Robot Simulation Device

The robot simulation device uses drive sound data to simulate and generate operating sounds, facilitating quicker and less burdensome assessment of robot motion quality.

JP7583184B2Active Publication Date: 2024-11-13FANUC LTD
View PDF 6 Cites 0 Cited by

Patent Information

Application Number
JP2023550862
Authority / Receiving Office
JP · JP
Patent Type
Patents
Current Assignee / Owner
Filing Date
2021-09-29
Publication Date
2024-11-13
Estimated Expiration
2041-09-29

AI Technical Summary

Technical Problem

Judging the quality of a robot's motion based on a taught program is time-consuming and burdensome, especially for multi-axis robots, as operators need to visually confirm various data such as axis movement, motor speed, acceleration, jerk, torque, and temperature.

Method used

A robot simulation device that executes motion simulation using drive sound data, generating and outputting drive sounds corresponding to the robot's operating state, allowing operators to assess the robot's operation by listening.

Benefits of technology

Reduces the time required to determine the quality of robot operations and lessens the operator's burden by enabling auditory evaluation of the robot's performance.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure 0007583184000001
    Figure 0007583184000001
  • Figure 0007583184000002
    Figure 0007583184000002
  • Figure 0007583184000003
    Figure 0007583184000003
Patent Text Reader

Abstract

This robot simulation device (50) is provided with an operation simulation execution unit (151) that executes an operation simulation of a robot in accordance with an operation program, and a driving sound generation unit (153) that simulates and generates a driving sound according to an operation state of the robot in the operation simulation, on the basis of driving sound data obtained by recording the driving sound of an actual robot.
Need to check novelty before this filing date? Find Prior Art

Description

[Technical field]

[0001] The present invention relates to a robot simulation device. [Background technology]

[0002] 2. Description of the Related Art Various types of devices are used as simulation devices for simulating the operation of robots and mechanical devices.

[0003] For example, Patent Document 1, in relation to an educational device applied to understanding the phenomena of plants and machinery, operation training, etc., states that "the third memory 6 is a memory for storing data such as outline drawings, part drawings, colors, operating sounds in various operating states, etc. of the machines, valves, piping, etc. that make up the plant or machinery, as shown in FIG. 2(C), as well as piping diagrams, etc., and is used by the image / operation sound generation device 5 to generate an image of the plant or machinery as seen from a position and direction specified by the learner, and the operating sounds of the plant or machinery in its operating state. Operating sounds are, for example, the sounds of rotating equipment such as pumps and motors that are generated by the rotation of the equipment, and in piping, etc., the sounds generated by water, steam, etc. flowing inside the equipment" (paragraph 0011).

[0004] Patent document 2 describes that "the robot 11 is equipped with a manipulator 21, a hand 22 attached to the tip of the manipulator 21, and a microphone 23 attached to the hand 22" (paragraph 0018), that "the microphone 23 is attached to the hand 22 as an example of a location where it is easy to input sound (sound waves) related to work by the hand 22" (paragraph 0020), and that "in the robot system 1 of this embodiment, for example, processing is not performed to Fourier transform sound information and perform frequency analysis, but rather the robot is controlled based on the volume of the sound, making it possible to reduce processing time and processing load" (paragraph 0034).

[0005] Patent Document 3, in relation to a teaching electric cutting tool, states that "a microphone 22 is placed near the workpiece 11T to detect the cutting sound during cutting and polishing with a grinding wheel 12T, and the detected sound is input to a recording device 20 via a signal line 23. The recording device 20 stores an audio frequency corresponding to the peripheral speed of the grinding wheel during cutting and the contact pressure of the force sensor 13 from the pitch of the cutting sound sent from the signal line 23 based on the rotation speed R of the grinding wheel 12T" (paragraph 0023), and that "the recording device 20 The court writes that "the work teaching operations of the teaching electric cutting tool 10T described above are stored from the working time when the skilled worker M processes the workpiece 11T with the teaching electric cutting tool 10T to the completion of the work, and this is used as the work teaching data" (paragraph 0024), and that "since the grinding wheel 12R wears down due to grinding and its peripheral speed also changes, the rotation speed of the grinding wheel 12R can be adjusted based on the audio frequency data stored in the work teaching data 24" (paragraph 0032). [Prior art documents] [Patent documents]

[0006] [Patent Document 1] Japanese Patent Application Publication No. 11-133848 [Patent Document 2] JP 2016-5856 A [Patent Document 3] JP 2017-217738 A Summary of the Invention [Problem to be solved by the invention]

[0007] Incidentally, with regard to a simulation device for teaching a robot, it is necessary to judge whether the robot's operation based on the program taught is good or bad. In such a case, the robot's operation and trajectory are generally judged visually, and information such as the amount of movement of each axis, the motor speed, acceleration, jerk, torque, current, and temperature are visualized and checked visually. In such a case of checking the operation, if the robot is a multi-axis robot such as a six-axis robot, various data must be checked for six axes, which takes time and places a heavy burden on the operator. [Means for solving the problem]

[0008] One aspect of the present disclosure is a robot simulation device that includes an operation simulation execution unit that executes an operation simulation of a robot in accordance with an operation program, and a driving sound generation unit that simulates and generates a driving sound corresponding to the operating state of the robot in the operation simulation based on driving sound data obtained by recording the driving sound of an actual robot. Effect of the Invention

[0009] An operator who is accustomed to teaching a real robot can judge the quality of the robot's operating state by listening to the driving sound that corresponds to the robot's operating state. Therefore, with the above configuration, the time required for confirmation work when judging the quality of the robot's operation according to the taught program is greatly reduced, and the burden on the operator is also reduced.

[0010] These and other objects, features and advantages of the present invention will become more apparent from the detailed description of exemplary embodiments of the invention that are illustrated in the accompanying drawings. [Brief description of the drawings]

[0011] [Figure 1]FIG. 1 is a perspective view of an actual robot that is the subject of simulation by a robot simulation device, and is also a diagram showing a system configuration including a robot control device and the robot simulation device. [Diagram 2] FIG. 2 illustrates an example of a hardware configuration of a robot simulation device. [Diagram 3] FIG. 2 is a functional block diagram of the robot simulation device. [Figure 4] 11 is a basic flowchart showing a driving sound generation process during a motion simulation of a robot. [Diagram 5] FIG. 2 is a diagram illustrating a scene of a robot operation simulation displayed on a display unit of the robot simulation device. [Figure 6] 4 is a functional block diagram illustrating an example of the configuration of a drive sound generating unit. FIG. [Figure 7] FIG. 2 is a diagram illustrating an example of the configuration of a learning unit. [Figure 8] 7 is a flowchart showing a drive sound generation process in a case where the configuration shown in FIG. 6 is adopted as the configuration of the drive sound generation unit. [Figure 9A] 1 is a table graph showing an example of the drive sound of a certain axis of a robot and the drive sound of a single motor of that axis. [Figure 9B] 4 is a graph showing an example of driving noise of a single reduction gear. [Figure 10] FIG. 13 illustrates another exemplary configuration of the learning unit. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0012] Next, an embodiment of the present disclosure will be described with reference to the drawings. In the drawings, similar components or functional parts are given similar reference symbols. To facilitate understanding, the scale of these drawings is appropriately changed. In addition, the form shown in the drawings is one example for implementing the present invention, and the present invention is not limited to the illustrated form.

[0013] A robot simulation device 50 according to an embodiment (see Figs. 1 to 3) will be described below. Fig. 1 shows a perspective view of an actual robot 1 to be simulated by the robot simulation device 50, and also shows a system configuration including a robot control device 70 and the robot simulation device 50. Here, as an example, the robot 1 is a six-axis articulated robot. Other types of robots may be used as the simulation target. The robot 1 is controlled by the robot control device 70. The robot simulation device 50 is connected to the robot control device 70 via, for example, a network. In this configuration, the robot control device 70 can control the robot 1 according to an operation program transmitted from the robot simulation device 50.

[0014] As will be described in detail below, the robot simulation device 50 not only simulates the operation of the robot 1, but also has a function of simulating (simulating and generating) the driving sound of the robot 1. In addition, as shown in Fig. 1, the robot simulation device 50 has a function of collecting the driving sound of the robot 1 via a microphone 61.

[0015] Here, the configuration of the robot 1 will be described. The robot 1 is a multi-axis robot including arms 12a, 12b, a wrist 16, and a plurality of joints 13. A work tool 17 is attached to the wrist 16 of the robot 1 as an end effector. The robot 1 includes a motor 14 for driving a driving member in each joint 13. By driving the motor 14 in each joint 13 based on a position command, the arms 12a, 12b and the wrist 16 can be set to a desired position and posture. The robot 1 also includes a base 19 fixed to an installation surface 20, and a rotating unit 11 that rotates relative to the base 19. In FIG. 1, the rotation directions of six axes (J1 axis, J2 axis, J3 axis, J4 axis, J5 axis, and J6 axis) are indicated by arrows 91, 92, 93, 94, 95, and 96, respectively.

[0016] In FIG. 1, the work tool 17 attached to the wrist 16 of the robot 1 is a welding gun for spot welding, but this is not limited to this, and various tools can be attached as the work tool depending on the work content.

[0017] FIG. 2 is a diagram showing an example of a hardware configuration of the robot simulation device 50. As shown in FIG. 2, the robot simulation device 50 may have a configuration as a general computer in which a memory 52 (ROM, RAM, non-volatile memory, etc.), a display unit 53, an operation unit 54 consisting of an input device such as a keyboard (or software key), a storage device 55 (HDD, etc.), an input / output interface 56, an audio input / output interface 57, etc. are connected to a processor 51 via a bus. A microphone 61 and a speaker 62 are connected to the audio input / output interface 57. The audio input / output interface 57 has a function of taking in audio data via the microphone 61, a function of processing the audio data, and a function of outputting the audio data via the speaker 62. A personal computer, a notebook computer, a tablet terminal, or other various information processing devices can be used as the robot simulation device 50.

[0018] 3 is a functional block diagram of the robot simulation device 50. As shown in FIG. 3, the robot simulation device 50 has an operation simulation execution unit 151, a sound recording unit 152, and a drive sound generation unit 153.

[0019] The motion simulation execution unit 151 executes a motion simulation to cause the robot 1 to perform a simulated motion in accordance with the motion program 170. The state in which the robot 1 performs the simulated motion is displayed on the display unit 53, for example.

[0020] The recording unit 152 has a function of processing the audio signal input via the microphone 61 and recording it as audio data. The microphone 61 and the recording unit 152 are used to record and store the drive sound for each axis when the robot 1 is actually driven. The details of recording the drive sound will be described later.

[0021] When the motion simulation execution unit 151 executes a motion simulation of the robot 1, the drive sound generation unit 153 simulates and generates a drive sound according to the motion state of the robot 1. The generated drive sound is output via the speaker 62.

[0022] Here, we will explain an example of collecting the driving sound of the actual robot 1 via the recording unit 152. Here, we assume that the main causes of the driving sound of the robot 1 are the motors and reducers of each axis, and consider that the driving sound depends on the torque and rotation speed of the motors, and the torque and rotation speed of the reducers.

[0023] The drive sound is collected, for example, by preparing an operation program for each axis, changing the speed (or maximum speed) and acceleration of the operation program, and recording the drive sound for each axis together with the torque and rotation speed of the motor and the torque and rotation speed of the reducer at that time. For example, for the J1 axis, the J1 axis is driven by an operation program that drives only the J1 axis at various speeds, etc., and the drive sound is collected. In order to increase the amount of drive sound data collected, the operation program may be executed while changing the robot's posture, wrist load, etc., to collect the drive sound. In addition, when collecting the drive sound of the robot 1, parameters that represent the operating state of the robot 1 when the drive sound is recorded (for example, the torque and rotation speed of the motor for each axis, and the torque and rotation speed of the reducer) are obtained from the robot control device 70. Such an operation can be realized by the robot simulation device 50 and the robot control device 70 operating in cooperation with each other. As an example, in this case, the command for the robot 1 may be generated by the recording unit 152 and the generated command may be sent to the robot control device 70 to drive the robot 1.

[0024] In this way, it is possible to create a database of the drive sounds of the robot 1 when the motor torque, motor rotation speed, reducer torque, and reducer rotation speed are changed as parameters for each axis. The drive sound data collected in this way is hereinafter also referred to as the drive sound database 160.

[0025] 4 is a basic flowchart showing a driving sound generation process during a motion simulation of the robot 1, which is executed by the robot simulation device 50. It is assumed that the motion simulation execution unit 151 starts a motion simulation of the robot 1 according to a motion program in response to a predetermined user operation. Then, the driving sound generation unit 153 acquires the motion state of the robot 1 during the motion simulation from the motion simulation execution unit 151, and simulates and generates a driving sound corresponding to the motion state (step S1).

[0026] More specifically, the drive sound generation unit 153 acquires the torque and rotation speed of the motor and the torque and rotation speed of the reducer as parameters for each axis of the robot 1 during the operation simulation from the operation simulation execution unit 151, and acquires drive sounds that match the parameters for each axis from the drive sound database 160. Then, the drive sound generation unit 153 generates the drive sound of the robot 1 by synthesizing the drive sounds acquired for each axis.

[0027] By the above operation, as shown in Fig. 5 as an example, a driving sound corresponding to one scene of the operation simulation of the robot 1 (robot model 1M) is output together with the simulated operation of the robot 1 (robot model 1M). An operator who is accustomed to teaching a real robot can judge the quality of the robot's operating condition by listening to the driving sound corresponding to the robot's operating condition. Therefore, according to the above configuration, the time required for confirmation work in a scene where the quality of the robot's operation according to the taught program is judged is greatly reduced, and the burden on the operator is also reduced.

[0028] Regarding the timing of playing the driving sound of the robot 1, in addition to synchronizing it with the movement of the robot 1 during the motion simulation, it is also possible to present the movement of the robot 1 and then play the driving sound corresponding to that movement.

[0029] Hereinafter, a specific example of the configuration of the drive sound generation unit 153 will be described. Fig. 6 is a functional block diagram showing an example of the configuration of the drive sound generation unit 153. The drive sound generation unit 153 in this example is configured to extract the relationship between the parameters representing the motion state of the robot 1 and the drive sound, and generate the drive sound from the motion state of the robot 1 in the motion simulation based on the extracted relationship.

[0030] As shown in FIG. 6, the drive sound generation unit 153 has a relationship extraction unit 154 and a drive sound simulation unit 155.

[0031] The relationship extraction unit 154 has a function of extracting and retaining the relationship between the operating state of the robot 1 and the driving sound data stored in the driving sound database 160. As an example, the relationship extraction unit 154 may include a learning unit 156 that learns the relationship between the operating state of the robot 1 and the driving sound and constructs a learning model.

[0032] The driving sound simulator 155 simulates and generates a driving sound corresponding to the motion state of the robot 1 based on the relationship held by the relationship extractor 154, the driving sound database 160, and the motion state of each axis of the robot 1 acquired from the motion simulation execution unit 151. The generated driving sound of the robot 1 is output via the speaker 62.

[0033] As described above, it is assumed that the recording unit 152 has prepared the drive sound database 160 in which predetermined parameters (motor torque, motor rotation speed, reducer torque, reducer rotation speed) are associated with drive sounds for each axis. The relationship extraction unit 154 derives the relationship between the predetermined parameters (motor torque and rotation speed, and reducer torque and rotation speed) and the drive sounds of the robot 1.

[0034] There are various methods for determining the relationship between these parameters and the drive sound, but here, a method for determining the relationship by machine learning will be described. In this embodiment, the learning unit 156 of the relationship extraction unit 154 uses machine learning to learn the relationship between the drive sound and parameters including the motor torque, motor rotation speed, reducer torque, and reducer rotation speed for each axis, and constructs a learning model.

[0035] There are various machine learning techniques, which can be broadly categorized into, for example, "supervised learning," "unsupervised learning," and "reinforcement learning." Furthermore, in order to realize these techniques, a technique called "deep learning" can also be used. In this embodiment, "supervised learning" is applied to the machine learning by the learning unit 156.

[0036] A specific configuration and learning method of the learning unit 156 will be described. As shown in Fig. 7, the learning unit 156 has a neural network 300. A learning model is constructed by applying teacher data consisting of input data (input parameters) and output data to this neural network 300. In the learning process, the weighting applied to each neuron of the neural network 300 is learned by the error backpropagation method.

[0037] By collecting the driving sounds described above, predetermined parameters (torque of the motor, rotation speed of the motor, torque of the reducer, and rotation speed of the reducer) are associated with the driving sounds. Here, the driving sounds are subjected to frequency analysis to obtain data on the sound pressure level for each frequency component obtained by dividing the audio frequency band into a predetermined number of frequency components. Although one neural network 300 is shown in FIG. 7, a neural network 300 may be prepared for each axis, and the driving sounds for each axis may be learned by each neural network 300.

[0038] A plurality of pieces of teacher data are prepared, in which input data is a predetermined parameter (in the above example, the torque of the motor, the rotational speed of the motor, the torque of the reducer, and the rotational speed of the reducer) and output data is a sound pressure level for each frequency component, and the neural network 300 is trained. This allows the construction of a learning model in which input data is a predetermined parameter and output data is a sound pressure level for each frequency component.

[0039] Once the learning model is constructed, the driving sound simulator 155 acquires predetermined parameters (in the above example, for each axis, the torque of the motor, the rotational speed of the motor, the torque of the reducer, and the rotational speed of the reducer) as the motion state of the robot 1 during the simulation motion of the robot 1, and inputs these to the trained neural network 300. As a result, the sound pressure level of each frequency component of the driving sound corresponding to the motion state of the robot 1 is output from the neural network 300. Then, for all axes of the robot 1, the sound pressure level of each frequency component corresponding to the motion state of the axis is obtained. The sound pressure levels of each frequency component for each axis obtained here are synthesized to obtain the driving sound of the robot 1 corresponding to the above motion state.

[0040] The synthesized driving sound is outputted via the speaker 62. As a result, the driving sound of the entire robot 1 corresponding to the torque and rotation speed of the motor for each axis of the robot 1 and the torque and rotation speed of the reducer during the simulation operation is outputted.

[0041] 8 is a flowchart showing the drive sound generation process of the robot 1 when the configuration shown in FIG. 6 is adopted as the configuration of the drive sound generation unit 153. In step S11, as described above, using the actual robot 1, the drive sound for each axis of the robot 1 is recorded while appropriately changing the motion speed, acceleration, posture of the robot 1, wrist load, etc. of the robot 1. Then, as described above, the relationship extraction unit 154 uses the recorded drive sound (drive sound database 160) to find the relationship between the predetermined parameters (motor torque, motor rotation speed, reducer torque, reducer rotation speed) and the drive sound for each axis.

[0042] Next, in step S12, the following process is performed. In response to a predetermined operation, the motion simulation execution unit 151 starts a motion simulation of the robot 1 according to the motion program. At this time, the drive sound simulator 155 acquires the motor torque, motor rotation speed, reducer torque, and reducer rotation speed for each axis of the robot 1 in the current motion simulation from the motion simulation execution unit 151 as the motion state, and inputs the parameters to the learning unit 156 (learning model) to obtain a drive sound (sound pressure level for each frequency component) corresponding to the parameters for each axis. The drive sound simulator synthesizes the sound pressure levels for each frequency component obtained for each axis, and generates a drive sound for the robot 1. The generated drive sound is output from the speaker 62.

[0043] Here, other data structure examples regarding the drive sound database will be described. In the above example, the drive sound database 160 is configured as data in which parameters consisting of the torque and rotation speed of the motor and the torque and rotation speed of the reducer are associated with the drive sound for each axis of the robot 1. Here, an example will be described in which the drive sound due to the torque and rotation speed of the motor alone and the drive sound due to the torque and rotation speed of the reducer alone are stored as separate data in a database for each axis of the robot 1.

[0044] First, the actual robot 1 is driven to prepare the drive sound database 160. Then, the drive sound of the motor alone is measured separately when the torque and rotation speed of the motor are changed, and the data is compiled into a database. For this measurement, it is preferable to use the motor alone, and to perform the measurement in a recording environment where no sounds other than those of the motor alone are mixed in. Then, the drive sound of the motor alone for each axis is subtracted from the drive sound for that axis prepared as the drive sound database 160, so that the drive sound of the reducer alone is extracted for each axis.

[0045] The calculation for subtracting the driving sound of the motor alone from the driving sound of each axis is performed, for example, as follows. First, the driving sound when an axis of the actual robot 1 is operated (i.e., the driving sound including the motor driving sound and the reducer driving sound) is frequency analyzed using a method such as Fourier transform to obtain data in the frequency domain. Graph 201 shown by a solid line in FIG. 9A is an example of a graph of data (frequency characteristics) in the frequency domain of the driving sound of the axis. Next, the driving sound of the motor alone constituting the axis is frequency analyzed to obtain data in the frequency domain. Graph 202 shown by a dashed line in FIG. 9A is an example of a graph of data (frequency characteristics) in the frequency domain of the driving sound of this motor alone.

[0046] By subtracting the driving sound data representing graph 202 from the driving sound data representing graph 201, graph 203 as shown in Fig. 9B is obtained as an example. Graph 203 is data (frequency characteristics) in the frequency domain of the driving sound of the reducer alone for the axis. For example, by applying an inverse Fourier transform to the frequency domain data of graph 203, driving sound data in the time domain of the reducer alone constituting the axis can be obtained.

[0047] As a result, the driving sound of the motor alone when the torque and rotation speed of the motor are changed as parameters, and the driving sound of the reducer alone when the torque and rotation speed of the reducer are changed as parameters can be stored in a database. When such a database is constructed, the relationship extraction unit 154 obtains the relationship (first relationship) between the torque and rotation speed of the motor and the driving sound of the motor alone, and the relationship (second relationship) between the torque and rotation speed of the reducer and the driving sound of the reducer alone. Specifically, in this case, the learning unit 156 is configured to have two neural networks 310 and 320 for learning the driving sound of the motor alone and the driving sound of the reducer alone, respectively. Note that two neural networks are shown in FIG. 10 for convenience of explanation, and a set of these two neural networks is prepared for each axis.

[0048] For the neural network 310, a plurality of pieces of teacher data are prepared, in which the torque and rotation speed of the motor are used as input data, and the sound pressure at each frequency component of the driving sound of the motor alone at the torque and rotation speed is used as output data, and the neural network 310 is caused to perform learning. In this way, the neural network 310 constructs a learning model that expresses the relationship between the torque and rotation speed of the motor and the driving sound of the motor alone. For the neural network 320, a plurality of pieces of teacher data are prepared, in which the torque and rotation speed of the reducer are used as input data, and the sound pressure at each frequency component of the driving sound of the reducer alone at the torque and rotation speed is used as output data, and the neural network 310 is caused to perform learning. In this way, the neural network 310 constructs a learning model that expresses the relationship between the torque and rotation speed of the reducer and the driving sound of the reducer alone.

[0049] During the execution of the motion simulation of the robot 1, the driving sound simulator 155 acquires the motion state of the robot 1, i.e., the torque and rotation speed of the motor, and the torque and rotation speed of the reducer, as well as the driving sound of the motor alone and the driving sound of the reducer alone corresponding to these parameters, from the database acquired as described above. Then, the driving sound simulator 155 inputs the acquired torque and rotation speed of the motor to the neural network 310 to acquire the sound pressure level of each frequency component of the driving sound of the motor alone corresponding to the torque and rotation speed. In addition, the driving sound simulator 155 executes the generation of the driving sound for such a motor alone for each axis. In addition, the driving sound simulator 155 inputs the acquired torque and rotation speed of the reducer to the neural network 320 to acquire the sound pressure level of each frequency component of the driving sound of the reducer alone corresponding to the torque and rotation speed. In addition, the driving sound simulator 155 executes the generation of the driving sound for such a reducer alone for each axis.

[0050] Then, the drive sound simulator 155 obtains the drive sound of the robot 1 related to the motor by synthesizing, for all axes, the sound pressures of the respective frequency components obtained as corresponding to the torque and rotation speed of the motor. Also, the drive sound simulator 155 obtains the drive sound of the robot 1 related to the reducer by synthesizing, for all axes, the sound pressures of the respective frequency components obtained as corresponding to the torque and rotation speed of the reducer. Furthermore, the drive sound simulator 155 synthesizes the drive sound of the motor and the drive sound of the reducer obtained as described above to generate the drive sound of the robot 1 as a whole.

[0051] In this way, by configuring the relationship between the parameters representing the operating state and the drive sound by separating the motor alone and the reducer alone, it is possible to derive a more accurate relationship, and it is believed that it is possible to improve the reproducibility of the drive sound of robot 1 as a whole.

[0052] According to the embodiment described above, it is possible to generate a driving sound according to the operating state of the robot, which significantly reduces the time required for a worker who is accustomed to teaching actual robots to check whether the robot's operation according to the program they have taught is good or bad, and also reduces the burden on the worker.

[0053] Although the present invention has been described using exemplary embodiments, those skilled in the art will understand that modifications and various other changes, omissions, and additions can be made to the above-described embodiments without departing from the scope of the present invention.

[0054] In the above embodiment, a configuration in which the relationship extraction unit 154 is used has been described as one specific example of the configuration of the drive sound generation unit 153, but in a configuration in which the relationship extraction unit 154 is not used, the drive sound generation unit 153 may be configured as follows. That is, the drive sound generation unit 153 may be configured to use a drive sound obtained from the drive sound database 160 when a drive sound that exactly matches parameters (torque and rotation speed of the motor, and torque and rotation speed of the reducer) that represent the operating state of the robot 1 during the operation simulation is present in the drive sound database 160, and to acquire a drive sound with parameters close to the parameters when a drive sound that exactly matches the parameters is not present in the drive sound database 160.

[0055] The system configuration examples shown in Figures 1, 3, 6, etc. are merely illustrative, and the system configuration can be modified in various ways. For example, the driving sound may be recorded using a recording device separate from the robot simulation device. In this case, the robot simulation device can be configured to receive the driving sound or the driving sound database from the recording device.

[0056] When collecting driving sounds of an actual robot, the sounds may be collected while changing at least one of the speed, acceleration, posture, and wrist load of the robot.

[0057] As a parameter representing the motion state of the robot, at least one of the torque of the motor, the rotational speed of the motor, the torque of the reducer, and the rotational speed of the reducer may be used. In addition, other parameters may be used.

[0058] The robot control device 70 may have a configuration as a general computer having a CPU, ROM, RAM, a storage device, an operation unit, a display unit, an input / output interface, a network interface, and the like.

[0059] The functional blocks of the robot simulation device shown in Figures 3 and 6 may be realized by a processor of the robot simulation device executing various software stored in a storage device, or may be realized by a configuration mainly based on hardware such as an ASIC (Application Specific Integrated Circuit).

[0060] The programs for executing various processes such as the drive sound generation process in the above-mentioned embodiments can be recorded on various computer-readable recording media (e.g., semiconductor memories such as ROM, EEPROM, and flash memory, magnetic recording media, and optical discs such as CD-ROM and DVD-ROM). [Explanation of symbols]

[0061] 1. Robot 11 Swivel section 12a, 12b Arms 13 Joints 14 Motor 16 Wrist part 17 Work Tools 19 Base 20 Installation surface 50 Robot simulation device 51 Processors 52 Memory 53 Display section 54 Operation section 55 Storage device 56 Input / Output Interface 57 Audio Input / Output Interface 61 Mike 62 Speaker 70 Robot control device 151 Operation Simulation Execution Unit 152 Recording Section 153 Drive sound generation unit 154 Relationship Extraction Unit 155 Driving sound simulation section 156 Learning Department 160 Drive Sound Database 170 Operation Program 300, 310, 320 Neural Networks

Claims

1. an operation simulation execution unit that executes an operation simulation of the robot according to the operation program; a driving sound generating unit that simulates and generates a driving sound corresponding to a motion state of the robot in the motion simulation based on driving sound data obtained by recording a driving sound of an actual robot; A robot simulation device comprising:

2. 2. The robot simulation device according to claim 1, wherein the driving sound data has a structure in which a predetermined parameter related to the operating state is associated with a driving sound of the robot corresponding to the predetermined parameter.

3. 3. The robot simulation device according to claim 2, further comprising a recording unit that records a driving sound from the actual robot and generates the driving sound data.

4. 4. The robot simulation device according to claim 3, wherein the driving sound of the actual robot is collected while changing at least one of a speed, an acceleration, a posture, and a wrist load of the actual robot.

5. The driving sound generating unit includes: a relationship extraction unit that extracts a relationship between the predetermined parameter and the driving sound of the robot based on the driving sound data; 5. The robot simulation device according to claim 2, further comprising: a drive sound simulator that simulates the drive sound according to the predetermined parameter that represents the motion state of the robot in the motion simulation based on the extracted relationship.

6. The robot simulation device according to claim 5 , wherein the relationship extraction unit includes a learning unit that learns the relationship by machine learning and constructs a learning model that represents the relationship.

7. 7. The robot simulation device according to claim 6, wherein the learning unit learns and extracts, as the relationship, a relationship between the predetermined parameter and a sound pressure for each frequency component obtained by dividing a characteristic in a frequency domain of the driving sound of the robot into a plurality of frequency components.

8. The robot is a multi-axis robot, the drive sound data has a structure in which the predetermined parameters are associated with the drive sounds of the robot corresponding to the predetermined parameters for each axis constituting the robot, The relationship extraction unit extracts a relationship between the predetermined parameter and the driving sound of the robot for each axis, The robot simulation device according to any one of claims 5 to 7, wherein the drive sound simulator generates drive sounds for each axis of the robot according to the predetermined parameters representing the motion state of the robot during the motion simulation based on the relationship, and synthesizes the generated drive sounds for each axis.

9. 9. The robot simulation device according to claim 8, wherein the predetermined parameters include at least one of a torque of a motor, a rotational speed of the motor, a torque of a reducer, and a rotational speed of the reducer.

10. The robot is a multi-axis robot, the predetermined parameters include a first predetermined parameter related to a motor and a second predetermined parameter related to a reducer, the drive sound data has a structure in which, for each axis constituting the robot, the first predetermined parameter is associated with a drive sound of the motor alone corresponding to the first predetermined parameter, and the second predetermined parameter is associated with a drive sound of the reducer alone corresponding to the second predetermined parameter; The relationship extraction unit extracts a first relationship between the first predetermined parameter and a driving sound of the motor alone, and extracts a second relationship between the second predetermined parameter and a driving sound of the reducer alone, The robot simulation device according to any one of claims 5 to 7, wherein the drive sound simulator generates, for each axis, a drive sound of the motor alone and a drive sound of the reducer alone that correspond respectively to the first predetermined parameter and the second predetermined parameter that represent the operating state of the robot during the operation simulation based on the first relationship and the second relationship, and synthesizes the generated drive sounds of the motor alone and the drive sounds of the reducer alone for each axis.

11. the first predetermined parameter includes at least one of a torque and a rotation speed of the motor; The robot simulation device according to claim 10 , wherein the second predetermined parameter includes at least one of a torque and a rotation speed of the reducer.

Citation Information

Patent Citations

  • Educational device

    JP1999133848A

  • State amount presentation device and method

    JP2004178447A

  • Control device and its control method

    JP2005316937A

  • Numerical control device for machine tool equipped with sound conversion device

    JP2013025776A

  • Robot system, robot, control unit and control method

    JP2016005856A