is determined in step S408 that data collection is possible without the need for worker monitoring, the calculation of available free time in the worker's schedule may be omitted.

[0043] Based on the free time in the schedule calculated up to this point, the warehouse operations management system 200 determines whether there are any products that can be monitored by an operator (step S410). In other words, it determines the time period in which the free time of the operator coincides with the time required for monitoring during data collection. For example, even if a product requires data collection, monitoring is not possible if the storage bin containing the product is being used for other shipping operations. Furthermore, for products that have been picked with high accuracy in past picking operations, monitoring by an operator may be omitted or they may be treated as products for which data collection can be performed in a short time. If there are any products that can be monitored (step S410: YES), the warehouse operations management system 200 proceeds to step S411. On the other hand, if there are no products that can be monitored (step S410: NO), the warehouse operations management system 200 proceeds to step S420.

[0044] The warehouse operations management system 200 instructs the automated guided vehicle 800, via the warehouse control system 500, to transport the storage bin containing the product that is the target of data collection, based on the free time in the schedule calculated so far (step S411). The warehouse operations management system 200 also instructs the automated guided vehicle 800 to move the bin that will be the destination of the product to be picked during data collection to a predetermined position near the robot 600. The bin that will be the destination of the product may be a bin that contains the same product as the storage bin, or it may be an empty bin prepared for data collection.

[0045] The warehouse operations management system 200 instructs the robot 600 to perform picking operations via the warehouse control system 300 based on the free time in the schedule calculated so far, thereby instructing the robot 600 to collect data (step S412). Details of this step will be described later with reference to FIG. 6 . The picking operations involved in data collection may include not only moving items from the storage bin in which they are stored to another bin, but also returning them from that bin to the original storage bin. Furthermore, during data collection, a series of picking operations are attempted while adjusting the robot's control parameters. Therefore, for a picking operation set for a certain time period, the control parameters may be changed multiple times to repeat the series of picking operations. After this step, the warehouse operations management system 200 proceeds to step S419.

[0046] Based on the schedule calculated so far, the warehouse operations management system 200 instructs the automated guided vehicle 800 via the warehouse control system 500 to collect the bins containing the products used in data collection (step S413). Then, this processing flow ends.

[0047] Based on the data collection status, the warehouse operations management system 200 calculates the time required for each item to be monitored and transported by a worker (step S414). For example, even if the automated guided vehicle 800 cannot transport the item, data collection is possible if the item can be manually moved to a location where picking work is performed. Therefore, the time period during which the item can be transported by a worker is calculated and used to determine whether manual transportation of the item is possible during that time period. The time required for manual transportation of the item may be predetermined based on the location of the storage bin in which the item is stored, the distance to the location of the work area where picking work is performed, the storage status of the item in the bin, and the like. Furthermore, the value calculated as the time required for monitoring in step S408 may differ from the value calculated as the time required for monitoring and transportation in step S414. For example, in this step, the desired time may be calculated by adding the time required for monitoring and the time required for transportation. The warehouse operations management system 200 then proceeds to step S415.

[0048] The warehouse operations management system 200 calculates available free time in the personnel schedule for monitoring and transportation based on the time calculated in step S414 (step S415).

[0049] The warehouse operations management system 200 determines whether there are any products that can be monitored and transported by an operator during the available time calculated in step S415 (step S416). For example, if only a small number of products are required for the picking operation and the storage bins do not need to be moved, data collection can be performed by having the operator transport the products. Alternatively, even if there are no available automated guided vehicles 800, data collection can be performed by having the operator transport the storage bins containing the products for which data collection is to be performed. If there are any products that can be monitored and transported (step S416: YES), the warehouse operations management system 200 proceeds to step S417. On the other hand, if there are no products that can be monitored and transported (step S416: NO), the warehouse operations management system 200 proceeds to step S420.

[0050] The warehouse operations management system 200 instructs the worker via the operation terminal 900 to transport the product to be the target of data collection or the storage bin in which the product is stored, based on the free time in the schedule calculated so far (step S411). The warehouse operations management system 200 also instructs the worker to move the bin to which the product to be picked during data collection will be moved to a predetermined position near the robot 600. The bin to which the product will be moved may be a bin that stores the same product as the storage bin, or may be an empty bin prepared for data collection.

[0051] The warehouse operations management system 200 instructs the robot 600 to perform picking work via the warehouse control system 300 based on the free time in the schedule calculated so far, thereby instructing the execution of data collection (step S418). Details of this step will be described later with reference to FIG. 6. After this step, the processing of the warehouse operations management system 200 proceeds to step S419.

[0052] The warehouse operations management system 200 instructs the operator via the operation terminal 900 to collect the bins containing the products used in the data collection based on the schedule calculated up to that point (step S419). Then, this processing flow ends.

[0053] The warehouse operations management system 200 determines that data collection will not be performed during the time period corresponding to the shipping instruction acquired in step S401 (step S420). Then, this processing flow ends. Note that if multiple robots 600 are provided and it is determined that at least one of these robots 600 is capable of performing data collection according to the schedule derived from the shipping instruction acquired in step S401, data collection may be performed. Alternatively, the multiple robots 600 may be controlled to perform data collection in parallel.

[0054] 5A is a conceptual diagram showing an example of comparing the available times of the robot 600 and the automated guided vehicle 800 in step S407 of FIG. 4. In the example of FIG. 5A, two time periods 501 and 502 are identified as matching available times in the time period from 10:00 to 12:00. The time periods here may be determined in predetermined time intervals (for example, in 10-minute increments). These time periods 501 and 502 are identified as the timing for collecting data.

[0055] 5B to 5D are conceptual diagrams showing examples of comparing the available times of the worker, the robot 600, and the automatic guided vehicle 800 in steps S408 to S410 and steps S414 to S416 in FIG.

[0056] In the example of FIG. 5B , two time slots 511 and 512 are identified as free times that match among the three subjects within the time slot from 10:00 to 12:00. For example, if the robot 600 attempts 40 picking operations and determines that product A, which has a gripping accuracy of 50%, requires monitoring by an operator, the time slots 511 and 512 shown in FIG. 5B may be used as the timing for data collection. This corresponds to the case where step S410 is determined to be YES. Examples of products that require monitoring may include products that are likely to be damaged.

[0057] In the example of FIG. 5C , two time slots 521 and 522 are identified as free times between the robot 600 and the automated guided vehicle 800 between 10:00 and 12:00. For example, if the robot 600 attempts 1,000 picking operations and determines that worker supervision is not required for product B, which has a gripping accuracy of 95%, the time slots 521 and 522 shown in FIG. 5C may be used as the timing for data collection. This corresponds to the case where, after the time requiring worker supervision is calculated as 0 in step S408 (i.e., human supervision is not required), a determination of YES is made in step S410. Examples of products that do not require supervision may include products that have high gripping accuracy based on historical information.

[0058] In the example of FIG. 5D , two time slots 532 and 534 are identified as free times that coincide between the robot 600 and the automated guided vehicle 800 within the time slot from 10:00 to 12:00. Furthermore, within that time slot, two time slots 531 and 533 are identified as free times that coincide between the worker, the robot 600, and the automated guided vehicle 800. For example, if the robot 600 attempts 20 picking operations and product C has a gripping accuracy of 95%, and the worker needs to monitor the product C for a short period of time, the time slots 532 and 533 shown in FIG. 5D may be set as the timing for data collection, and the time slots 531 and 533 may be set as the timing for worker monitoring. This corresponds to the case where the time required for worker monitoring is calculated as a short period of time (e.g., 5 minutes) in step S408, and then a determination of YES is made in step S410. In this case, the worker monitoring is preferably set at the end of the time slot for data collection. Examples of products that may require short monitoring times include products that are not easily damaged.

[0059] For example, when selecting products for which data collection is to be performed in step S403, steps S408 to S410, and steps S414 to S416 in Fig. 4, product priorities may be set based on historical information about past picking operations. For example, a list such as that shown in Table 1 below for each product may be generated and used based on the product information for each product managed in the automated warehouse 700.

[0060]

[0061] The priority when determining products to collect data from may be set so that new products registered within a certain range from the present, products whose grasping success rate is below a predetermined threshold, products whose inventory in a storage bin, or products whose total number of grasping attempts is below a predetermined threshold, etc. are given a higher priority. Also, a setting may be provided to exclude certain products from data collection. Note that the priority settings and criteria are merely examples and are not limited to these.

[0062] Furthermore, the number of picking attempts that can be performed during free time and the end time of data collection may be predicted based on statistics of the time required for past picking operations. Furthermore, picking operations do not need to be performed continuously, and may be defined as being sufficient as long as a predetermined number of attempts can be performed within a time range, such as that shown in FIG. 5B. In other words, picking operations for data collection may be controlled so that they are completed by the time the next scheduled actual shipping operation begins.

[0063] Furthermore, "free time" is not limited to time periods when each processing entity is not performing any work. For example, time periods with extremely low processing loads or time periods when the number of processing cases within a given time interval is below a certain value may also be treated as free time.

[0064] 5A to 5D are merely examples and are not limiting. For example, data collection may be divided into several processes, and then free time may be identified. For example, as described above, the data collection work for each of the transport, installation, picking, monitoring, and collection of products (bins) includes a series of actions. Therefore, free time for data collection may be identified based on the task owner, required time, and load status of each process.

[0065] In this case, it is not necessary for the free time of the work agents to be the same throughout all time periods for data collection. For example, if the bins are transported (placed and collected) by an AGV and human supervision is required, there may be free time for the work agent after the picking work by the picking robot is completed. Similarly, if the bins are transported (placed and collected) by a human and human supervision is not required, there may be free time for the work agent before and after the picking work by the picking robot. In this way, the free time of each processing agent does not necessarily have to be the same, and the handling of "free time" may differ depending on the content that each processing agent is to perform.

[0066] Furthermore, if data collection is considered as a series of operations consisting of multiple steps such as transporting and placing products (bins), picking work, monitoring, and collecting products (bins), these do not need to be performed without any free time. In other words, provided that data collection does not interfere with actual shipping work, there may be a waiting time between the placement of bins for data collection and the picking work for data collection.

[0067] (Data Collection Process) Figure 6 is a flowchart of the data collection process according to this embodiment. This process corresponds to steps S412 and S418 in the flowchart shown in Figure 4, and is implemented by the warehouse control systems 300 to 500 cooperating with each other based on instructions from the warehouse operations management system 200. Note that, although the processes of steps S412 and S418 will be described here as being executed in the same manner, some operations may be changed depending on whether or not an operator is monitoring the processes.

[0068] The warehouse operations management system 200 acquires information about the products for which data collection is to be performed (step S601). The product information here may include control parameters used in past picking operations, upper and lower limit values ​​of control parameters according to product attributes, and the like.

[0069] The warehouse operations management system 200 sets control parameters for data collection (step S602). The control parameters set here may include parameters related to the gripping position, gripping strength, movement speed, and movement trajectory of the robot 600 with respect to the product. Furthermore, the control parameters for data collection may be set by changing only one item or multiple items based on control parameters that have been successfully or unsuccessfully tried in the past, based on historical information about the picking operation. Furthermore, the control parameters for data collection may be set based on a predetermined setting pattern. Furthermore, by repeatedly performing picking operations using the same control parameters, the gripping accuracy for a given product using those control parameters may be derived and confirmed.

[0070] For example, the gripping position may be based on the center position of the product, and the control parameters may be changed by shifting the gripping position from the center position. The gripping strength may be controlled to be stronger if the history information indicates a control parameter that has fallen, or weaker if the history information indicates a control parameter that has resulted in successful gripping. Upper and lower limits may also be set for the gripping strength. The movement speed may be controlled to be slower if the history information indicates a control parameter that has fallen during movement, or faster if the history information indicates a control parameter that has resulted in successful movement. Furthermore, if the history information includes information about the state of the product when it is being gripped, such as vibration information or image information, data collection may be performed by adjusting the movement speed based on the degree of shaking of the product during the picking operation.

[0071] The warehouse operations management system 200 determines whether various bins for the picking operation for data collection have been installed (step S603). The bins here refer to storage bins in which products are stored and bins to which products are to be moved. Whether or not the bins have been installed may be determined, for example, based on images acquired by a camera 30 installed around the work area where the picking operation is performed.

[0072] The warehouse operations management system 200 causes the robot 600 to perform the picking operation using the control parameters set in step S602 (step S604).

[0073] The warehouse operations management system 200 determines whether or not the product has failed to be grasped as a result of step S604 (step S605). A failure here corresponds to a product falling into a storage bin during the picking operation. If the product has failed to be grasped (step S605: YES), the warehouse operations management system 200 proceeds to step S608. On the other hand, if the product has not failed to be grasped (step S605: NO), the warehouse operations management system 200 proceeds to step S606.

[0074] The warehouse operations management system 200 determines whether the product has fallen outside the bin as a result of step S604 (step S606). A product falling outside the bin corresponds to a case where the product falls outside the bin to which it is to be moved during a picking operation. For example, this corresponds to a case where the product is successfully lifted (moved vertically) but then dropped during a horizontal movement. If the product has fallen outside the bin (step S606: YES), the warehouse operations management system 200 proceeds to step S608. On the other hand, if the product has not fallen outside the bin, i.e., if the product has been successfully moved into the bin to which it is to be moved (step S606: NO), the warehouse operations management system 200 proceeds to step S607.

[0075] The warehouse operations management system 200 associates the data collection parameters set in step S602 with the product information and registers the result as a successful result (step S607).Then, the process of the warehouse operations management system 200 proceeds to step S609.

[0076] The warehouse operations management system 200 associates the data collection parameters set in step S602 with the product information and registers the result as a failure record (step S608).Then, the process of the warehouse operations management system 200 proceeds to step S609.

[0077] The warehouse operations management system 200 determines whether or not the storage bin information needs to be updated as a result of the product picking operation (step S609). For example, if an item is moved from one storage bin to another, the number of items contained in the storage bin changes, and therefore this update is performed. Furthermore, if an item is moved to a destination bin and the destination bin becomes the storage bin for that item, the information is newly registered. Note that if the item is moved back and forth during the picking operation, the status of the original storage bin remains unchanged, and therefore no update is required. If the storage bin information needs to be updated (step S609: YES), the warehouse operations management system 200 proceeds to step S610. On the other hand, if the storage bin information does not need to be updated (step S609: NO), the warehouse operations management system 200 proceeds to step S611.

[0078] The warehouse operations management system 200 updates the storage bin for the product to the bin to which the product was moved in the picking operation (step S610). Furthermore, the warehouse operations management system 200 updates the inventory quantity of the product in the original storage bin to the latest. Then, the process of the warehouse operations management system 200 proceeds to step S611.

[0079] The warehouse operations management system 200 determines whether to end data collection (step S611). For example, if multiple control parameters for data collection were set in step S602, the warehouse operations management system 200 may determine whether trials using all of the control parameters have been completed. Alternatively, if the end of the time period shown in FIG. 5B or the like is approaching during data collection, the warehouse operations management system 200 may control the data collection to end at that point, even if other control parameters for data collection have been set. If the data collection is to be ended (step S611: YES), the warehouse operations management system 200 proceeds to step S612. On the other hand, if the data collection is not to be ended (step S611: NO), the warehouse operations management system 200 returns to step S602 and repeats the process.

[0080] The warehouse operations management system 200 outputs the information registered in steps S607 and S608 as history information to a database (not shown) of the warehouse operations management system 200 (step S612), and then ends this processing flow.

[0081] In the data collected as described above, control parameters that have proven successful for a certain product may be used as they are in the picking operation of the robot 600 for that product. Alternatively, the collected data may be defined as learning data, and machine learning may be performed using this learning data. By using the data in this manner, a configuration can be realized in which control parameters for unknown products can be estimated.

[0082] When machine learning is performed using collected data, the learning algorithm of the machine learning and which of the learning data is used as the learned input and output may be changed depending on the configuration of the warehouse system 1. For example, a learned model may be generated by machine learning, using the type, size, weight, shape, etc. of the product as input and outputting the gripping position, movement speed, movement amount, movement trajectory, etc. of the robot 600 during picking.

[0083] Furthermore, when there are multiple robots 600 of the same type, control parameters based on data obtained from one robot may be diverted as control parameters for other robots of the same type.

[0084] The collected data may also be used to evaluate the warehouse system at that time. The evaluation here may be an evaluation of each of the multiple robots 600, or an evaluation related to the workload of the workers.

[0085] As described above, a warehouse system (e.g., 1, 200) according to the present embodiment is a warehouse system that collects data related to picking operations by a picking robot (e.g., 600), and includes: an identification unit (e.g., 11) that identifies a time period in which an available time in the work schedule of the picking robot (e.g., 600) coincides with an available time in the work schedule of at least one of a worker and an automated guided vehicle (e.g., 800) in the warehouse system; a determination unit (e.g., 11) that determines the product for which the data will be collected during the time period; and an instruction unit (e.g., 11) that instructs the worker and / or the automated guided vehicle and the picking robot to adjust control parameters for the picking operation and attempt to pick the product during the time period to collect the data. This configuration enables efficient data collection related to robot picking operations in the warehouse.

[0086] In addition, in the warehouse system, the determination unit determines whether or not a picking operation for a product requires worker supervision based on the product attributes, and determines a product determined not to require worker supervision as a product that can be picked during a time period when the picking robot is available and the automatic guided vehicle is available. With this configuration, data collection for products that do not require worker supervision can be performed even during a time period when the worker is not available, making it possible to collect data efficiently.

[0087] In addition, in the warehouse system, the determination unit determines products that can be transported by an automated guided vehicle during a time period when the free time of the picking robot and the free time of the automated guided vehicle coincide, but the free time of the automated guided vehicle and the free time of the worker do not coincide, and determines the products that are determined to be transportable by an automated guided vehicle as products that can be picked. With this configuration, even during a time period when the automated guided vehicle is not free, data collection for the products can be performed by the worker transporting the products, thereby enabling efficient data collection.

[0088] In addition, in the warehouse system, the determination unit determines the product based on history information indicating the history of picking work for the product. According to this configuration, by using the history information for the product, it is possible to perform data collection in order of product priority within the warehouse system.

[0089] In addition, in the warehouse system, the history information includes any one of the picking success rate, the total number of attempts, and status information indicating the status of the product at the time of picking. With this configuration, it is possible to adjust the control parameters based on the picking success rate, the total number of attempts, and the status information of the product at the time of picking, which are based on past picking operations, and to attempt more appropriate picking operations.

[0090] In addition, in the warehouse system, the control parameters include at least one of the gripping position, gripping strength, and movement speed of the product by the picking robot. With this configuration, by changing and trying out various control parameters in the product picking work, it is possible to identify more appropriate control parameter values ​​and use them for subsequent control.

[0091] <Other Embodiments> In the above embodiment, the number of workers is not particularly limited. However, for example, if there are multiple workers, free time may be identified based on the work schedule of each worker. Furthermore, workers who perform monitoring and transportation may be assigned preferentially to workers with a lighter load of normal shipping work. Furthermore, data collection may be controlled so that it is performed only during time periods when a certain number of workers or more are present.

[0092] Furthermore, since data collection requires the robot 600 and the automatic guided vehicle 800 to be driven, data collection may be controlled to be performed during a time period when the driving costs are low. For example, data collection may be performed taking into consideration a time period when electricity costs are low.

[0093] Furthermore, when data collection is completed, the system may be configured to notify the worker, etc. Furthermore, the system may be configured to explicitly notify the worker of the products for which the level of data collection is low or high.

[0094] Furthermore, when a certain robot attempts to pick a certain number of times, if the success rate of grasping a product is low, the robot may be controlled to perform the picking work and collect data. Furthermore, the robot that performs the picking work for data collection may be fixed depending on the attributes of the product.

[0095] Furthermore, in 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.

[0096] 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.

[0097] 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.

[0098] (Additional Notes) The above description of the embodiments discloses the following techniques.

[0099] (Technology 1) A warehouse system that collects data related to picking work by a picking robot, comprising: an identification unit that identifies a time period in which an available time in the work schedule of the picking robot in the warehouse system coincides with an available time in the work schedule of at least one of a worker and an automated guided vehicle; a determination unit that determines the products for which the data will be collected during the time period; and an instruction unit that instructs at least one of the worker and the automated guided vehicle, and the picking robot, to collect the data by adjusting control parameters for the picking work and attempting the picking work on the products during the time period.

[0100] This configuration makes it possible to efficiently collect data related to robot picking operations within a warehouse.

[0101] (Technology 2) The warehouse system according to Technology 1, wherein the determination unit determines whether or not the worker needs to monitor the picking operation of the product based on the attributes of the product, and determines a product for which it is determined that the worker does not need to monitor the picking operation as a product for which the picking operation can be performed during a time period when the available time of the picking robot and the available time of the automatic guided vehicle coincide.

[0102] With this configuration, data collection can be performed for products that do not require worker supervision even during times when workers are not available, making it possible to collect data efficiently.

[0103] (Technology 3) The warehouse system according to Technology 1 or Technology 2, wherein the determination unit determines products that can be transported by the automated guided vehicle during a time period when the available time of the picking robot and the available time of the automated guided vehicle coincide and when the available time of the automated guided vehicle and the available time of the worker do not coincide, and determines the products that are determined to be transportable by the automated guided vehicle as products that can be picked.

[0104] With this configuration, even during times when the automated guided vehicle is not idle, data collection for the product can be performed by having the worker transport the product, making it possible to collect data efficiently.

[0105] (Technology 4) The warehouse system according to any one of Technology 1 to Technology 3, wherein the determination unit determines the product based on history information indicating a history of a picking operation for the product.

[0106] With this configuration, it is possible to collect data in the warehouse system in order of priority for the products based on the history information for the products.

[0107] (Technology 5) The warehouse system according to Technology 4, wherein the history information includes any one of a picking success rate, a total number of attempts, and status information indicating the status of the product at the time of picking.

[0108] With this configuration, it is possible to adjust control parameters based on the picking success rate, total number of attempts, and product condition information at the time of picking, which are based on past picking operations, and to attempt more appropriate picking operations.

[0109] (Technology 6) The warehouse system according to any one of Technology 1 to Technology 5, wherein the control parameters include at least one of a gripping position, a gripping strength, and a moving speed of the product by the picking robot.

[0110] With this configuration, by changing and experimenting with various control parameters in the product picking operation, it is possible to identify more appropriate control parameter values ​​and use them for subsequent control.

[0111] (Technology 7) A data collection method in which a processor and a memory work together to collect data regarding picking work by a picking robot, the data collection method including: an identifying step of identifying a time period in which an available time in the work schedule of the picking robot in a warehouse system coincides with an available time in the work schedule of at least one of a worker and an automated guided vehicle; a determining step of determining products for which the data will be collected during the time period; and an instructing step of instructing at least one of the worker and the automated guided vehicle, and the picking robot, to collect the data by adjusting control parameters for the picking work and attempting the picking work on the products during the time period.

[0112] This configuration makes it possible to efficiently collect data related to robot picking operations within a warehouse.

[0113] The present disclosure is useful as a warehouse system and a data collection method.

[0114] 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 that collects data related to picking work by a picking robot, comprising: an identification unit that identifies a time period in which an available time in the work schedule of a picking robot within the warehouse system coincides with an available time in the work schedule of at least one of a worker and an automated guided vehicle; a determination unit that determines the products for which the data will be collected during the time period; and an instruction unit that instructs at least one of the worker and the automated guided vehicle, and the picking robot, to collect the data by adjusting control parameters for the picking work and attempting the picking work on the products during the time period.

2. The warehouse system described in claim 1, wherein the determination unit determines whether or not the worker needs to monitor the picking operation for the product based on the attributes of the product, and determines a product for which it is determined that the worker does not need to monitor the picking operation as a product for which the picking operation can be performed during a time period when the picking robot's available time and the unmanned guided vehicle's available time coincide.

3. The warehouse system according to claim 1, wherein the determination unit determines which products can be transported by the automated guided vehicle during a time period when the available time of the picking robot and the available time of the automated guided vehicle coincide, but when the available time of the automated guided vehicle and the available time of the worker do not coincide, and determines the products determined to be available for transport by the automated guided vehicle as products that can be picked.

4. The warehouse system according to claim 1, wherein the determination unit determines the product based on history information indicating a history of picking work for the product.

5. The warehouse system of claim 4, wherein the history information includes any one of the following: a picking success rate, a total number of attempts, and status information indicating the status of the product at the time of picking.

6. A warehouse system according to any one of claims 1 to 5, wherein the control parameters include at least one of the gripping position, gripping strength, and movement speed of the product by the picking robot.

7. A data collection method in which a processor and a memory work together to collect data regarding picking work by a picking robot, the data collection method comprising: an identifying step of identifying a time period in which an available time in the work schedule of the picking robot in a warehouse system coincides with an available time in the work schedule of at least one of a worker and an automated guided vehicle; a determining step of determining products for which the data will be collected during the time period; and an instructing step of instructing the worker and / or the automated guided vehicle, and the picking robot, to collect the data by adjusting control parameters for the picking work and attempting the picking work on the products during the time period.

Images