WO2018061504A1 - Control device, system, control method, and program - Google Patents

Control device, system, control method, and program Download PDF

Info

Publication number
WO2018061504A1
WO2018061504A1 PCT/JP2017/029429 JP2017029429W WO2018061504A1 WO 2018061504 A1 WO2018061504 A1 WO 2018061504A1 JP 2017029429 W JP2017029429 W JP 2017029429W WO 2018061504 A1 WO2018061504 A1 WO 2018061504A1
Authority
WO
WIPO (PCT)
Prior art keywords
skill level
information
work
unit
acquired
Prior art date
Application number
PCT/JP2017/029429
Other languages
French (fr)
Japanese (ja)
Inventor
豪 青木
Original Assignee
オムロン株式会社
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by オムロン株式会社 filed Critical オムロン株式会社
Publication of WO2018061504A1 publication Critical patent/WO2018061504A1/en

Links

Images

Classifications

    • GPHYSICS
    • G05CONTROLLING; REGULATING
    • G05BCONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
    • G05B19/00Programme-control systems
    • G05B19/02Programme-control systems electric
    • G05B19/18Numerical control [NC], i.e. automatically operating machines, in particular machine tools, e.g. in a manufacturing environment, so as to execute positioning, movement or co-ordinated operations by means of programme data in numerical form
    • G05B19/416Numerical control [NC], i.e. automatically operating machines, in particular machine tools, e.g. in a manufacturing environment, so as to execute positioning, movement or co-ordinated operations by means of programme data in numerical form characterised by control of velocity, acceleration or deceleration
    • GPHYSICS
    • G05CONTROLLING; REGULATING
    • G05BCONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
    • G05B19/00Programme-control systems
    • G05B19/02Programme-control systems electric
    • G05B19/418Total factory control, i.e. centrally controlling a plurality of machines, e.g. direct or distributed numerical control [DNC], flexible manufacturing systems [FMS], integrated manufacturing systems [IMS] or computer integrated manufacturing [CIM]
    • BPERFORMING OPERATIONS; TRANSPORTING
    • B25HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
    • B25JMANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
    • B25J13/00Controls for manipulators
    • B25J13/08Controls for manipulators by means of sensing devices, e.g. viewing or touching devices
    • YGENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02PCLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
    • Y02P90/00Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
    • Y02P90/02Total factory control, e.g. smart factories, flexible manufacturing systems [FMS] or integrated manufacturing systems [IMS]

Definitions

  • This disclosure relates to a control device, a system, a control method, and a program, and more particularly, to a control device, a system, a control method, and a program that control a drive unit for production.
  • workers may perform work in cooperation with robots and other machines.
  • it is desired to control a machine such as a robot in accordance with the level of skill of the worker for the work.
  • Patent Document 1 Japanese Patent Application Laid-Open No. 2015-230621 holds (stores) in advance in a personal information holding unit the skill level and physical characteristics of an operator's work when the worker and the robot work together.
  • a configuration is disclosed in which the skill level of the worker is acquired by referring to the stored personal information, and the behavior (position and orientation and activation) of the robot is set according to the acquired skill level. .
  • Patent Literature 1 is cumbersome because it is necessary to perform processing for acquiring and storing (storing) information on skill level for each worker in advance.
  • the configuration of Patent Document 1 is introduced into a large-scale work process with many workers or a work process in which workers are frequently replaced, the cost (time, There are problems such as an increase in memory capacity.
  • a control device for controlling a drive unit for production stores an acquisition unit that acquires biological information measured from an operator, and biological information corresponding to the skill level for each skill level of the work The biometric information acquired by the acquisition unit at the time of work and the biometric information possessed by the biometric information for each skill level of the storage unit are compared, and the acquired based on the comparison result A determination unit that determines which skill level the biological information corresponds to, and a determination unit that determines a control amount of the drive unit based on the determined skill level.
  • the biological information includes information indicating the movement of the body during work.
  • the information processing apparatus further includes a storage unit that acquires, for each skill level, a feature amount of biometric information corresponding to the skill level and stores the feature amount in the storage unit.
  • the feature amount stored in the storage unit includes a feature amount included in the biological information corresponding to the skill level determined by the determination unit.
  • the control device further includes a work information acquisition unit that acquires work information indicating a movement of a work handled by an operator during work, and a work information storage for storing work information corresponding to the skill level for each skill level.
  • a work information acquisition unit that acquires work information indicating a movement of a work handled by an operator during work
  • a work information storage for storing work information corresponding to the skill level for each skill level.
  • the feature quantity of the work information acquired at the time of the work of the operator and the feature quantity of the work information for each skill level of the work information storage section are compared, and based on the comparison result,
  • a work information determination unit that determines which skill level the information corresponds to, and the determination unit performs control based on the skill level determined by the determination unit and the skill level determined by the work information determination unit Determine the amount.
  • the feature amount includes a feature amount that can identify the skill level.
  • the determination unit determines the skill level every predetermined time, and the control device statistics the skill level determined every predetermined time and outputs statistical information.
  • a system includes a drive unit for production, a sensor that measures the biological information of the worker, and a control device that controls the drive unit.
  • the control device includes an acquisition unit that acquires biological information output from the sensor, a storage unit that stores biological information corresponding to the skill level of each work skill level, and a biological information acquired when the operator works Judgment to determine which skill level the acquired biometric information corresponds to by comparing the feature value of the information with the feature value of the biometric information for each skill level of the storage unit And a determination unit that determines a control amount of the drive unit based on the determined skill level.
  • a control method is a method of controlling a drive unit for production, the step of acquiring biological information measured from an operator, and a biological body acquired at the time of the operator's work The step of comparing the feature quantity of the information with the feature quantity of the biometric information for each skill level stored in the storage unit, and based on the comparison result, the acquired biometric information corresponds to any skill level And a step of determining a control amount of the drive unit based on the determined skill level.
  • a program according to still another aspect of the present disclosure is a program for causing a computer to execute a method of controlling a drive unit for production, and the method acquires biological information measured from an operator. And the step of comparing the feature amount of the biometric information acquired at the time of the work of the operator with the feature amount of the biometric information stored for each skill level stored in the storage unit, and the acquired based on the comparison result And a step of determining to which skill level the biometric information corresponds to, and a step of determining a control amount of the drive unit based on the determined skill level.
  • FIG. 1 is a diagram schematically illustrating an overall configuration of a system 1 according to a first embodiment. It is a figure which shows typically the hardware constitutions of the control computer 100 of FIG. It is a figure which shows schematically the structure of the robot 60 of FIG. It is a figure which illustrates the biometric information concerning Embodiment 1.
  • FIG. 2 is a diagram schematically illustrating a functional configuration of a control computer 100 according to the first embodiment. 4 is a process flowchart of “learning mode” according to the first exemplary embodiment;
  • FIG. 7 is a diagram for explaining a method of determining an effective pattern EP and threshold values TH1 to TH3 according to the first embodiment.
  • FIG. 4 is a process flowchart of “operation mode” according to the first exemplary embodiment; It is a figure which shows typically the other example of the determination method of the threshold value in the learning mode concerning Embodiment 1.
  • FIG. FIG. 10 is a diagram showing a display example of the recording content of skill level according to the second embodiment. It is a figure which shows the example of a display of the change of the moving speed of the hand during work. It is a figure which shows the example of a display of the change of the acceleration concerning the movement of the hand during work.
  • FIG. 6 is a diagram schematically illustrating a functional configuration of a control computer 100 according to a fourth embodiment. 10 is a process flowchart of “learning mode” according to the fourth exemplary embodiment; 10 is a process flowchart of “operation mode” according to the fourth exemplary embodiment;
  • FIG. 1 is a diagram schematically illustrating an overall configuration of a system 1 according to the first embodiment.
  • a production line such as FA (Factory Automation) includes one or a plurality of units 200 used for the work of the worker 10, a control computer 100 such as a PLC (Programmable Logic Controller), and a management computer 300 operated by the administrator. . These units communicate with each other by wire or wireless.
  • the control computer 100 can communicate with the terminal 11 carried by the worker 10, but the management computer 300 may communicate with the terminal 11.
  • the system 1 should just be installed in a production site, and the installation object is not limited to a production line.
  • the unit 200 includes an industrial robot 60 (hereinafter simply referred to as a robot 60) that cooperates with the worker 10 and a sensor 50 that detects human biological information in a non-contact manner.
  • a robot 60 an industrial robot 60 that cooperates with the worker 10 and a sensor 50 that detects human biological information in a non-contact manner.
  • the worker 10 performs a work of transporting the workpiece W in cooperation with the robot 60, for example.
  • the level of skill of the work (hereinafter referred to as skill level) is determined from the “biological information” at the time of the work of the worker 10, and the control amount of the robot 60 is determined using the determined skill level. To do.
  • Sensor 50 has a function of measuring changes in body movement over time (posture change, movement, etc.). Specifically, it includes a distance image sensor as a hardware circuit, and a microcomputer that executes a software program for estimating the movement of the human body from the output of the distance image sensor.
  • the distance image sensor acquires a distance image by analyzing an infrared pattern obtained by irradiating an object (human body) with infrared rays.
  • the microcomputer collates the distance image with a pre-registered pattern image, and based on the result of the collation, each part of the body (head, torso, shoulders, arms, waist, legs, hands, fingers, etc.) in the distance image. The position (coordinate value) is detected.
  • the sensor 50 transmits the biological information 107 indicating the temporal change in the movement of the worker's body located in the infrared irradiation range to the control computer 100.
  • the method of measuring the movement of the body is not limited to the method of measuring from the distance image such as the sensor 50.
  • the sensor 50 is provided for each unit 200, but one sensor 50 may be shared by a plurality of units 200.
  • the biological information 107 is not limited to information indicating the change of the body movement over time.
  • the biological information 107 may further include information indicating changes over time such as the body temperature, the respiratory rate, the pulse rate, and the blood pressure of the worker 10.
  • the body temperature and the respiratory rate can be measured from an infrared image captured by the sensor 50.
  • the pulse, blood pressure, and the like are measured by a wristwatch type device carried by the operator 10, and the device transmits measurement data to the control computer 100.
  • FIG. 2 is a diagram schematically showing a hardware configuration of the control computer 100 of FIG.
  • control computer 100 includes a CPU (Central Processing Unit) 110 that is an arithmetic processing unit, a memory 112 and a hard disk 114 as a storage unit, and a timer 113 that measures time and outputs timing data to CPU 110.
  • An input interface 118 a display controller 120 for controlling the display 122, a communication interface 124, and a data reader / writer 126. These units are connected to each other via a bus 128 so that data communication is possible.
  • the CPU 110 executes various calculations by executing a program (code) stored in the hard disk 114.
  • the memory 112 is typically a volatile storage device such as a DRAM (Dynamic Random Access Memory), and in addition to program data read from the hard disk 114, biological information received from the sensor 50, and work Data etc. are stored.
  • DRAM Dynamic Random Access Memory
  • the input interface 118 mediates data transmission between the CPU 110 and an input device such as a keyboard 121, a mouse (not shown), a touch panel (not shown). That is, the input interface 118 accepts an operation command given by the user operating the input device.
  • the communication interface 124 mediates data transmission between the unit 200 (the sensor 50, the robot 60), the management computer 300, or the terminal 11.
  • the data reader / writer 126 mediates data transmission between the CPU 110 and the memory card 123 that is a recording medium.
  • FIG. 3 is a diagram schematically showing the configuration of the robot 60 of FIG.
  • the robot 60 includes an arm 63 that freely rotates to grip and transfer the workpiece W, a drive unit 62 that rotates the arm 63 to transfer the workpiece W, and a controller that controls the drive unit 62. 61 is provided.
  • the work content is not limited to the conveyance of the work W, and may be an attachment work of the work W to the main body when the work W is a part.
  • the drive unit 62 is, for example, a servo motor.
  • the arm 63 of the robot 60 is connected to a drive unit 62 (rotary shaft of a servo motor).
  • An encoder (not shown) is attached to the drive unit 62.
  • the encoder detects a physical quantity indicating the operating state of the drive unit 62, generates a feedback signal indicating the detected physical quantity, and outputs the feedback signal to the controller 61 corresponding to the servo driver.
  • the feedback signal includes, for example, position information about the rotation position (angle) of the rotation shaft of the motor of the drive unit 62, information on the rotation speed of the rotation shaft, and the like.
  • the rotational position and rotational speed of the rotating shaft of the motor are detected as physical quantities indicating the operating state of the drive unit 62 (servo motor).
  • acceleration, change amount (movement amount), change direction (movement direction), and the like may be detected.
  • the controller 61 receives the command signal 106 from the control computer 100 and the feedback signal output from the encoder.
  • the controller 61 drives the drive unit 62 based on the command signal 106 from the control computer 100 and the feedback signal from the encoder.
  • the controller 61 sets a command value related to the operation of the drive unit 62 based on the command signal 106 from the control computer 100. Furthermore, the controller 61 drives the drive unit 62 so that the operation of the drive unit 62 follows the command value. Specifically, the controller 61 controls the drive current of the drive unit 62 (servo motor) according to the command value.
  • the control amount of the arm 63 (angle, direction, speed, etc. for rotating the arm) is as follows.
  • the controller 61 and the drive unit 62 are variably controlled remotely by a command signal 106 from the control computer 100.
  • Bio information and features 4 and 5 are diagrams illustrating the biological information according to the first embodiment.
  • the skill level of the work is determined using the feature value of the biological information 107.
  • information on temporal changes in body movement included in the biological information 107 (information on temporal changes in position, movement speed, movement acceleration, movement distance of each part of the body) is included. Use the feature quantity.
  • the skill level can be determined in the same manner by using a feature amount included in information indicating changes with time such as body temperature, pulse, blood pressure, and the like.
  • the biological information 107 includes, for example, a change in the amount of movement of the head (specifically, a change in the position of the head over time).
  • FIG. 4 is a graph showing a temporal change in the amount of movement of the head (change in the position of the head over time) when the worker 10 is an expert.
  • FIG. The graph shows the change over time in the position of the head when the user is a beginner (such as a beginner).
  • the movement amount of the head of the worker 10 is taken on the vertical axis, and the time is taken on the horizontal axis.
  • the amount of head movement converges within a certain range.
  • the amount of head movement does not converge to a certain range over time. Therefore, the inventor has learned from experiments that it is possible to estimate the degree of skill of the worker 10 from the movement of each part of the body of the worker 10 acquired during the work.
  • FIG. 6 is a diagram schematically illustrating a functional configuration of the control computer 100 according to the first embodiment.
  • the function shown in FIG. 6 includes a function of determining the control amount of the drive unit 62 from the biological information 107 of the worker.
  • the operation mode of the control computer 100 according to the first embodiment includes a “learning mode” and an “operation mode”.
  • the control computer 100 includes a learning unit 101, an acquisition unit 103 that acquires biological information 107 from the sensor 50, a determination unit 104 that determines the skill level of the work of the worker 10, and a control amount determination unit 105. Is provided.
  • the control computer 100 also includes an information memory 102 corresponding to a storage unit (such as the hard disk 114).
  • the learning unit 101 stores the biological information 107 acquired by the acquisition unit 103 in the information memory 102 and identifies the skill level based on the stored biological information 107.
  • a quantity (hereinafter also referred to as an identification feature quantity) is determined.
  • the determination unit 104 includes a feature amount corresponding to the identification feature amount among a plurality of types of feature amounts (hereinafter, also referred to as acquired feature amounts) included in the biological information 107 acquired from the worker 10. And the threshold value are compared, and based on the comparison result, it is determined to which skill level the acquired biological information 107 corresponds.
  • the control amount determination unit 105 determines the control amount of the drive unit 62 based on the determined skill level.
  • the skill level is classified into three categories: high (hereinafter referred to as high skill level), medium (hereinafter referred to as medium skill level), and low (hereinafter referred to as low skill level), but the classification is limited to three.
  • the number may be two, or four or more.
  • information memory 102 includes areas E1, E2, E3, and E4.
  • the area E1 is a storage area for storing high skill level information 151, medium skill level information 152, and low skill level information 153.
  • the area E2 is an area for storing the learning result of the “learning mode”.
  • the learning result includes a pattern EP indicating a combination of one or more identification feature values and thresholds TH1, TH2, and TH3 for determining the skill level.
  • Areas E3 and E4 correspond to work areas.
  • the high skill level information 151 includes biometric information BM1 that is a plurality of pieces of biometric information 107 acquired at the time of work of the worker 10 who is highly skilled in the “learning mode”.
  • the medium skill level information 152 includes biometric information BM1 that is a plurality of pieces of biometric information 107 acquired at the time of the work of the worker 10 having the medium skill level in the “learning mode”.
  • the low skill level information 153 includes biometric information BM1 that is a plurality of pieces of biometric information 107 acquired at the time of the work of the worker 10 who has a low skill level in the “learning mode”.
  • the capacity required for the information memory 102 can be reduced.
  • the acquisition unit 103 controls the communication interface 124 to acquire (receive) the biological information 107 from the sensor 50, and output the acquired biological information 107 to each unit.
  • the learning unit 101 When the operation mode of the control computer 100 is “learning mode”, the learning unit 101 inputs biometric information 107 for each skill level from the acquisition unit 103, and associates the input biometric information 107 with each skill level in the information memory. 102 in the area E1. Thereby, in the “learning mode”, a plurality of pieces of biological information 107 are accumulated (stored) in the information memory 102 for each skill level.
  • the learning unit 101 is an example of an “accumulation unit” that accumulates the biological information 107 in the information memory 102 for each skill level.
  • the learning unit 101 determines one or more of the acquired feature amounts CRi from the biological information BM1 of the high skill level information 151 of the information memory 102 as the identification feature amount CRi. In addition, the learning unit 101 stores the combination including the determined one or more identification feature amounts CRi in the region E2 as the effective pattern EP.
  • the effective pattern EP indicates a combination of one or more identification feature amounts CRi effective for identifying the skill level.
  • the learning unit 101 includes a combination of acquired feature amounts CRi corresponding to a combination of the identification feature amounts CRi of the effective pattern EP among the acquired feature amounts CRi of the high skill level information 151, the medium skill level information 152, and the low skill level information 153. Is identified. Then, based on the specified combination value, threshold values TH1, TH2, and TH3 are acquired and stored in the region E2.
  • the determination unit 104 acquires the biological information 107 of the worker 10 engaged in the work from the acquisition unit 103 when the operation mode of the control computer 100 is the “operation mode”.
  • the determination unit 104 identifies a combination of feature amounts CRi corresponding to the combination of the identification feature amounts CRi of the effective pattern EP from the feature amounts CRi included in the biological information 107.
  • the determination unit 104 compares the combination value of the specified feature amount CRi with threshold values TH1, TH2, and TH3. Then, based on the comparison result, it is determined to which skill level the obtained biological information 107 corresponds.
  • each of the threshold values TH1, TH2, and TH3 for each skill level is set as a width (range) of values having an upper limit value and a lower limit value.
  • the determination unit 104 determines 'high skill level' when the value of one or more acquired feature values CRi corresponding to the effective pattern EP of the biological information 107 acquired from the worker 10 is within the range of the threshold value TH1. When it is within the range of the threshold value TH2, it is determined as “medium skill level”, and when it is within the range of the threshold value TH3, it is determined as “low skill level”.
  • Control amount determination unit 105 determines the control amount of drive unit 62 based on the skill level determined by determination unit 104 in the “operation mode”. The control amount determination unit 105 generates a command signal 106 indicating the determined control amount and transmits the command signal 106 to the controller 61 of the robot 60 via the communication interface 124.
  • Each skill data in the information memory 102 may be variable. For example, when the type of the work W is changed, the “learning mode” may be performed and the data in the information memory 102 may be changed.
  • the biological information 107 of the worker 10 is stored in the high skill level information.
  • the biometric information BM1 is added to the area E1 of the information memory 102, and the learning unit 101 may acquire the effective pattern EP and the threshold values TH1, TH2, and TH3 again based on the information of the added area E1. Good.
  • the identification feature amount CRi indicated by the effective pattern EP can be changed to one having a higher identification rate.
  • the threshold values TH1, TH2, and TH3 can be changed to values that make the skill level determination accuracy more accurate.
  • FIG. 7 is a process flowchart of the “learning mode” according to the first exemplary embodiment.
  • FIG. 8 is a diagram for explaining a method of determining the effective pattern EP and the thresholds TH1 to TH3 according to the first embodiment.
  • FIG. 9 is a process flowchart of the “operation mode” according to the first exemplary embodiment. 7 and 9 is stored as a program in a storage unit (memory 112, hard disk 114, memory card 123, etc.) of the control computer 100.
  • CPU110 reads a program from a memory
  • the production line includes a sensor (not shown) that detects the completion of each transfer operation. For example, a proximity switch that detects that the workpiece W has moved to a predetermined position on the production line.
  • the control computer 100 processes the detection signal from the sensor as a timing signal that indicates the repetitive timing of each transfer operation.
  • control computer 100 that implements the “learning mode” may be the same as or different from the control computer 100 that implements the “operation mode”. If they are different, the control computer 100 in the “operation mode” sends the high skill level information 151, the medium skill level information 152 and the low skill level information 153, and the effective pattern EP and the threshold values TH1 to TH3 to other control computers. 100 and received in the areas E1 and E2 of the information memory 102. Alternatively, these pieces of information are read from the memory card 123 and stored in the areas E1 and E2 of the information memory 102.
  • the controller 61 is given a command signal 106 indicating a standard control amount.
  • the acquisition unit 103 acquires the biological information 107 from the sensor 50 when the skilled worker 10 is working (step S3), and the learning unit 101 acquires the feature amount CRi included in the biological information 107 from the acquisition unit 103 (step S3). S4).
  • the learning unit 101 stores the acquired feature amount (acquired feature amount) CRi in the information memory 102 with a label indicating the skill level of the worker 10 (step S5).
  • the learning unit 101 processes the biological information 107 from the acquisition unit 103, and extracts feature amounts indicating changes over time in the movement of each part of the body, as shown in FIG. 4 or FIG.
  • Each part of the body includes the head, torso, shoulders, arms, waist, legs, hands, fingers, and the like.
  • the learning unit 101 acquires feature quantities (changes in movement over time) of each part.
  • the feature amount may be a change over time in the relative positional relationship between different parts of the body (for example, the positional relationship indicated by the distance between the head and the arm).
  • the high skill level information 151 the medium skill level information 152, and the low skill level information 153 are registered in the area E1.
  • the administrator inputs the labels LB 1, LB 2, and LB 3 indicating the type of skill level from the keyboard 121.
  • the learning unit 101 performs an analysis process on the information stored in the area E1 (step S6).
  • the analysis process includes a process (steps S7, S8 and S9) for determining the effective pattern EP.
  • the learning unit 101 generates a plurality of combinations of acquired feature amounts CRi of the high skill level information 151 of the area E1 in the work area E3 (Step S7).
  • An identification rate for identifying the skill level for each pattern is calculated (step S8).
  • the pattern uses a representative value of the acquired feature amount CRi.
  • This representative value may include, for example, an average value, median value, integral value, variance value, mode value, and the like of the amount of change in movement (for example, the amount of head movement). Note that the types of representative values are not limited to these.
  • the learning unit 101 calculates the above-described identification rate by calculation according to a known pattern classification method (step S8).
  • the discrimination rate of each pattern is calculated in accordance with the discrimination function of SVM (support vector machine) (see area E3 in FIG. 8).
  • the calculation of the identification rate is not limited to a method according to SVM, and may be a calculation method according to NN (neural network).
  • the learning unit 101 identifies a pattern corresponding to, for example, the maximum identification rate among the identification rates calculated for each pattern (see the region E3 in FIG. 8), and determines the identified pattern as an effective pattern EP. (Step S9).
  • Learning unit 101 acquires threshold values TH1, TH2, and TH3 based on the combination of feature amount CR1 and feature amount CR2 indicated by the determined effective pattern EP (step S10).
  • the learning unit 101 defines a two-dimensional plane based on the combination (CR1, CR2) of the identification feature amounts CRi of the effective pattern EP in the work area E4. Then, the combination values (CR1, CR2) of the acquired feature amounts CR1 and CR2 corresponding to the biological information BM1 of the high skill level information 151 of the area E1 are plotted on the specified plane (marks in the area E4 in FIG. 8). X ′). Further, on this plane, the combination values (CR1, CR2) of the feature amounts CR1 and CR2 corresponding to each biological information BM1 of the medium skill level information 152 in the area E1 are plotted (see the mark “Y” in the area E4 in FIG. 8). To do.
  • the combination values (CR1, CR2) of the feature amounts CR1 and CR2 corresponding to each biological information BM1 of the low skill level information 153 of the region E1 are plotted (see the mark “Z” in the region E4 in FIG. 8). To do.
  • the learning unit 101 is a region where the combination values (CR1, CR2) of the high skill level, the medium skill level, and the low skill level are plotted on the two-dimensional plane of the region E4 based on the distribution state of the plot values of each skill level. Boundary lines B1, B2 and B3 are identified.
  • the learning unit 101 determines threshold values TH1, TH2, and TH3 based on the values indicated by the boundary lines B1, B2, and B3. For example, the learning unit 101 determines the combination value (CR1, CR2) near the boundary line B1 as the threshold value TH1 for determining the high skill level. Similarly, the combination value (CR1, CR2) near the boundary line B2 is determined as the threshold value TH2 for determining the intermediate skill level. Similarly, the combination value (CR1, CR2) near the boundary line B3 is determined as the threshold value TH2 for determining the low skill level.
  • the learning unit 101 stores the determined effective pattern EP and the acquired threshold values TH1, TH2, and TH3 in the area E2 of the information memory 102 (step S11). Thus, the “learning mode” process ends.
  • step S3 since a sufficient number of pieces of biological information 107 are acquired for each skill level in step S3, it is not necessary to repeat the process of FIG. 7, but a sufficient number of pieces of biological information 107 have been acquired. If not, the process of FIG. 7 may be repeated.
  • Whether or not to repeat the process is determined based on the distribution situation on the two-dimensional plane. Specifically, it is determined whether or not a number of combination values (CR1, CR2) that can specify the boundary lines B1, B2, and B3 are plotted, and it is determined whether to repeat the processing based on the determination result.
  • the learning unit 101 returns to step S3 in FIG. 7 and performs subsequent processing (acquisition of biological information 107 according to each skill level (step S3), acquisition of feature amount CRi (step S4), Label addition (step S5) and analysis processing (step S6)) are performed in the same manner as described above.
  • the plane dimension is not limited to two dimensions. That is, this dimension is variable depending on the number of identification feature amounts CRi included in the effective pattern EP.
  • the “operation mode” process will be described with reference to FIG.
  • the effective pattern EP and the threshold values TH1, TH2, and TH3 are stored in the area E2 of the information memory 102.
  • the controller 61 is given a command signal 106 indicating a standard control amount (corresponding to a medium skill level).
  • the acquisition unit 103 acquires the biological information 107 of the worker 10 on the production line from the sensor 50 (step S23).
  • the determination unit 104 acquires the feature amount (identification feature amount) of the set indicated by the effective pattern EP from the feature amount CRi included in the acquired biological information 107 of the worker 10 (step S25), and the acquired feature amount And the thresholds TH1, TH2, and TH3 stored in the information memory 102, the skill level corresponding to the biological information 107 is determined based on the comparison result, and the determination result is output (step S27). Thereby, the skill level of the operator 10 is determined.
  • the skill level is determined by comparing the value of the identification feature amount CRi included in the acquired biological information 107 with the threshold values TH1, TH2, and TH3, and comparing the value of the identification feature amount CRi with the high skill level of the region E1. This corresponds to a comparison with the value of the identification feature amount CRi included in each of the biometric information 107 of the medium skill level and the low skill level. Therefore, the skill level determination method is not limited to the comparison method with the threshold values TH1, TH2, and TH3.
  • the value of the identification feature amount CRi included in the acquired biological information 107 is plotted on the two-dimensional plane of the region E4, and based on the positional relationship between the plotted position and the boundary lines B1, B2, and B3, The degree may be determined.
  • the control amount determination unit 105 generates a command signal 106 indicating the speed V that is the calculated control amount, and outputs it via the communication interface 124 (step S39).
  • the acquisition of the control amount is not limited to such a calculation method. For example, a table in which a plurality of sets of skill levels and control amounts are registered is stored, the table is searched based on the skill levels determined in step S27, and the corresponding control amounts are read from the table. Good.
  • the CPU 110 determines whether or not to end the repetitive work. When determining that the repetitive work is not to be ended, the CPU 110 returns to step S23 and repeats the subsequent processes, but ends the repetitive work. At the time (for example, when the operation of the production line itself is finished), the processing of FIG. 9 is finished.
  • the process of FIG. 9 may be performed every predetermined time.
  • the CPU 110 may perform the process of FIG. 9 every time the above timing signal is input from the production line a predetermined number of times.
  • FIG. 10 is a diagram schematically illustrating another example of the threshold value determination method in the learning mode according to the first embodiment.
  • the threshold values TH1, TH2, and TH3 are acquired according to the distribution state of the combination values (CR1, CR2) of the two feature amounts that are the effective patterns EP in the two-dimensional plane.
  • the acquisition method is not limited to this method. .
  • a method for determining a threshold value TH for distinguishing between a group of high skill levels, a medium skill level, and a group of low skill levels when the effective pattern EP is composed of one feature amount CRi will be described. To do.
  • the characteristic amount CRi for determining the threshold value TH indicates the amount of head movement.
  • step S ⁇ b> 10 the learning unit 101 acquires the value of each feature amount CRi included in each of the biological information BM ⁇ b> 1 of the high skill level information 151, the medium skill level information 152, and the low skill level information 153 of the region E ⁇ b> 1. Perform the process of counting the number of times.
  • FIG. 10 schematically shows the result of the counting process in a graph.
  • the horizontal axis represents the value of the characteristic amount CRi (the average head movement amount (unit: m / frame)), and the vertical axis represents the frequency (count value) at which each value is acquired. .
  • the learning unit 101 can determine, for example, that the value corresponding to the boundary dividing the high / medium skill level and the low skill level is 0.017 (m / frame) from the count processing result (see FIG. 10). Therefore, the learning unit 101 can determine 0.017 (m / frame) as the threshold value TH.
  • FIG. 11 is a diagram illustrating a display example of the recording content of the skill level according to the second embodiment.
  • the CPU 110 stores the determined skill level for each worker 10 in the storage unit in association with the number of work days (first day, second day, third day,).
  • the association period is not limited to every day, and may be every few hours or every week, for example.
  • CPU 110 performs statistical processing of the skill level of each worker 10 (for example, calculation of an average value, a variance value, the number of appearances (frequency) of each skill level, and the like) from the stored association information, and is obtained Display data based on the statistical value is created and driven to the display 122 according to the display data. Thereby, for example, a graph as shown in FIG. 11 is displayed on the display 122.
  • the manager 11 can provide the manager with information indicating the skill level of each worker 10 and the change in skill level.
  • the administrator can use the statistical information for process management or production management. For example, the manager adjusts the work time zone of the worker 10 so that a person with high skill and a person with low skill work in the same time zone.
  • information on the skill level of the worker 10 can be provided as a support tool for leveling work and improving productivity. Note that the screen of FIG. 11 may be displayed on the management computer 300.
  • FIG. 12 is a diagram illustrating a display example of changes in the moving speed of the hand during work.
  • FIG. 13 is a diagram illustrating a display example of a change in acceleration according to movement of a hand during work.
  • the combination value (CR1, CR2) of the identification feature amount indicated by the effective pattern EP indicates (hand movement speed, hand movement acceleration).
  • the CPU 110 acquires the identification feature amounts CR1 and CR2 of the worker 10 when the work W is transported. Then, the CPU 110 displays display data for displaying the acquired identification feature value CR1 and the highly skilled person's feature value CR1 in association with each other, and displays the acquired identification feature value CR1 and the highly skilled person's feature value CR1 in association with each other. Display data to be generated, and the generated display data is transmitted to the terminal 11. The terminal 11 displays an image (see FIGS. 12 and 13) according to the received display data.
  • the screen of FIG. 12 or FIG. 13 visually provides the worker 10 with the current skill level, information indicating changes in the skill level, the size of the gap between the high skill level of his / her skill level, and the like. can do.
  • the worker 10 can obtain a guideline for correcting his / her hand movement to a highly skilled movement from the provided information.
  • the skill level is determined from the change in the movement of the workpiece W over time.
  • the skill level is determined using the biological information 107 of the worker 10, but in the fourth embodiment, the movement of the workpiece W also changes according to the change in the movement of the worker 10's body. Focusing on the points, the skill level is determined from the change in the movement of the workpiece W.
  • the production line includes a sensor 50A that measures the movement of the workpiece W having the same function as the sensor 50.
  • the sensor 50A detects (measures) the workpiece information 107A indicating the change in the movement of the workpiece W over time.
  • the feature amount of the work information 107A a change with time of the movement of each part of the work W (change with time such as position, moving speed, moving acceleration, etc.) can be used.
  • the sensor 50A is provided independently of the sensor 50, but the sensor 50 may have the function of the sensor 50A.
  • FIG. 14 is a diagram schematically illustrating a functional configuration of the control computer 100 according to the fourth embodiment.
  • FIG. 15 is a process flowchart of the “learning mode” according to the fourth embodiment.
  • FIG. 16 is a process flowchart of the “operation mode” according to the fourth exemplary embodiment.
  • step S3 in FIG. 7 is changed to step S3a, but the other steps are the same as in FIG.
  • step S23 of FIG. 9 is changed to step S23a, but other steps are the same as those of FIG. Therefore, in FIG. 15 and FIG. 16, the changed steps S3a and S23a will be described, and description of other processes will not be repeated.
  • processing of the flowcharts of FIGS. 15 and 16 is stored as a program in a storage unit (memory 112, hard disk 114, memory card 123, etc.) of the control computer 100.
  • CPU110 reads a program from a memory
  • the control computer 100 uses the acquisition unit 103A that acquires the workpiece information 107A from the sensor 50A and the workpiece information 107A that is acquired by the acquisition unit 103A in the “learning mode” to use the effective pattern EP1 and the threshold value TH11. , TH22 and TH33 are provided with a learning unit 101A and an information memory 102A. Further, the control computer 100 determines the skill level of the work information 107A acquired by the acquisition unit 103A in the “operation mode”, the determination unit 104A, and the drive unit 62 based on the determined skill level. A control amount determination unit 105A that determines a control amount and outputs a command signal 106A indicating the determined control amount to the controller 61.
  • information memory 102 includes areas E11, E22, E33, and E44.
  • the area E11 is a storage area for storing high skill level information 1511, medium skill level information 1521, and low skill level information 1531.
  • the region E22 is a region for storing a pattern EP1 indicating one or more combinations of identification feature amounts determined in the “learning mode” and thresholds TH11, TH22, and TH33 for determining the skill level.
  • the area E33 and the area E44 correspond to a work area for the “operation mode”.
  • the high skill level information 1511 includes work information BM11 which is a plurality of work information 107A acquired at the time of the work of the worker 10 having a high skill level in the “learning mode”.
  • the medium skill level information 1521 includes a plurality of pieces of work information BM11, a label LB2 associated with each piece of work information BM11, and a plurality of acquired feature amounts CR1i acquired from the work information BM11.
  • the low skill level information 1531 includes a plurality of pieces of work information BM11, a label LB3 associated with each piece of work information BM11, and a plurality of acquired feature amounts CR1i acquired from the work information BM11.
  • the work information BM11 in the area E11 in FIG. 12 may be deleted when the learning mode ends. Thereby, it is possible to save the consumption capacity in the information memory 102A.
  • the learning unit 101A associates the work information 107A from the acquisition unit 103 with each skill level in the area E11 as in the learning unit 101 of the first embodiment. To store.
  • the learning unit 101A is an example of an “accumulation unit” that accumulates work information 107A in the information memory 102A for each skill level.
  • the learning unit 101A when the learning unit 101A is in the “learning mode”, one of the acquired feature values CRi included in the work information BM11 of the high skill level information 1511 of the area E1 is the same as the learning unit 101 of the first embodiment.
  • the identification feature amount CRi described above is determined, and a set of one or more determined identification feature amounts CRi is stored in the region E22 as an effective pattern EP1 for identifying the skill level.
  • the learning unit 101A also includes the feature amount CRi of the effective pattern EP1 among the acquired feature amounts CRi of the high skill level information 1511, the medium skill level information 1521, and the low skill level information 1531. Threshold values TH11, TH22, and TH33 for determining each skill level are acquired based on the set values and stored in the region E22.
  • the determination unit 104A acquires the feature amount CR1i included in the work information 107A acquired from the acquisition unit 103A, as in the determination unit 104 of the first embodiment. Then, one or more identification feature amounts CR1i corresponding to the effective pattern EP1 among the acquired feature amounts CR1i are compared with threshold values TH11, TH22, and TH33. Then, based on the comparison result, it is determined to which skill level the acquired work information 107A corresponds.
  • control amount determination unit 105A determines the control amount based on the skill level determined by the determination unit 104A in the “operation mode” and indicates the determined control amount.
  • a command signal 106 is generated and transmitted to the controller 61 of the robot 60.
  • the acquisition unit 103A acquires the work information 107A from the sensor 50A when the skilled worker 10 is working (step S3a).
  • the learning unit 101A performs the same processing as the learning unit 101 of the first embodiment using the acquired work information 107A. Accordingly, the effective pattern EP1 and the threshold values TH11, TH22, and TH33 are stored in the region E22, and the “learning mode” process ends.
  • acquisition unit 103A acquires work information 107A from sensor 50A when worker 10 is working (step S23a).
  • the determination unit 104A performs the same processing as in the first embodiment and the determination unit 104 using the acquired work information 107A.
  • a command signal 106 indicating a control amount corresponding to the skill level of the worker 10 is output to the controller 61 of the robot 60.
  • the skill level of the worker 10 is determined from the workpiece information 107A indicating the change over time of the movement of the workpiece W handled by the worker 10 in cooperation with the robot 60 in the production line.
  • the drive unit 62 can be controlled in accordance with the control amount based on the skill level.
  • both the determination of the skill level from the biological information 107 described in the first to third embodiments and the determination of the skill level from the work information 107A of the fourth embodiment are performed.
  • the skill level of the operator 10 may be comprehensively determined based on the results of both determinations. For example, when both determination results are different, the lower skill level (or the higher skill level) may be selected.
  • a program for causing the CPU 110 of the control computer 100 to execute at least one of the “learning mode” and the “operation mode” in each of the above embodiments is provided.
  • a program is recorded on a computer-readable recording medium such as a flexible disk attached to the control computer 100, a CD-ROM (Compact Disk-Read Only Memory), a ROM, a RAM, and a memory card 123 to obtain a program product.
  • the program can be provided by being recorded on a recording medium such as the hard disk 114 built in the control computer 100.
  • the program can also be provided by downloading from a network (not shown) via the communication interface 124.
  • the program may be a program module that is provided as part of the OS (operating system) of the control computer 100 and that calls necessary modules in a predetermined arrangement at a predetermined timing to execute processing. .
  • the program itself does not include the module, and the process is executed in cooperation with the OS.
  • a program that does not include such a module can also be included in the program of the fifth embodiment.
  • the program according to the fifth embodiment may be provided by being incorporated in a part of another program. Even in this case, the program itself does not include the module included in the other program, and the process is executed in cooperation with the other program. Such a program incorporated in another program can also be included in the program according to the second embodiment.
  • the provided program product is installed in a program storage unit such as a hard disk and executed.
  • the program product includes the program itself and a recording medium on which the program is recorded.
  • the control computer 100 of the above embodiment corresponds to a control device that controls the drive unit 62 for production.
  • the control device includes an acquisition unit 103 that acquires biological information 107 measured from the worker 10, high skill level information 151 including medium information 107 corresponding to the skill level for each skill level, and medium skill level information.
  • the storage unit (information memory 102), the characteristic amount CRi of the biological information 107 acquired by the acquisition unit 103 during work, and the biological information for each skill level of the storage unit (The feature amount CRi included in the high skill level information 151, the medium skill level information 152, and the low skill level information 153) is compared, and based on the comparison result, which skill level the acquired biological information 107 corresponds to And a determination unit (control amount determination unit 105) that determines a control amount of the drive unit 62 based on the determined skill level.
  • the skill level for the work can be determined, and the drive unit 62 can be controlled with a control amount corresponding to the determined skill level.
  • the biological information 107 includes information indicating the movement of the body during work. Therefore, the skill level can be determined from the body movement of the worker 10.
  • the control computer 100 further includes a storage unit that acquires the characteristic amount CRi of the biological information 107 corresponding to the skill level and stores it in the storage unit (area E1 of the information memory 102) for each skill level.
  • This accumulation unit corresponds to the learning unit 101.
  • the biometric information 107 having the feature amount CRi for each skill level can be obtained by learning by the learning unit 101.
  • the above-described accumulated feature amount includes the feature amount included in the biological information corresponding to the skill level determined by the determination unit 104. Therefore, the feature amount acquired in both the learning mode by the learning unit 101 and the operation mode by the determination unit 104 can be included in the feature amount of the storage unit.
  • the control device further includes a work information acquisition unit (acquisition unit 103A) that acquires work information 107A indicating the movement of the work W handled by the worker 10 during work, and work information corresponding to the skill level for each skill level.
  • the work information storage unit (area E11) for storing information, the feature amount CR1i of the work information 107A acquired when the worker 10 is working, and the work information (high skill level information) for each skill level of the work information storage unit 1511, the medium skill level information 1521 and the low skill level information 1531) are compared with the characteristic amount CR1i, and based on the comparison result, the work level for which the acquired work information 107A corresponds to which skill level is determined.
  • An information determination unit (determination unit 104A), and the determination unit determines the skill level determined by the determination unit 104 and the skill level determined by the work information determination unit. Based on time, to determine the control amount.
  • the skill level can be determined by using both the feature amount CRi of the movement of the worker 10 and the feature amount CR1i of the movement of the workpiece W.
  • the above-described feature amounts CRi and CR1i include feature amounts (effective patterns EP, EP1) that can identify skill levels. Accordingly, it is possible to determine the skill level of the worker 10 using the feature amount that can identify the skill level.
  • the determination units 104 and 104A determine the skill level at each predetermined time, and the control device statistics the skill level determined at the predetermined time and provides statistical information (see FIG. 11). Output. Thereby, the support information in the case of managing the worker in production can be provided.
  • the control computer 100 of the above embodiment corresponds to a control device that controls the drive unit 62 for production.
  • This control device stores a work information acquisition unit (acquisition unit 103A) that acquires work information 107A indicating the movement of the work W handled by the worker 10 during work, and workpiece information corresponding to the skill level for each skill level.
  • acquisition unit 103A work information acquisition unit
  • Work information storage unit (area E11), feature amount CR1i of the work information 107A acquired when the worker 10 works, and work information for each skill level of the work information storage unit (high skill level information 1511, medium The skill information 1521 and the low skill information 1531) are compared with the characteristic amount CR1i, and based on the comparison result, a work information determination unit that determines which skill level the acquired work information 107A corresponds to (Determination unit 104A) and a determination unit (control amount determination unit 105A) that determines the control amount of the drive unit 62 based on the determined skill level.
  • the system of each embodiment includes a drive unit 62 for production, a sensor 50 that measures the biological information 107 of the worker, and a control computer 100 that controls the drive unit.
  • the control computer 100 includes an acquisition unit 103 that acquires the biological information 107 output from the sensor 50, and a storage unit (an area of the information memory 102) that stores the biological information 107 corresponding to the skill level for each work skill level.
  • E1 is compared with the feature amount CRi included in the biological information 107 acquired when the worker 10 is working, and the feature amount CRi included in the biological information 107 for each skill level of the storage unit. Based on the comparison result, A determination unit 104 that determines to which skill level the acquired biological information 107 corresponds, and a control amount determination unit 105 that determines a control amount of the drive unit 62 based on the determined skill level.
  • the system of each embodiment includes a drive unit 62 for production, a sensor 50A that measures workpiece information 107A indicating the movement of the workpiece W handled by the worker 10 during work, a control computer 100 that controls the drive unit, Is provided.
  • the control computer 100 includes an acquisition unit 103A that acquires the work information 107A output from the sensor 50A, and a storage unit (an area of the information memory 102A) that stores the work information 107A corresponding to the skill level for each work skill level.
  • E11 is compared with the feature amount CRi possessed by the work information 107A acquired at the time of the work of the worker 10 and the feature amount CRi possessed by the work information 107A for each skill level of the storage unit, and based on the comparison result, A determination unit 104A that determines to which skill level the acquired workpiece information 107A corresponds, and a control amount determination unit 105A that determines a control amount of the drive unit 62 based on the determined skill level.
  • the control method of each embodiment is a method of controlling the drive unit 62 for production, and the steps of obtaining the biological information 107 measured from the worker 10 (Step S3, Step S23) and the worker 10 And the biometric information (high skill level information 151, medium skill level information 152, and low level) for each skill level stored in the storage unit (area E1 of the information memory 102).
  • a step of determining a control amount of the drive unit based on the determined skill level step S37).
  • the control method of each embodiment is a method of controlling the drive unit 62 for production, the step of acquiring the workpiece information 107A indicating the movement of the workpiece W handled by the worker 10 during the work, The feature amount CRi of the work information 107A acquired at the time of work, and the work information (high skill level information 1511, medium skill level information 1521 and low skill level) for each skill level stored in the storage unit (area E11 of the information memory 102A).
  • a step of comparing the feature amount CRi included in the degree information 1531), a step of determining which skill level the acquired work information 107A corresponds to based on the comparison result, and the determined skill level And a step of determining a control amount of the drive unit based on.
  • the skill level of the worker 10 is determined in real time from the biological information 107 or work information 107A being worked, and the control amount is changed according to the determined skill level. If it is determined that the skill level is low, for example, the robot 60 (more specifically, the arm 63) changes the control amount so that it moves slower than usual, thereby reducing human errors and increasing the skill level. If it is determined, the production efficiency can be increased by changing the control amount of the robot 60 (more specifically, the arm 63) so as to move faster than usual.

Landscapes

  • Engineering & Computer Science (AREA)
  • Manufacturing & Machinery (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Automation & Control Theory (AREA)
  • General Engineering & Computer Science (AREA)
  • Quality & Reliability (AREA)
  • Human Computer Interaction (AREA)
  • General Factory Administration (AREA)
  • Numerical Control (AREA)
  • Manipulator (AREA)

Abstract

A control device is provided with: an acquisition unit (103) for acquiring biological information (107) measured from an operator; a storage unit for storing the biological information according to a skill level for each skill level of an operation; a determination unit for comparing a characteristic amount (Cri) of the biological information acquired during an operation with the characteristic amount of biological information (BM1) for each skill level in the storage unit, and determining, on the basis of the result of the comparison, the skill level to which the acquired biological information corresponds; and a decision unit for deciding the control amount of a drive unit on the basis of the determined skill level.

Description

制御装置、システム、制御方法およびプログラムControl device, system, control method and program
 この開示は制御装置、システム、制御方法およびプログラムに関し、特に、生産のための駆動部を制御する制御装置、システム、制御方法およびプログラムに関する。 This disclosure relates to a control device, a system, a control method, and a program, and more particularly, to a control device, a system, a control method, and a program that control a drive unit for production.
 工場の生産ラインでは作業者はロボットなどの機械と協調しながら作業を実施する場合がある。この場合において、作業に対する作業者の熟練の程度に合わせてロボットなどの機械を制御することが望まれている。 In the factory production line, workers may perform work in cooperation with robots and other machines. In this case, it is desired to control a machine such as a robot in accordance with the level of skill of the worker for the work.
 特許文献1(特開2015-230621号公報)は、作業者とロボットが共同で作業する場合に、作業者の作業に対する熟練度や身体特徴などを予め個人情報保持部に保持(記憶)しておき、作業時は、保持された個人情報を参照することで、作業者の熟練度を取得し、取得された熟練度に応じてロボットの挙動(位置姿勢や起動)を設定する構成を開示する。 Patent Document 1 (Japanese Patent Application Laid-Open No. 2015-230621) holds (stores) in advance in a personal information holding unit the skill level and physical characteristics of an operator's work when the worker and the robot work together. In addition, during the work, a configuration is disclosed in which the skill level of the worker is acquired by referring to the stored personal information, and the behavior (position and orientation and activation) of the robot is set according to the acquired skill level. .
特開2015-230621号公報Japanese Patent Laying-Open No. 2015-230621
 特許文献1の構成は、事前に各作業者について熟練度の情報を取得して保持(記憶)するための処理を実施する必要があり、煩わしい。また、作業者が多い大規模な作業工程または作業者の入れ替わりが頻繁である作業工程に、特許文献1の構成を導入する場合には、当該熟練度の情報の保持処理にかかるコスト(時間、メモリ容量など)が大きくなるなどの課題がある。 The configuration of Patent Literature 1 is cumbersome because it is necessary to perform processing for acquiring and storing (storing) information on skill level for each worker in advance. In addition, when the configuration of Patent Document 1 is introduced into a large-scale work process with many workers or a work process in which workers are frequently replaced, the cost (time, There are problems such as an increase in memory capacity.
 そのため、作業者の作業の熟練度に応じた生産ラインの駆動部制御を実施することが望まれている。 Therefore, it is desired to control the drive unit of the production line according to the skill level of the operator's work.
 開示のある局面に従う、生産のための駆動部を制御する制御装置は、作業者から測定された生体情報を取得する取得部と、作業の熟練度ごとに当該熟練度に応じた生体情報を記憶するための記憶部と、作業時に取得部により取得される生体情報が有する特徴量と、記憶部の熟練度ごとの生体情報が有する特徴量とを比較し、比較の結果に基づき、当該取得される生体情報がいずれの熟練度に該当するかを判定する判定部と、判定された熟練度に基づき駆動部の制御量を決定する決定部と、を備える。 A control device for controlling a drive unit for production according to an aspect of the disclosure stores an acquisition unit that acquires biological information measured from an operator, and biological information corresponding to the skill level for each skill level of the work The biometric information acquired by the acquisition unit at the time of work and the biometric information possessed by the biometric information for each skill level of the storage unit are compared, and the acquired based on the comparison result A determination unit that determines which skill level the biological information corresponds to, and a determination unit that determines a control amount of the drive unit based on the determined skill level.
 好ましくは、生体情報は、作業時の身体の動作を示す情報を含む。
 好ましくは、熟練度ごとに当該熟練度に応じた生体情報が有する特徴量を取得し記憶部に蓄積する蓄積部を、さらに備える。
Preferably, the biological information includes information indicating the movement of the body during work.
Preferably, the information processing apparatus further includes a storage unit that acquires, for each skill level, a feature amount of biometric information corresponding to the skill level and stores the feature amount in the storage unit.
 好ましくは、記憶部に蓄積される特徴量は、判定部より判定された熟練度に応じた生体情報が有する特徴量を含む。 Preferably, the feature amount stored in the storage unit includes a feature amount included in the biological information corresponding to the skill level determined by the determination unit.
 上記の制御装置は、さらに、作業者が作業時に扱うワークの動きを示すワーク情報を取得するワーク情報取得部と、熟練度ごとに当該熟練度に応じたワーク情報を記憶するためのワーク情報記憶部と、作業者の作業時に取得されるワーク情報が有する特徴量と、ワーク情報記憶部の熟練度ごとのワーク情報が有する特徴量とを比較し、比較の結果に基づき、当該取得されるワーク情報がいずれの熟練度に該当するかを判定するワーク情報判定部と、を備え、決定部は、判定部により判定された熟練度と、ワーク情報判定部により判定された熟練度に基づき、制御量を決定する。 The control device further includes a work information acquisition unit that acquires work information indicating a movement of a work handled by an operator during work, and a work information storage for storing work information corresponding to the skill level for each skill level The feature quantity of the work information acquired at the time of the work of the operator and the feature quantity of the work information for each skill level of the work information storage section are compared, and based on the comparison result, A work information determination unit that determines which skill level the information corresponds to, and the determination unit performs control based on the skill level determined by the determination unit and the skill level determined by the work information determination unit Determine the amount.
 好ましくは、特徴量は、熟練度を識別可能な特徴量を含む。
 好ましくは、判定部は、予め定められた時間毎に熟練度を判定し、制御装置は、予め定められた時間毎に判定された熟練度を統計し、統計情報を出力する。
Preferably, the feature amount includes a feature amount that can identify the skill level.
Preferably, the determination unit determines the skill level every predetermined time, and the control device statistics the skill level determined every predetermined time and outputs statistical information.
 この開示の他の局面にかかるシステムは、生産のための駆動部と、作業者の生体情報を測定するセンサと、駆動部を制御する制御装置と、を備える。制御装置は、センサから出力される生体情報を取得する取得部と、作業の熟練度ごとに当該熟練度に応じた生体情報を記憶するための記憶部と、作業者の作業時に取得される生体情報が有する特徴量と、記憶部の熟練度ごとの生体情報が有する特徴量とを比較し、比較の結果に基づき、当該取得される生体情報がいずれの熟練度に該当するかを判定する判定部と、判定された熟練度に基づき駆動部の制御量を決定する決定部と、を含む。 A system according to another aspect of the present disclosure includes a drive unit for production, a sensor that measures the biological information of the worker, and a control device that controls the drive unit. The control device includes an acquisition unit that acquires biological information output from the sensor, a storage unit that stores biological information corresponding to the skill level of each work skill level, and a biological information acquired when the operator works Judgment to determine which skill level the acquired biometric information corresponds to by comparing the feature value of the information with the feature value of the biometric information for each skill level of the storage unit And a determination unit that determines a control amount of the drive unit based on the determined skill level.
 この開示のさらに他の局面にかかる制御方法は、生産のための駆動部を制御する方法であって、作業者から測定された生体情報を取得するステップと、作業者の作業時に取得される生体情報が有する特徴量と、記憶部に格納された熟練度ごとの生体情報が有する特徴量とを比較するステップと、比較の結果に基づき、当該取得される生体情報がいずれの熟練度に該当するかを判定するステップと、判定された熟練度に基づき駆動部の制御量を決定するステップと、を備える。 A control method according to still another aspect of the present disclosure is a method of controlling a drive unit for production, the step of acquiring biological information measured from an operator, and a biological body acquired at the time of the operator's work The step of comparing the feature quantity of the information with the feature quantity of the biometric information for each skill level stored in the storage unit, and based on the comparison result, the acquired biometric information corresponds to any skill level And a step of determining a control amount of the drive unit based on the determined skill level.
 この開示のさらに他の局面にかかるプログラムは、生産のための駆動部を制御する方法をコンピュータに実行させるためのプログラムであって、この方法は、作業者から測定された生体情報を取得するステップと、作業者の作業時に取得される生体情報が有する特徴量と、記憶部に格納された熟練度ごとの生体情報が有する特徴量とを比較するステップと、比較の結果に基づき、当該取得される生体情報がいずれの熟練度に該当するかを判定するステップと、判定された熟練度に基づき駆動部の制御量を決定するステップと、を備える。 A program according to still another aspect of the present disclosure is a program for causing a computer to execute a method of controlling a drive unit for production, and the method acquires biological information measured from an operator. And the step of comparing the feature amount of the biometric information acquired at the time of the work of the operator with the feature amount of the biometric information stored for each skill level stored in the storage unit, and the acquired based on the comparison result And a step of determining to which skill level the biometric information corresponds to, and a step of determining a control amount of the drive unit based on the determined skill level.
 作業者の作業の熟練度に応じて生産のための駆動部を制御する。 制 御 Control the drive unit for production according to the skill level of the worker's work.
実施の形態1にかかるシステム1の全体構成を概略的に示す図である。1 is a diagram schematically illustrating an overall configuration of a system 1 according to a first embodiment. 図1の制御コンピュータ100のハードウェア構成を模式的に示す図である。It is a figure which shows typically the hardware constitutions of the control computer 100 of FIG. 図1のロボット60の構成を概略的に示す図である。It is a figure which shows schematically the structure of the robot 60 of FIG. 実施の形態1にかかる生体情報を例示する図である。It is a figure which illustrates the biometric information concerning Embodiment 1. FIG. 実施の形態1にかかる生体情報を例示する図である。It is a figure which illustrates the biometric information concerning Embodiment 1. FIG. 実施の形態1にかかる制御コンピュータ100の機能の構成を模式的に示す図である。FIG. 2 is a diagram schematically illustrating a functional configuration of a control computer 100 according to the first embodiment. 実施の形態1にかかる「学習モード」の処理フローチャートである。4 is a process flowchart of “learning mode” according to the first exemplary embodiment; 実施の形態1にかかる有効パターンEPおよび閾値TH1~TH3の決定方法を説明するための図である。FIG. 7 is a diagram for explaining a method of determining an effective pattern EP and threshold values TH1 to TH3 according to the first embodiment. 実施の形態1にかかる「運用モード」の処理フローチャートである。4 is a process flowchart of “operation mode” according to the first exemplary embodiment; 実施の形態1にかかる学習モードにおける閾値の決定方法の他の例を模式的に示す図である。It is a figure which shows typically the other example of the determination method of the threshold value in the learning mode concerning Embodiment 1. FIG. 実施の形態2にかかる熟練度の記録内容の表示例を示す図である。FIG. 10 is a diagram showing a display example of the recording content of skill level according to the second embodiment. 作業中の手の移動速度の変化の表示例を示す図である。It is a figure which shows the example of a display of the change of the moving speed of the hand during work. 作業中の手の移動にかかる加速度の変化の表示例を示す図である。It is a figure which shows the example of a display of the change of the acceleration concerning the movement of the hand during work. 実施の形態4にかかる制御コンピュータ100の機能の構成を模式的に示す図である。FIG. 6 is a diagram schematically illustrating a functional configuration of a control computer 100 according to a fourth embodiment. 実施の形態4にかかる「学習モード」の処理フローチャートである。10 is a process flowchart of “learning mode” according to the fourth exemplary embodiment; 実施の形態4にかかる「運用モード」の処理フローチャートである。10 is a process flowchart of “operation mode” according to the fourth exemplary embodiment;
 本発明の実施の形態について、図面を参照しながら詳細に説明する。なお、以下の図面において、同一または相当する部分には同一の参照番号を付してその説明は繰り返さない。 Embodiments of the present invention will be described in detail with reference to the drawings. In the following drawings, the same or corresponding parts are denoted by the same reference numerals, and the description thereof will not be repeated.
 [実施の形態1]
 (システムの構成)
 図1は、実施の形態1にかかるシステム1の全体構成を概略的に示す図である。FA(Factory Automation)などの生産ラインには、作業者10の作業に用いられる1または複数のユニット200、PLC(Programmable Logic Controller)などの制御コンピュータ100、および管理者が操作する管理コンピュータ300を備える。これらの各部は、有線または無線で相互に通信する。また、制御コンピュータ100は、作業者10が携帯する端末11と通信することができるが、管理コンピュータ300は、端末11と通信するとしてもよい。なお、システム1は生産現場に設置されるものであればよく、設置対象は生産ラインに限定されない。
[Embodiment 1]
(System configuration)
FIG. 1 is a diagram schematically illustrating an overall configuration of a system 1 according to the first embodiment. A production line such as FA (Factory Automation) includes one or a plurality of units 200 used for the work of the worker 10, a control computer 100 such as a PLC (Programmable Logic Controller), and a management computer 300 operated by the administrator. . These units communicate with each other by wire or wireless. The control computer 100 can communicate with the terminal 11 carried by the worker 10, but the management computer 300 may communicate with the terminal 11. In addition, the system 1 should just be installed in a production site, and the installation object is not limited to a production line.
 ユニット200は、作業者10と協調作業する産業用ロボット60(以下、単にロボット60という)、および人の生体情報を非接触形式で検出するセンサ50を備える。図1では、作業者10は、例えばロボット60と協調してワークWを搬送する作業を実施する。 The unit 200 includes an industrial robot 60 (hereinafter simply referred to as a robot 60) that cooperates with the worker 10 and a sensor 50 that detects human biological information in a non-contact manner. In FIG. 1, the worker 10 performs a work of transporting the workpiece W in cooperation with the robot 60, for example.
 実施の形態1では、作業者10の作業時の「生体情報」から、作業の熟練の程度(以下、熟練度という)を判定し、判定された熟練度を用いてロボット60の制御量を決定する。 In the first embodiment, the level of skill of the work (hereinafter referred to as skill level) is determined from the “biological information” at the time of the work of the worker 10, and the control amount of the robot 60 is determined using the determined skill level. To do.
 センサ50は身体の動きの経時的変化(姿勢の変化、移動など)を測定する機能を備える。具体的には、ハードウェア回路としての距離画像センサと、距離画像センサの出力から人体の動きを推定するソフトウェアプログラムを実行するマイクロコンピュータとを備える。距離画像センサは対象(人体)に赤外線を照射して得られた赤外線パターンを解析することにより距離画像を取得する。マイクロコンピュータは、距離画像と予め登録されているパターン画像とを照合し、照合の結果に基づき、距離画像において身体の各部(頭、胴体、肩、腕、腰、足、手、指など)の位置(座標値)を検出する。そして、時系列に取得される距離画像から、身体の各部の位置の経時的な変化が検出される。このように、センサ50は、赤外線の照射範囲に位置する作業者の身体の動きの経時的な変化を示す生体情報107を、制御コンピュータ100に送信する。 Sensor 50 has a function of measuring changes in body movement over time (posture change, movement, etc.). Specifically, it includes a distance image sensor as a hardware circuit, and a microcomputer that executes a software program for estimating the movement of the human body from the output of the distance image sensor. The distance image sensor acquires a distance image by analyzing an infrared pattern obtained by irradiating an object (human body) with infrared rays. The microcomputer collates the distance image with a pre-registered pattern image, and based on the result of the collation, each part of the body (head, torso, shoulders, arms, waist, legs, hands, fingers, etc.) in the distance image. The position (coordinate value) is detected. And the change with time of the position of each part of the body is detected from the distance image acquired in time series. As described above, the sensor 50 transmits the biological information 107 indicating the temporal change in the movement of the worker's body located in the infrared irradiation range to the control computer 100.
 なお、身体の動きを測定する方法は、センサ50のような距離画像から測定する方法に限定されない。また、図1では、センサ50はユニット200毎に備えたが、1台のセンサ50を複数のユニット200で共用してもよい。 Note that the method of measuring the movement of the body is not limited to the method of measuring from the distance image such as the sensor 50. In FIG. 1, the sensor 50 is provided for each unit 200, but one sensor 50 may be shared by a plurality of units 200.
 また、生体情報107は、上記の身体の動きの経時的な変化を示す情報に限定されない。たとえば、生体情報107は、さらに、作業者10の体温、呼吸数、脈拍、血圧等の経時的な変化を示す情報を含み得る。体温、呼吸数は、センサ50が撮像する赤外線画像から測定することができる。また、脈拍、血圧等は作業者10が携帯する腕時計タイプの装置により測定されて、当該装置は、測定データを制御コンピュータ100に送信する。 Further, the biological information 107 is not limited to information indicating the change of the body movement over time. For example, the biological information 107 may further include information indicating changes over time such as the body temperature, the respiratory rate, the pulse rate, and the blood pressure of the worker 10. The body temperature and the respiratory rate can be measured from an infrared image captured by the sensor 50. Further, the pulse, blood pressure, and the like are measured by a wristwatch type device carried by the operator 10, and the device transmits measurement data to the control computer 100.
 (制御コンピュータ100の構成)
 図2は、図1の制御コンピュータ100のハードウェア構成を模式的に示す図である。図2を参照して、制御コンピュータ100は、演算処理部であるCPU(Central Processing Unit)110と、記憶部としてのメモリ112およびハードディスク114と、時間を計時し計時データをCPU110に出力するタイマ113と、入力インタフェイス118と、ディスプレイ122を制御する表示コントローラ120と、通信インタフェイス124と、データリーダ/ライタ126とを含む。これらの各部は、バス128を介して、互いにデータ通信可能に接続される。
(Configuration of control computer 100)
FIG. 2 is a diagram schematically showing a hardware configuration of the control computer 100 of FIG. Referring to FIG. 2, control computer 100 includes a CPU (Central Processing Unit) 110 that is an arithmetic processing unit, a memory 112 and a hard disk 114 as a storage unit, and a timer 113 that measures time and outputs timing data to CPU 110. An input interface 118, a display controller 120 for controlling the display 122, a communication interface 124, and a data reader / writer 126. These units are connected to each other via a bus 128 so that data communication is possible.
 CPU110は、ハードディスク114に格納されたプログラム(コード)を実行することで、各種の演算を実施する。メモリ112は、典型的には、DRAM(Dynamic Random Access Memory)などの揮発性の記憶装置であり、ハードディスク114から読み出されたプログラム・データに加えて、センサ50から受信する生体情報、およびワークデータなどが格納される。 The CPU 110 executes various calculations by executing a program (code) stored in the hard disk 114. The memory 112 is typically a volatile storage device such as a DRAM (Dynamic Random Access Memory), and in addition to program data read from the hard disk 114, biological information received from the sensor 50, and work Data etc. are stored.
 入力インタフェイス118は、CPU110とキーボード121、マウス(図示せず)、タッチパネル(図示せず)などの入力装置との間のデータ伝送を仲介する。すなわち、入力インタフェイス118は、ユーザが入力装置を操作することで与えられる操作命令を受付ける。 The input interface 118 mediates data transmission between the CPU 110 and an input device such as a keyboard 121, a mouse (not shown), a touch panel (not shown). That is, the input interface 118 accepts an operation command given by the user operating the input device.
 通信インタフェイス124は、ユニット200(センサ50,ロボット60)または管理コンピュータ300または端末11との間のデータ伝送を仲介する。データリーダ/ライタ126は、CPU110と記録媒体であるメモリカード123との間のデータ伝送を仲介する。 The communication interface 124 mediates data transmission between the unit 200 (the sensor 50, the robot 60), the management computer 300, or the terminal 11. The data reader / writer 126 mediates data transmission between the CPU 110 and the memory card 123 that is a recording medium.
 (ロボット60の構成)
 図3は、図1のロボット60の構成を概略的に示す図である。ロボット60は、ワークWを把持して搬送するために自在に回動するアーム63と、ワークWを搬送するようにアーム63を回動させるための駆動部62、および駆動部62を制御するコントローラ61を備える。なお、作業内容はワークWの搬送に限定されず、ワークWが部品であった場合にはワークWの本体への取付け作業などであってもよい。
(Configuration of robot 60)
FIG. 3 is a diagram schematically showing the configuration of the robot 60 of FIG. The robot 60 includes an arm 63 that freely rotates to grip and transfer the workpiece W, a drive unit 62 that rotates the arm 63 to transfer the workpiece W, and a controller that controls the drive unit 62. 61 is provided. The work content is not limited to the conveyance of the work W, and may be an attachment work of the work W to the main body when the work W is a part.
 駆動部62は、たとえばサーボモータである。ロボット60のアーム63は、駆動部62(サーボモータの回転軸)に接続される。図示されないエンコーダが、駆動部62に取付けられる。エンコーダは、駆動部62の動作状態を示す物理量を検出し、検出された物理量を示すフィードバック信号を生成するとともに、そのフィードバック信号をサーボドライバに相当するコントローラ61に出力する。フィードバック信号は、たとえば駆動部62のモータの回転軸の回転位置(角度)についての位置情報、その回転軸の回転速度の情報などを含む。実施の形態1においては、駆動部62(サーボモータ)の動作状態を示す物理量としてモータの回転軸の回転位置および回転速度が検出される。なお、回転位置および回転速度に加えてもしくは代わりに、加速度、変化量(移動量)、変化方向(移動方向)などを検出するようにしてもよい。 The drive unit 62 is, for example, a servo motor. The arm 63 of the robot 60 is connected to a drive unit 62 (rotary shaft of a servo motor). An encoder (not shown) is attached to the drive unit 62. The encoder detects a physical quantity indicating the operating state of the drive unit 62, generates a feedback signal indicating the detected physical quantity, and outputs the feedback signal to the controller 61 corresponding to the servo driver. The feedback signal includes, for example, position information about the rotation position (angle) of the rotation shaft of the motor of the drive unit 62, information on the rotation speed of the rotation shaft, and the like. In the first embodiment, the rotational position and rotational speed of the rotating shaft of the motor are detected as physical quantities indicating the operating state of the drive unit 62 (servo motor). In addition to or instead of the rotation position and rotation speed, acceleration, change amount (movement amount), change direction (movement direction), and the like may be detected.
 コントローラ61は、制御コンピュータ100から指令信号106を受けるとともに、エンコーダから出力されたフィードバック信号を受ける。コントローラ61は、制御コンピュータ100からの指令信号106およびエンコーダからのフィードバック信号に基づいて、駆動部62を駆動する。 The controller 61 receives the command signal 106 from the control computer 100 and the feedback signal output from the encoder. The controller 61 drives the drive unit 62 based on the command signal 106 from the control computer 100 and the feedback signal from the encoder.
 コントローラ61は、制御コンピュータ100からの指令信号106に基づいて、駆動部62の動作に関する指令値を設定する。さらにコントローラ61は、駆動部62の動作が指令値に追従するように駆動部62を駆動する。具体的には、コントローラ61は、その指令値に従って、駆動部62(サーボモータ)の駆動電流を制御する。 The controller 61 sets a command value related to the operation of the drive unit 62 based on the command signal 106 from the control computer 100. Furthermore, the controller 61 drives the drive unit 62 so that the operation of the drive unit 62 follows the command value. Specifically, the controller 61 controls the drive current of the drive unit 62 (servo motor) according to the command value.
 このように、ロボット60は、アーム63に把持したワークWを作業者10と協調して搬送する場合に、アーム63の制御量(アームを回動させるための角度、方向、速度など)は、コントローラ61および駆動部62を介して、制御コンピュータ100からの指令信号106により遠隔から可変に制御される。 Thus, when the robot 60 transports the workpiece W gripped by the arm 63 in cooperation with the operator 10, the control amount of the arm 63 (angle, direction, speed, etc. for rotating the arm) is as follows. The controller 61 and the drive unit 62 are variably controlled remotely by a command signal 106 from the control computer 100.
 (生体情報と特徴量)
 図4と図5は、実施の形態1にかかる生体情報を例示する図である。実施の形態1では、生体情報107が有する特徴量を用いて作業の熟練度を判定する。説明を簡単にするために、生体情報107に含まれる身体の動きの経時的な変化の情報(身体の各部位の位置、移動速度、移動加速度、移動距離などの経時的な変化の情報)が有する特徴量を用いる。なお、体温、脈拍、血圧等の経時的な変化を示す情報が有する特徴量を用いても同様に熟練度を判定することができる。
(Biological information and features)
4 and 5 are diagrams illustrating the biological information according to the first embodiment. In the first embodiment, the skill level of the work is determined using the feature value of the biological information 107. In order to simplify the description, information on temporal changes in body movement included in the biological information 107 (information on temporal changes in position, movement speed, movement acceleration, movement distance of each part of the body) is included. Use the feature quantity. It should be noted that the skill level can be determined in the same manner by using a feature amount included in information indicating changes with time such as body temperature, pulse, blood pressure, and the like.
 生体情報107は、たとえば、頭の移動量の変化(特定的には、頭の位置の経時的な変化)を含む。図4は、作業者10が熟練者であるときの頭の移動量(頭の位置の経時的な変化)の経過的な変化をグラフで示し、同様に図5は、作業者10が非熟練者(初心者など)であるときの頭の位置の経時的な変化をグラフで示す。これらグラフは、発明者らの実験により取得されたデータである。 The biological information 107 includes, for example, a change in the amount of movement of the head (specifically, a change in the position of the head over time). FIG. 4 is a graph showing a temporal change in the amount of movement of the head (change in the position of the head over time) when the worker 10 is an expert. Similarly, FIG. The graph shows the change over time in the position of the head when the user is a beginner (such as a beginner). These graphs are data acquired by the inventors' experiments.
 図4と図5のグラフでは縦軸に作業者10の頭の移動量がとられて、横軸に時間がとられている。図4の熟練者の場合には、頭の移動量は一定の範囲に収束する。これに対して、図5の非熟練者の場合には、頭の移動量は時間が経過しても一定の範囲に収束することはない。したがって、発明者は、実験から、作業時に取得される作業者10の身体の各部位の動きから、作業者10の熟練の程度を推定することが可能になるとの知見を得た。 In the graphs of FIGS. 4 and 5, the movement amount of the head of the worker 10 is taken on the vertical axis, and the time is taken on the horizontal axis. In the case of the skilled person in FIG. 4, the amount of head movement converges within a certain range. On the other hand, in the case of the unskilled person in FIG. 5, the amount of head movement does not converge to a certain range over time. Therefore, the inventor has learned from experiments that it is possible to estimate the degree of skill of the worker 10 from the movement of each part of the body of the worker 10 acquired during the work.
 (制御コンピュータ100の機能構成)
 図6は、実施の形態1にかかる制御コンピュータ100の機能の構成を模式的に示す図である。図6に示される機能は、作業者の生体情報107から駆動部62の制御量を決定する機能を含む。実施の形態1にかかる制御コンピュータ100の動作モードは、「学習モード」と「運用モード」とを含む。図6を参照して、制御コンピュータ100は、学習部101、センサ50から生体情報107を取得する取得部103、作業者10の作業に対する熟練度を判定する判定部104、および制御量決定部105を備える。また、制御コンピュータ100は、記憶部(ハードディスク114など)に対応する情報メモリ102を備える。
(Functional configuration of control computer 100)
FIG. 6 is a diagram schematically illustrating a functional configuration of the control computer 100 according to the first embodiment. The function shown in FIG. 6 includes a function of determining the control amount of the drive unit 62 from the biological information 107 of the worker. The operation mode of the control computer 100 according to the first embodiment includes a “learning mode” and an “operation mode”. Referring to FIG. 6, the control computer 100 includes a learning unit 101, an acquisition unit 103 that acquires biological information 107 from the sensor 50, a determination unit 104 that determines the skill level of the work of the worker 10, and a control amount determination unit 105. Is provided. The control computer 100 also includes an information memory 102 corresponding to a storage unit (such as the hard disk 114).
 実施の形態1では、「学習モード」において学習部101は、取得部103により取得される生体情報107を情報メモリ102に格納し、格納された生体情報107に基づき熟練度を識別するための特徴量(以下、識別特徴量ともいう)を決定する。また、「運用モード」において判定部104は、作業者10から取得される生体情報107が有する複数種類の特徴量(以下、取得特徴量ともいう)のうち上記の識別特徴量に対応した特徴量と閾値とを比較し、比較の結果に基づき、当該取得される生体情報107がいずれの熟練度に該当するかを判定する。制御量決定部105は、判定された熟練度に基づき駆動部62の制御量を決定する。 In the first embodiment, in the “learning mode”, the learning unit 101 stores the biological information 107 acquired by the acquisition unit 103 in the information memory 102 and identifies the skill level based on the stored biological information 107. A quantity (hereinafter also referred to as an identification feature quantity) is determined. Further, in the “operation mode”, the determination unit 104 includes a feature amount corresponding to the identification feature amount among a plurality of types of feature amounts (hereinafter, also referred to as acquired feature amounts) included in the biological information 107 acquired from the worker 10. And the threshold value are compared, and based on the comparison result, it is determined to which skill level the acquired biological information 107 corresponds. The control amount determination unit 105 determines the control amount of the drive unit 62 based on the determined skill level.
 ここでは、熟練度は、高(以下、高熟練度という)、中(以下、中熟練度という)、低(以下、低熟練度という)の3つに分類するが、分類は3つに限定されず、2つであってもよく、または4つ以上であってもよい。 Here, the skill level is classified into three categories: high (hereinafter referred to as high skill level), medium (hereinafter referred to as medium skill level), and low (hereinafter referred to as low skill level), but the classification is limited to three. The number may be two, or four or more.
 図6を参照して、情報メモリ102は領域E1、E2、E3およびE4を含む。領域E1は、高熟練度の情報151、中熟練度の情報152および低熟練度の情報153を格納するための記憶領域である。領域E2は、「学習モード」の学習結果を格納するための領域である。学習結果は、1以上の識別特徴量の組合せを示すパターンEPと熟練度を判別するための閾値TH1、TH2およびTH3とを含む。領域E3およびE4は、作業領域に相当する。 Referring to FIG. 6, information memory 102 includes areas E1, E2, E3, and E4. The area E1 is a storage area for storing high skill level information 151, medium skill level information 152, and low skill level information 153. The area E2 is an area for storing the learning result of the “learning mode”. The learning result includes a pattern EP indicating a combination of one or more identification feature values and thresholds TH1, TH2, and TH3 for determining the skill level. Areas E3 and E4 correspond to work areas.
 高熟練度情報151は、「学習モード」において高熟練度である作業者10の作業時に取得される複数の生体情報107である生体情報BM1を含む。高熟練度情報151は、さらに、各生体情報BM1に関連付けて‘高熟練度’を示すラベルLB1、当該生体情報BM1から取得される複数の取得特徴量CRi(i=1,2,3・・・,n)を含む。 The high skill level information 151 includes biometric information BM1 that is a plurality of pieces of biometric information 107 acquired at the time of work of the worker 10 who is highly skilled in the “learning mode”. The high skill level information 151 further includes a label LB1 indicating “high skill level” in association with each biological information BM1, and a plurality of acquired feature amounts CRi (i = 1, 2, 3,...) Acquired from the biological information BM1. ., N) are included.
 同様に、中熟練度情報152は、「学習モード」において中熟練度である作業者10の作業時に取得される複数の生体情報107である生体情報BM1を含む。中熟練度情報152は、さらに、各生体情報BM1に関連付けて‘中熟練度’を示すラベルLB2、当該生体情報BM2から取得される複数の取得特徴量CRi(i=1,2,3・・・,n)を含む。 Similarly, the medium skill level information 152 includes biometric information BM1 that is a plurality of pieces of biometric information 107 acquired at the time of the work of the worker 10 having the medium skill level in the “learning mode”. The medium skill level information 152 further includes a label LB2 indicating “medium skill level” in association with each biological information BM1, and a plurality of acquired feature amounts CRi (i = 1, 2, 3,...) Acquired from the biological information BM2. ., N) are included.
 同様に、低熟練度情報153は、「学習モード」において低熟練度である作業者10の作業時に取得される複数の生体情報107である生体情報BM1を含む。低熟練度情報153は、さらに、各生体情報BM1に関連付けて‘低熟練度’を示すラベルLB3、当該生体情報BM1から取得される複数の取得特徴量CRi(i=1,2,3・・・,n)を含む。 Similarly, the low skill level information 153 includes biometric information BM1 that is a plurality of pieces of biometric information 107 acquired at the time of the work of the worker 10 who has a low skill level in the “learning mode”. The low skill level information 153 further includes a label LB3 indicating “low skill level” in association with each biological information BM1, and a plurality of acquired feature amounts CRi (i = 1, 2, 3,...) Acquired from the biological information BM1. ., N) are included.
 図6の領域E1の生体情報BM1は、学習モードが終了したときに削除されるとしてもよい。この場合には、情報メモリ102に必要な容量を少なくすることができる。 6 may be deleted when the learning mode ends. In this case, the capacity required for the information memory 102 can be reduced.
 取得部103は、通信インタフェイス124を制御して、センサ50から生体情報107を取得(受信)し、取得された生体情報107を各部に出力する。 The acquisition unit 103 controls the communication interface 124 to acquire (receive) the biological information 107 from the sensor 50, and output the acquired biological information 107 to each unit.
 学習部101は、制御コンピュータ100の動作モードが「学習モード」であるとき、取得部103から熟練度ごとの生体情報107を入力し、入力した生体情報107を各熟練度に対応付けて情報メモリ102の領域E1に格納する。これにより、「学習モード」において、複数の生体情報107が情報メモリ102に熟練度ごとに蓄積(格納)される。学習部101は、生体情報107を情報メモリ102に熟練度ごとに蓄積する「蓄積部」の一実施例である。 When the operation mode of the control computer 100 is “learning mode”, the learning unit 101 inputs biometric information 107 for each skill level from the acquisition unit 103, and associates the input biometric information 107 with each skill level in the information memory. 102 in the area E1. Thereby, in the “learning mode”, a plurality of pieces of biological information 107 are accumulated (stored) in the information memory 102 for each skill level. The learning unit 101 is an example of an “accumulation unit” that accumulates the biological information 107 in the information memory 102 for each skill level.
 また、学習部101は、「学習モード」であるとき、情報メモリ102の高熟練度情報151の生体情報BM1からの取得特徴量CRiのうちの1つ以上を識別特徴量CRiと決定する。また、学習部101は、決定された1つ以上の識別特徴量CRiからなる組合せを、有効パターンEPとして領域E2に格納する。有効パターンEPは、熟練度を識別するために有効な1つ以上の識別特徴量CRiの組合せを示す。学習部101は、高熟練度情報151、中熟練度情報152および低熟練度情報153の取得特徴量CRiのうちの、有効パターンEPの識別特徴量CRiの組合せに対応した取得特徴量CRiの組合せを特定する。そして、特定された組合せの値に基づき、閾値TH1、TH2およびTH3を取得し、領域E2に格納する。 Further, when in the “learning mode”, the learning unit 101 determines one or more of the acquired feature amounts CRi from the biological information BM1 of the high skill level information 151 of the information memory 102 as the identification feature amount CRi. In addition, the learning unit 101 stores the combination including the determined one or more identification feature amounts CRi in the region E2 as the effective pattern EP. The effective pattern EP indicates a combination of one or more identification feature amounts CRi effective for identifying the skill level. The learning unit 101 includes a combination of acquired feature amounts CRi corresponding to a combination of the identification feature amounts CRi of the effective pattern EP among the acquired feature amounts CRi of the high skill level information 151, the medium skill level information 152, and the low skill level information 153. Is identified. Then, based on the specified combination value, threshold values TH1, TH2, and TH3 are acquired and stored in the region E2.
 判定部104は、制御コンピュータ100の動作モードが「運用モード」であるとき、取得部103から、作業に従事している作業者10の生体情報107を取得する。判定部104は、当該生体情報107が有する特徴量CRiのうちから、有効パターンEPの識別特徴量CRiの組合せに対応した特徴量CRiの組合せを特定する。判定部104は、特定された特徴量CRiの組合せの値を、閾値TH1、TH2およびTH3と比較する。そして、比較の結果に基づき、当該取得される生体情報107がいずれの熟練度に該当するかを判定する。 The determination unit 104 acquires the biological information 107 of the worker 10 engaged in the work from the acquisition unit 103 when the operation mode of the control computer 100 is the “operation mode”. The determination unit 104 identifies a combination of feature amounts CRi corresponding to the combination of the identification feature amounts CRi of the effective pattern EP from the feature amounts CRi included in the biological information 107. The determination unit 104 compares the combination value of the specified feature amount CRi with threshold values TH1, TH2, and TH3. Then, based on the comparison result, it is determined to which skill level the obtained biological information 107 corresponds.
 実施の形態1では、熟練度ごとの閾値TH1、TH2およびTH3のそれぞれは、上限値と下限値を有した値の幅(範囲)として設定される。判定部104は、作業者10から取得される生体情報107の有効パターンEPに対応した1つ以上の取得特徴量CRiの値が閾値TH1の範囲内にあるとき‘高熟練度’と判定し、閾値TH2の範囲内にあるときは‘中熟練度’と判定し、閾値TH3の範囲内にあるときは‘低熟練度’と判定する。 In Embodiment 1, each of the threshold values TH1, TH2, and TH3 for each skill level is set as a width (range) of values having an upper limit value and a lower limit value. The determination unit 104 determines 'high skill level' when the value of one or more acquired feature values CRi corresponding to the effective pattern EP of the biological information 107 acquired from the worker 10 is within the range of the threshold value TH1. When it is within the range of the threshold value TH2, it is determined as “medium skill level”, and when it is within the range of the threshold value TH3, it is determined as “low skill level”.
 制御量決定部105は、「運用モード」において、判定部104により判定された熟練度に基づき駆動部62の制御量を決定する。制御量決定部105は、決定した制御量を示す指令信号106を生成し、通信インタフェイス124を介してロボット60のコントローラ61に送信する。 Control amount determination unit 105 determines the control amount of drive unit 62 based on the skill level determined by determination unit 104 in the “operation mode”. The control amount determination unit 105 generates a command signal 106 indicating the determined control amount and transmits the command signal 106 to the controller 61 of the robot 60 via the communication interface 124.
 (情報メモリ102の変更)
 上記の情報メモリ102の各熟練度のデータは可変であってよい。たとえば、ワークWの種類が変更したときに「学習モード」が実施されて情報メモリ102のデータが変更されてもよい。
(Change of information memory 102)
Each skill data in the information memory 102 may be variable. For example, when the type of the work W is changed, the “learning mode” may be performed and the data in the information memory 102 may be changed.
 また、「運用モード」において、同一の作業者10について「高熟練度」の判定がN回(ただし、N>2)連続したときは、当該作業者10の生体情報107を、高熟練度情報151の生体情報BM1として情報メモリ102の領域E1に追加し、学習部101は、追加後の領域E1の情報に基づき、有効パターンEPおよび閾値TH1、TH2およびTH3を、再度、取得し直すとしてもよい。これにより、有効パターンEPが示す識別特徴量CRiを、より識別率が高いものに変更することができる。また、閾値TH1、TH2およびTH3を、熟練度の判別精度をより正確にするような値に変更することが可能となる。 Further, in the “operation mode”, when the determination of “high skill level” continues for N times (however, N> 2) for the same worker 10, the biological information 107 of the worker 10 is stored in the high skill level information. 151, the biometric information BM1 is added to the area E1 of the information memory 102, and the learning unit 101 may acquire the effective pattern EP and the threshold values TH1, TH2, and TH3 again based on the information of the added area E1. Good. Thereby, the identification feature amount CRi indicated by the effective pattern EP can be changed to one having a higher identification rate. Further, the threshold values TH1, TH2, and TH3 can be changed to values that make the skill level determination accuracy more accurate.
 (処理フローチャート)
 上記の「学習モード」および「運用モード」の処理を説明する。なお、図1の各ユニット200においては、以下に説明する「学習モード」および「運用モード」の処理が同様に実施される。
(Processing flowchart)
The processing of the above “learning mode” and “operation mode” will be described. In each unit 200 of FIG. 1, the “learning mode” and “operation mode” processes described below are similarly performed.
 図7は、実施の形態1にかかる「学習モード」の処理フローチャートである。図8は、実施の形態1にかかる有効パターンEPおよび閾値TH1~TH3の決定方法を説明するための図である。図9は、実施の形態1にかかる「運用モード」の処理フローチャートである。図7と図9のフローチャートの処理はプログラムとして制御コンピュータ100の記憶部(メモリ112、ハードディスク114、メモリカード123など)に格納されている。CPU110は、記憶部からプログラムを読出し、実行する。なお、ここでは、生産ラインにおいて、作業者10はロボット60とワークWの搬送作業を終了すると、次のワークWの搬送作業を同様に繰返す。生産ラインは、各回の搬送作業を終了したことを検出する図示しないセンサを備える。例えば、ワークWが生産ラインの所定位置にまで移動したことを検出する近接スイッチなどである。制御コンピュータ100は、当該センサからの検出信号を、各搬送作業の繰り返しタイミングを指示するタイミング信号として処理する。 FIG. 7 is a process flowchart of the “learning mode” according to the first exemplary embodiment. FIG. 8 is a diagram for explaining a method of determining the effective pattern EP and the thresholds TH1 to TH3 according to the first embodiment. FIG. 9 is a process flowchart of the “operation mode” according to the first exemplary embodiment. 7 and 9 is stored as a program in a storage unit (memory 112, hard disk 114, memory card 123, etc.) of the control computer 100. CPU110 reads a program from a memory | storage part and performs it. Here, in the production line, when the worker 10 finishes the transfer operation of the robot 60 and the workpiece W, the transfer operation of the next workpiece W is similarly repeated. The production line includes a sensor (not shown) that detects the completion of each transfer operation. For example, a proximity switch that detects that the workpiece W has moved to a predetermined position on the production line. The control computer 100 processes the detection signal from the sensor as a timing signal that indicates the repetitive timing of each transfer operation.
 なお、「学習モード」を実施する制御コンピュータ100は「運用モード」を実施する制御コンピュータ100と同じであってもよく、または異なっていてもよい。異なっている場合には、「運用モード」の制御コンピュータ100は、高熟練度情報151、中熟練度情報152および低熟練度情報153、ならびに有効パターンEPおよび閾値TH1~TH3を、他の制御コンピュータ100から受信し情報メモリ102の領域E1とE2に格納する。または、これら情報をメモリカード123から読取り、情報メモリ102の領域E1およびE2に格納する。 Note that the control computer 100 that implements the “learning mode” may be the same as or different from the control computer 100 that implements the “operation mode”. If they are different, the control computer 100 in the “operation mode” sends the high skill level information 151, the medium skill level information 152 and the low skill level information 153, and the effective pattern EP and the threshold values TH1 to TH3 to other control computers. 100 and received in the areas E1 and E2 of the information memory 102. Alternatively, these pieces of information are read from the memory card 123 and stored in the areas E1 and E2 of the information memory 102.
 (「学習モード」の処理)
 図7を参照して「学習モード」において、コントローラ61には標準の制御量を示す指令信号106が与えられている。取得部103は、熟練した作業者10の作業時に生体情報107をセンサ50から取得し(ステップS3)、学習部101は、取得部103からの生体情報107が有する特徴量CRiを取得する(ステップS4)。学習部101、取得された特徴量(取得特徴量)CRiを当該作業者10の熟練度を示すラベルを付加して情報メモリ102に格納する(ステップS5)。
("Learning mode" processing)
Referring to FIG. 7, in the “learning mode”, the controller 61 is given a command signal 106 indicating a standard control amount. The acquisition unit 103 acquires the biological information 107 from the sensor 50 when the skilled worker 10 is working (step S3), and the learning unit 101 acquires the feature amount CRi included in the biological information 107 from the acquisition unit 103 (step S3). S4). The learning unit 101 stores the acquired feature amount (acquired feature amount) CRi in the information memory 102 with a label indicating the skill level of the worker 10 (step S5).
 (特徴量の取得(ステップS4))
 生体情報107から特徴量を取得する処理を説明する。学習部101は、取得部103からの生体情報107を処理して、図4または図5に示されたように、身体の各部位の動きの経時的な変化を示す特徴量を抽出する。身体の各部位としては、頭、胴体、肩、腕、腰、足、手、指などが含まれる。学習部101は、各部位の特徴量(動きの経時的な変化)を取得する。なお、特徴量は、身体の異なる部分の相対的な位置関係(たとえば、頭と腕の距離により示される位置関係)の経時的な変化であってもよい。
(Acquisition of feature amount (step S4))
Processing for acquiring a feature amount from the biological information 107 will be described. The learning unit 101 processes the biological information 107 from the acquisition unit 103, and extracts feature amounts indicating changes over time in the movement of each part of the body, as shown in FIG. 4 or FIG. Each part of the body includes the head, torso, shoulders, arms, waist, legs, hands, fingers, and the like. The learning unit 101 acquires feature quantities (changes in movement over time) of each part. Note that the feature amount may be a change over time in the relative positional relationship between different parts of the body (for example, the positional relationship indicated by the distance between the head and the arm).
 上記のステップS3~S5の処理が異なる熟練度の作業者10を対象に繰返されることにより、領域E1には、高熟練度情報151、中熟練度情報152および低熟練度情報153が登録される。なお、ここでは、熟練度の種類を示すラベルLB1、LB2およびLB3は、キーボード121から管理者が入力する。 By repeating the processes in steps S3 to S5 for the workers 10 having different skill levels, the high skill level information 151, the medium skill level information 152, and the low skill level information 153 are registered in the area E1. . Here, the administrator inputs the labels LB 1, LB 2, and LB 3 indicating the type of skill level from the keyboard 121.
 (分析処理(ステップS6))
 学習部101は、領域E1に格納された情報の分析処理を実施する(ステップS6)。分析処理は、有効パターンEPを決定するための処理(ステップS7、S8およびS9)を含む。
(Analysis process (step S6))
The learning unit 101 performs an analysis process on the information stored in the area E1 (step S6). The analysis process includes a process (steps S7, S8 and S9) for determining the effective pattern EP.
 まず、学習部101は、図8に示されるように、作業領域E3において、領域E1の高熟練度情報151の取得特徴量CRiの組合せのパターンを複数生成して(ステップS7)、生成された各パターンについて熟練度を識別するための識別率を算出する(ステップS8)。識別率の算出を簡単にするために、パターンは、取得特徴量CRiの代表値を用いる。この代表値には、たとえば、動きの変化量(たとえば頭の移動量)の平均値、中央値、積分値、分散値、最頻値などが含まれ得る。なお、代表値の種類はこれらに限定されない。 First, as shown in FIG. 8, the learning unit 101 generates a plurality of combinations of acquired feature amounts CRi of the high skill level information 151 of the area E1 in the work area E3 (Step S7). An identification rate for identifying the skill level for each pattern is calculated (step S8). In order to simplify the calculation of the identification rate, the pattern uses a representative value of the acquired feature amount CRi. This representative value may include, for example, an average value, median value, integral value, variance value, mode value, and the like of the amount of change in movement (for example, the amount of head movement). Note that the types of representative values are not limited to these.
 学習部101は、上記の識別率を、周知のパターン分類法に従う演算により算出する(ステップS8)。実施の形態1では、たとえばSVM(support vector machine)の識別関数に従い各パターンの識別率を算出する(図8の領域E3参照)。なお、識別率の算出は、SVMに従う方法に限定されず、NN(neural network)に従う算出方法であってもよい。 The learning unit 101 calculates the above-described identification rate by calculation according to a known pattern classification method (step S8). In the first embodiment, for example, the discrimination rate of each pattern is calculated in accordance with the discrimination function of SVM (support vector machine) (see area E3 in FIG. 8). The calculation of the identification rate is not limited to a method according to SVM, and may be a calculation method according to NN (neural network).
 学習部101は、各パターンについて算出された識別率(図8の領域E3を参照)のうち、たとえば最大値である識別率に対応のパターンを特定し、特定されたパターンを有効パターンEPとして決定する(ステップS9)。図8を参照すると、識別率が最大値(=0.9)の組合せは(CR1,CR2)と特定されるので、ここでは、有効パターンEPの識別特徴量CRiの組合せは(CR1,CR2)と決定される。 The learning unit 101 identifies a pattern corresponding to, for example, the maximum identification rate among the identification rates calculated for each pattern (see the region E3 in FIG. 8), and determines the identified pattern as an effective pattern EP. (Step S9). Referring to FIG. 8, since the combination with the maximum identification rate (= 0.9) is specified as (CR1, CR2), here, the combination of the identification features CRi of the effective pattern EP is (CR1, CR2). Is determined.
 学習部101は、決定された有効パターンEPが示す特徴量CR1と特徴量CR2の組合せに基づき、閾値TH1、TH2およびTH3を取得する(ステップS10)。 Learning unit 101 acquires threshold values TH1, TH2, and TH3 based on the combination of feature amount CR1 and feature amount CR2 indicated by the determined effective pattern EP (step S10).
 具体的には、学習部101は、作業領域E4において、有効パターンEPの識別特徴量CRiの組合せ(CR1,CR2)による2次元平面を規定する。そして、規定された平面上に、領域E1の高熟練度情報151の各生体情報BM1に対応した取得特徴量CR1とCR2の組合せ値(CR1,CR2)をプロット(図8の領域E4のマーク‘X’参照)する。また、この平面上に領域E1の中熟練度情報152の各生体情報BM1に対応した特徴量CR1とCR2の組合せ値(CR1,CR2)をプロット(図8の領域E4のマーク‘Y’参照)する。また、この平面上に領域E1の低熟練度情報153の各生体情報BM1に対応した特徴量CR1とCR2の組合せ値(CR1,CR2)をプロット(図8の領域E4のマーク‘Z’参照)する。 Specifically, the learning unit 101 defines a two-dimensional plane based on the combination (CR1, CR2) of the identification feature amounts CRi of the effective pattern EP in the work area E4. Then, the combination values (CR1, CR2) of the acquired feature amounts CR1 and CR2 corresponding to the biological information BM1 of the high skill level information 151 of the area E1 are plotted on the specified plane (marks in the area E4 in FIG. 8). X ′). Further, on this plane, the combination values (CR1, CR2) of the feature amounts CR1 and CR2 corresponding to each biological information BM1 of the medium skill level information 152 in the area E1 are plotted (see the mark “Y” in the area E4 in FIG. 8). To do. Further, on this plane, the combination values (CR1, CR2) of the feature amounts CR1 and CR2 corresponding to each biological information BM1 of the low skill level information 153 of the region E1 are plotted (see the mark “Z” in the region E4 in FIG. 8). To do.
 学習部101は、領域E4の2次元平面上において、各熟練度のプロット値の分布状況に基づき、高熟練度、中熟練度および低熟練度の組合せ値(CR1,CR2)がプロットされた領域を区分する境界線B1、B2およびB3を特定する。学習部101は、境界線B1、B2およびB3が示す値に基づき閾値TH1、TH2およびTH3を決定する。たとえば、学習部101は、境界線B1付近の組合せ値(CR1,CR2)を、高熟練度と判定するための閾値TH1と決定する。同様に、境界線B2付近の組合せ値(CR1,CR2)を、中熟練度と判定するための閾値TH2と決定する。同様に、境界線B3付近の組合せ値(CR1,CR2)を、低熟練度と判定するための閾値TH2と決定する。 The learning unit 101 is a region where the combination values (CR1, CR2) of the high skill level, the medium skill level, and the low skill level are plotted on the two-dimensional plane of the region E4 based on the distribution state of the plot values of each skill level. Boundary lines B1, B2 and B3 are identified. The learning unit 101 determines threshold values TH1, TH2, and TH3 based on the values indicated by the boundary lines B1, B2, and B3. For example, the learning unit 101 determines the combination value (CR1, CR2) near the boundary line B1 as the threshold value TH1 for determining the high skill level. Similarly, the combination value (CR1, CR2) near the boundary line B2 is determined as the threshold value TH2 for determining the intermediate skill level. Similarly, the combination value (CR1, CR2) near the boundary line B3 is determined as the threshold value TH2 for determining the low skill level.
 学習部101は、決定された有効パターンEPと取得された閾値TH1、TH2およびTH3を、情報メモリ102の領域E2に格納する(ステップS11)。これにより、「学習モード」の処理は終了する。 The learning unit 101 stores the determined effective pattern EP and the acquired threshold values TH1, TH2, and TH3 in the area E2 of the information memory 102 (step S11). Thus, the “learning mode” process ends.
 なお、図7では、ステップS3において各熟練度について十分な件数の生体情報107が取得されるとしているので、図7の処理を繰返す必要はないが、十分な件数の生体情報107が取得されていない場合には、図7の処理を繰返すとしてもよい。 In FIG. 7, since a sufficient number of pieces of biological information 107 are acquired for each skill level in step S3, it is not necessary to repeat the process of FIG. 7, but a sufficient number of pieces of biological information 107 have been acquired. If not, the process of FIG. 7 may be repeated.
 処理を繰返すか否かは、上記の2次元平面上の分布状況に基づき判定する。具体的には、境界線B1、B2およびB3を特定可能な数の組合せ値(CR1,CR2)がプロットされたか否かを判定し、判定の結果に基づき処理を繰返すか否かを決定する。処理を繰返す場合には、学習部101は、図7のステップS3に戻って以降の処理(各熟練度に応じた生体情報107の取得(ステップS3)、特徴量CRiの取得(ステップS4)、ラベル付加(ステップS5)および分析処理(ステップS6))を前述と同様に実施する。 Whether or not to repeat the process is determined based on the distribution situation on the two-dimensional plane. Specifically, it is determined whether or not a number of combination values (CR1, CR2) that can specify the boundary lines B1, B2, and B3 are plotted, and it is determined whether to repeat the processing based on the determination result. In the case of repeating the processing, the learning unit 101 returns to step S3 in FIG. 7 and performs subsequent processing (acquisition of biological information 107 according to each skill level (step S3), acquisition of feature amount CRi (step S4), Label addition (step S5) and analysis processing (step S6)) are performed in the same manner as described above.
 なお、図8では2次元平面を規定したが、平面の次元は2次元に限定されない。すなわち、この次元は、有効パターンEPに含まれる識別特徴量CRiの個数により可変である。 Although a two-dimensional plane is defined in FIG. 8, the plane dimension is not limited to two dimensions. That is, this dimension is variable depending on the number of identification feature amounts CRi included in the effective pattern EP.
 (「運用モード」の処理)
 図9を参照して「運用モード」の処理を説明する。なお、「運用モード」の開始時には、情報メモリ102の領域E2には、有効パターンEPならびに閾値TH1、TH2およびTH3が格納されている。また、「運用モード」の開始時には、コントローラ61には標準(中熟練度に対応)の制御量を示す指令信号106が与えられている。
("Operation mode" processing)
The “operation mode” process will be described with reference to FIG. At the start of the “operation mode”, the effective pattern EP and the threshold values TH1, TH2, and TH3 are stored in the area E2 of the information memory 102. At the start of the “operation mode”, the controller 61 is given a command signal 106 indicating a standard control amount (corresponding to a medium skill level).
 まず、取得部103は、生産ラインの作業者10の生体情報107をセンサ50から取得する(ステップS23)。 First, the acquisition unit 103 acquires the biological information 107 of the worker 10 on the production line from the sensor 50 (step S23).
 判定部104は、取得された作業者10の生体情報107が有する特徴量CRiのうち、有効パターンEPが示す組の特徴量(識別特徴量)を取得し(ステップS25)、取得された特徴量と情報メモリ102に格納されている閾値TH1、TH2およびTH3と比較し、比較の結果に基づき、当該生体情報107に対応した熟練度を判定し、判定結果を出力する(ステップS27)。これにより、作業者10の熟練度が判定される。 The determination unit 104 acquires the feature amount (identification feature amount) of the set indicated by the effective pattern EP from the feature amount CRi included in the acquired biological information 107 of the worker 10 (step S25), and the acquired feature amount And the thresholds TH1, TH2, and TH3 stored in the information memory 102, the skill level corresponding to the biological information 107 is determined based on the comparison result, and the determination result is output (step S27). Thereby, the skill level of the operator 10 is determined.
 このように、熟練度の判定は、取得された生体情報107が有する識別特徴量CRiの値と閾値TH1、TH2およびTH3との比較は、当該識別特徴量CRiの値と領域E1の高熟練度、中熟練度および低熟練度の各生体情報107が有する識別特徴量CRiの値との比較に相当する。したがって、熟練度の判定方法は閾値TH1、TH2およびTH3との比較方法に限定されない。たとえば、取得された生体情報107が有する識別特徴量CRiの値を、領域E4の2次元平面上にプロットして、プロットされた位置と境界線B1、B2およびB3との位置関係に基づき、熟練度を判定してもよい。 As described above, the skill level is determined by comparing the value of the identification feature amount CRi included in the acquired biological information 107 with the threshold values TH1, TH2, and TH3, and comparing the value of the identification feature amount CRi with the high skill level of the region E1. This corresponds to a comparison with the value of the identification feature amount CRi included in each of the biometric information 107 of the medium skill level and the low skill level. Therefore, the skill level determination method is not limited to the comparison method with the threshold values TH1, TH2, and TH3. For example, the value of the identification feature amount CRi included in the acquired biological information 107 is plotted on the two-dimensional plane of the region E4, and based on the positional relationship between the plotted position and the boundary lines B1, B2, and B3, The degree may be determined.
 制御量決定部105は、判定部104の判定が示す熟練度に基づき駆動部62の制御量を決定する(ステップS29~S35)。たとえば、制御量としてアーム63の速度V(V=α×V1、ただしV1は基本速度およびαは係数)を決定する場合を説明する。 The control amount determination unit 105 determines the control amount of the drive unit 62 based on the skill level indicated by the determination of the determination unit 104 (steps S29 to S35). For example, a case where the speed V of the arm 63 (V = α × V1, where V1 is a basic speed and α is a coefficient) is determined as the control amount will be described.
 制御量決定部105は、判定結果が低熟練度を示すと判定すると(ステップS29で‘低’)、係数αを(α<1)と設定し(ステップS31)、判定結果が中熟練度を示すと判定すると(ステップS29で‘中’)、係数αを(α=1)と設定し(ステップS33)、判定結果が高熟練度を示すと判定すると(ステップS29で‘高’)、係数αを(α>1)と設定し(ステップS35)する。 When it is determined that the determination result indicates the low skill level (“low” in step S29), the control amount determination unit 105 sets the coefficient α as (α <1) (step S31), and the determination result indicates the medium skill level. If it is determined that it is shown (“medium” in step S29), the coefficient α is set to (α = 1) (step S33), and if it is determined that the determination result indicates a high skill level (“high” in step S29), the coefficient α is set as (α> 1) (step S35).
 そして、制御量決定部105は、判定された熟練度に従って設定された係数αを用いて、速度V(V=α×V1)を算出する(ステップS37)。 Then, the control amount determination unit 105 calculates the speed V (V = α × V1) using the coefficient α set according to the determined skill level (step S37).
 制御量決定部105は、算出された制御量である速度Vを示す指令信号106を生成して、通信インタフェイス124を介して出力する(ステップS39)。なお、制御量の取得は、このような算出方法に限定されない。たとえば、熟練度と制御量の組が複数登録されたテーブルを記憶しておき、ステップS27で判定された熟練度に基づきテーブルを検索し、テーブルから対応する制御量を読出す方法であってもよい。 The control amount determination unit 105 generates a command signal 106 indicating the speed V that is the calculated control amount, and outputs it via the communication interface 124 (step S39). The acquisition of the control amount is not limited to such a calculation method. For example, a table in which a plurality of sets of skill levels and control amounts are registered is stored, the table is searched based on the skill levels determined in step S27, and the corresponding control amounts are read from the table. Good.
 CPU110は、生産ラインからの信号に基づき、繰返し作業を終了するか否かを判定し、繰返し作業を終了しないと判定するときは、ステップS23に戻り以降の処理を繰返すが、繰返し作業を終了するとき(例えば、生産ライン自体の稼働を終了するとき)などは図9の処理を終了する。 Based on the signal from the production line, the CPU 110 determines whether or not to end the repetitive work. When determining that the repetitive work is not to be ended, the CPU 110 returns to step S23 and repeats the subsequent processes, but ends the repetitive work. At the time (for example, when the operation of the production line itself is finished), the processing of FIG. 9 is finished.
 なお、図9の処理は、予め定められた時間毎に実施されてもよい。たとえば、CPU110は生産ラインから上記のタイミング信号を予め定められた回数入力する毎に、図9の処理を実施するとしてもよい。 Note that the process of FIG. 9 may be performed every predetermined time. For example, the CPU 110 may perform the process of FIG. 9 every time the above timing signal is input from the production line a predetermined number of times.
 (熟練度の分類と閾値の設定例)
 図10は、実施の形態1にかかる学習モードにおける閾値の決定方法の他の例を模式的に示す図である。図8では、有効パターンEPである2つの特徴量の組合せ値(CR1,CR2)の2次元平面における分布状況に従い、閾値TH1、TH2およびTH3を取得したが、取得方法は、この方法に限定されない。
(Example of skill level classification and threshold setting)
FIG. 10 is a diagram schematically illustrating another example of the threshold value determination method in the learning mode according to the first embodiment. In FIG. 8, the threshold values TH1, TH2, and TH3 are acquired according to the distribution state of the combination values (CR1, CR2) of the two feature amounts that are the effective patterns EP in the two-dimensional plane. However, the acquisition method is not limited to this method. .
 図10を参照して、有効パターンEPが1つの特徴量CRiからなる場合において、高熟練度と中熟練度の群と、低熟練度の群を判別するための閾値THを決定する方法を説明する。閾値THを決定するための特徴量CRiは頭の移動量を示す。 Referring to FIG. 10, a method for determining a threshold value TH for distinguishing between a group of high skill levels, a medium skill level, and a group of low skill levels when the effective pattern EP is composed of one feature amount CRi will be described. To do. The characteristic amount CRi for determining the threshold value TH indicates the amount of head movement.
 ステップS10において、学習部101は、領域E1の高熟練度情報151、中熟練度情報152および低熟練度情報153の各生体情報BM1が有する特徴量CRiの値のそれぞれについて、当該値が取得された回数をカウントする処理を実施する。図10には、このカウント処理の結果がグラフで模式的に示されている。図10では、横軸に特徴量CRiの値(頭の平均移動量(単位:m/frame))がとられて、縦軸に各値が取得された頻度(カウント値)がとられている。学習部101は、カウント処理の結果から、たとえば高/中熟練度と低熟練度と区分する境界に相当する値は0.017(m/frame)と判定することができる(図10参照)。したがって、学習部101は、閾値THとして0.017(m/frame)を決定することができる。 In step S <b> 10, the learning unit 101 acquires the value of each feature amount CRi included in each of the biological information BM <b> 1 of the high skill level information 151, the medium skill level information 152, and the low skill level information 153 of the region E <b> 1. Perform the process of counting the number of times. FIG. 10 schematically shows the result of the counting process in a graph. In FIG. 10, the horizontal axis represents the value of the characteristic amount CRi (the average head movement amount (unit: m / frame)), and the vertical axis represents the frequency (count value) at which each value is acquired. . The learning unit 101 can determine, for example, that the value corresponding to the boundary dividing the high / medium skill level and the low skill level is 0.017 (m / frame) from the count processing result (see FIG. 10). Therefore, the learning unit 101 can determine 0.017 (m / frame) as the threshold value TH.
 [実施の形態2]
 実施の形態2では、作業者10の熟練度を管理する方法を説明する。制御コンピュータ100は、各作業者10について、判定部104により判定された熟練度をハードディスク114などの記憶部に記録(記憶)し、記録した内容を出力(表示)する。図11は、実施の形態2にかかる熟練度の記録内容の表示例を示す図である。
[Embodiment 2]
In the second embodiment, a method for managing the skill level of the worker 10 will be described. The control computer 100 records (stores) the skill level determined by the determination unit 104 for each worker 10 in a storage unit such as the hard disk 114, and outputs (displays) the recorded content. FIG. 11 is a diagram illustrating a display example of the recording content of the skill level according to the second embodiment.
 CPU110は、作業者10毎に、判定された熟練度を、作業日数(1日目、2日目、3日目、・・・)と関連付けて記憶部に格納する。ここでは、関連付ける期間は、1日毎に限定されず、たとえば数時間毎、または1週間毎などであってもよい。 The CPU 110 stores the determined skill level for each worker 10 in the storage unit in association with the number of work days (first day, second day, third day,...). Here, the association period is not limited to every day, and may be every few hours or every week, for example.
 CPU110は、格納された関連付けの情報から、各作業者10の熟練度の統計処理(たとえば、平均値、分散値、各熟練度の出現回数(頻度)などの算出)を実施し、得られた統計値に基づく表示データを作成し、表示データに従いディスプレイ122に駆動する。これにより、たとえば図11のようなグラフがディスプレイ122に表示される。 CPU 110 performs statistical processing of the skill level of each worker 10 (for example, calculation of an average value, a variance value, the number of appearances (frequency) of each skill level, and the like) from the stored association information, and is obtained Display data based on the statistical value is created and driven to the display 122 according to the display data. Thereby, for example, a graph as shown in FIG. 11 is displayed on the display 122.
 図11の画面により、管理者に対して、各作業者10の熟練度と、熟練度の変化とを示す情報を提供することができる。管理者は、統計情報を工程管理または生産管理に利用することができる。たとえば、管理者は、熟練度が高い人と低い人が同じ時間帯で作業するように作業者10の作業時間帯を調整する。このように、実施の形態2によれば、作業者10の熟練度の情報を、作業の平準化および生産性向上の支援ツールとして提供することができる。なお、図11の画面は、管理コンピュータ300に表示されてもよい。 11 can provide the manager with information indicating the skill level of each worker 10 and the change in skill level. The administrator can use the statistical information for process management or production management. For example, the manager adjusts the work time zone of the worker 10 so that a person with high skill and a person with low skill work in the same time zone. As described above, according to the second embodiment, information on the skill level of the worker 10 can be provided as a support tool for leveling work and improving productivity. Note that the screen of FIG. 11 may be displayed on the management computer 300.
 [実施の形態3]
 実施の形態3では、作業者10に対して、端末11を介して、特徴量または熟練度に関する情報を提供する。図12は、作業中の手の移動速度の変化の表示例を示す図である。図13は、作業中の手の移動にかかる加速度の変化の表示例を示す図である。実施の形態3では、有効パターンEPが示す識別特徴量の組合せ値(CR1,CR2)は、(手の移動速度,手の移動加速度)を示す。
[Embodiment 3]
In the third embodiment, information relating to the feature amount or the skill level is provided to the worker 10 via the terminal 11. FIG. 12 is a diagram illustrating a display example of changes in the moving speed of the hand during work. FIG. 13 is a diagram illustrating a display example of a change in acceleration according to movement of a hand during work. In Embodiment 3, the combination value (CR1, CR2) of the identification feature amount indicated by the effective pattern EP indicates (hand movement speed, hand movement acceleration).
 CPU110は、ワークWの搬送作業時に作業者10の識別特徴量CR1とCR2を取得する。そして、CPU110は、取得された識別特徴量CR1と高熟練者の特徴量CR1を関連付けて表示するための表示データと、取得された識別特徴量CR1と高熟練者の特徴量CR1を関連付けて表示するための表示データとを生成し、生成された表示データを端末11に送信する。端末11は、受信した表示データに従う画像(図12と図13を参照)を表示する。 The CPU 110 acquires the identification feature amounts CR1 and CR2 of the worker 10 when the work W is transported. Then, the CPU 110 displays display data for displaying the acquired identification feature value CR1 and the highly skilled person's feature value CR1 in association with each other, and displays the acquired identification feature value CR1 and the highly skilled person's feature value CR1 in association with each other. Display data to be generated, and the generated display data is transmitted to the terminal 11. The terminal 11 displays an image (see FIGS. 12 and 13) according to the received display data.
 図12または図13の画面により、作業者10に対して、現在の熟練度と、熟練度の変化示す情報と、自己の熟練度の高熟練度とのギャップの大きさ等を視覚的に提供することができる。また、作業者10は、提供された情報から、自己の手の動きを高熟練度の動きに修正するための目安を得ることが可能となる。このように、実施の形態3によれば、作業者10に対して、作業時の身体の動きを高熟練度作業者の動きに整合させるための支援ツールを提供することができる。 The screen of FIG. 12 or FIG. 13 visually provides the worker 10 with the current skill level, information indicating changes in the skill level, the size of the gap between the high skill level of his / her skill level, and the like. can do. In addition, the worker 10 can obtain a guideline for correcting his / her hand movement to a highly skilled movement from the provided information. As described above, according to the third embodiment, it is possible to provide the worker 10 with a support tool for matching the movement of the body during work with the movement of the highly skilled worker.
 [実施の形態4]
 実施の形態4では、ワークWの動きの経時的な変化から、熟練度を判定する。上記の各実施の形態では、作業者10の生体情報107を用いて熟練度を判定したが、実施の形態4では、作業者10の身体の動きの変化に応じてワークWの動きも変化する点に着目して、ワークWの動きの変化から、熟練度が判定される。
[Embodiment 4]
In the fourth embodiment, the skill level is determined from the change in the movement of the workpiece W over time. In each of the above embodiments, the skill level is determined using the biological information 107 of the worker 10, but in the fourth embodiment, the movement of the workpiece W also changes according to the change in the movement of the worker 10's body. Focusing on the points, the skill level is determined from the change in the movement of the workpiece W.
 具体的には、生産ラインは、センサ50と同様な機能を有したワークWの動きを測定するセンサ50Aを備える。センサ50Aは、ワークWの動きの経時的な変化を示すワーク情報107Aを検出(測定)する。ワーク情報107Aの特徴量として、ワークWの各部位の動きの経時的な変化(位置、移動速度、移動加速度などの経時的な変化)を用いることができる。なお、センサ50Aはセンサ50とは独立して設けたが、センサ50Aの機能をセンサ50が兼ね備えるとしてもよい。 Specifically, the production line includes a sensor 50A that measures the movement of the workpiece W having the same function as the sensor 50. The sensor 50A detects (measures) the workpiece information 107A indicating the change in the movement of the workpiece W over time. As the feature amount of the work information 107A, a change with time of the movement of each part of the work W (change with time such as position, moving speed, moving acceleration, etc.) can be used. The sensor 50A is provided independently of the sensor 50, but the sensor 50 may have the function of the sensor 50A.
 図14は、実施の形態4にかかる制御コンピュータ100の機能の構成を模式的に示す図である。図15は、実施の形態4にかかる「学習モード」の処理フローチャートである。図16は、実施の形態4にかかる「運用モード」の処理フローチャートである。図15のフローチャートは、図7のステップS3をステップS3aに変更しているが、他のステップは図7と同様である。また、図16のフローチャートは、図9のステップS23をステップS23aに変更しているが、他のステップは図9と同様である。したがって、図15と図16では、変更されたステップS3aとステップS23aについて説明し、他の処理についての説明は繰返さない。 FIG. 14 is a diagram schematically illustrating a functional configuration of the control computer 100 according to the fourth embodiment. FIG. 15 is a process flowchart of the “learning mode” according to the fourth embodiment. FIG. 16 is a process flowchart of the “operation mode” according to the fourth exemplary embodiment. In the flowchart in FIG. 15, step S3 in FIG. 7 is changed to step S3a, but the other steps are the same as in FIG. In the flowchart of FIG. 16, step S23 of FIG. 9 is changed to step S23a, but other steps are the same as those of FIG. Therefore, in FIG. 15 and FIG. 16, the changed steps S3a and S23a will be described, and description of other processes will not be repeated.
 なお、図15と図16のフローチャートの処理はプログラムとして制御コンピュータ100の記憶部(メモリ112、ハードディスク114、メモリカード123など)に格納されている。CPU110は、記憶部からプログラムを読出し、実行する。 Note that the processing of the flowcharts of FIGS. 15 and 16 is stored as a program in a storage unit (memory 112, hard disk 114, memory card 123, etc.) of the control computer 100. CPU110 reads a program from a memory | storage part and performs it.
 図14を参照して、制御コンピュータ100は、センサ50Aからワーク情報107Aを取得する取得部103Aと、「学習モード」において取得部103Aにより取得されたワーク情報107Aを用いて有効パターンEP1および閾値TH11、TH22およびTH33を取得する学習部101Aおよび情報メモリ102Aを備える。さらに、制御コンピュータ100は、「運用モード」において取得部103Aにより取得されるワーク情報107Aがいずれの熟練度に該当するかを判定する判定部104Aと、判定された熟練度に基づき駆動部62の制御量を決定し、決定された制御量を示す指令信号106Aをコントローラ61に出力する制御量決定部105Aと、を備える。 Referring to FIG. 14, the control computer 100 uses the acquisition unit 103A that acquires the workpiece information 107A from the sensor 50A and the workpiece information 107A that is acquired by the acquisition unit 103A in the “learning mode” to use the effective pattern EP1 and the threshold value TH11. , TH22 and TH33 are provided with a learning unit 101A and an information memory 102A. Further, the control computer 100 determines the skill level of the work information 107A acquired by the acquisition unit 103A in the “operation mode”, the determination unit 104A, and the drive unit 62 based on the determined skill level. A control amount determination unit 105A that determines a control amount and outputs a command signal 106A indicating the determined control amount to the controller 61.
 図14を参照して、情報メモリ102は領域E11、E22、E33およびE44を含む。領域E11は、高熟練度の情報1511、中熟練度の情報1521および低熟練度の情報1531を格納するための記憶領域である。領域E22は、「学習モード」において決定された識別特徴量の1つ以上の組合せを示すパターンEP1と熟練度を判別するための閾値TH11、TH22およびTH33とを格納するための領域である。領域E33および領域E44は、「運用モード」のための作業領域に相当する。 Referring to FIG. 14, information memory 102 includes areas E11, E22, E33, and E44. The area E11 is a storage area for storing high skill level information 1511, medium skill level information 1521, and low skill level information 1531. The region E22 is a region for storing a pattern EP1 indicating one or more combinations of identification feature amounts determined in the “learning mode” and thresholds TH11, TH22, and TH33 for determining the skill level. The area E33 and the area E44 correspond to a work area for the “operation mode”.
 高熟練度情報1511は、「学習モード」において高熟練度である作業者10の作業時に取得される複数のワーク情報107Aであるワーク情報BM11を含む。高熟練度情報1511は、さらに、各ワーク情報BM11に関連付けて‘高熟練度’を示すラベルLB1、当該ワーク情報BM11から取得される複数の取得特徴量CR1i(i=1,2,3・・・,n)を含む。 The high skill level information 1511 includes work information BM11 which is a plurality of work information 107A acquired at the time of the work of the worker 10 having a high skill level in the “learning mode”. The high skill level information 1511 further includes a label LB1 indicating “high skill level” in association with each piece of work information BM11, and a plurality of acquired feature amounts CR1i (i = 1, 2, 3,...) Acquired from the work information BM11. ., N) are included.
 同様に、中熟練度情報1521は、複数のワーク情報BM11、各ワーク情報BM11に関連付けてラベルLB2、当該ワーク情報BM11から取得される複数の取得特徴量CR1iを含む。 Similarly, the medium skill level information 1521 includes a plurality of pieces of work information BM11, a label LB2 associated with each piece of work information BM11, and a plurality of acquired feature amounts CR1i acquired from the work information BM11.
 同様に、低熟練度情報1531は、複数のワーク情報BM11、各ワーク情報BM11に関連付けてラベルLB3、当該ワーク情報BM11から取得される複数の取得特徴量CR1iを含む。 Similarly, the low skill level information 1531 includes a plurality of pieces of work information BM11, a label LB3 associated with each piece of work information BM11, and a plurality of acquired feature amounts CR1i acquired from the work information BM11.
 図12の領域E11のワーク情報BM11は学習モードが終了したときに削除してよい。これにより、情報メモリ102Aに消費容量を節約することができる。 The work information BM11 in the area E11 in FIG. 12 may be deleted when the learning mode ends. Thereby, it is possible to save the consumption capacity in the information memory 102A.
 学習部101Aは、制御コンピュータ100の動作モードが「学習モード」であるとき、実施の形態1の学習部101と同様に、取得部103からのワーク情報107Aを各熟練度に対応付けて領域E11に格納する。学習部101Aは、ワーク情報107Aを情報メモリ102Aに熟練度ごとに蓄積する「蓄積部」の一実施例である。 When the operation mode of the control computer 100 is the “learning mode”, the learning unit 101A associates the work information 107A from the acquisition unit 103 with each skill level in the area E11 as in the learning unit 101 of the first embodiment. To store. The learning unit 101A is an example of an “accumulation unit” that accumulates work information 107A in the information memory 102A for each skill level.
 また、学習部101Aは、「学習モード」であるとき、実施の形態1の学習部101と同様に、領域E1の高熟練度情報1511のワーク情報BM11が有する取得特徴量CRiのうちから1つ以上の識別特徴量CRiを決定し、決定された1つ以上の識別特徴量CRiからなる組を、熟練度を識別するための有効パターンEP1として領域E22に格納する。また、学習部101Aは、実施の形態1の学習部101と同様に、高熟練度情報1511、中熟練度情報1521および低熟練度情報1531の取得特徴量CRiのうち有効パターンEP1の特徴量CRiの組の値に基づき、各熟練度を決定するための閾値TH11、TH22およびTH33を取得し、領域E22に格納する。 Further, when the learning unit 101A is in the “learning mode”, one of the acquired feature values CRi included in the work information BM11 of the high skill level information 1511 of the area E1 is the same as the learning unit 101 of the first embodiment. The identification feature amount CRi described above is determined, and a set of one or more determined identification feature amounts CRi is stored in the region E22 as an effective pattern EP1 for identifying the skill level. Similar to the learning unit 101 of the first embodiment, the learning unit 101A also includes the feature amount CRi of the effective pattern EP1 among the acquired feature amounts CRi of the high skill level information 1511, the medium skill level information 1521, and the low skill level information 1531. Threshold values TH11, TH22, and TH33 for determining each skill level are acquired based on the set values and stored in the region E22.
 判定部104Aは、制御コンピュータ100の動作モードが「運用モード」であるとき、実施の形態1の判定部104と同様に、取得部103Aから取得するワーク情報107Aが有する特徴量CR1iを取得する。そして、取得された特徴量CR1iのうち有効パターンEP1に対応した1以上の識別特徴量CR1iを、閾値TH11、TH22およびTH33と比較する。そして、比較の結果に基づき、当該取得されるワーク情報107Aがいずれの熟練度に該当するかを判定する。 When the operation mode of the control computer 100 is “operation mode”, the determination unit 104A acquires the feature amount CR1i included in the work information 107A acquired from the acquisition unit 103A, as in the determination unit 104 of the first embodiment. Then, one or more identification feature amounts CR1i corresponding to the effective pattern EP1 among the acquired feature amounts CR1i are compared with threshold values TH11, TH22, and TH33. Then, based on the comparison result, it is determined to which skill level the acquired work information 107A corresponds.
 制御量決定部105Aは、実施の形態1の制御量決定部105と同様に、「運用モード」において、判定部104Aにより判定された熟練度に基づき制御量を決定し、決定した制御量を示す指令信号106を生成し、ロボット60のコントローラ61に送信する。 Similarly to the control amount determination unit 105 of the first embodiment, the control amount determination unit 105A determines the control amount based on the skill level determined by the determination unit 104A in the “operation mode” and indicates the determined control amount. A command signal 106 is generated and transmitted to the controller 61 of the robot 60.
 図15を参照して、「学習モード」においては、取得部103Aは、熟練した作業者10の作業時にワーク情報107Aをセンサ50Aから取得する(ステップS3a)。以降の処理では、学習部101Aは、取得されたワーク情報107Aを用いて実施の形態1の学習部101と同様の処理を実施する。これにより、有効パターンEP1と閾値TH11、TH22およびTH33が領域E22に格納されて、「学習モード」の処理は終了する。 Referring to FIG. 15, in the “learning mode”, the acquisition unit 103A acquires the work information 107A from the sensor 50A when the skilled worker 10 is working (step S3a). In the subsequent processing, the learning unit 101A performs the same processing as the learning unit 101 of the first embodiment using the acquired work information 107A. Accordingly, the effective pattern EP1 and the threshold values TH11, TH22, and TH33 are stored in the region E22, and the “learning mode” process ends.
 図14を参照して、「運用モード」においては、取得部103Aは、作業者10の作業時にワーク情報107Aをセンサ50Aから取得する(ステップS23a)。以降の処理では、判定部104Aは、取得されたワーク情報107Aを用いて実施の形態1と判定部104と同様の処理を実施する。これにより、作業者10の熟練度に応じた制御量を示す指令信号106がロボット60のコントローラ61に出力される。 Referring to FIG. 14, in “operation mode”, acquisition unit 103A acquires work information 107A from sensor 50A when worker 10 is working (step S23a). In the subsequent processing, the determination unit 104A performs the same processing as in the first embodiment and the determination unit 104 using the acquired work information 107A. Thereby, a command signal 106 indicating a control amount corresponding to the skill level of the worker 10 is output to the controller 61 of the robot 60.
 実施の形態4によれば、作業者10が生産ラインにおいてロボット60との協同作業で取扱うワークWの動きの経時的な変化を示すワーク情報107Aから、作業者10の熟練度の判定と、判定された熟練度に基づく制御量に従う駆動部62の制御が可能である。 According to the fourth embodiment, the skill level of the worker 10 is determined from the workpiece information 107A indicating the change over time of the movement of the workpiece W handled by the worker 10 in cooperation with the robot 60 in the production line. The drive unit 62 can be controlled in accordance with the control amount based on the skill level.
 なお、「運用モード」では、実施の形態1~3に説明した生体情報107からの熟練度の判定と、実施の形態4のワーク情報107Aからの熟練度の判定との両方を実施して、両判定の結果に基づき、作業者10の熟練度を総合的に判定するとしてもよい。たとえば、両判定結果が異なるときは、低い方の熟練度(または高い方の熟練度)を選択するとしてもよい。 In the “operation mode”, both the determination of the skill level from the biological information 107 described in the first to third embodiments and the determination of the skill level from the work information 107A of the fourth embodiment are performed. The skill level of the operator 10 may be comprehensively determined based on the results of both determinations. For example, when both determination results are different, the lower skill level (or the higher skill level) may be selected.
 [実施の形態5]
 実施の形態5では、上記の各実施の形態における上述の「学習モード」および「運用モード」の少なくとも一方を制御コンピュータ100のCPU110に実行させるためのプログラムが提供される。このようなプログラムは、制御コンピュータ100に付属するフレキシブルディスク、CD-ROM(Compact Disk-Read Only Memory)、ROM、RAMおよびメモリカード123などのコンピュータ読み取り可能な記録媒体にて記録させて、プログラム製品として提供することもできる。あるいは、制御コンピュータ100に内蔵するハードディスク114などの記録媒体にて記録させて、プログラムを提供することもできる。また、図示しないネットワークから通信インタフェイス124を介したダウンロードによって、プログラムを提供することもできる。
[Embodiment 5]
In the fifth embodiment, a program for causing the CPU 110 of the control computer 100 to execute at least one of the “learning mode” and the “operation mode” in each of the above embodiments is provided. Such a program is recorded on a computer-readable recording medium such as a flexible disk attached to the control computer 100, a CD-ROM (Compact Disk-Read Only Memory), a ROM, a RAM, and a memory card 123 to obtain a program product. Can also be provided. Alternatively, the program can be provided by being recorded on a recording medium such as the hard disk 114 built in the control computer 100. The program can also be provided by downloading from a network (not shown) via the communication interface 124.
 なお、プログラムは、制御コンピュータ100のOS(オペレーティングシステム)の一部として提供されるプログラムモジュールのうち、必要なモジュールを所定の配列で所定のタイミングで呼出して処理を実行させるものであってもよい。その場合、プログラム自体には上記モジュールが含まれずOSと協働して処理が実行される。このようなモジュールを含まないプログラムも、実施の形態5のプログラムに含まれ得る。 The program may be a program module that is provided as part of the OS (operating system) of the control computer 100 and that calls necessary modules in a predetermined arrangement at a predetermined timing to execute processing. . In that case, the program itself does not include the module, and the process is executed in cooperation with the OS. A program that does not include such a module can also be included in the program of the fifth embodiment.
 また、実施の形態5にかかるプログラムは他のプログラムの一部に組込まれて提供されるものであってもよい。その場合にも、プログラム自体には上記他のプログラムに含まれるモジュールが含まれず、他のプログラムと協働して処理が実行される。このような他のプログラムに組込まれたプログラムも、本実施の形態2にかかるプログラムに含まれ得る。 Also, the program according to the fifth embodiment may be provided by being incorporated in a part of another program. Even in this case, the program itself does not include the module included in the other program, and the process is executed in cooperation with the other program. Such a program incorporated in another program can also be included in the program according to the second embodiment.
 提供されるプログラム製品は、ハードディスクなどのプログラム格納部にインストールされて実行される。なお、プログラム製品は、プログラム自体と、プログラムが記録された記録媒体とを含む。 The provided program product is installed in a program storage unit such as a hard disk and executed. The program product includes the program itself and a recording medium on which the program is recorded.
 [実施の形態の構成]
 上記の実施の形態の制御コンピュータ100は、生産のための駆動部62を制御する制御装置に相当する。この制御装置は、作業者10から測定された生体情報107を取得する取得部103と、作業の熟練度ごとに当該熟練度に応じた生体情報107からなる高熟練度情報151、中熟練度情報152および低熟練度情報153を記憶するための記憶部(情報メモリ102)と、作業時に取得部103により取得される生体情報107が有する特徴量CRiと、記憶部の熟練度ごとの生体情報(高熟練度情報151、中熟練度情報152および低熟練度情報153)が有する特徴量CRiとを比較し、比較の結果に基づき、当該取得される生体情報107がいずれの熟練度に該当するかを判定する判定部104と、判定された熟練度に基づき駆動部62の制御量を決定する決定部(制御量決定部105)と、を備える。
[Configuration of the embodiment]
The control computer 100 of the above embodiment corresponds to a control device that controls the drive unit 62 for production. The control device includes an acquisition unit 103 that acquires biological information 107 measured from the worker 10, high skill level information 151 including medium information 107 corresponding to the skill level for each skill level, and medium skill level information. 152 and the low skill level information 153, the storage unit (information memory 102), the characteristic amount CRi of the biological information 107 acquired by the acquisition unit 103 during work, and the biological information for each skill level of the storage unit ( The feature amount CRi included in the high skill level information 151, the medium skill level information 152, and the low skill level information 153) is compared, and based on the comparison result, which skill level the acquired biological information 107 corresponds to And a determination unit (control amount determination unit 105) that determines a control amount of the drive unit 62 based on the determined skill level.
 したがって、生産のための作業時の作業者10から取得される生体情報107に従い、作業に対する熟練度を判定し、判定された熟練度に応じた制御量で駆動部62を制御することができる。 Therefore, according to the biological information 107 acquired from the worker 10 at the time of work for production, the skill level for the work can be determined, and the drive unit 62 can be controlled with a control amount corresponding to the determined skill level.
 上記の生体情報107は、作業時の身体の動きを示す情報を含む。したがって、作業者10の身体の動きから、熟練度を判定することができる。 The biological information 107 includes information indicating the movement of the body during work. Therefore, the skill level can be determined from the body movement of the worker 10.
 制御コンピュータ100は、熟練度ごとに当該熟練度に応じた生体情報107が有する特徴量CRiを取得し記憶部(情報メモリ102の領域E1)に蓄積する蓄積部を、さらに備える。この蓄積部は、学習部101に相当する。 The control computer 100 further includes a storage unit that acquires the characteristic amount CRi of the biological information 107 corresponding to the skill level and stores it in the storage unit (area E1 of the information memory 102) for each skill level. This accumulation unit corresponds to the learning unit 101.
 したがって、学習部101の学習により、熟練度ごとの特徴量CRiを有した生体情報107を得ることができる。 Therefore, the biometric information 107 having the feature amount CRi for each skill level can be obtained by learning by the learning unit 101.
 上記の蓄積される特徴量は、判定部104より判定された熟練度に応じた生体情報が有する特徴量を含む。したがって、記憶部の特徴量に、学習部101による学習モードと判定部104による運用モードとの両方のモードにおいて取得された特徴量を含めることができる。 The above-described accumulated feature amount includes the feature amount included in the biological information corresponding to the skill level determined by the determination unit 104. Therefore, the feature amount acquired in both the learning mode by the learning unit 101 and the operation mode by the determination unit 104 can be included in the feature amount of the storage unit.
 上記の制御装置は、さらに、作業者10が作業時に扱うワークWの動きを示すワーク情報107Aを取得するワーク情報取得部(取得部103A)と、熟練度ごとに当該熟練度に応じたワーク情報を記憶するためのワーク情報記憶部(領域E11)と、作業者10の作業時に取得されるワーク情報107Aが有する特徴量CR1iと、ワーク情報記憶部の熟練度ごとのワーク情報(高熟練度情報1511、中熟練度情報1521および低熟練度情報1531)が有する特徴量CR1iとを比較し、比較の結果に基づき、当該取得されるワーク情報107Aがいずれの熟練度に該当するかを判定するワーク情報判定部(判定部104A)と、を備え、決定部は、判定部104により判定された熟練度と、ワーク情報判定部により判定された熟練度に基づき、制御量を決定する。 The control device further includes a work information acquisition unit (acquisition unit 103A) that acquires work information 107A indicating the movement of the work W handled by the worker 10 during work, and work information corresponding to the skill level for each skill level. The work information storage unit (area E11) for storing information, the feature amount CR1i of the work information 107A acquired when the worker 10 is working, and the work information (high skill level information) for each skill level of the work information storage unit 1511, the medium skill level information 1521 and the low skill level information 1531) are compared with the characteristic amount CR1i, and based on the comparison result, the work level for which the acquired work information 107A corresponds to which skill level is determined. An information determination unit (determination unit 104A), and the determination unit determines the skill level determined by the determination unit 104 and the skill level determined by the work information determination unit. Based on time, to determine the control amount.
 したがって、熟練度を、作業者10の身体の動きの特徴量CRiと、ワークWの動きの特徴量CR1iとの両方を用いて判定することができる。 Therefore, the skill level can be determined by using both the feature amount CRi of the movement of the worker 10 and the feature amount CR1i of the movement of the workpiece W.
 上記の特徴量CRiおよびCR1iは、熟練度を識別可能な特徴量(有効パターンEP、EP1)を含む。したがって、熟練度を識別可能な特徴量を用いて作業者10の熟練度を判定することができる。 The above-described feature amounts CRi and CR1i include feature amounts (effective patterns EP, EP1) that can identify skill levels. Accordingly, it is possible to determine the skill level of the worker 10 using the feature amount that can identify the skill level.
 上記の判定部104および104Aは、予め定められた時間毎に熟練度を判定し、制御装置は、予め定められた時間毎に判定された熟練度を統計し、統計情報(図11参照)を出力する。これにより、生産における作業者を管理する場合の支援情報を提供することができる。 The determination units 104 and 104A determine the skill level at each predetermined time, and the control device statistics the skill level determined at the predetermined time and provides statistical information (see FIG. 11). Output. Thereby, the support information in the case of managing the worker in production can be provided.
 上記の実施の形態の制御コンピュータ100は、生産のための駆動部62を制御する制御装置に相当する。この制御装置は、作業者10が作業時に扱うワークWの動きを示すワーク情報107Aを取得するワーク情報取得部(取得部103A)と、熟練度ごとに当該熟練度に応じたワーク情報を記憶するためのワーク情報記憶部(領域E11)と、作業者10の作業時に取得されるワーク情報107Aが有する特徴量CR1iと、ワーク情報記憶部の熟練度ごとのワーク情報(高熟練度情報1511、中熟練度情報1521および低熟練度情報1531)が有する特徴量CR1iとを比較し、比較の結果に基づき、当該取得されるワーク情報107Aがいずれの熟練度に該当するかを判定するワーク情報判定部(判定部104A)と、判定された熟練度に基づき駆動部62の制御量を決定する決定部(制御量決定部105A)と、を備える。 The control computer 100 of the above embodiment corresponds to a control device that controls the drive unit 62 for production. This control device stores a work information acquisition unit (acquisition unit 103A) that acquires work information 107A indicating the movement of the work W handled by the worker 10 during work, and workpiece information corresponding to the skill level for each skill level. Work information storage unit (area E11), feature amount CR1i of the work information 107A acquired when the worker 10 works, and work information for each skill level of the work information storage unit (high skill level information 1511, medium The skill information 1521 and the low skill information 1531) are compared with the characteristic amount CR1i, and based on the comparison result, a work information determination unit that determines which skill level the acquired work information 107A corresponds to (Determination unit 104A) and a determination unit (control amount determination unit 105A) that determines the control amount of the drive unit 62 based on the determined skill level.
 各実施の形態のシステムは、生産のための駆動部62と、作業者の生体情報107を測定するセンサ50と、駆動部を制御する制御コンピュータ100と、を備える。制御コンピュータ100は、センサ50から出力される生体情報107を取得する取得部103と、作業の熟練度ごとに当該熟練度に応じた生体情報107を記憶するための記憶部(情報メモリ102の領域E1)と、作業者10の作業時に取得される生体情報107が有する特徴量CRiと、記憶部の熟練度ごとの生体情報107が有する特徴量CRiとを比較し、比較の結果に基づき、当該取得される生体情報107がいずれの熟練度に該当するかを判定する判定部104と、判定された熟練度に基づき駆動部62の制御量を決定する制御量決定部105と、を含む。 The system of each embodiment includes a drive unit 62 for production, a sensor 50 that measures the biological information 107 of the worker, and a control computer 100 that controls the drive unit. The control computer 100 includes an acquisition unit 103 that acquires the biological information 107 output from the sensor 50, and a storage unit (an area of the information memory 102) that stores the biological information 107 corresponding to the skill level for each work skill level. E1) is compared with the feature amount CRi included in the biological information 107 acquired when the worker 10 is working, and the feature amount CRi included in the biological information 107 for each skill level of the storage unit. Based on the comparison result, A determination unit 104 that determines to which skill level the acquired biological information 107 corresponds, and a control amount determination unit 105 that determines a control amount of the drive unit 62 based on the determined skill level.
 各実施の形態のシステムは、生産のための駆動部62と、作業者10が作業時に扱うワークWの動きを示すワーク情報107Aを測定するセンサ50Aと、駆動部を制御する制御コンピュータ100と、を備える。制御コンピュータ100は、センサ50Aから出力されるワーク情報107Aを取得する取得部103Aと、作業の熟練度ごとに当該熟練度に応じたワーク情報107Aを記憶するための記憶部(情報メモリ102Aの領域E11)と、作業者10の作業時に取得されるワーク情報107Aが有する特徴量CRiと、記憶部の熟練度ごとのワーク情報107Aが有する特徴量CRiとを比較し、比較の結果に基づき、当該取得されるワーク情報107Aがいずれの熟練度に該当するかを判定する判定部104Aと、判定された熟練度に基づき駆動部62の制御量を決定する制御量決定部105Aと、を含む。 The system of each embodiment includes a drive unit 62 for production, a sensor 50A that measures workpiece information 107A indicating the movement of the workpiece W handled by the worker 10 during work, a control computer 100 that controls the drive unit, Is provided. The control computer 100 includes an acquisition unit 103A that acquires the work information 107A output from the sensor 50A, and a storage unit (an area of the information memory 102A) that stores the work information 107A corresponding to the skill level for each work skill level. E11) is compared with the feature amount CRi possessed by the work information 107A acquired at the time of the work of the worker 10 and the feature amount CRi possessed by the work information 107A for each skill level of the storage unit, and based on the comparison result, A determination unit 104A that determines to which skill level the acquired workpiece information 107A corresponds, and a control amount determination unit 105A that determines a control amount of the drive unit 62 based on the determined skill level.
 各実施の形態の制御方法は、生産のための駆動部62を制御する方法であって、作業者10から測定された生体情報107を取得するステップ(ステップS3、ステップS23)と、作業者10の作業時に取得される生体情報107が有する特徴量CRiと、記憶部(情報メモリ102の領域E1)に格納された熟練度ごとの生体情報(高熟練度情報151、中熟練度情報152および低熟練度情報153)が有する特徴量CRiとを比較するステップ(ステップS27)と、比較の結果に基づき、当該取得される生体情報がいずれの熟練度に該当するかを判定するステップ(ステップS27)と、判定された熟練度に基づき駆動部の制御量を決定するステップ(ステップS37)と、を備える。 The control method of each embodiment is a method of controlling the drive unit 62 for production, and the steps of obtaining the biological information 107 measured from the worker 10 (Step S3, Step S23) and the worker 10 And the biometric information (high skill level information 151, medium skill level information 152, and low level) for each skill level stored in the storage unit (area E1 of the information memory 102). A step of comparing the feature amount CRi of the skill level information 153) (step S27) and a step of determining which skill level the acquired biological information corresponds to based on the comparison result (step S27) And a step of determining a control amount of the drive unit based on the determined skill level (step S37).
 各実施の形態の制御方法は、生産のための駆動部62を制御する方法であって、作業者10が作業時に扱うワークWの動きを示すワーク情報107Aを取得するステップと、作業者10の作業時に取得されるワーク情報107Aが有する特徴量CRiと、記憶部(情報メモリ102Aの領域E11)に格納された熟練度ごとのワーク情報(高熟練度情報1511、中熟練度情報1521および低熟練度情報1531)が有する特徴量CRiとを比較するステップと、比較の結果に基づき、当該取得されるワーク情報107Aがいずれの熟練度に該当するかを判定するステップと、判定された熟練度に基づき駆動部の制御量を決定するステップと、を備える。 The control method of each embodiment is a method of controlling the drive unit 62 for production, the step of acquiring the workpiece information 107A indicating the movement of the workpiece W handled by the worker 10 during the work, The feature amount CRi of the work information 107A acquired at the time of work, and the work information (high skill level information 1511, medium skill level information 1521 and low skill level) for each skill level stored in the storage unit (area E11 of the information memory 102A). A step of comparing the feature amount CRi included in the degree information 1531), a step of determining which skill level the acquired work information 107A corresponds to based on the comparison result, and the determined skill level And a step of determining a control amount of the drive unit based on.
 [実施の形態の効果]
 上記の実施の形態によれば、作業者10の熟練度を、作業中の生体情報107またはワーク情報107Aからリアルタイムに判定し、判定された熟練度に応じて制御量を変更する。熟練度が低いと判定された場合には、たとえばロボット60(より特定的にはアーム63)は通常よりも遅く動くように制御量を変更することで人的ミスを少なくし、熟練度が高いと判定された場合には、ロボット60(より特定的にはアーム63)の制御量を通常より速く動くように変更することで生産効率を上げることが可能となる。
[Effect of the embodiment]
According to the above embodiment, the skill level of the worker 10 is determined in real time from the biological information 107 or work information 107A being worked, and the control amount is changed according to the determined skill level. If it is determined that the skill level is low, for example, the robot 60 (more specifically, the arm 63) changes the control amount so that it moves slower than usual, thereby reducing human errors and increasing the skill level. If it is determined, the production efficiency can be increased by changing the control amount of the robot 60 (more specifically, the arm 63) so as to move faster than usual.
 今回開示された実施の形態は、すべての点で例示であって制限的なものではないと考えられるべきである。本発明の範囲は上記した説明ではなくて請求の範囲によって示され、請求の範囲と均等の意味および範囲内でのすべての変更が含まれることが意図される。 The embodiment disclosed this time should be considered as illustrative in all points and not restrictive. The scope of the present invention is defined by the terms of the claims, rather than the description above, and is intended to include any modifications within the scope and meaning equivalent to the terms of the claims.
1 システム、10 作業者、11 端末、50,50A センサ、60 ロボット、61 コントローラ、62 駆動部、63 アーム、100 制御コンピュータ、101,101A 学習部、102,102A 情報メモリ、103,103A 取得部、104,104A 判定部、105,105A 制御量決定部、106,106A 指令信号、107,BM1 生体情報、107A,BM11 ワーク情報、112 メモリ、113 タイマ、114 ハードディスク、118 入力インタフェイス、120 表示コントローラ、121 キーボード、122 ディスプレイ、123 メモリカード、124 通信インタフェイス、151,1511 高熟練度情報、152,1521 中熟練度情報、153,1531 低熟練度情報、200 ユニット、300 管理コンピュータ、B1,B2,B3 境界線、CR1i,CRi 識別特徴量、E1,E2,E3,E4,E11,E22,E33,E44 領域、EP,EP1 有効パターン、LB1,LB2,LB3 ラベル、TH,TH1,TH2,TH3,TH11,TH22,TH33 閾値、V 速度、W ワーク。 1 system, 10 workers, 11 terminals, 50, 50A sensor, 60 robot, 61 controller, 62 drive unit, 63 arm, 100 control computer, 101, 101A learning unit, 102, 102A information memory, 103, 103A acquisition unit, 104, 104A determination unit, 105, 105A control amount determination unit, 106, 106A command signal, 107, BM1 biological information, 107A, BM11 work information, 112 memory, 113 timer, 114 hard disk, 118 input interface, 120 display controller, 121 keyboard, 122 display, 123 memory card, 124 communication interface, 151, 1511 high skill information, 152, 1521 medium skill information, 153, 1531 Degree information, 200 units, 300 management computer, B1, B2, B3 boundary line, CR1i, CRi identification feature, E1, E2, E3, E4, E11, E22, E33, E44 area, EP, EP1 effective pattern, LB1, LB2, LB3 label, TH, TH1, TH2, TH3, TH11, TH22, TH33 threshold, V speed, W work.

Claims (10)

  1.  生産のための駆動部を制御する制御装置であって、
     作業者から測定された生体情報を取得する取得部と、
     作業の熟練度ごとに当該熟練度に応じた前記生体情報を記憶するための記憶部と、
     作業時に前記取得部により取得される前記生体情報が有する特徴量と、前記記憶部の熟練度ごとの前記生体情報が有する特徴量とを比較し、比較の結果に基づき、当該取得される生体情報がいずれの熟練度に該当するかを判定する判定部と、
     判定された前記熟練度に基づき前記駆動部の制御量を決定する決定部と、を備える、制御装置。
    A control device for controlling a drive unit for production,
    An acquisition unit for acquiring biological information measured from an operator;
    A storage unit for storing the biological information corresponding to the skill level for each skill level of work;
    The biometric information acquired by the biometric information acquired by the acquisition unit during work is compared with the characteristic amount of the biometric information for each skill level of the storage unit, and the biometric information acquired is based on the comparison result. A determination unit that determines to which skill level
    And a determination unit that determines a control amount of the drive unit based on the determined skill level.
  2.  前記生体情報は、作業時の身体の動きを示す情報を含む、請求項1に記載の制御装置。 The control apparatus according to claim 1, wherein the biological information includes information indicating a movement of the body at the time of work.
  3.  前記熟練度ごとに当該熟練度に応じた前記生体情報が有する特徴量を取得し前記記憶部に蓄積する蓄積部を、さらに備える、請求項1または2に記載の制御装置。 The control device according to claim 1, further comprising a storage unit that acquires a feature amount of the biological information corresponding to the skill level for each skill level and stores the feature amount in the storage unit.
  4.  前記記憶部に蓄積される特徴量は、前記判定部より判定された熟練度に応じた前記生体情報が有する特徴量を含む、請求項1から3のいずれか1項に記載の制御装置。 The control device according to any one of claims 1 to 3, wherein the feature amount stored in the storage unit includes a feature amount included in the biological information according to the skill level determined by the determination unit.
  5.  前記制御装置は、さらに、
     作業者が作業時に扱うワークの動きを示すワーク情報を取得するワーク情報取得部と、
     前記熟練度ごとに当該熟練度に応じた前記ワーク情報を記憶するためのワーク情報記憶部と、
     前記作業者の作業時に取得される前記ワーク情報が有する特徴量と、前記ワーク情報記憶部の熟練度ごとの前記ワーク情報が有する特徴量とを比較し、比較の結果に基づき、当該取得されるワーク情報がいずれの熟練度に該当するかを判定するワーク情報判定部と、を備え、
     前記決定部は、前記判定部により判定された熟練度と、前記ワーク情報判定部により判定された熟練度に基づき、前記制御量を決定する、請求項1から4のいずれか1項に記載の制御装置。
    The control device further includes:
    A workpiece information acquisition unit that acquires workpiece information indicating the movement of the workpiece handled by the worker during the operation;
    A work information storage unit for storing the work information according to the skill level for each skill level;
    The feature amount possessed by the work information acquired at the time of the work of the worker is compared with the feature amount possessed by the work information for each skill level of the work information storage unit, and the feature amount is acquired based on a comparison result. A work information determination unit that determines which skill level the work information corresponds to;
    5. The determination unit according to claim 1, wherein the determination unit determines the control amount based on the skill level determined by the determination unit and the skill level determined by the work information determination unit. Control device.
  6.  前記特徴量は、前記熟練度を識別可能な特徴量を含む、請求項1から5のいずれか1項に記載の制御装置。 The control device according to any one of claims 1 to 5, wherein the feature amount includes a feature amount capable of identifying the skill level.
  7.  前記判定部は、予め定められた時間毎に前記熟練度を判定し、
     前記制御装置は、前記予め定められた時間毎に判定された熟練度を統計し、統計情報を出力する、請求項1から6のいずれか1項に記載の制御装置。
    The determination unit determines the skill level at predetermined time intervals,
    The said control apparatus is a control apparatus of any one of Claim 1 to 6 which statistics the skill level determined for every said predetermined time, and outputs statistical information.
  8.  生産のための駆動部と、
     作業者の生体情報を測定するセンサと、
     前記駆動部を制御する制御装置と、を備え、
     前記制御装置は、
     前記センサから出力される前記生体情報を取得する取得部と、
     作業の熟練度ごとに当該熟練度に応じた前記生体情報を記憶するための記憶部と、
     前記作業者の作業時に取得される前記生体情報が有する特徴量と、前記記憶部の熟練度ごとの前記生体情報が有する特徴量とを比較し、比較の結果に基づき、当該取得される生体情報がいずれの熟練度に該当するかを判定する判定部と、
     判定された前記熟練度に基づき前記駆動部の制御量を決定する決定部と、を含む、システム。
    A drive for production,
    A sensor for measuring the biological information of the worker;
    A control device for controlling the drive unit,
    The control device includes:
    An acquisition unit for acquiring the biological information output from the sensor;
    A storage unit for storing the biological information corresponding to the skill level for each skill level of work;
    The biometric information acquired at the time of the operator's work is compared with the characteristic amount of the biometric information for each skill level of the storage unit, and the acquired biometric information is based on the comparison result. A determination unit that determines to which skill level
    A determination unit that determines a control amount of the drive unit based on the determined skill level.
  9.  生産のための駆動部を制御する方法であって、
     作業者から測定された生体情報を取得するステップと、
     前記作業者の作業時に取得される前記生体情報が有する特徴量と、記憶部に格納された熟練度ごとの前記生体情報が有する特徴量とを比較するステップと、
     比較の結果に基づき、当該取得される生体情報がいずれの熟練度に該当するかを判定するステップと、
     判定された前記熟練度に基づき前記駆動部の制御量を決定するステップと、を備える、制御方法。
    A method for controlling a drive for production comprising:
    Obtaining biological information measured from the operator;
    Comparing the feature quantity possessed by the biological information acquired during the work of the worker with the feature quantity possessed by the biometric information for each skill level stored in a storage unit;
    A step of determining which skill level the acquired biological information corresponds to based on a result of the comparison;
    Determining a control amount of the drive unit based on the determined skill level.
  10.  生産のための駆動部を制御する方法をコンピュータに実行させるためのプログラムであって、
     前記方法は、
     作業者から測定された生体情報を取得するステップと、
     前記作業者の作業時に取得される前記生体情報が有する特徴量と、記憶部に格納された熟練度ごとの前記生体情報が有する特徴量とを比較するステップと、
     比較の結果に基づき、当該取得される生体情報がいずれの熟練度に該当するかを判定するステップと、
     判定された前記熟練度に基づき前記駆動部の制御量を決定するステップと、を備える、プログラム。
    A program for causing a computer to execute a method for controlling a drive unit for production,
    The method
    Obtaining biological information measured from the operator;
    Comparing the feature quantity possessed by the biological information acquired during the work of the worker with the feature quantity possessed by the biometric information for each skill level stored in a storage unit;
    A step of determining which skill level the acquired biological information corresponds to based on a result of the comparison;
    Determining a control amount of the drive unit based on the determined skill level.
PCT/JP2017/029429 2016-09-30 2017-08-16 Control device, system, control method, and program WO2018061504A1 (en)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
JP2016-194282 2016-09-30
JP2016194282A JP6330882B2 (en) 2016-09-30 2016-09-30 Control device

Publications (1)

Publication Number Publication Date
WO2018061504A1 true WO2018061504A1 (en) 2018-04-05

Family

ID=61759432

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/JP2017/029429 WO2018061504A1 (en) 2016-09-30 2017-08-16 Control device, system, control method, and program

Country Status (2)

Country Link
JP (1) JP6330882B2 (en)
WO (1) WO2018061504A1 (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2020171211A1 (en) * 2019-02-22 2020-08-27 日本電信電話株式会社 Information processing device and method

Families Citing this family (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP7170496B2 (en) * 2018-10-18 2022-11-14 オークマ株式会社 MACHINING DATA LABELING METHOD FOR BUILDING MACHINING ERROR DIAGNOSIS MODEL IN MACHINE TOOL AND MACHINING ABNORMALITY DIAGNOSTIC SYSTEM
US11119716B2 (en) 2018-10-31 2021-09-14 Fanuc Corporation Display system, machine learning device, and display device
JP6912513B2 (en) * 2018-10-31 2021-08-04 ファナック株式会社 Display system, machine learning device, and display device
JP2020129018A (en) 2019-02-07 2020-08-27 株式会社日立製作所 System and method for evaluating operations
JP2022097249A (en) 2020-12-18 2022-06-30 オムロン株式会社 Recommended load determination device, ability parameter estimation model learning device, method, and program

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2007109095A (en) * 2005-10-14 2007-04-26 Omron Corp Process management apparatus, process management system, process management method, control program, and recording medium
JP2012234406A (en) * 2011-05-02 2012-11-29 Kawasaki Heavy Ind Ltd Work support device and work support method
JP2013200440A (en) * 2012-03-26 2013-10-03 Mitsubishi Electric Corp Video display device
JP2015230621A (en) * 2014-06-05 2015-12-21 キヤノン株式会社 Information processing device, control method of information processing device, and program

Family Cites Families (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP6283231B2 (en) * 2014-02-14 2018-02-21 日本電信電話株式会社 Proficiency assessment method and program

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2007109095A (en) * 2005-10-14 2007-04-26 Omron Corp Process management apparatus, process management system, process management method, control program, and recording medium
JP2012234406A (en) * 2011-05-02 2012-11-29 Kawasaki Heavy Ind Ltd Work support device and work support method
JP2013200440A (en) * 2012-03-26 2013-10-03 Mitsubishi Electric Corp Video display device
JP2015230621A (en) * 2014-06-05 2015-12-21 キヤノン株式会社 Information processing device, control method of information processing device, and program

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2020171211A1 (en) * 2019-02-22 2020-08-27 日本電信電話株式会社 Information processing device and method
JP2020135608A (en) * 2019-02-22 2020-08-31 日本電信電話株式会社 Information processing apparatus and method

Also Published As

Publication number Publication date
JP2018055611A (en) 2018-04-05
JP6330882B2 (en) 2018-05-30

Similar Documents

Publication Publication Date Title
JP6330882B2 (en) Control device
CN108136592B (en) Control device, control system, control method, and computer-readable storage medium
Li et al. A Control Framework for Tactile Servoing.
JP7010542B2 (en) Work analyzer, work analysis method, and program
CN102310409A (en) Robot apparatus and gripping method for use in robot apparatus
CN108687770B (en) Device, system and method for automatically generating motion track of robot
JP7171407B2 (en) Information processing device, production instruction support method
JP7160602B2 (en) Tool identification device and tool identification system
Diego-Mas et al. Using RGB-D sensors and evolutionary algorithms for the optimization of workstation layouts
US20210116906A1 (en) Controller and control system
US20210034043A1 (en) Industrial manufacturing plant and method for an automated booking of manual activities
Al-Amin et al. Sensor data based models for workforce management in smart manufacturing
CN110065064A (en) A kind of robot sorting control method
WO2022234678A1 (en) Machine learning device, classification device, and control device
JP4895188B2 (en) Inspection business system
JP4023614B2 (en) Gripping device, gripping control method, gripping control program, and recording medium
CN109934155A (en) A kind of cooperation robot gesture identification method and device based on deep vision
Ishiguro et al. Behavior selection and environment recognition methods for humanoids based on sensor history
JP7235533B2 (en) Robot controller and robot control system
JP6731603B1 (en) Inspection system
CN107745378B (en) Intelligent learning control method for high-power manipulator
CN109992093B (en) Gesture comparison method and gesture comparison system
Miyashita et al. Methods for Environment Recognition based on Active Behaviour Selection and Simple Sensor History
JP3005358B2 (en) Human body activity analyzer
Yan et al. An optimization method for human-robot collaboration in a production unit in the context of intelligent manufacturing

Legal Events

Date Code Title Description
DPE2 Request for preliminary examination filed before expiration of 19th month from priority date (pct application filed from 20040101)
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 17855462

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 17855462

Country of ref document: EP

Kind code of ref document: A1