Simulation system

Abstract

To provide a technique that enables effective learning of cooperation between works which continue before and after.SOLUTION: A simulation system performs a simulation of a work line including a first work and a second work, which continue before and after. A first model motion includes a motion serving as a model when a first target worker passes a resultant product of the first work to a second target worker. A second model motion includes a motion serving as a model when the second target worker receives the resultant product of the first work from the first target worker. When the first target worker performs the motion related to the first work in a virtual space, the simulation system draws a first model worker performing the first model motion. When the second target worker performs the motion related to the second work in the virtual space, the simulation system draws a second model worker performing the second model motion.SELECTED DRAWING: Figure 4

Description

[Technical field]

[0001] The present disclosure relates to a technique for simulating a production line in a virtual space. [Background technology]

[0002] Patent Document 1 discloses a learning support system. The learning support system displays a model video of an instructor, which serves as a model for the learner's movements, superimposed on a video of the learner's field of vision. Basic information of the learner includes the learner's age, dominant hand, eyesight, grip strength, etc. The learning support system changes the display content of the model video according to the learner's basic information. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] JP 2020-144233 A Summary of the Invention [Problem to be solved by the invention]

[0004] In a production line, there may be cooperation between adjacent tasks. One object of the present disclosure is to provide a technology capable of effectively learning cooperation between adjacent tasks. [Means for solving the problem]

[0005] One aspect of the present disclosure relates to a simulation system that simulates a production line in a virtual space. The work line includes a first task performed by a first target worker and a second task performed by a second target worker on a result of the first task. The first model action includes an action that serves as a model for when the first target worker hands over the result of the first task to the second target worker. The second model action includes an action that serves as a model for the second target worker when receiving the result of the first task from the first target worker. The simulation system includes one or more processors. The one or more processors determine a combination of the first model behavior and the second model behavior. When a first target worker performs an action related to a first task in the virtual space, the one or more processors render a first model worker performing a first model action in the virtual space. When a second target worker performs an action related to a second task in the virtual space, the one or more processors render a second model worker performing a second model action in the virtual space. Effect of the Invention

[0006] According to the present disclosure, a first model worker performing a first model action and a second model worker performing a second model action are rendered in a virtual space. The first model action includes an action that serves as a model for when the first target worker hands over a result of the first work to the second target worker. The second model action includes an action that serves as a model for when the second target worker receives the result of the first work from the first target worker. This enables the first target worker and the second target worker to effectively learn efficient cooperation between the first work and the second work. [Brief description of the drawings]

[0007] [Figure 1] 1 is a conceptual diagram for explaining an overview of a simulation system according to an embodiment; [Diagram 2] 1 is a block diagram showing an example of a configuration of a simulation system according to an embodiment; [Diagram 3] FIG. 1 is a conceptual diagram for explaining cooperation between adjacent operations on a work line. [Figure 4] FIG. 11 is a conceptual diagram for explaining a simulation of a work line according to an embodiment. [Diagram 5] FIG. 13 is a conceptual diagram for explaining a modified example of the simulation of the work line according to the embodiment. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0008] 1. Overview of the Simulation System Consider a predetermined task performed by a worker in a real space. For example, the predetermined task is performed in a real factory. The predetermined task is, for example, assembling parts. According to this embodiment, a simulation is utilized to efficiently train (study) a worker who performs the predetermined task.

[0009] FIG. 1 is a conceptual diagram for explaining an overview of a simulation system 100 according to this embodiment. The simulation system 100 performs a simulation of a predetermined task performed by a worker in a virtual space. To achieve this, the simulation system 100 virtually reproduces, in the virtual space, a work environment in which the worker performs the predetermined task. For example, the simulation system 100 reproduces (draws) the work environment in the virtual space based on DigitalTwin technology. For example, the simulation system 100 reproduces, in the virtual space, a virtual factory (DigitalTwin factory) that simulates an actual factory.

[0010] A worker to be trained (hereinafter, referred to as "target worker TW") can experience a predetermined task in a virtual space by using an experience device. For example, the experience device is a wearable device such as a head mounted display (HMD). The head mounted display displays the virtual space reproduced by the simulation system 100. The motion of the target worker TW in the real space (e.g., hand motion) is recognized by a motion capture technique. For example, the target worker TW is photographed by a camera, and the motion of the target worker TW is recognized. As another example, an inertial sensor (gyro sensor, acceleration sensor, etc.) may be attached to the body of the target worker TW, and the motion of the target worker TW may be recognized based on the detection result of the inertial sensor. The simulation system 100 draws the recognized motion of the target worker TW by superimposing it on the virtual space. For example, the simulation system 100 draws the recognized hand motion of the target worker TW by superimposing it on the virtual space. This allows the target worker TW to get the feeling that he or she is performing a predetermined task in the virtual space. That is, the target worker TW can experience a predetermined task in the virtual space.

[0011] Furthermore, the simulation system 100 may draw a virtual model worker MW performing a model action superimposed on the virtual space. The model action is an action that serves as a model when the target worker TW performs a specified task. In the virtual space, the virtual model worker MW performs the model action. The model worker MW may also be called a "ghost worker." In the virtual space, the target worker TW performs a specified task by imitating the model action performed by the model worker MW. This enables efficient and effective training.

[0012] 2 is a block diagram showing an example of the configuration of a simulation system 100 according to this embodiment. The simulation system 100 includes a sensor 110, an input device 120, an output device 130, and an experience device 140.

[0013] The sensor 110 is disposed in the real space and detects various information. For example, the sensor 110 detects the motion of a worker in the real space. Examples of the sensor 110 that detects the motion of a worker include a camera, an infrared sensor, an inertial sensor, and the like. For example, the motion of a worker can be detected by photographing the worker with a camera. As another example, an inertial sensor (gyro sensor, acceleration sensor, etc.) may be attached to the body of the worker, and the motion of the worker may be detected by the inertial sensor.

[0014] As another example, the sensor 110 may detect physical characteristics of the worker in real space. Examples of physical characteristics include handedness, hand size, grip strength, height, muscle mass, eyesight, and the like. For example, the handedness of the worker is detected based on the movement of the worker captured by a camera. As another example, the hand size, height, and the like are detected based on an image of the worker captured by a camera. In addition, the sensor 110 may include a height gauge, a weight scale, a body composition scale, a grip strength meter, an eyesight meter, and the like.

[0015] As yet another example, the sensor 110 may include a biosensor that detects bioinformation of the worker in the real space. Examples of the bioinformation include body temperature, heart rate, fatigue level, stress level, and the like.

[0016] Examples of the input device 120 include a touch panel, a keyboard, a mouse, a microphone, etc. Examples of the output device 130 include a display, a touch panel, a speaker, etc.

[0017] The experience device 140 is used to allow the target worker TW to experience the work environment and a predetermined task in a virtual space. For example, the experience device 140 is a wearable device such as a head mounted display (HMD). The head mounted display displays the virtual space reproduced by the simulation system 100.

[0018] The simulation system 100 further includes one or more processors 150 (hereinafter simply referred to as "processor 150") and one or more storage devices 160 (hereinafter simply referred to as "storage device 160"). The processor 150 executes various processes. Examples of the processor 150 include a central processing unit (CPU), a graphics processing unit (GPU), an application specific integrated circuit (ASIC), and a field-programmable gate array (FPGA). The storage device 160 stores various information. Examples of the storage device 160 include a hard disk drive (HDD), a solid state drive (SSD), a volatile memory, and a non-volatile memory.

[0019] The simulation program 170 is a computer program for performing a simulation in the above-mentioned virtual space, and is executed by the processor 150. Various processes by the simulation system 100 may be realized by cooperation between the processor 150 executing the simulation program 170 and the storage device 160. The simulation program 170 is stored in the storage device 160. The simulation program 170 may be recorded in a computer-readable recording medium.

[0020] The work environment information 180 is information about a work environment (e.g., an actual factory) reproduced in a virtual space. For example, the work environment information 180 indicates a three-dimensional arrangement of structures (lines, machines, walls, pillars, etc.) in the work environment. For example, the three-dimensional arrangement of structures is expressed by CAD data. The work environment information 180 is stored in the storage device 160.

[0021] The storage device 160 further stores a database 200. The database 200 includes a worker characteristic database 210, a work performance database 220, and a model operation database 230.

[0022] The worker characteristic database 210 is a database showing the physical characteristics of each worker. Examples of the physical characteristics include handedness, hand size, grip strength, height, muscle mass, eyesight, etc. For example, the physical characteristics of each worker are detected by the above-mentioned sensor 110. As another example, each worker may input his / her own physical characteristics using the input device 120. Physical characteristics expressed by numerical values ​​such as height may be grouped according to a predetermined range.

[0023] The work history database 220 is a database showing the results of predetermined work performed by various workers. For example, the work history database 220 includes video of the worker performing the predetermined work. The video of the worker is captured by a camera included in the above-mentioned sensor 110. As another example, the work history database 220 may show the content of the action performed by the worker during the predetermined work. As yet another example, the work history database 220 may show the time it took for the worker to complete the predetermined work. Such a work history database 220 is generated based on the action of the worker detected by the above-mentioned sensor 110.

[0024] The model action database 230 is a database related to model actions that serve as a model when the target worker TW performs a predetermined task. The model actions related to the predetermined task may be created in advance based on the task record database 220.

[0025] The processor 150 reproduces, in a virtual space, a work environment in which a worker performs a predetermined work, based on the work environment information 180. For example, the processor 150 reproduces (draws) the work environment in the virtual space based on DigitalTwin technology.

[0026] Moreover, the processor 150 recognizes the motion of the target worker TW, who is the training target, using the sensor 110. The motion of the target worker TW in the real space is recognized by a motion capture technique. For example, the motion of the target worker TW is recognized by photographing the target worker TW with a camera. As another example, an inertial sensor may be attached to the body of the target worker TW, and the motion of the target worker TW may be recognized based on the detection result of the inertial sensor. The processor 150 draws the recognized motion of the target worker TW by superimposing it on the virtual space. For example, the processor 150 draws the recognized hand movement of the target worker TW by superimposing it on the virtual space. The target worker TW can get a sense of performing a predetermined task in the virtual space via the experience device 140. That is, the target worker TW can experience a predetermined task in the virtual space via the experience device 140.

[0027] Furthermore, the processor 150 determines a model action to be a model for the target worker TW to perform a predetermined task based on the model action database 230. Then, the processor 150 draws a virtual model worker MW performing the model action by superimposing it on the virtual space. In the virtual space, the target worker TW performs the predetermined task by imitating the model action performed by the model worker MW. This enables efficient and effective training.

[0028] 2.Production line simulation 2-1. Overview Next, consider the cooperation between consecutive tasks on a work line. FIG. 3 is a conceptual diagram for explaining the cooperation between consecutive tasks on a work line. The work line includes a first task on the upstream side and a second task on the downstream side. A first worker W1 performs the first task on the upstream side. For example, the first worker W1 assembles a part. The first worker W1 passes the result of the first task (e.g., the assembled part) to a second worker W2 on the downstream side. The first worker W1 may pass the result directly or indirectly via a conveyor belt or the like. The second worker W2 on the downstream side receives the result of the first task from the first worker W1. The second worker W2 may receive the result directly or indirectly via a conveyor belt or the like. Then, the second worker W2 performs the second task on the downstream side for the result of the first task that he received.

[0029] It is desirable to effectively learn the cooperation between such a first task and a second task. In the following description, the first worker W1 to be trained is referred to as a "first target worker TW1," and the second worker W2 to be trained is referred to as a "second target worker TW2."

[0030] 4 is a conceptual diagram for explaining a simulation of a production line according to the present embodiment. A simulation system 100 performs a simulation of a production line in a virtual space.

[0031] The "first model motion MO1" is a model motion related to the first task. The first model motion includes a model motion when the first target worker TW1 hands over the result of the first task to the second target worker TW2. Furthermore, the first model motion may include a model motion when the first target worker TW1 performs the first task.

[0032] On the other hand, the "second model motion MO2" is a model motion related to the second task. The second model motion includes a model motion for the second target worker TW2 to receive the result of the first task from the first target worker TW1. Furthermore, the second model motion may include a model motion for the second target worker TW2 to perform the second task.

[0033] The simulation system 100 determines a combination of the first model action MO1 and the second model action MO2. Typically, the simulation system 100 determines a combination of the first model action MO1 and the second model action MO2 so as to satisfy a predetermined condition. Various examples of a method for determining the first model action MO1 and the second model action MO2 will be described later. The combination of the first model action MO1 and the second model action MO2 for the combination of the first task and the second task is registered in the model action database 230.

[0034] The first model worker MW1 is a model worker MW performing a first model action MO1. The second model worker MW2 is a model worker MW performing a second model action MO2. The simulation system 100 renders the first model worker MW1 and the second model worker MW2 in a virtual space based on the model action database 230.

[0035] More specifically, when the first target worker TW1 performs an action related to the first task in the virtual space, the simulation system 100 renders the first model worker MW1 performing the first model action MO1 in the virtual space. The first target worker TW1 performs the action related to the first task by imitating the first model action MO1 performed by the first model worker MW1. Also, when the second target worker TW2 performs an action related to the second task in the virtual space, the simulation system 100 renders the second model worker MW2 performing the second model action MO2 in the virtual space. The second target worker TW2 performs the action related to the second task by imitating the second model action MO2 performed by the second model worker MW2. This allows the first target worker TW1 and the second target worker TW2 to effectively learn efficient cooperation between the first task and the second task.

[0036] 2-2. Example of how to determine the first and second model actions Various examples of methods for determining the first model action MO1 and the second model action MO2 will be described below. Typically, a combination of the first model action MO1 and the second model action MO2 is determined so as to satisfy a "predetermined condition."

[0037] 2-2-1. First example In a first example, the simulation system 100 acquires characteristic information indicating a first characteristic of the first target worker TW1. The first characteristic of the first target worker TW1 includes physical characteristics of the first target worker TW1 (e.g., handedness, height, etc.). The physical characteristics of the first target worker TW1 are obtained from the worker characteristic database 210. The simulation system 100 determines a combination of the first model motion MO1 and the second model motion MO2 based on the physical characteristics of the first target worker TW1.

[0038] For example, taking into consideration the handedness of the first target worker TW1, the first model motion MO1 is determined so that the first target worker TW1 can easily pass the result of the first task to the second target worker TW2. Once the first model motion MO1 is determined, the second model motion MO2 is determined so that the second target worker TW2 can receive the result passed by the first model motion MO1.

[0039] As another example, a target position where the first target worker TW1 can easily place the result of the first task is determined in consideration of the height of the first target worker TW1. The first model motion MO1 is determined to place the result of the first task at the target position. The second model motion MO2 is determined to take the result of the first task from the target position.

[0040] The first characteristic of the first target worker TW1 may include the proficiency of the first target worker TW1. The proficiency of the first target worker TW1 is estimated based on the work record database 220. For example, it is estimated that the faster the motion related to the first work, the higher the proficiency. When the proficiency of the first target worker TW1 is low, the first model motion MO1 is determined to be as simple as possible. Once the first model motion MO1 is determined, the second model motion MO2 is determined so as to be able to receive the resultant product delivered by the first model motion MO1.

[0041] In general, the predetermined condition in the first example is that "the load of the first target worker TW1 when handing over the result of the first work is less than a threshold value." The load when handing over the result of the first work is calculated based on the degree of twisting of the body, the movement time, and the like. The loads for various movement patterns are obtained from the work record database 220 or through simulation. The simulation system 100 determines a combination of the first model motion MO1 and the second model motion MO2 based on the first characteristic of the first target worker TW1 so that the load of the first target worker TW1 when handing over the result of the first work is less than a threshold value. Since the first characteristic of the first target worker TW1 is taken into consideration, it becomes possible to learn more efficient cooperation.

[0042] 2-2-2. Second example In the second example, the simulation system 100 acquires characteristic information indicating a second characteristic of the second target worker TW2. The second characteristic of the second target worker TW2 includes physical characteristics of the second target worker TW2 (e.g., handedness, height, etc.). The physical characteristics of the second target worker TW2 are obtained from the worker characteristic database 210. The simulation system 100 determines a combination of the first model motion MO1 and the second model motion MO2 based on the physical characteristics of the second target worker TW2.

[0043] For example, taking into consideration the handedness of the second target worker TW2, one of the first model motion MO1 and the second model motion MO2 is determined so that the second target worker TW2 can easily receive the result of the first task. Once one of the first model motion MO1 and the second model motion MO2 is determined, the other of the first model motion MO1 and the second model motion MO2 is determined.

[0044] As another example, a target position where the second target worker TW2 can easily pick up the result of the first task is determined in consideration of the height of the second target worker TW2. The first model motion MO1 is determined to place the result of the first task at the target position. The second model motion MO2 is determined to pick up the result of the first task from the target position.

[0045] The second characteristic of the second target worker TW2 may include the proficiency of the second target worker TW2. The proficiency of the second target worker TW2 is estimated based on the work record database 220. For example, it is estimated that the faster the motion related to the second work, the higher the proficiency. When the proficiency of the second target worker TW2 is low, the second model motion MO2 is determined to be as simple as possible. When the second model motion MO2 is determined, the first model motion MO1 is determined accordingly.

[0046] In general, the predetermined condition in the second example is that "the load of the second target worker TW2 when receiving the result of the first work is less than a threshold value." The load when receiving the result of the first work is calculated based on the degree of twisting of the body, the movement time, etc. The load for various movement patterns is obtained from the work record database 220 or through simulation. The simulation system 100 determines a combination of the first model motion MO1 and the second model motion MO2 based on the second characteristic of the second target worker TW2 so that the load of the second target worker TW2 when receiving the result of the first work is less than a threshold value. Since the second characteristic of the second target worker TW2 is taken into consideration, it becomes possible to learn more efficient cooperation.

[0047] 2-2-3.Third example It is also possible to combine the first and second examples described above. Since both the first characteristic of the first target worker TW1 and the second characteristic of the second target worker TW2 are taken into account, it is possible to learn more efficient cooperation.

[0048] 2-2-4. Fourth Example In the fourth example, the predetermined condition is that "the delivery time of the result of the first task from the first target worker TW1 to the second target worker TW2 is shorter than a predetermined time." A combination of the first model motion MO1 and the second model motion MO2 that satisfies this predetermined condition may be searched for in the task record database 220 or may be searched for through a simulation. The fourth example also makes it possible to learn efficient cooperation.

[0049] 2-2-5. Fifth Example In the fifth example, at least one of the first model motion MO1 and the second model motion MO2 is set to an actual motion of a veteran worker. Both the first model motion MO1 and the second model motion MO2 may be set to an actual motion of a veteran worker. The actual motion of the veteran worker is obtained from the work record database 220. According to the fifth example, it is possible to effectively learn efficient cooperation by veteran workers.

[0050] 2-3.Effects As described above, according to this embodiment, the first model worker MW1 performing the first model action MO1 and the second model worker MW2 performing the second model action MO2 are rendered in a virtual space. The first model action MO1 includes a model action for the first target worker TW1 to hand over the result of the first work to the second target worker TW2. The second model action MO2 includes a model action for the second target worker TW2 to receive the result of the first work from the first target worker TW1. This enables the first target worker TW1 and the second target worker TW2 to effectively learn efficient cooperation between the first work and the second work.

[0051] 3. Variations FIG. 5 is a conceptual diagram for explaining a modified example. As described above, the first model motion MO1 and the second model motion MO2 are set in advance. The first target worker TW1 performs a motion related to the first task by imitating the first model motion MO1 performed by the first model worker MW1. However, the actual motion of the first target worker TW1 does not necessarily follow the first model motion MO1. There is a possibility that the actual motion of the first target worker TW1 may deviate (diverge) from the first model motion MO1. In that case, the second target worker TW2 on the downstream side cannot successfully receive the result of the first task if the preset second model motion remains.

[0052] Therefore, in this modified example, the simulation system 100 dynamically corrects the second model motion MO2 in accordance with the motion result of the first target worker TW1.

[0053] More specifically, the first action WO1 is an actual action when the first target worker TW1 passes the result of the first work to the second target worker TW2 in the virtual space. The simulation system 100 acquires information on the first action WO1 of the first target worker TW1 by the sensor 110. Next, the simulation system 100 compares the first action WO1 with the first model action MO1 to calculate the deviation of the first action WO1 from the first model action MO1. If the deviation exceeds a threshold, the simulation system 100 corrects the second model action MO2 so that the result of the first work passed by the first action WO1 can be received. In other words, the simulation system 100 corrects the second model action MO2 so as to follow the first action WO1.

[0054] The corrected second model action MO2' is a result of correcting the second model action MO2. The simulation system 100 renders the second model worker MW2 performing the corrected second model action MO2' in the virtual space. The second target worker TW2 performs an action related to the second task by imitating the corrected second model action MO2' performed by the second model worker MW2.

[0055] As described above, according to the modified example, even if the first movement of the first target worker TW1 on the upstream side deviates (diverges) from the first model movement MO1, it is possible to continue training of the second target worker TW2 on the downstream side. [Explanation of symbols]

[0056] 100...simulation system, 110...sensor, 120...input device, 130...output device, 140...experience device, 150...processor, 160...storage device, 170...simulation program, 180...work environment information, 200...database, 210...worker characteristic database, 220...work performance database, 230...model operation database

Claims

1. A simulation system for simulating a production line in a virtual space, comprising: The work line includes a first task performed by a first target worker and a second task performed by a second target worker on a result of the first task, The first model action includes an action that serves as a model when the first target worker hands over the result of the first task to the second target worker, The second model action includes an action that serves as a model for when the second target worker receives the result of the first task from the first target worker; The simulation system includes one or more processors; The one or more processors: determining a combination of the first model motion and the second model motion; When the first target worker performs an action related to the first task in the virtual space, a first model worker is drawn performing the first model action in the virtual space; When the second target worker performs an action related to the second task in the virtual space, a second model worker performing the second model action is drawn in the virtual space. It was configured as Simulation system.

2. 2. The simulation system according to claim 1, The one or more processors further include: acquiring characteristic information indicating at least one of a first characteristic of the first target worker and a second characteristic of the second target worker; determining the combination of the first model behavior and the second model behavior based on the at least one of the first characteristic and the second characteristic; Simulation system.

3. The simulation system according to claim 2, The characteristic information indicates at least the first characteristic of the first target worker, The one or more processors determine the combination of the first model action and the second model action based on the first characteristic of the first target worker such that a load on the first target worker when transferring the result of the first task is less than a threshold. Simulation system.

4. The simulation system according to claim 2, The characteristic information indicates at least the second characteristic of the second target worker, The one or more processors determine the combination of the first model operation and the second model operation based on the second characteristic of the second target worker such that a load on the second target worker when receiving the result of the first task is less than a threshold. Simulation system.

5. A simulation system according to any one of claims 1 to 4, The one or more processors: acquiring information on a first action of the first target worker when the first target worker delivers the result of the first task to the second target worker in the virtual space; correcting the second model behavior to receive the result of the first operation passed by the first behavior when the deviation of the first behavior from the first model behavior exceeds a threshold value; Simulation system.

Images