DATA COLLECTION SYSTEM, AUTOMATED WORK SYSTEM, DATA COLLECTION PROGRAM, AND AUTOMATED WORK PROGRAM GENERATION PROGRAM
Patent Information
- Application Number
- FR2024009638
- Authority / Receiving Office
- FR · FR
- Patent Type
- Applications
- Current Assignee / Owner
- Priority Date
- 2023-09-14
- Filing Date
- 2024-09-11
- Publication Date
- 2025-03-21
Smart Images
Figure 00000000_0000_ABST
Abstract
Description
Title of the invention: DATA COLLECTION SYSTEM, AUTOMATED WORK SYSTEM, DATA COLLECTION PROGRAM, AND AUTOMATED WORK PROGRAM GENERATION PROGRAM Technical field
[0001] The present disclosure relates to a data collection system, an automated work system, a data collection program and an automated work program generation program. State of the art
[0002] An automated work system that controls an operation of a control target such as a robot by an automated work program generated in advance, and causes the robot to perform predetermined work has been provided. For example, JP 2018-206286 A discloses a technology in which a simulated model of an operation by a worker is constructed by machine learning learning the data necessary to generate an automated work program in units of work items.
[0003] In the technology disclosed in JP 2018-206286 A, machine learning of a huge amount of training data in units of work items is required to construct the simulated model. Therefore, a problem arises in that the data required to generate the automated work program cannot be collected efficiently.
[0004] It is therefore desirable to provide a data collection system which is capable of efficiently and appropriately collecting the data necessary to generate an automated work program, an automated work system, a data collection program, and an automated work program generation program. Summary
[0005] A first aspect of the present disclosure relates to a data collection system which collects data necessary for generating an automated work program causing a control target to automatically perform a predetermined job. The data collection system comprises: a work guide presentation instruction unit which instructs the presentation of a work guide indicating a work process for the work items; a an operation log acquisition unit that acquires an operation log from a log collection system during execution of the work item; an image log acquisition unit that acquires an image log from the log collection system during execution of the work item; a time data acquisition unit that acquires time data indicating the time required to execute the work item; an evaluation data acquisition unit that acquires evaluation data indicating the evaluation of an execution result of the work item; and a data storage control unit that causes a work item log to be stored in a data storage unit, in the work item units in association with the operation log, the image log, the time data, and the evaluation data.
[0006] A second aspect of the present disclosure relates to an automated work system which generates data necessary for generating an automated work program causing a control target to automatically perform a predetermined work is collected and the automated work program. The automated work system comprises: a work guide presentation instruction unit which instructs presentation of a work guide indicating a work process for work items; an operation log acquisition unit which acquires an operation log from a log collection system during execution of the work item; an image log acquisition unit which acquires an image log from the log collection system during execution of the work item;a time data acquisition unit that acquires time data indicating the time required to execute the work item; an evaluation data acquisition unit that acquires evaluation data indicating the evaluation of an execution result of the work item; a data storage control unit that causes a work item log to be stored in a data storage unit, in the work item units in association with the operation log, the image log, the time data, and the evaluation data; and an automated work program generation unit that generates the automated work program on the basis of the work item logs in the work item units stored in the data storage unit.
[0007] A third aspect of the present disclosure relates to a non-transitory computer-readable storage medium having stored therein a data collection program that is read and executed by a processor included in a control unit of a data collection system that collects the data necessary to generate an automated work program causing a control target to be performed. automatically a predetermined job. When read and executed by the processor, the data collection program causes the processor to implement: a job guide presentation instruction step instructing presentation of a job guide indicating a work process for the work items; an operation log acquisition step acquiring an operation log of a log collection system during execution of the work item; an image log acquisition step acquiring an image log of the log collection system during execution of the work item; a time data acquisition step acquiring time data indicating the time required to execute the work item; an evaluation data acquisition step acquiring evaluation data indicating evaluation of an execution result of the work item;and an evaluation data acquisition step causing a work item log to be stored in a data storage unit, in the work item units in association with the operation log, the image log, the time data and the evaluation data.;
[0008] A fourth aspect of the present disclosure relates to a non-transitory computer-readable storage medium in which is stored an automated work schedule generation program that is read and executed by a processor included in a control unit of an automated work system having a data collection system that collects data necessary for generating an automated work schedule causing a control target to automatically perform predetermined work and a control target that automatically performs the predetermined work. When read and executed by the processor, the automated work schedule generation program causes the processor to implement: a work guide presentation instruction step instructing presentation of a work guide indicating a work process for the work items;an operation log acquisition step acquiring an operation log from a log collection system during execution of the work item; an image log acquisition step acquiring an image log from the log collection system during execution of the work item; a time data acquisition step acquiring time data indicating the time required to execute the work item; an evaluation data acquisition step acquiring evaluation data indicating the evaluation of an execution result of the work item; a data storage control step causing a work item log to be stored in a data storage unit, in the work item units in association with the operation log, the image log, the time data and the data; evaluation; and an automated work program generation step generating the automated work program based on the work item logs in the work item units stored in the data storage unit.
[0009] As a result of issuing the work guide presentation instruction, a worker can divide the work operation into the work item units based on the work guide and collect data. With reference to the time data or the evaluation data, the work item logs having excellent time data or evaluation data can be selected as optimal work item logs in the work item units. As a result of combining the selected optimal work item logs in the work item units, the automated work program can be generated. Therefore, machine learning of a huge amount of learning data in the work item units is not required. The data required to generate the automated work program can be collected appropriately and efficiently. Brief description of the drawings
[0010] In the accompanying drawings:
[0011] [Fig. 1] [Fig. 1] is a functional block diagram illustrating an overall configuration according to a first embodiment;
[0012] [Fig.2] [Fig.2] is a functional block diagram illustrating a control unit;
[0013] [Fig.3] [Fig.3] is a diagram illustrating work elements;
[0014] [Fig.4] [Fig.4] is a diagram illustrating a permutation of logs of optimal work elements;
[0015] [Fig.5] [Fig.5] is a diagram illustrating a mode of connection of an automated work system;
[0016] [Fig.6] [Fig.6] is a diagram illustrating another mode of connection of the automated work system;
[0017] [Fig.7] [Fig.7] is a flowchart illustrating a data collection process;
[0018] [Fig.8] [Fig.8] is a flowchart illustrating an automated work program generation process;
[0019] [Fig.9] [Fig.9] is a flowchart illustrating an automated work program execution process; and
[0020] [Fig. 10] [Fig. 10] is a functional block diagram illustrating an overall configuration according to a second embodiment. Description of the embodiments
[0021] Several embodiments, in which the present disclosure is applied to a data collection system that collects data necessary for generating an automated work program causing a robot to automatically perform a job of dismantling a scrap automobile, will be described hereinafter. The description of sections identical to those of previous embodiments may be omitted in later embodiments. Here, the present disclosure may also be applied to others as long as the system makes it possible to collect data necessary for generating an automated work program causing a control target to automatically perform a predetermined job, in addition to the automated work program causing a robot to automatically perform the job of dismantling a scrap automobile. First embodiment of the invention
[0022] A first embodiment will be described with reference to [Fig. 1] to 9. The first embodiment provides the example of a case where the data necessary for generating an automated work program is collected using a robot that performs the work of dismantling a junk automobile that is actually a real machine. In this case, a data collection system and an automated work system have an identical relationship. The data collection system and the automated work system have an identical relationship in the case of a configuration where the data necessary for generating an automated work program is collected using a control target that performs predetermined work using a real machine, i.e., where the data collection system comprises the control target.The relationship between the data collection system and the automated work system is such that the automated work system includes the data collection system in the case of a configuration where the data necessary to generate an automated work program is collected using a control target that performs predetermined work using a model, simulator and the like, described below, and where the data collection system does not include the control target.
[0023] As shown in [Fig.l], an automated work system 1 has an identical relationship to a data collection system 2. The automated work system 1 comprises a log collection system 3 which collects logs accompanying the dismantling of a scrap automobile (corresponding to a work target), a control unit 4 which controls the entire system, and a database 5 (corresponding to a data storage unit). The control unit 4 and the database 5 may be integrated or separated. The database 5 may also be managed in the cloud.
[0024] The log collection system 3 comprises an instructor robot 6 and a disassembly system 7 which performs the work of disassembling a junk automobile. That is, the disassembly system 7 is controlled as a part of the log collection system 3. The disassembly system 7 comprises an executing robot 8 (corresponding to a control target) and a camera 9 which captures images of the executing robot 8. The instructor robot 6 and the executing robot 8 are connected so as to be able to exchange data by a wired circuit or a wireless circuit.
[0025] The instructor robot 6 is operated by a worker who performs the work of dismantling the junk automobile. The instructor robot 6 operates to follow an operation from the worker and outputs an operation instruction signal indicating the operation to the executing robot 8. The executing robot 8 performs the work of dismantling the junk automobile. When the operation instruction signal is input from the instructor robot 6, the executing robot 8 analyzes the input operation instruction signal and operates based on the analysis result. That is, the executing robot 8 operates to follow the instructor robot 6.Furthermore, when the operation instruction signal is input from the control unit 4 by executing an automated work program, the executing robot 8 operates on the basis of the input operation instruction signal and automatically performs the work of dismantling the unusable automobile without requiring the operation from the worker.
[0026] The disassembly system 7 may include, for example, a turntable capable of rotating in a horizontal direction in a state where the scrap automobile is placed thereon. For example, the executing robot 8 may be a six-axis articulated robot having six axes in an X-axis direction, a Y-axis direction, and a Z-axis direction, and around the X-axis, the Y-axis, and the Z-axis. The executing robot 8 performs operations in the axial directions and operations around the axes in a three-dimensional space. For example, in the executing robot 8, an attachment having a pair of movable teeth may be attached to a tip end portion of an arm so as to swing and rotate freely. The executing robot 8 disassembles the scrap automobile by grasping, pulling, breaking, and bending a portion of the scrap automobile in three dimensions from an arbitrary direction using the pair of movable teeth of the attachment.The robot executing 8 outputs time series data indicating the operation of dismantling the junk car in the form of an operation log. The operation log includes a position log indicating a position of the robot executing 8 and an attitude log indicating an attitude. Here, the configuration of the robot executing 8 described above is an example. Any configuration having a shape, a number of units, . a size and the like is possible as long as the robot executing 8 is able to dismantle the unusable automobile.
[0027] The disassembly of the scrap automobile is carried out successively in the work element units prescribed in advance. As also shown in [Fig. 3], steps described below for disassembling the scrap automobile are, for example, divided into "1. Disassembly of front door", "2. Disassembly of B-pillar", "3. Disassembly of front seat", and "4. Disassembly of steering wheel". Furthermore, the step "1. Disassembly of front door" is, for example, subdivided into "1-1. Installation of a door lowering guide column (left and right)", "1-2. Cutting of the section below the hinge (left and right)", and "1-3. Cutting of the section above the hinge (left and right)". Step "2. B-pillar removal" is for example divided into "2-1. Cutting the lower part of the B-pillar (left and right)", and "2-2. Cutting the upper part of the B-pillar (left and right)". Similarly, steps "3. Front seat removal" and "4.Dismantling of the steering wheel" are also divided into a plurality of steps. In this case, a work unit into which the work is finally divided is a work element unit. Here, the steps of dismantling the unusable automobile also include other steps than those described above. These steps can be carried out successively by a single worker or can be distributed among a plurality of workers.
[0028] For example, the camera 9 may be defined so as to be movable on a rail that is laid on an overall periphery of the scrap automobile. The camera 9 has an autofocus function for automatically adjusting a focal point using a sensor, a motor, and the like, as well as a function for detecting distance and size of an image area. The camera 9 simultaneously captures images of a working section of the scrap automobile and the attachment on the executing robot 8, and outputs the captured images including the distance and size, as well as the time series data indicating imaging positions as an image log. Here, the camera 9 may be a single camera or a plurality of cameras.
[0029] The control unit 4 comprises a communication unit 4a, a storage unit 4b, and a calculation unit 4c. The communication unit 4a is an interface for transmitting and receiving electrical signals. The communication unit 4a outputs electrical signals to and receives them from the log collection system 3, the database 5, and the like. The storage unit 4b is a tangible, non-transitory storage medium that non-temporarily stores data, programs, and the like, which can be read by a computer or a processor. The storage unit 4b has a volatile memory and a non-volatile memory, and can be a memory type, a disk type, a tape type and the like. The storage unit 4b stores various types of data input to the communication unit 4a, various programs and various reference values used by the calculation unit 4c for calculation processes, various processing results by the calculation unit 4c and the like.
[0030] The computing unit 4c has a processor. The processor includes, among the constituent elements of a computer, a processing unit that performs computing and converting data, executing programs, controlling other devices, and the like. The processor generally includes a central processing unit (CPU) that controls an entire computer or a microprocessing unit (MPU; microprocessor) in which some of the functions of the CPU are integrated. The computing unit 4c processes electrical signals input from the outside via the communication unit 4a based on a predetermined procedure, and outputs the processed electrical signals to the outside based on the predetermined procedure via the communication unit 4a.
[0031] As shown in [Fig.2], the control unit 4 comprises a data collection unit 10, an automated work program generation unit 11, and an automated work program execution unit 12 for each function. Using a data collection program, the data collection unit 10 collects the data necessary for generating the automated work program by the calculation unit 4c which performs a data collection process. Using an automated work program generation program, the automated work program generation unit 11 generates the automated work program by the calculation unit 4c which performs an automated work program generation process.Using an automated work program execution program, the automated work program execution unit 12 executes the automated work program by the calculation unit 4c which performs an automated work program execution process. The data collection program, the automated work program generation program and the automated work program execution program are stored in the storage unit 4b. Here, the calculation unit which performs the data collection process, the calculation unit which performs the automated work program generation process and the calculation unit which performs the automated work program execution process may be separate calculation units.In addition, the storage unit that stores the data collection program, the storage unit that stores the automated work program generation program, and the storage unit that stores the automated work program execution program may be separate storage units.
[0032] The data collection unit 10 comprises a work guide presentation instruction unit 13, a work start identification unit 14, a work end identification unit 15, an operation log acquisition unit 16, an image log acquisition unit 17, a time data acquisition unit 18, an evaluation data acquisition unit 19, a data storage control unit 20, and a work guide reflection unit 21.
[0033] The work guide presentation instruction unit 13 outputs a work guide presentation instruction signal indicating a work process for the work items to a work guide presentation unit 26, and causes the work guide presentation unit 26 to present the work guide. For example, the work guide presentation unit 26 may be a monitor that displays the work guide. The worker operates the instructor robot 6 while viewing the work guide presented in the work guide presentation unit 26 and performs the work of dismantling the unusable automobile manually. The present embodiment provides as an example a configuration in which the work guide is displayed.However, a configuration in which the work guide is output audibly, or a configuration in which both the display and the audio output of the work guide are used is also possible.
[0034] The worker performs a start operation via a work start input unit 27 at the start of each work item. Upon receiving the start operation for the work item from the worker, the work start input unit 27 outputs a work start reception signal to the work start identification unit 14. The work start identification unit 14 identifies the start of the work item when the work start reception signal is input from the work start input unit 27. Here, the start of the work item can be identified based on the operation log or the image log, for example, in addition to the start operation from the worker.
[0035] The worker performs an end operation via a work end input unit 28 at the end of each work item. Upon receiving the end operation for the work item from the worker, the work end input unit 28 outputs a work end reception signal to the work end identification unit 15. The work end identification unit 15 identifies the end of the work item when the work end reception signal is input from the work end input unit 28. Here, the end of the work item can be identified based on the operation log or the image log, for example, in addition to the end operation from the worker. Furthermore, when the work items are performed successively, the end of a preceding work item can be identified by identifying the start of a subsequent work item.
[0036] The operation log acquisition unit 16 acquires the operation log input from the executing robot 8 of the disassembly system 7. The image log acquisition unit 17 acquires the image log input from the camera 9 of the disassembly system 7.
[0037] A time measurement unit 29 outputs time data to the time data acquisition unit 18. The time data acquisition unit 18 acquires the time data indicating an amount of time required to complete the work item based on the difference between the time when the start of the work item is identified by the work start identification unit 14 and the time when the end of the work item is identified by the work end identification unit 15. That is, if a single worker performs the same work item multiple times, or if multiple workers perform the same work item, each execution of the work item can be evaluated as good or bad based on the time data.
[0038] When an evaluation data input operation from the worker is received, an evaluation data input unit 30 outputs to the evaluation data acquisition unit 19 an evaluation data reception signal indicating the evaluation data received through the input operation. An evaluation data generation unit 31 generates the evaluation data by a predetermined evaluation algorithm prescribed in advance, and outputs to the evaluation data acquisition unit 19 an evaluation data generation signal indicating the generated evaluation data. The evaluation data acquisition unit 19 acquires the evaluation data when the evaluation data reception signal is input from the evaluation data input unit 30 or when the evaluation data generation signal is input from the evaluation data generation unit 31.That is, if a single worker performs the same work item multiple times or if multiple workers perform the same work item, each execution of the work item can be evaluated as good or bad based on the evaluation data.
[0039] The evaluation data is an index that indicates an evaluation of an execution result of the work item. For example, the evaluation data is evaluation data based on a degree of load placed on the executing robot 8 when the executing robot 8 performs the work of dismantling the scrap automobile, evaluation data based on a degree of damage to the scrap automobile, or evaluation data based on a degree of damage to a recyclable component. For example, the evaluation data may be a numerical evaluation score. The recyclable component is, for example, a component such as a side mirror or a bumper attached to the car is out of use and is a component that can be reused if the degree of damage is relatively low.
[0040] For example, if the degree of load placed on the executing robot 8 is relatively small, the evaluation data is relatively high. If the degree of load placed on the executing robot 8 is relatively large, the evaluation data is relatively low. If the degree of damage to the scrap automobile is relatively small, the evaluation data is relatively high. If the degree of damage to the scrap automobile is relatively large, the evaluation data is relatively low. If the degree of damage to the recyclable component is relatively small, the evaluation data is relatively high. If the degree of damage to the recyclable component is relatively large, the evaluation data is relatively low.The present embodiment provides as an example a configuration in which both the evaluation data input unit 30 and the evaluation data generation unit 31 are used. However, a configuration comprising only one or the other of the evaluation data input unit 30 and the evaluation data generation unit 31 is also possible.
[0041] As shown in [Fig. 3], the data storage control unit 20 stores in the database 5 the operation logs acquired by the operation log acquisition unit 16, the image logs acquired by the image log acquisition unit 17, the time data acquired by the time data acquisition unit, and the evaluation data acquired by the evaluation data acquisition unit 19, in association with the work item logs in the work item units. In this case, if multiple workers are involved, the data storage control unit 20 stores the work item logs in the work item units for each worker.
[0042] The work guide reflection unit 21 reflects the work item logs in the work item units stored in the database 5 in the work guide. The automated work program generation unit 11 generates the automated work program by combining optimal work item logs described below. The automated work program generation unit 11 has a permutation generation unit 22, an operation speed adjustment unit 23, an operation trajectory interpolation unit 24, and an operation confirmation unit 25.The permutation generation unit 22 selects the optimal work item logs in the work item units according to a predetermined rule on the basis of the operation logs, the image logs, the time data, and the evaluation data, and generates a permutation of the selected optimal work item logs.
[0043] For example, if the rule is to select the work items having the highest evaluation data, the permutation generation unit 22 selects the work items having the highest evaluation data in the work item units. For example, if the rule is to select the work items having the shortest time data, the permutation generation unit 22 selects the work items having the shortest time data in the work item units.
[0044] When selecting the work items having the highest evaluation data in the work item units, as shown in [Fig. 4], if the evaluation data of a worker A is the highest with respect to the work item "1-1. Installation of a door lowering guide column (left and right)", the permutation generation unit 22 selects, for example, the work item log of worker A as the optimal work item log. If the evaluation data of a worker C is the highest with respect to the work item "1-2. Cutting of the section below the hinge (left and right)", the permutation generation unit 22 selects, for example, the work item log of worker C as the optimal work item log.The permutation generation unit 22 similarly selects the optimal work item logs for all work items.
[0045] After selecting the optimal work item logs for all work items, the permutation generation unit 22 generates a permutation of the selected optimal work item logs. As described above, the permutation generation unit 22 selects, for example, the work item log of worker A as the optimal work item log for work item "1-1. Installation of a door lowering guide column (left and right)", selects, for example, the work item log of worker C as the optimal work item log for work item "1-2. Cutting the section below the hinge (left and right)", and selects the optimal work item logs for the following work items. Then, the permutation generation unit 22 generates a permutation of the selected optimal work item logs.
[0046] The operation speed setting unit 23 sets the speed of an operation of the executing robot 8 for the work items in the permutation of the optimal work item logs generated by the permutation generation unit 22. For example, the operation speed setting unit 23 determines whether an operation log that does not involve contact between the attachment on the executing robot 8 and the disabled automobile is present in the operation logs indicating that the worker is working at a low speed. When it is determined that an operation log operations that do not involve contact between the accessory on the executing robot 8 and the unusable automobile is present, the operation speed adjustment unit 23 retrieves the operation log and sets the operation speed so that the operation speed of the executing robot 8 is improved to reach a limit speed for the segment of the retrieved operation log. That is, the operation speed adjustment unit 23 sets the operation speed to exceed the working speed of the worker in the segment of the operation log that does not involve contact between the accessory on the executing robot 8 and the unusable automobile.
[0047] Furthermore, the operation speed adjustment unit 23 adjusts the operation speed of the executing robot 8 by taking into account the speed differences before and after the work item. At the time of switching from one work item to the next, the difference between the operation speed of the executing robot 8 at the end of the previous work item and the operation speed of the executing robot 8 at the beginning of the next work item is preferably small. When the difference in the operation speed of the executing robot 8 at the time of switching from one work item to the next is large, the operation of the executing robot 8 at the time of switching from one work item to the next may lose smoothness. The operation speed adjustment unit 23 calculates the difference in the operation speed of the executing robot 8 between the previous work item and the next work item.If the calculated difference is equal to or greater than a predetermined value, the operation speed adjustment unit 23 adjusts the operation speed of the executing robot 8 for the work items so that the difference in operation speed of the executing robot 8 between the previous work item and the next work item is less than the predetermined value.
[0048] That is, the operation speed setting unit 23 calculates, for example, the difference between the operation speed of the robot executing 8 at the end of the previous work item and the operation speed of the robot executing 8 at the start of the next work item. For example, if the operation speed of the robot executing 8 at the end of the previous work item is faster than the operation speed of the robot executing 8 at the start of the next work item and the difference is equal to or greater than the predetermined value, the operation speed setting unit 23 sets the operation speed of the robot executing 8 at the end of the previous work item to be slower, or sets the operation speed of the robot executing 8 at the start of the next work item to be faster, thereby eliminating the difference in the operation speed of the robot executing 8 at the time of switching from one work item to another.For example, if the operation speed of the robot executing 8 at the end of the previous work item is slower than the operation speed of the robot executing 8 at the start of the next work item and the difference is equal to or greater than the predetermined value, the operation speed adjustment unit 23 adjusts . the operating speed of the robot executing 8 at the end of the previous work item to be faster, or sets the operating speed of the robot executing 8 at the start of the next work item to be slower, thus removing the difference in operating speed of the robot executing 8 when switching from one work item to the next.
[0049] The operation trajectory interpolation unit 24 interpolates the trajectory of an operation of the executing robot 8 between the work items in the permutation of the optimal work item logs generated by the permutation generation unit 22. The operation trajectory indicates the trajectory of an operation corresponding to the position and attitude of the executing robot 8. At the time of switching from one work item to another, the operation trajectory of the executing robot 8 at the end of the previous work item and the operation trajectory of the executing robot 8 at the beginning of the next work item preferably coincide. If the operation trajectories of the executing robot 8 at the time of switching from one work item to another do not coincide, the operation of the executing robot 8 at the time of switching from one work item to another may lose smoothness.The operation trajectory interpolation unit 24 calculates the operation trajectory difference before and after the work item and linearly interpolates the operation trajectory of the executing robot 8 based on the calculated difference.
[0050] That is, the operation trajectory interpolation unit 24 linearly interpolates the operation trajectory of the executing robot 8 so that the three-dimensional coordinates of a specific point of the executing robot 8 at the end of the previous work item and the three-dimensional coordinates of a specific point of the executing robot 8 at the beginning of the next work item are connected by a straight line. Here, in a case in which an obstruction is present on a linear path formed by linear interpolation, the operation trajectory interpolation unit 24 interpolates the operation trajectory of the executing robot 8 so as to avoid the obstruction.
[0051] The operation confirmation unit 25 confirms the operation of the automated work program by a simulator which reproduces the operation of the executing robot 8 in a virtual space.
[0052] The automated work program execution unit 12 executes the automated work program generated by the automated work program generation unit 11.
[0053] As shown in [Fig.5] and [Fig.6], the data collection system 2 configured as described above can be connected to another data collection system 2 by a communication network in order to be able to exchange data. For example, as a mode in which a plurality of data collection systems data 2 are connected, there is a mode in which a data aggregation server that aggregates data from a plurality of data collection systems 2 is set, and a mode in which a data aggregation server is not set.
[0054] As shown in [Fig. 5], in the mode in which the data aggregation server is set, the plurality of data collection systems 2 and a data aggregation server 32 (corresponding to a data aggregation unit) are connected by a communication network 33 so as to be able to exchange data. The data aggregation server 32 is connected to an aggregation database 34. The work item logs in the work item units stored in the database 5 of each data collection system 2 are transmitted to the data aggregation server 32 over the communication network 33 from each data collection system 2, for example at a time when a recorded content of the database 5 is updated, or at a fixed periodic time, and then aggregated in the aggregation database 34 and shared.That is, in a case in which the data collection systems 2 are defined in a plurality of disassembly plant bases A, B, and C for example, the work item logs in the work item units of a worker at disassembly plant A, a worker at disassembly plant B, and a worker at disassembly plant C are aggregated in the aggregation database 34. If there are a plurality of workers in each of the disassembly plants A, B, and C, the respective work item logs in the work item units of the plurality of workers at disassembly plant A, the plurality of workers at disassembly plant B, and the plurality of workers at disassembly plant C are aggregated in the aggregation database 34.
[0055] The work item logs in the work item units aggregated in the aggregation database 34 are provided to the automated work system 1 over the communication network 33 from the data aggregation server 32, for example at the time when the recorded contents of the aggregation database 34 are updated or at a fixed periodic time. That is, the work item logs in the work item units from the plurality of databases are provided to the automated work system 1.In the automated work system 1, when the automated work schedule generation unit 11 generates the automated work schedule as described above, the automated work schedule generation unit 11 may select the optimal work item logs from the work item logs stored in its own database 5, i.e., local work item logs corresponding to a base, or may select the optimal work item logs from the work item logs output by the data aggregation server 32. that is, globalized work item logs corresponding to the plurality of bases.
[0056] As shown in [Fig. 6], in the mode in which the data aggregation server is not defined, the plurality of data collection systems 2 are connected by the communication network 33 so as to be able to exchange data. In this case, the database 5 of each data collection system 2 relates to the function of the aggregation database 34 of the data aggregation server 32 described above. The work item logs in the work item units stored in the database 5 of each data collection system 2 are, for example, from the data collection system 2 to another data collection system 2 over the communication network 32 and shared, for example, at the time when the recorded contents of the aggregation database 34 are updated or at a fixed periodic time.The work item logs in the work item units stored in the database 5 of each data collection system 2 are used by the automated work system 1 or provided to the automated work system 1 over the communication network 33, for example at the time when the recorded content of the aggregation database 34 is updated or at a fixed periodic time.In this case also, when the automated work program is generated as described above, the automated work system 1 can select the optimal work item logs from the work item logs stored in its own database 5, i.e., local work item logs corresponding to one base, or select the optimal work item logs from the work item logs delivered by another automated work system 1, i.e., globalized work item logs corresponding to the plurality of bases.
[0057] Furthermore, the work item logs in the work item units are not limited to data acquired using the unused automobile that is an actual machine, as described above, and may be data acquired using a model or a simulator. In this case, the model is a scale model of an automobile formed by three-dimensional molding or the like. In cases where the data of the work item logs in the work item units are collected using a model, the instructor robot 6 and the executing robot 8 are smaller in size than those in cases where an actual machine is used. The simulator is a three-dimensional model of an automobile.In cases where the data of the work item logs in the work item units are collected using a simulator, the instructor robot 6 is the same size as or smaller than that in cases where a real machine is used, and the executing robot 8 is a virtual robot that operates in the simulator. The fact that the item logs . of work in work item units can be acquired by a model or in a simulator results in work item logs in work item units can be collected from a larger number of workers, even in an environment where the scrap car, which is a real machine, is not readily available. Here, the environments faced by workers do not necessarily completely match the cases using the real machine, the model or the simulator. Therefore, the differences with the environments can for example be supplemented by setting a coefficient or similar.
[0058] Furthermore, when collecting the work item logs in the work item units, a game element may be included. The game element relates to creating a competition relating to the quality of evaluation data or the time data, and providing incentives such as prizes for the winners based on the results of the competition. By using the game element, a person who does not actually disassemble the junk automobile may be included as a collection target for the work item logs, thereby expanding the collection targets for the work item logs. Improvement in the efficiency of collecting the work item logs may be expected by creating a competition relating to the quality of evaluation data or the time data and providing incentives such as prizes for the winners.
[0059] The operation of the above-described configuration will be described next with reference to [Fig. 7] to 9. The control unit 4 performs the data collection process, the automated work program generation process, and the automated work program execution process. The processes will be successively described below. Here, the data collection process and the automated work program generation process may use either of the optimal local work item logs corresponding to a single base and the optimal globalized work item logs corresponding to a plurality of bases, as described above.
[0060] Data collection process (see [Fig.7])
[0061] When the data collection process starts, the control unit 4 outputs the presentation instruction signal to the work guide presentation unit 26 and causes the work guide presentation unit 26 to present the work guide (S1; corresponding to a work guide presentation instruction step). The control unit 4 then waits for the identification of the start of a work item (S2).
[0062] When the work start reception signal is input from the work start input unit 27 following the work start input unit 27 receiving the start operation from the worker for the work item, the control unit 4 determines that the start of the work item is identified (YES in S2; corresponding to a work start identification step). The control unit 4 starts storing the operation log inputted from the executing robot 8 of the disassembly system 7 (S3; corresponding to an operation log acquisition step) and starts storing the image log inputted from the camera 9 of the disassembly system 7 (S4; corresponding to an image log acquisition step). The control unit 4 then waits for the work item completion identification (S5).
[0063] When the work completion reception signal is input from the work completion input unit 28 as a result of the work completion input unit 28 receiving the completion operation for the work item from the worker, the control unit 4 determines that the completion of the work item is identified (YES in S5; corresponding to a work completion identification step). The control unit 4 terminates the storage of the operation logs inputted from the executing robot 8 of the disassembly system 7 (S6) and terminates the storage of the image logs inputted from the camera 9 of the disassembly system 7 (S7).
[0064] The control unit 4 acquires time data indicating the amount of time required to execute the work item based on the difference between the time when the start of the work item is identified and the time when the end of the work item is identified (S8; corresponding to a time data acquisition step). When the evaluation data reception signal is input from the evaluation data input unit 30 or when the evaluation data generation signal is input from the evaluation data generation unit 31, the control unit 4 acquires evaluation data (S9; corresponding to an evaluation data acquisition step).
[0065] The control unit 4 stores the work item logs in the work item units in the database 5 in association with the operation logs, the image logs, the time data, and the evaluation data (S 10; corresponding to a data storage control step). The control unit 4 determines whether to execute a next work item whose data is to be collected (S1 1). When it is determined that the next work item whose data is to be collected is to be executed (YES in S1 1), the control unit 4 returns to the step S1 described above and repeats the step S1 and the following steps. When it is determined that there is no need to execute the work item, the control unit 4 returns to the step S1 described above and repeats the step S1 and the following steps. next job whose data is to be collected does not (NO in SI 1), the control unit 4 terminates the data collection process.
[0066] Automated work program generation process (see [Fig.8])
[0067] When the automated work schedule generation process starts, the control unit 4 selects the optimal work item logs in the work item units based on a predetermined rule as described above, and generates a permutation of the selected optimal work item logs (S21). That is, the control unit 4 selects the work items having the highest evaluation data, if the rule is to select the work items having the highest evaluation data. The control unit 4 selects the work items having the shortest time data for each work item if the rule is to select the work items having the shortest time data.Here, for example, the control unit 4 may combine the rule for selecting the work items having the highest evaluation data and the rule for selecting the work items having the shortest time data. For example, the control unit 4 may apply the rule for selecting the work items having the highest evaluation data from "1-1" to "2-2", and the rule for selecting the work item having the shortest time data from "3-1" to "4-4".
[0068] The control unit 4 determines whether adjustment of the operating speed of the executing robot 8 for the work items is necessary (S22). When it is determined that adjustment of the operating speed of the executing robot 8 is necessary (YES in S22), the control unit 4 adjusts the operating speed of the executing robot 8 for the work items (S23). When it is determined that adjustment of the operating speed of the executing robot 8 is not necessary (NO in S22), the control unit 4 does not adjust the operating speed of the executing robot 8 for the work items.
[0069] The control unit 4 determines whether interpolation of the operation trajectory of the executing robot 8 between the work items is necessary (S24). When it is determined that interpolation of the operation trajectory of the executing robot 8 is necessary (YES in S24), the control unit 4 interpolates the operation trajectory of the executing robot 8 between the work items (S25). When it is determined that interpolation of the operation trajectory of the executing robot 8 is not necessary (NO in S24), the control unit 4 does not interpolate the operation trajectory.
[0070] The control unit 4 generates the automated work program for the corresponding work item on the basis of the operation logs and image logs of the corresponding work item (S26; corresponding to an automated work program generation step). The control unit 4 determines whether the automated work program is generated for all work items (S27). When it is determined that the automated work program is not generated for all work items, i.e., there is a work item for which the automated work program is not yet generated (NO in S27), the control unit 4 returns to step S22 and repeats step S22 and the following steps.
[0071] When it is determined that the automated work program is generated for all work items, i.e., there are no work items for which the automated work program has not yet been generated (YES in S27), the control unit 4 terminates the automated work program generation process.
[0072] Automated work program execution process (see [Fig.9])
[0073] When the automated work program execution process begins, when it is determined that an execution start condition for the automated work program is satisfied (YES in S31), the control unit 4 begins execution of the automated work program (S32). When it is determined that an end condition for execution of the automated work program is satisfied (YES in S33), the control unit 4 terminates execution of the automated work program (S34) and terminates the automated work program execution process.
[0074] As described above, according to the first embodiment, the following work effects can be achieved. In the data collection system 2, a worker can give an instruction to present a work guide and thus divide a work operation into work item units on the basis of the work guide, and collect data. The work item logs of the work item units to which the operation logs, image logs, time data, and evaluation data on the basis of the execution of the work items are associated are stored in the database 5. With reference to the time data or the evaluation data, the work item logs having excellent time data or evaluation data can be selected as optimal work item logs in the work item units.As a result of combining the selected optimal work item logs into the work item units, the automated work schedule can be generated. Therefore, machine learning of a huge amount of training data in the work item units is not required. The data required to generate the automated work schedule can be collected appropriately and efficiently.
[0075] Evaluation data input by the worker or the evaluation data calculated on the basis of a predetermined evaluation algorithm prescribed in advance is acquired. The optimal work item log can be selected by reference to assessment data entered by the worker or assessment data calculated from a predetermined assessment algorithm prescribed in advance.
[0076] Evaluation data based on a degree of load placed on the executing robot 8 is acquired. As a result of classifying the evaluation data based on the degree of load placed on the executing robot 8, an automated work program specially generated for removing the load placed on the executing robot 8 can be generated. It can be expected that work that removes the load placed on the executing robot 8 will be encouraged.
[0077] Evaluation data based on a degree of damage of the scrap automobile is acquired. As a result of classifying the evaluation data based on the degree of damage of the scrap automobile, an automated work program specially generated for removing damage to the scrap automobile can be generated. It can be expected that the work that removes damage to the scrap automobile will be promoted.
[0078] Evaluation data based on a degree of damage of a recyclable component attached to the scrap automobile is acquired. As a result of classifying the evaluation data based on the degree of damage of the recyclable component, an automated work program specially generated for removing damage to the recyclable component can be generated. It can be expected that the work that removes damage to the recyclable component will be promoted.
[0079] The work item logs in the work item units are reflected in the work guide. The work guide reflecting the work item logs in the work item units may be presented in the work guide presentation unit 26.
[0080] Work item logs in work item units are acquired using an actual machine, a model, or a simulator. Work item logs in work item units can be collected from a larger number of workers. Work item logs in work item units can be collected even in an environment where an actual machine is not readily available, through the use of a model or a simulator.
[0081] Work item logs in work item units having a game element are acquired. By using the game element, a person who does not actually disassemble the junk automobile may be included as a collection target for the work item logs. Expansion of collection targets for the work item logs may be expected.
[0082] The work item logs in the work item units of a plurality of data collection systems 2 can be shared. The collection targets for the work item logs in the work item units can be expanded, thereby expecting collection of the work item logs in the work item units having excellent evaluation data and time data.
[0083] The optimal work item logs in the work item units are selected according to a predetermined rule, based on the operation logs, image logs, time data, and evaluation data. A permutation of the selected optimal work item logs is generated, and the automated work schedule is generated. For example, if the rule is to select the work items having the highest evaluation data, as a result of selecting the work items having the highest evaluation data in the work item units, an automated work schedule reflecting the work items having the highest evaluation data can be generated.For example, if the rule is to select the work items with the shortest time data, then following the selection of the work items with the shortest time data in the work item units, an automated work schedule reflecting the work items with the shortest time data can be generated.
[0084] The operating speed of the executing robot 8 for the work items in the permutation of the optimal work item logs is adjusted. For example, the operating speed of the executing robot 8 can be improved to achieve a limiting speed in a segment of an operation log that does not involve contact between the attachment on the executing robot 8 and the disabled automobile in the operation logs where the worker is working at a low speed. Furthermore, as a result of reducing the difference between the operating speed of the executing robot 8 at the end of the previous work item and the operating speed of the executing robot 8 at the beginning of the next work item at the time of switching from one work item to the next, the operation of the executing robot 8 can be ensured smoothly at the time of switching from one work item to the next.
[0085] The operation trajectory of the robot executing 8 between the work items in the permutation of the optimal work item logs is interpolated. Even if the operation trajectory of the robot executing 8 at the end of the previous work item and the operation trajectory of the robot executing 8 at the beginning of the next work item do not coincide at the time of switching from one work item to the next, thanks to the linear interpolation of the operation trajectory of the robot executing 8, the operation of the robot running 8 can be ensured smoothly when moving from one work item to another.
[0086] The operation of the automated work program is confirmed by a simulator that reproduces the operation of the robot executing 8 in a virtual space. The operation of the automated work program can be tested in the virtual space. Second embodiment of the invention
[0087] A second embodiment will be described with reference to [Fig. 10]. The first embodiment is for example configured so that the worker operates the instructor robot 6, and the executing robot 8 operates to follow the instructor robot 6 and outputs operation logs. However, the second embodiment is for example configured so that the worker operates a control device, and the control device outputs the operation logs. According to the second embodiment, a robot performs the work of disassembling the components removed from a scrap automobile.
[0088] Similar to the first embodiment, an example is given of a case in which the data necessary for generating an automated work program is collected using a robot that performs the work of disassembling a component that is actually a real machine. In this case too, the data collection system and the automated work system have an identical relationship.
[0089] As shown in [Fig. 10], an automated work system 41 has an identical relationship with a data collection system 42. The automated work system 41 includes a log collection system 43 that collects logs accompanying the disassembly of a component removed from a scrap automobile, a disassembly system 44, a control unit 45 that controls the entire system, and a database 5.
[0090] The log collection system 43 includes a controller 46 and a camera 47. For example, the controller 46 may be equipment that includes a joystick operable by a worker. The controller 46 outputs time series data prescribing an operation of the robot 48 based on an operation from the worker as an operation log. The camera 47 may, for example, be movably set in a robot to fix a camera. The camera 47 relates to a function for detecting the distance and size of an imaging location. The camera 47 simultaneously captures images of a working section of a component removed from the unused automobile and an accessory on the controller 46, and outputs the captured images including the distance and size and time series data indicating imaging positions as an image log.Here, the camera 47 may be a single camera or a plurality of cameras.
[0091] The disassembly system 44 comprises a robot 48 (corresponding to a control target) which performs the work of disassembling the component removed from the unusable automobile and a camera 49. The camera 49 relates to a function for detecting the distance and size of an imaging location. The camera 49 simultaneously captures images of the working section of the component removed from the unusable automobile and an accessory on the control device 46. The robot 48 is similar to the executing robot 8 described according to the first embodiment. When an operation instruction signal is input from the control unit 45 by executing an automated work program, the robot 48 operates based on the input operation instruction signal and automatically performs the work of disassembling the component removed from the unusable automobile without requiring the operation from the worker.
[0092] The control unit 45 is similar to the control unit 4 according to the first embodiment. That is, the control unit 45 comprises a communication unit 45a, a storage unit 45b, and a calculation unit 45c. The units 45a to 45c respectively perform functions equivalent to those of the units 4a to 4c. Furthermore, the control unit 45 comprises the data collection unit 10, the automated work program generation unit 11, and the automated work program execution unit 12 for each function, and performs the data collection process, the automated work program generation process, and the automated work program execution process.
[0093] Here, the first embodiment is configured so that the disassembly system 7 is controlled as a part of the log collection system 3. Since the executing robot 8 of the disassembly system 7 outputs the operation logs, the control unit 4 sets the operation speed and interpolates the operation trajectory of the executing robot 8 on the basis of the operation logs output from the executing robot 8. Whereas according to the second embodiment, the log collection system 43 and the disassembly system 44 are controlled separately, and the controller 46 of the log collection system 43 outputs the operation logs. Therefore, the control unit 45 sets the operation speed and interpolates the operation trajectory of the robot 48 of the disassembly system 44 on the basis of the operation logs output from the controller 46.
[0094] As described above, according to the second embodiment, the following work effects can be achieved. In the automated work system 41, the work item logs of work item units with which the operation logs prescribing the operation of the robot 48, the image logs indicating the images of the control device 46, the time data and the evaluation data are associated are stored in the database 5. Similar to the first embodiment, with reference to the time data or the data evaluation, work item logs with excellent time data or evaluation data can be selected as optimal work item logs in the work item units. As a result of combining the selected optimal work item logs into the work item units, the automated work schedule can be generated.
[0095] The present disclosure includes the following aspects in addition to the citations within the scope of the claims.
[0096] First aspect
[0097] A data collection system (2, 42) that collects data necessary for generating an automated work program causing a control target to automatically perform a predetermined work, the data collection system comprising: a work guide presentation instruction unit (13) that instructs presentation of a work guide indicating a work process for work items; an operation log acquisition unit (16) that acquires an operation log of a log collection system during execution of the work item; an image log acquisition unit (17) that acquires an image log of the log collection system during execution of the work item; a time data acquisition unit (18) that acquires time data indicating the time required to execute the work item;an evaluation data acquisition unit (19) which acquires evaluation data indicating the evaluation of an execution result of the work item; and a data storage control unit (20) which causes a work item log to be stored in a data storage unit (5), in the work item units in association with the operation log, the image log, the time data and the evaluation data. ;
[0098] Second aspect
[0099] The data collection system according to the first aspect, wherein the evaluation data acquisition unit acquires evaluation data input by a worker or evaluation data calculated using a predetermined evaluation algorithm prescribed in advance. Third aspect
[0100] The data collection system according to the first or second aspect, wherein the evaluation data acquisition unit acquires evaluation data which is based on a degree of a load placed on the control target when the control target performs the predetermined work. Fourth aspect
[0101] The data collection system according to one of the first to third aspects, wherein the control target performs work involving a work target as a predetermined work, and the evaluation data acquisition unit acquires evaluation data based on a damage degree of the work target when the control target performs the predetermined work. Fifth aspect
[0102] The data collection system according to one of the first to fourth aspects, wherein the work target of the control target performs work involving a work target having a recyclable component as a predetermined work; and the evaluation data acquisition unit acquires evaluation data based on a degree of damage of the recyclable component when the control target performs the predetermined work. Sixth aspect
[0103] The data collection system according to any one of the first to fifth aspects comprises a work guide reflection unit (20) which reflects the work item logs in the work item units stored in the data storage unit in the work guide. Seventh aspect
[0104] The data collection system according to any one of the first to sixth aspects, wherein the work item log in the work item units consists of data acquired using an actual machine, a model or a simulator. Eighth aspect
[0105] The data collection system according to any one of the first to seventh aspects, wherein the work item log in the work item units consists of data acquired so as to include a game element. Ninth aspect
[0106] The data collection system according to the first aspect, wherein the work item logs in the work item units stored in a plurality of data storage units are shared. Tenth aspect
[0107] The data collection system according to the ninth aspect, wherein the work item logs in the work item units stored in the data storage unit are transmitted to a data aggregation unit (32). Other embodiments
[0108] Although the present disclosure has been described with reference to embodiments, it is understood that the disclosure is not limited to the embodiments and constructions. This disclosure is intended to cover various examples of modifications and modifications within the range of equivalence. In addition, various combinations and configurations, as well as other combinations and configurations having more, less, or a single element, are also within the spirit and scope of this disclosure.
[0109] The control unit and its method described in the present disclosure may be updated by a dedicated computer that is provided to be configured by a processor and a memory, the processor being programmed to provide one or more functions that are performed by a computer program. Alternatively, the control unit and its method described in the present disclosure may be updated by a dedicated computer that is provided by a processor configured by one or more dedicated hardware logic circuits. Further, alternatively, the control unit and its method described in the present disclosure may be updated by one or more dedicated computers. The dedicated computer may be configured by a combination of a processor that is programmed to provide one or more functions, a memory, and a processor that is configured by one or more hardware logic circuits.Further, the computer program may be stored on a tangible, non-transitory, computer-readable storage medium that can be read by a computer in the form of instructions performed by the computer.
Claims
Claims
1. A data collection system (2, 42) that collects data necessary for generating an automated work program causing a control target to automatically perform a predetermined work, the data collection system comprising: a work guide presentation instruction unit (13) that instructs presentation of a work guide indicating a work process for work items; an operation log acquisition unit (16) that acquires an operation log of a log collection system during execution of the work item; an image log acquisition unit (17) that acquires an image log of the log collection system during execution of the work item; a time data acquisition unit (18) that acquires time data indicating the time required to execute the work item;an evaluation data acquisition unit (19) which acquires evaluation data indicating the evaluation of an execution result of the work item; and a data storage control unit (20) which causes a work item log to be stored in a data storage unit (5), in the work item units in association with the operation log, the image log, the time data and the evaluation data.;
2. The data collection system of claim 1, wherein: the evaluation data acquisition unit acquires evaluation data input by a worker or evaluation data calculated using a predetermined evaluation algorithm prescribed in advance.
3. The data collection system according to claim 1, wherein: the evaluation data acquisition unit acquires evaluation data which is based on a degree of a load placed on the control target when the control target performs the predetermined work.
4. The data collection system according to claim 1, wherein: the control target performs work involving a work target as a predetermined work; and the evaluation data acquisition unit acquires evaluation data based on a degree of damage of the work target when the control target performs the predetermined work.
5. The data collection system according to claim 1, wherein: the work target of the control target performs work involving a work target having a recyclable component as a predetermined work; and the evaluation data acquisition unit acquires evaluation data based on a degree of damage of the recyclable component when the control target performs the predetermined work.
6. The data collection system of claim 1, further comprising: a work guide reflection unit (20) which reflects the work item logs in the work item units stored in the data storage unit in the work guide.
7. The data collection system of claim 1, wherein: the work item log in the work item units consists of data acquired using an actual machine, a model, or a simulator.
8. The data collection system of claim 7, wherein: the work item log in the work item units consists of data acquired so as to include a game element.
9. The data collection system of claim 1, wherein: the work item logs in the work item units stored in a plurality of data storage units are shared.
10. A data collection system according to claim 9, wherein: the work item logs in the work item units stored in the data storage unit are transmitted to a data aggregation unit (32).
11. An automated work system (1, 41) which collects data necessary for generating an automated work program causing a control target to automatically perform predetermined work, and which generates the automated work program, the automated work system comprising: a work guide presentation instruction unit (13) which instructs presentation of a work guide indicating a work process for the work items; an operation log acquisition unit (16) which acquires an operation log from a log collection system during execution of the work item; an image log acquisition unit (17) which acquires an image log from the log collection system during execution of the work item; a time data acquisition unit (18) which acquires time data indicating the time required to execute the work item; an evaluation data acquisition unit (19) which acquires evaluation data indicating the evaluation of an execution result of the work item; a data storage control unit (20) which causes a work item log to be stored in a data storage unit (5), in the work item units in association with the operation log, the image log, the time data and the evaluation data; and an automated work schedule generation unit (10) which generates the automated work schedule on the basis of the work item logs in the work item units stored in the data storage unit.
12. The automated work system of claim 11, wherein: the automated work schedule generation unit comprises a permutation generation unit (22) which selects optimal work item logs from the work item units according to a predetermined rule, on the basis of the operation logs, the image logs, the time data and the evaluation data, and which generates a permutation of the selected optimal work item logs.
13. An automated work system according to claim 12, further comprising: a control target (8, 48) which automatically performs the predetermined work.
14. The automated work system according to claim 13, wherein: the automated work program generation unit has an operation speed adjustment unit (23) which adjusts the speed of an operation of the control target for the work items in the permutation of the optimal work item logs generated by the permutation generation unit.
15. The automated work system according to claim 13, wherein: the automated work program generation unit has an operation trajectory interpolation unit (24) which interpolates the trajectory of an operation of the control target between the work items in the permutation of the optimal work item logs generated by the permutation generation unit.
16. The automated work system of claim 11, wherein: the automated work program generation unit comprises an operation confirmation unit (25) which confirms an operation of the automated work program by a simulator which reproduces the operation of the control target in a virtual space.
17. A non-transitory computer-readable storage medium in which is stored a data collection program that is read and executed by a processor included in a control unit (4, 45) of a data collection system (2, 42) that collects data necessary for generating an automated work program causing a control target to automatically perform predetermined work, the data collection program causing the processor to implement: a work guide presentation instruction step instructing presentation of a work guide indicating a work process for work items; an operation log acquisition step acquiring an operation log of a log collection system during execution of the work item; an image log acquisition step acquiring an image log from the log collection system during execution of the work item; a time data acquisition step acquiring time data indicating the time required to execute the work item; an evaluation data acquisition step acquiring evaluation data indicating the evaluation of an execution result of the work item; and a data storage control step causing a work item log to be stored in a data storage unit (5), in the work item units in association with the operation log, the image log, the time data and the evaluation data.
18. A non-transitory computer-readable storage medium in which is stored an automated work schedule generation program that is read and executed by a processor included in a control unit (4, 45) of an automated work system (1, 41) having a data collection system that collects data necessary for generating an automated work schedule causing a control target to automatically perform predetermined work and a control target that automatically performs the predetermined work, the automated work schedule generation program causing the processor to perform: a work guide presentation instruction step instructing presentation of a work guide indicating a work process for the work items;an operation log acquisition step acquiring an operation log from a log collection system during execution of the work item; an image log acquisition step acquiring an image log from the log collection system during execution of the work item; a time data acquisition step acquiring time data indicating the time required to execute the work item; an evaluation data acquisition step acquiring evaluation data indicating the evaluation of an execution result of the work item; a data storage control step causing a work item log to be stored in a data storage unit (5), in the work item units in association with the operation log, the image log, the time data and the evaluation data; and an automated work program generation step generating the automated work program based on the work item logs in the work item units stored in the data storage unit.