Processing device, processing method, and program

Abstract

This processing device comprises a selection means that, on the basis of a relationship between objects that is identified on the basis of a first simulation result in a first simulation using a first model for digital twins with which the first simulation is performed, selects a second model for digital twins corresponding to part of the first model.

Description

Processing device, control device, simulation system, processing method, control method, and recording medium

[0001] The present disclosure relates to a processing device, a control device, a simulation system, a processing method, a control method, and a recording medium.

[0002] There is a technology called digital twin that imitates physical situations in the real world in a digital virtual space. Patent Literature 1 discloses a related technology relating to digital twins.

[0003] Japanese Patent Application Laid-Open No. 2021-064370

[0004] Meanwhile, there is a demand for technology that can create highly useful information from digital twin models.

[0005] One of the objectives of each aspect of the present disclosure is to provide a processing device, a control device, a simulation system, a processing method, a control method, and a recording medium that can solve the above-mentioned problems.

[0006] According to one aspect of the present disclosure, the processing device includes a selection means for executing a first simulation and selecting a second model for the digital twin that corresponds to a part of the first model based on relationships between objects identified based on a first simulation result in the first simulation using the first model for the digital twin.

[0007] According to another aspect of the present disclosure, a processing method selects a second model for the digital twin corresponding to a part of the first model based on relationships between objects identified based on a first simulation result in a first simulation using the first model for the digital twin, the second model being a part of the first model.

[0008] According to another aspect of the present disclosure, a recording medium stores a program that causes a computer to execute a first simulation, and select a second model for the digital twin that corresponds to a part of the first model based on relationships between objects identified based on a first simulation result in the first simulation using the first model for the digital twin.

[0009] According to another aspect of the present disclosure, the processing device is provided with a generation means for generating display data that displays a second model for a digital twin corresponding to a part of the first model identified based on a first simulation result in a first simulation using the first model for the digital twin, and that allows an area processed using the second model and an area processed without using the second model to be distinguishable from each other.

[0010] According to another aspect of the present disclosure, a processing method includes performing a first simulation, generating a second model for a digital twin corresponding to a part of the first model identified based on a first simulation result in the first simulation using the first model for the digital twin, and generating display data that allows an area processed using the second model to be distinguished from an area processed without using the second model.

[0011] According to another aspect of the present disclosure, a recording medium stores a program that causes a computer to execute a first simulation, the second model for a digital twin corresponding to a part of the first model identified based on a first simulation result in the first simulation using the first model for the digital twin, and generates display data that displays an area processed using the second model in a distinguishable manner from an area processed without using the second model.

[0012] According to each aspect of the present disclosure, highly convenient information can be created from a model for a digital twin.

[0013] FIG. 1 is a diagram illustrating an example of the configuration of a simulation system according to an embodiment of the present disclosure. FIG. 2 is a diagram illustrating an example of a processing flow of a simulation system according to an embodiment of the present disclosure. FIG. 3 is a diagram illustrating an example of a warehouse in an embodiment of the present disclosure. FIG. 4 is a diagram illustrating an example of a portion of the warehouse shown in FIG. 3. FIG. 5 is a diagram illustrating a simulation system with a minimum configuration according to an embodiment of the present disclosure. FIG. 6 is a diagram illustrating an example of a processing flow of a simulation system with a minimum configuration. FIG. 7 is a schematic block diagram illustrating the configuration of a computer according to at least one embodiment.

[0014] Hereinafter, an embodiment will be described in detail with reference to the drawings. <Embodiment> A simulation system 1 according to an embodiment of the present disclosure is a system that, based on the results of a certain simulation (hereinafter referred to as a first simulation) using digital twin technology, identifies a desired portion of a first model used in the first simulation, and enables a simulation (hereinafter referred to as a second simulation) using a partial model (hereinafter referred to as a second model) of the identified portion. In other words, the second model is a part of the first model, and the first model is realized by combining multiple second models. Digital twin technology is a technology that uses models to simulate physical objects in the real world, and is one of the technologies for performing simulations.

[0015] (Configuration of Simulation System) Fig. 1 is a diagram showing an example of the configuration of a simulation system 1 according to an embodiment of the present disclosure. As shown in Fig. 1, the simulation system 1 includes a processing device 10 and a display device 20.

[0016] As shown in FIG. 1, the processing device 10 includes a setting unit 101, an execution unit 102, a first storage unit 103, a second storage unit 104, a first identification unit 105, a second identification unit 106, and a selection unit 107.

[0017] The setting unit 101 sets conditions for a first simulation using a first model for a digital twin. The execution unit 102 executes the first simulation using the first model based on the conditions set by the setting unit 101.

[0018] The first storage unit 103 stores a first model for a digital twin for executing the first simulation. The second storage unit 104 stores the simulation results of the first simulation executed by the execution unit 102 (hereinafter referred to as the first simulation results).

[0019] The first identification unit 105 identifies relationships between objects based on the results of the first simulation. The second identification unit 106 identifies objects to be included in the second model based on the relationships identified by the first identification unit 105. The selection unit 107 selects a second model for the digital twin that corresponds to a part of the first model based on the relationships between objects identified based on the results of the first simulation in the first simulation using the first model for the digital twin for executing the first simulation. More specific processing of the setting unit 101, the execution unit 102, the first storage unit 103, the second storage unit 104, the first identification unit 105, the second identification unit 106, and the selection unit 107 will be described later.

[0020] As shown in FIG. 1 , the display device 20 includes a control unit 201 and a display unit 202. The control unit 201 controls the display of the display unit 202. For example, the control unit 201 causes the display unit 202 to display a second model for a digital twin identified based on the results of a first simulation using the first model, in such a way that an area processed using the second model and an area processed without using the second model can be distinguished from each other. Under the control of the control unit 201, the display unit 202 displays an area processed using the second model and an area processed without using the second model in such a way that the area processed using the second model and the area processed without using the second model can be distinguished from each other. Examples of distinguishable displays include a display in which either the area processed using the second model or the area processed without using the second model is framed, a display in which the area processed without using the second model is filled in with a predetermined color as the background, and a display in which the area processed without using the second model is blurred as the background.

[0021] The processes performed by the processing device 10 and the display device 20 described above are merely examples, and the processes described below may be performed.

[0022] (Processing Performed by Simulation System) Fig. 2 is a diagram showing an example of a processing flow of the simulation system 1 according to an embodiment of the present disclosure. Next, processing performed by the simulation system 1 will be described with reference to Fig. 2 and Figs. 3 and 4 described below.

[0023] Below, we will explain the processing of the simulation system 1 by giving a specific example of using the first model (i.e., a model for a digital twin of an object existing in a warehouse) when a robot moves goods by running or grasping goods within a warehouse.

[0024] The first storage unit 103 stores a first model for a digital twin for executing a first simulation (step S1). FIG. 3 is a diagram illustrating an example of a warehouse W according to an embodiment of the present disclosure. FIG. 4 is a diagram illustrating an example of a portion of the warehouse W illustrated in FIG. 3. For example, the first model includes models of all objects within the warehouse W illustrated in FIG. 3, including objects in the portion of the warehouse W illustrated in FIG. 4. The models of all the objects are defined by parameters, such as their shape, size, initial position within the warehouse W, and initial orientation. Furthermore, among the models of all the objects, models of objects that may move or whose orientation may change within the warehouse W have variable parameters for defining a relative change in position from the initial position or a relative change in orientation from the initial orientation. Note that for models of objects that may move or whose orientation may change within the warehouse W, arbitrary initial positions and arbitrary initial orientations are set by the setting unit 101, as described below. In other words, arbitrary initial positions and arbitrary initial orientations can be set for objects that may move or whose orientation may change within the warehouse W.

[0025] As shown in FIG. 3 , the warehouse W includes, for example, a storage space SP1, a sorting space SP2, and a distribution processing space SP3. As shown in FIG. 3 , multiple shelves s1 (e.g., shelves s1a, s1b, s1c, s1d, s1e, and s1f) are installed in the storage space SP1. For example, each of the multiple shelves s1 is a shelf for storing distribution-processed products. For example, each of the multiple shelves s1 is a stationary shelf (i.e., a shelf that cannot be moved while work related to the products is being performed). Therefore, the model of each of the multiple shelves s1 does not have variable parameters related to movement or posture. Note that, although each of the multiple shelves s1 is described here as a stationary shelf, some or all of the multiple shelves s1 may be movable. In this case, the model of the movable shelf s1 may have variable parameters related to movement and posture.

[0026] Also, as shown in FIG. 3 , multiple platforms d1 (e.g., platforms d1a and d1b) are installed in the sorting space SP2. For example, each of the multiple platforms d1 is a platform for sorting products. Each of the multiple platforms d1 is, for example, a stationary platform (i.e., a platform that cannot be moved while a product-related task is being performed). Therefore, the model of each of the multiple platforms d1 does not have variable parameters related to movement or posture. Note that, although each of the multiple platforms d1 is described here as a stationary platform, some or all of the multiple platforms d1 may be movable. In that case, the model of the movable platform d1 may have variable parameters related to movement and posture.

[0027] As shown in FIG. 3, the sorting space SP2 is also provided with a plurality of robots Rt1 that can perform sorting work, as configured by a setting unit 101 (to be described later).

[0028] Also, as shown in FIG. 3, multiple platforms d2 (e.g., platforms d2a, d2b, d2c, and d2d) are installed in the distribution processing space SP3. For example, each of the multiple platforms d2 is a platform for performing distribution processing on products. Each of the multiple platforms d2 is, for example, a stationary platform (i.e., a platform that cannot be moved while work related to the products is being performed). Therefore, the model of each of the multiple platforms d2 does not have variable parameters related to movement or posture. Note that, although each of the multiple platforms d2 is described here as a stationary platform, some or all of the multiple platforms d2 may be movable. In that case, the model of the movable platform d2 may have variable parameters related to movement and posture.

[0029] Figure 4 shows a portion of the storage space SP1 and a portion of the distribution processing space SP3. In the specific example shown here, as shown in Figure 4, in a portion of the storage space SP1 and a portion of the distribution processing space SP3 in the warehouse W, one robot Rt2 performs distribution processing on products on one platform d2 in the distribution processing space SP3, and the processed products are placed on one shelf in the storage space SP1, based on settings made by the setting unit 101 described below. Note that objects such as an imaging device 30 capable of photographing each object shown in Figure 4, and a controller that controls the operation of the robot Rt1 and the robot Rt2, which are not shown in Figures 3 and 4, are also modeled and included in the first model.

[0030] The setting unit 101 sets conditions for a first simulation using a first model for a digital twin (step S2). The conditions for the first simulation include conditions for executing a desired process in the simulation and conditions for obtaining a desired first simulation result. Examples of the conditions for the first simulation include a simulation time, a time step in the simulation, constraints in the simulation, an initial position of an object that may move within the warehouse W, an initial attitude of an object whose attitude may change, information about the movement path of the product, a first threshold value indicating the distance from an object that may move within the warehouse W, and a second threshold value indicating the distance from an object whose attitude may change. For example, a user inputs the conditions for the first simulation to the setting unit 101. The setting unit 101 then sets the conditions for the first simulation input by the user in a predetermined setting location. Examples of methods for the user to input the conditions for the first simulation to the setting unit 101 include a method in which the user directly inputs the conditions for the first simulation via a user interface such as an input device such as a touch panel, and a method in which the setting unit 101 reads and inputs the conditions for the first simulation from a file containing the conditions for the first simulation. However, the method in which the user inputs the conditions for the first simulation to the setting unit 101 is not limited to the above. As long as the conditions for the first simulation are appropriately input to the setting unit 101, any method may be used to input the conditions for the first simulation to the setting unit 101.

[0031] The simulation time corresponds to real time in the real world corresponding to the first simulation. In other words, the simulation time sets the time required to reproduce the real world. The time step in the simulation is a value that determines how precisely the simulation is performed relative to the simulation time. In other words, the smaller the time step, the smoother the movement of objects becomes, similar to the movement of objects in the real world. However, the smaller the time step, the greater the amount of calculation required in the simulation and the longer the time required to perform the simulation. The constraints in the simulation correspond to the constraints in the real world corresponding to the first simulation. Examples of constraints include the travelable area of ​​the robots Rt1 and Rt2, the range of motion of the robot arms of the robots Rt1 and Rt2, and no-entry areas such as obstacles that cannot be used as product movement paths. Examples of information regarding the product movement path include coordinates within the warehouse W that directly indicate the product movement path, and the origin and destination of the product movement. The first threshold and the second threshold are thresholds for identifying objects to be included in the second model. For example, the first threshold value and the second threshold value are set based on the idea of ​​modeling an object that moves or changes its posture within the threshold value. Note that the first threshold value and the second threshold value may be set in any way as long as appropriate values ​​are set for each object. For example, the first threshold value and the second threshold value may be the same value. Furthermore, for example, different values ​​may be set for each object.

[0032] The execution unit 102 executes a first simulation using the first model based on the conditions set by the setting unit 101 (step S3). For example, to create a model in which one robot Rt2 performs distribution processing on a product on one platform d2 in the distribution processing space SP3 and places the processed product on one shelf in the storage space SP1, the setting unit 101 sets parameters for the initial position and initial posture of the model of the robot Rt1 to be fixed. Furthermore, the setting unit 101 sets point A in FIG. 3 as the origin and point B in FIG. 3 as the destination, as information about the product movement path. Furthermore, the setting unit 101 sets a simulation time, a time step in the simulation, constraints in the simulation, an initial position of an object that may move within the warehouse W, an initial posture of an object whose posture may change, a first threshold value indicating the distance from an object that may move within the warehouse W, and a second threshold value indicating the distance from an object whose posture may change. In this case, for example, the controller controlling the operation of the robot Rt2 is modeled as AI (Artificial Intelligence). Specifically, for example, the controller is modeled using a trained model in which parameters indicating the weighting of data connections between nodes in a neural network, which is a learning model, are determined by learning using training data. Note that training data is data used to determine parameter values ​​in a learning model in which parameter values ​​have not yet been determined. In this case, the training data includes, for example, a plurality of pairs of data in which the source and destination of the product, and simulation constraints are used as input data, and control signals for the robot Rt2 are used as output data to realize the operation of the robot Rt2 corresponding to the source, destination, and product movement path in accordance with the constraints. The trained model is then generated by inputting the input data to the controller and changing the values ​​of the parameters indicating the weighting of data connections between nodes so that the corresponding control signals are output. Examples of product movement paths in accordance with the source, destination, and constraints include a path that minimizes the product movement path and a path that minimizes the energy consumption of the robot Rt2.

[0033] The execution unit 102 inputs information about the product's path, such as the product's origin and destination, and simulation constraints, into the controller modeled by the learned model. The execution unit 102 then executes a simulation to control the robot Rt2 using the control signal for the robot Rt2, which is the output of the controller. That is, for all objects in the warehouse W whose initial positions and initial orientations are set, the execution unit 102 controls one robot Rt2 using the control signal for the robot Rt2, which is the output of the controller. The execution unit 102 executes a simulation with the accuracy set by the time step, in which the robot Rt2 performs distribution processing on the products on one table d2 in the distribution processing space SP3 and places the processed products on one shelf in the storage space SP1. As a result, data indicating the position and orientation of each object for each time step corresponding to the actual time set by the simulation time is obtained as a first simulation result. The execution unit 102 then writes the obtained first simulation result to the second storage unit 104 (step S4). The execution unit 102 performs the processing of step S4 for each time step.

[0034] The controller model may be one in which the value of a parameter indicating the weighting of data connections between nodes is changed by reinforcement learning. For example, as a reward in reinforcement learning, a route that minimizes the movement path of the product depending on the source and destination, or a route that minimizes the amount of energy consumed by the robot Rt2, may be set. Then, the parameter indicating the weighting of data connections between nodes in the controller may be changed so as to maximize the reward obtained in the first simulation result by the execution unit 102. The reinforcement learning may be performed in a first simulation unit in which the product moves from the source to the destination. The reinforcement learning may also be performed in a simulation unit of any length during the movement of the product from the source to the destination.

[0035] The first identification unit 105 identifies the relationship between the objects based on the first simulation result (step S5). For example, the first identification unit 105 identifies objects that have moved for all time steps from the first simulation result, which is data indicating the position of each object for each time step corresponding to real time set by the simulation time. Then, for each time step, the first identification unit 105 determines whether all objects other than the identified object (i.e., the moved object) are within a first threshold value from the identified object. If the first identification unit 105 determines that an object is within the first threshold value, it determines whether the object is in contact with the identified object (i.e., the moved object). If the first identification unit 105 determines that the object is in contact with the identified object (i.e., the moved object), it assigns, for example, a code O1 to the object and writes the object's identifier and the code O1 in association with each other in the second storage unit 104. Furthermore, if the first identification unit 105 determines that there is no contact with the identified object (i.e., the moved object), it assigns, for example, a code O2 to the object, associates the object's identifier with the code O2, and writes them into the second memory unit 104.

[0036] Furthermore, for example, the first identification unit 105 identifies objects whose postures have changed for all time steps from data indicating the postures of each object for each time step during the first simulation result, which corresponds to real time set by the simulation time. Then, for each time step, the first identification unit 105 determines whether all objects other than the identified object (i.e., the object whose posture has changed) are within a second threshold value from the identified object. If the first identification unit 105 determines that an object is within the second threshold value, it determines whether the object is in contact with the identified object (i.e., the object whose posture has changed). If the first identification unit 105 determines that the object is in contact with the identified object (i.e., the object whose posture has changed), it assigns, for example, a code O1 to the object and writes the object's identifier and the code O1 in association with each other in the second storage unit 104. Furthermore, if the first identification unit 105 determines that it is not in contact with the identified object (i.e., the object whose posture has changed), it assigns, for example, a code O2 to the object, associates the object's identifier with the code O2, and writes them into the second memory unit 104.

[0037] The second identification unit 106 identifies objects to be included in the second model based on the relationships identified by the first identification unit 105 (step S6). For example, the second identification unit 106 identifies an object with an identifier associated with code O1 and an object with an identifier associated with code O2 in the second storage unit 104. The objects identified by the second identification unit 106 in this manner are objects to be included in the second model based on the relationships identified by the first identification unit 105.

[0038] The selection unit 107 also generates a model that performs a simulation regarding an object that is related to or likely to be related to the object whose posture has changed (step S7). An example of an object that is related to or likely to be related to the object whose posture has changed is an object that satisfies the "condition for determining that the object whose posture has changed is affected." An example of an object that satisfies the "condition for determining that the object whose posture has changed is affected" is an object that is in contact with the object whose posture has changed. For example, the selection unit 107 selects a second model for the digital twin that corresponds to a part of the first model based on the relationship identified by the first identification unit 105.

[0039] Specifically, the selection unit 107 deletes from the first model all models other than the objects identified by the second identification unit 106 (i.e., the objects included in the second model based on the relationships identified by the first identification unit 105). The second model is the first model from which all models other than the objects identified by the second identification unit 106 have been deleted. The selection unit 107 also deletes information related to physical simulation (e.g., the mass and moment of inertia of the object) from the model of the object with the identifier associated with code O2. This is based on the idea that the object with the identifier associated with code O2 is an object that does not move, and information related to physical simulation of the object with the identifier associated with code O2 is not used in the simulation. Deleting this information related to physical simulation can reduce the data size of the second model.

[0040] Specifically, for example, suppose the first identification unit 105 associates the identifiers of shelves s1c, s1e, and platforms d2a, d2c, and d2d with a code O2 and writes them into the second storage unit 104. Furthermore, suppose the first identification unit 105 associates the identifiers of shelves s1d and platform d2b with a code O1 and writes them into the second storage unit 104. In this case, the selection unit 107 deletes the models of shelves s1a, s1b, and s1f, platforms d1a and d1b, and robot Rt1 from the first model. As a result, the selection unit 107 selects the models of shelves s1c, s1d, and s1e, and platforms d2a, d2b, d2c, and d2d as the second model. The selection unit 107 deletes information related to the physical simulation of the selected second model. The selection unit 107 then writes the selected second model into the second storage unit 104.

[0041] The setting unit 101 sets conditions for a second simulation using a second model for the digital twin (step S8). The conditions for the second simulation include conditions for executing a desired process in the simulation and conditions for obtaining a desired second simulation result. Examples of conditions for the second simulation include a simulation time, a time step in the simulation, constraints in the simulation, the initial positions of objects that may move within the warehouse W, the initial attitude of objects whose attitude may change, and information about the movement path of goods. For example, a user inputs the conditions for the second simulation to the setting unit 101. The setting unit 101 then sets the conditions for the second simulation input by the user in a predetermined setting location. Examples of methods for the user to input the conditions for the second simulation to the setting unit 101 include directly inputting the conditions for the second simulation via a user interface such as an input device such as a touch panel, and inputting the conditions by having the setting unit 101 read a file containing the conditions for the second simulation. However, the method for the user to input the conditions for the second simulation to the setting unit 101 is not limited to the above. As long as the conditions for the second simulation are appropriately input to the setting unit 101, any method may be used to input the conditions for the second simulation to the setting unit 101.

[0042] The simulation time here corresponds to real time in the real world corresponding to the second simulation. In other words, the simulation time sets the time required to reproduce the real world. The time step in the simulation is a value that determines how precisely the simulation is executed relative to the simulation time. In other words, the smaller the time step, the smoother the movement of an object becomes, similar to the movement of an object in the real world. However, the smaller the time step, the greater the amount of calculation required in the simulation and the longer the time required to execute the simulation. The constraints in the simulation here correspond to constraints in the real world corresponding to the second simulation. Examples of constraints include the travelable area of ​​the robot Rt2, the range of motion of the robot arm of the robot Rt2, and no-entry areas such as obstacles that cannot be used as a path for moving the product. Examples of information regarding the path for moving the product include coordinates within the warehouse W that directly indicate the path for moving the product, and the source and destination of the movement of the product.

[0043] The execution unit 102 executes a second simulation using the second model based on the conditions set by the setting unit 101 (step S9). For example, to simulate a process in which one robot Rt2 performs distribution processing on a product on one table d2 in the distribution processing space SP3 and places the processed product on one shelf in the storage space SP1, the setting unit 101 sets point A in Figure 3 as the origin and point B in Figure 3 as the destination, as information regarding the product movement path. The setting unit 101 also sets the simulation time, the time step in the simulation, the constraints in the simulation, the initial positions of objects that may move within the warehouse W, and the initial postures of objects that may change posture.

[0044] The execution unit 102 inputs information about the product's path, including the product's origin and destination, and simulation constraints, into the controller. The execution unit 102 then executes a simulation to control the robot Rt2 using the control signal for the robot Rt2 output from the controller. That is, for all objects in the warehouse W whose initial positions and initial orientations are set, the execution unit 102 controls one robot Rt2 using the control signal for the robot Rt2 output from the controller. The execution unit 102 executes a simulation with the accuracy set by the time step, in which the robot Rt2 performs distribution processing on the products on one platform d2 in the distribution processing space SP3 and places the processed products on one shelf in the storage space SP1. As a result, data indicating the position and orientation of each object for each time step corresponding to the actual time set by the simulation time is obtained as a second simulation result. The execution unit 102 generates display data based on the obtained second simulation result (step S10). The display data is data for displaying each object at a corresponding position within the warehouse W for each time step corresponding to the real time set by the simulation time, and is data for displaying the areas processed using the second model and the areas processed without using the second model in a distinguishable manner as the simulation results by the execution unit 102 using the second model.

[0045] The control unit 201 uses the display data generated by the execution unit 102 to cause the display unit 202 to display an area processed using the second model and an area processed without using the second model in a distinguishable manner (step S11). Under the control of the control unit 201, the display unit 202 displays an area processed using the second model and an area processed without using the second model in a distinguishable manner.

[0046] The execution unit 102 may generate, based on the results of the first simulation, data to be displayed on the display unit 202. The data to be displayed on the display unit 202 refers to data for displaying each object at a corresponding position in the warehouse W for each time step corresponding to the real time set by the simulation time.

[0047] (Advantages) The above has described the simulation system 1 according to the first embodiment of the present disclosure. In the processing device 10 included in the simulation system 1, the selection unit 107 (an example of a selection means) selects a second model for a digital twin that corresponds to a part of the first model, based on the relationships between objects identified based on the first simulation results of a first simulation using the first model for a digital twin for executing a first simulation.

[0048] This simulation system 1 makes it possible to create highly convenient information from a model for a digital twin.

[0049] <Modification of Embodiment> Next, a simulation system 1 according to a modification of the embodiment of the present disclosure will be described. In the modification of the embodiment of the present disclosure, the information regarding the product movement path may be coordinates within the warehouse W that indicate the product movement path determined in response to a user operation. For example, the user performs an operation to grasp and move a product using an operation unit for operating the robot arm of the robot Rt2 while viewing a display of the warehouse W displayed on a display such as a head-mounted display. In this case, the movement path and posture of the robot arm that moves in response to the operation may be information regarding the product movement path. The controller may generate a control signal for moving the robot arm of the robot Rt2 in response to the operation. The execution unit 102 may then calculate the product movement path from the movement path and posture of the robot arm and perform the first simulation.

[0050] (Advantages) The simulation system 1 according to the modified example of the embodiment of the present disclosure has been described above. With this simulation system 1, it is possible to use the operation by the user as information regarding the movement path of the product.

[0051] In the above-described embodiments, the display device 20 has been described as including the control unit 201. Also, in the above-described embodiments, the processing device 10 has been described as including the execution unit 102. However, in another embodiment, the processing device 10 may be configured as including the control unit 201. Also, in another embodiment, the display device 20 may have at least one of a function of the execution unit 102 to generate display data by the second simulation and a function of generating data to be displayed on the display unit 202 by the first simulation.

[0052] A simulation system 1 with a minimum configuration according to an embodiment of the present disclosure will be described. FIG. 5 is a diagram illustrating the simulation system 1 with a minimum configuration according to an embodiment of the present disclosure. The simulation system 1 with a minimum configuration according to an embodiment of the present disclosure includes a selection unit 200 (an example of a selection means). The selection unit 200 selects a second model for a digital twin that corresponds to a part of the first model based on the relationship between objects identified based on the results of a first simulation in a first simulation using the first model for a digital twin that executes a first simulation. The selection unit 200 can be realized, for example, using the functions of the selection unit 107 illustrated in FIG. 1.

[0053] Next, a description will be given of the processing of the simulation system 1 with the minimum configuration. Fig. 6 is a diagram showing an example of a processing flow of the simulation system 1 with the minimum configuration. Here, the processing of the simulation system 1 with the minimum configuration will be described with reference to Fig. 6.

[0054] The selection unit 200 selects a second model for the digital twin that corresponds to a part of the first model based on the relationships between objects identified based on the results of the first simulation in the first simulation using the first model for the digital twin that executes the first simulation (step S101). By doing so, the simulation system 1 can create highly convenient information from the model for the digital twin.

[0055] The order of the processes in the embodiments of the present disclosure may be changed as long as the processes are performed appropriately.

[0056] Although the embodiments of the present disclosure have been described, the above-described simulation system 1, processing device 10, display device 20, and other control devices may have a computer device inside. The above-described processing steps are stored in the form of a program on a computer-readable recording medium, and the above processing is performed by reading and executing this program by a computer. Specific examples of computers are shown below.

[0057] 7 is a schematic block diagram showing the configuration of a computer according to at least one embodiment. As shown in FIG. 7 , the computer 5 includes a CPU (Central Processing Unit) 6, a main memory 7, a storage 8, and an interface 9. For example, the simulation system 1, the processing device 10, the display device 20, and other control devices described above are each implemented in the computer 5. The operations of each of the processing units described above are stored in the storage 8 in the form of a program. The CPU 6 reads the program from the storage 8, loads it into the main memory 7, and executes the above-described processing in accordance with the program. The CPU 6 also allocates storage areas in the main memory 7 corresponding to each of the storage units described above in accordance with the program.

[0058] Examples of storage 8 include a hard disk drive (HDD), a solid state drive (SSD), a magnetic disk, a magneto-optical disk, a compact disc read-only memory (CD-ROM), a digital versatile disc read-only memory (DVD-ROM), and a semiconductor memory. Storage 8 may be an internal medium directly connected to the bus of computer 5, or an external medium connected to computer 5 via interface 9 or a communication line. Furthermore, if the program is distributed to computer 5 via a communication line, computer 5 that receives the program may load the program into main memory 7 and execute the above-described processing. In at least one embodiment, storage 8 is a non-transitory tangible storage medium.

[0059] The program may also implement some of the functions described above. Furthermore, the program may be a file that can implement the functions described above in combination with a program already stored in the computer device, a so-called differential file (differential program).

[0060] Although several embodiments of the present disclosure have been described, these embodiments are merely examples and do not limit the scope of the disclosure. Various additions, omissions, substitutions, and modifications may be made to these embodiments without departing from the spirit of the disclosure.

[0061] Note that part or all of the above-described embodiments can be described as, but are not limited to, the following supplementary notes.

[0062] (Supplementary Note 1) A processing device comprising: a selection means for executing a first simulation, and selecting a second model for a digital twin that corresponds to a part of the first model based on a relationship between objects identified based on a first simulation result in the first simulation using the first model for the digital twin.

[0063] (Supplementary Note 2) The processing device according to Supplementary Note 1, further comprising: a first specifying unit that specifies the relationship based on the first simulation result.

[0064] (Supplementary Note 3) The processing device according to Supplementary Note 1 or Supplementary Note 2, further comprising: a second identification means for identifying an object to be included in the second model based on the relationship; and the selection means for selecting the second model based on the object identified by the second identification means.

[0065] (Supplementary Note 4) The processing device according to any one of Supplementary Note 1 to Supplementary Note 3, further comprising: a setting unit that sets conditions for the first simulation.

[0066] (Supplementary Note 5) The processing device according to any one of Supplementary Note 1 to Supplementary Note 4, comprising: an execution means for executing the first simulation.

[0067] (Supplementary Note 6) A processing method comprising: executing a first simulation; and selecting a second model for a digital twin corresponding to a part of the first model based on relationships between objects identified based on the results of the first simulation using the first model for the digital twin.

[0068] (Supplementary Note 7) A recording medium storing a program that causes a computer to execute the following steps: select a second model for a digital twin that corresponds to a part of the first model, based on relationships between objects identified based on the results of a first simulation in which a first simulation is performed using the first model for a digital twin.

[0069] (Supplementary Note 8) A processing device comprising: a generation means for generating display data that displays a second model for a digital twin corresponding to a part of the first model identified based on a first simulation result in a first simulation using the first model for the digital twin, the second model being used to execute a first simulation, and that allows a region processed using the second model and a region processed without using the second model to be distinguishable from each other.

[0070] (Supplementary Note 9) The processing device according to Supplementary Note 8, further comprising: a display means for displaying the display data in a manner that allows a region processed using the second model and a region processed without using the second model to be distinguished from each other.

[0071] (Supplementary Note 10) A processing method for executing a first simulation, which uses a first model for a digital twin to create a second model corresponding to a part of the first model identified based on a first simulation result in the first simulation, and generating display data that displays an area processed using the second model and an area processed without using the second model in a distinguishable manner.

[0072] (Supplementary Note 11) The processing method according to Supplementary Note 10, wherein the display data is displayed so that an area processed using the second model and an area processed without using the second model can be distinguished.

[0073] (Supplementary Note 12) A recording medium storing a program for causing a computer to execute the following: a second model for a digital twin that corresponds to a part of the first model identified based on a first simulation result in a first simulation using the first model for the digital twin; and an area processed using the second model and an area processed without using the second model are displayed in a distinguishable manner.

[0074] (Supplementary Note 13) A recording medium according to Supplementary Note 12, storing a program for causing a computer to execute the following: displaying the display data in a manner that allows areas processed using the second model and areas processed without using the second model to be distinguishable.

[0075] According to each aspect of the present disclosure, highly convenient information can be created from a model for a digital twin.

[0076] REFERENCE SIGNS LIST 1 Simulation system 5 Computer 6 CPU 7 Main memory 8 Storage 9 Interface 10 Processing device 20 Display device 101 Setting unit 102 Execution unit 103 First storage unit 104 Second storage unit 105 First identification unit 106 Second identification unit 107, 200 Selection unit 201 Control unit 202 Display unit

Claims

1. a selection means for executing a first simulation and selecting a second model for the digital twin corresponding to a part of the first model based on a relationship between objects identified based on a first simulation result in the first simulation using the first model for the digital twin; A processing device comprising:

2. a first specifying means for specifying the relationship based on the first simulation result; The processing device of claim 1 , comprising:

3. a second identification means for identifying an object to be included in the second model based on the relationship; Equipped with The selection means selecting the second model based on the object identified by the second identification means; The processing device of claim 1 .

4. a setting means for setting conditions for the first simulation; The processing device of claim 1 , comprising:

5. an execution means for executing the first simulation; The processing device of claim 1 , comprising:

6. A processing device comprising: performing a first simulation; and selecting a second model for the digital twin corresponding to a part of the first model based on a relationship between objects identified based on a first simulation result of the first simulation using the first model for the digital twin; Processing method.

7. executing a first simulation using a first model for a digital twin, and selecting a second model for the digital twin corresponding to a part of the first model based on relationships between objects identified based on a first simulation result of the first simulation using the first model for the digital twin; A program that causes a computer to execute the following.

8. a generation means for executing a first simulation, which generates display data for displaying a second model for a digital twin corresponding to a part of the first model identified based on a first simulation result in the first simulation using the first model for the digital twin, the second model being a part of the first model, in such a way that an area processed using the second model and an area processed without using the second model can be distinguished from each other; A processing device comprising:

9. A processing device comprising: A first simulation is performed, and a second model for the digital twin corresponding to a part of the first model identified based on a first simulation result in the first simulation using the first model for the digital twin is generated, and display data is generated that displays an area processed using the second model and an area processed without using the second model in a distinguishable manner. Processing method.

10. Executing a first simulation, a second model for a digital twin corresponding to a part of the first model identified based on a first simulation result in the first simulation using the first model for the digital twin, and generating display data for displaying an area processed using the second model in a manner that allows an area processed without using the second model to be distinguished; A program that causes a computer to execute the following.