JP2020078852A - Learning system and robot position adjustment system - Google Patents

Abstract

To prevent a trouble in a work due to a work robot even in a case where a stop position of an unmanned carrier or carriage is displaced from a predetermined and prescribed stop position in a learning system and a robot position adjustment system.SOLUTION: A learning system performs machine learning of arm position correctness determination NN55 on the basis of image data transmitted from a robot 2 (image data taken by a camera 4 at each stop position of an unmanned carrier) and position correctness information input by a worker on a centralized control board 7, determines whether or not there is a problem in a position of an arm 5 of the robot 2 on the basis of the image data transmitted from a transmission/reception line 31 of the robot 2 by using the learned arm position correctness determination NN55, and performs control so that a server 8 or the like transmits an instruction command for adjusting the position of the arm 5 of the robot 2 to a robot controller 9 when there is a problem in the position of the arm 5 of the robot 2, thereby preventing a trouble in a work due to the robot 2.SELECTED DRAWING: Figure 3

Description

  The present invention relates to a learning system and a robot position adjusting system, and more particularly to a technique for adjusting a work position of a robot.

  Conventionally, as shown in FIG. 14, in a factory having a plurality of (production) lines, when the work such as processing or assembling of parts or products in each line is performed in different time zones, the worker is Work is often performed on these lines by moving between them.

  On the other hand, in recent years, in a (production) line in a factory, a mobile robot having a work robot mounted on an automated guided vehicle is automatically moved by stopping it in front of each facility in the line while traveling along a traveling path. A robot system that performs work such as processing and assembly has appeared (for example, see Patent Document 1).

JP 2002-73171 A

  However, in the robot system as disclosed in Patent Document 1, the stop position of the automatic guided vehicle is deviated from the predetermined stop position, which causes a deviation in the (work) position of the work robot. Occurrence of work troubles such as stop of work of the work robot and failure of work, assembly, and the like by the work robot may occur.

  In particular, when the above mobile robot is commonly used for a plurality of lines in a factory, compared with the case where it is used for only one line, the number of equipments at the stop position of the automated guided vehicle on the line and Since there are many types, there is a high possibility that the stop position of the automated guided vehicle will deviate from the predetermined stop position, and therefore the above-mentioned work robot is likely to have a trouble in work.

  The above problem is caused by a worker carrying a trolley equipped with a work robot and stopping it in front of each facility (each work position) on the line to perform work such as machining and assembly. The same applies to the case.

  The present invention is to solve the above-mentioned problems, and even when the stop position of the automatic guided vehicle or the carriage is deviated from a predetermined stop position, it is possible to prevent work troubles caused by the work robot. A learning system and a robot position adjusting system are provided.

  In order to solve the above problems, the learning system according to the first aspect of the present invention has a camera, a work robot in a factory line, and a mobile robot including an automated guided vehicle for moving the work robot, A learning system comprising a position correctness information input unit for inputting position correctness information indicating whether or not there is a problem in the position of the work robot, and a computer that communicates with the mobile robot. The robot includes a robot-side transmission unit that transmits image data captured by the camera at each stop position of the automatic guided vehicle to the computer, and the computer includes the image data transmitted from the robot-side transmission unit. Based on the above, a neural network storage unit that stores a neural network that determines whether there is a problem in the position of the work robot, the image data transmitted from the robot side transmission unit, and the position correctness information input A machine learning unit that performs machine learning of the neural network based on the position correctness information input by the user from the unit.

  In this learning system, the mobile robot is commonly used in a plurality of lines in the factory, and the machine learning unit is configured when the mobile robot is located in any one of the plurality of lines. Also, machine learning of the neural network may be performed based on the image data transmitted from the robot-side transmission unit and the position correctness information input by the user from the position correctness information input unit. ..

  A learning system according to a second aspect of the present invention indicates whether or not there is a problem in a work robot having a camera in a factory line, a dolly equipped with the work robot, and the position of the work robot. A learning system comprising a position correctness information input unit for inputting position correctness information and a computer that communicates with the work robot, wherein the work robot, at each work position on the line, The robot-side transmitting unit that transmits the image data captured by the camera to the computer is provided, and the computer has a problem in the position of the work robot based on the image data transmitted from the robot-side transmitting unit. In the neural network storage unit that stores a neural network that determines whether or not there is the image data transmitted from the robot side transmission unit, and the position correctness information input by the user from the position correctness information input unit. And a machine learning unit for performing machine learning of the neural network based on the above.

  In this learning system, the work robot is commonly used in a plurality of lines in the factory, and in the machine learning unit, the work robot is located in any one of the plurality of lines. Even at this time, machine learning of the neural network is performed based on the image data transmitted from the robot-side transmitter and the position correctness information input by the user from the position correctness information input unit. Good.

  A robot position adjusting system according to a third aspect of the present invention includes a work robot having a camera in a factory line, a mobile robot including an automated guided vehicle for moving the work robot, and control of the work robot. A robot position adjusting system comprising: a robot control unit that performs the operation of the mobile robot; and a computer that communicates with the mobile robot, wherein the mobile robot displays image data captured by the camera at each stop position of the automatic guided vehicle. A robot-side transmitter for transmitting to the computer, the robot controller moves the work robot based on an instruction command received from the computer, and the computer sends the instruction command to the robot controller. Position correct/incorrect to determine whether or not there is a problem in the position of the work robot based on the image data transmitted from the robot side transmission unit by using a computer side transmission unit that transmits and a learned neural network As a result of the determination by the determination unit and the position correctness determination unit, when there is a problem in the position of the work robot, the position of the work robot is adjusted to the robot control unit by using the computer side transmission unit. And a command transmission control unit that controls to transmit an instruction command for performing the command.

  In this robot position adjusting system, the mobile robot is commonly used in a plurality of lines in the factory, and the position correct/wrong determination unit determines the position of the mobile robot in any one of the plurality of lines. Also at this time, whether or not there is a problem in the position of the work robot may be determined based on the image data transmitted from the robot side transmission unit.

  In this robot position adjustment system, the position correctness determination unit determines whether or not there is a problem in the position of the arm of the work robot based on the image data transmitted from the robot side transmission unit, The command command that the command transmission control unit controls to transmit may be an command command for adjusting the position of the arm of the work robot.

  A robot position adjusting system according to a fourth aspect of the present invention includes a work robot having a camera in a factory line, a mobile robot including an automated guided vehicle for moving the work robot, and control of the work robot. A robot position adjusting system including a robot control unit for performing, wherein the robot control unit uses a learned neural network to convert image data captured by the camera at each stop position of the automatic guided vehicle. On the basis of the position correctness determination unit that determines whether or not there is a problem in the position of the work robot based on the determination result by the position correctness determination unit, when there is a problem in the position of the work robot, The robot is controlled to adjust the position.

  In this robot position adjusting system, the mobile robot is commonly used in a plurality of lines in the factory, and the position correct/wrong determination unit determines the position of the mobile robot in any one of the plurality of lines. Also at this time, whether or not there is a problem in the position of the work robot may be determined based on the image data taken by the camera at each stop position of the automatic guided vehicle.

  A robot position adjusting system according to a fifth aspect of the present invention includes a work robot having a camera in a factory line, a dolly on which the work robot is mounted, and a robot controller that controls the work robot. A robot position adjusting system including a computer that communicates with the work robot, wherein the work robot transmits image data captured by the camera at each work position on the line to the computer. A robot side transmitter, the robot controller moves the work robot based on an instruction command received from the computer, and the computer transmits the instruction command to the robot controller. And a position correctness determination unit that determines whether there is a problem in the position of the work robot based on the image data transmitted from the robot side transmission unit using a learned neural network, and the position. As a result of the determination by the correctness determination unit, when there is a problem in the position of the work robot, an instruction command for adjusting the position of the work robot is sent to the robot control unit using the computer side transmission unit. And a command transmission control unit for controlling transmission.

  In this robot position adjusting system, the work robot is commonly used in a plurality of lines in the factory, and the position correct/wrong determination unit is configured such that the work robot uses any one of the plurality of lines. Even when the robot is located at the position, whether or not there is a problem in the position of the work robot may be determined based on the image data transmitted from the robot side transmission unit.

  In this robot position adjustment system, the position correctness determination unit determines whether or not there is a problem in the position of the arm of the work robot based on the image data transmitted from the robot side transmission unit, The command command that the command transmission control unit controls to transmit may be an command command for adjusting the position of the arm of the work robot.

  A robot position adjusting system according to a sixth aspect of the present invention includes a work robot in a factory line having a camera, a trolley in which the work robot is mounted, and a robot control unit which controls the work robot. In the robot position adjusting system, the robot control unit uses a learned neural network, based on image data taken by the camera at each work position of the work robot, based on the image data of the work robot. A position correctness determination unit for determining whether or not there is a problem in position is provided, and when there is a problem in the position of the work robot as a result of the determination by the position correctness determination unit, the position of the work robot is adjusted. To control.

  In this robot position adjusting system, the mobile robot is commonly used in a plurality of lines in the factory, and the position correct/wrong determination unit determines the position of the mobile robot in any one of the plurality of lines. Also in this case, whether or not there is a problem in the position of the work robot may be determined based on the image data taken by the camera at each work position of the work robot.

  According to the learning system of the first aspect of the present invention, the image data transmitted from the robot side transmission unit (image data photographed by the camera at each stop position of the automatic guided vehicle) and the work input by the user Machine learning of a neural network can be performed based on position correctness information indicating whether or not there is a problem in the position of the robot for use. Then, the learned neural network after the machine learning can determine whether or not there is a problem in the position of the work robot based on the image data transmitted from the robot side transmission unit. As a result, even if the stop position of the automatic guided vehicle deviates from the predetermined stop position determined in advance, the positional deviation of the work robot due to the deviation of the stop position of the automatic guided vehicle is at a problem level. Since it can be determined whether or not there is a problem in the position of the work robot, it is possible to prevent work troubles caused by the work robot based on the result of this determination.

  According to the learning system of the second aspect of the present invention, the image data transmitted from the robot side transmitter (the image data photographed by the camera at each work position on the line of the work robot) and the user input Machine learning of the neural network can be performed based on the position correctness information indicating whether or not there is a problem in the position of the work robot. Then, the learned neural network after the machine learning can determine whether or not there is a problem in the position of the work robot based on the image data transmitted from the robot side transmission unit. As a result, even if the stop position of the trolley deviates from a predetermined predetermined stop position, whether or not the position deviation of the work robot due to the deviation of the stop position of the dolly is at a problematic level (work Since it is possible to determine whether or not there is a problem in the position of the work robot, it is possible to prevent work troubles caused by the work robot based on the result of the determination.

  According to the robot position adjusting system of the third aspect of the present invention, the computer has a problem in the position of the work robot based on the image data transmitted from the robot side transmitting unit using the learned neural network. It is determined whether or not there is a problem with the position of the work robot as a result of this determination, and control is performed to send an instruction command for adjusting the position of the work robot to the robot control unit. Then, the robot controller moves the work robot based on the instruction command received from the computer to adjust the position of the work robot. As a result, even if the stop position of the automatic guided vehicle deviates from the predetermined stop position determined in advance, the positional deviation of the work robot due to the deviation of the stop position of the automatic guided vehicle is at a problem level. It is possible to determine whether or not there is a problem with the position of the work robot, and as a result of this determination, when there is a problem with the position of the work robot, the position of the work robot can be adjusted. Therefore, it is possible to prevent a work trouble caused by the work robot.

  According to the robot position adjusting system of the fourth aspect of the present invention, the robot control unit uses the learned neural network to perform work based on the image data taken by the camera at each stop position of the automatic guided vehicle. It is determined whether or not there is a problem with the position of the robot, and as a result of this determination, when there is a problem with the position of the work robot, control is performed to adjust the position of the work robot. As a result, even if the stop position of the automatic guided vehicle deviates from the predetermined stop position determined in advance, the positional deviation of the work robot due to the deviation of the stop position of the automatic guided vehicle is at a problem level. It is possible to determine whether or not there is a problem with the position of the work robot, and as a result of this determination, when there is a problem with the position of the work robot, the position of the work robot can be adjusted. Therefore, it is possible to prevent a work trouble caused by the work robot.

  According to the robot position adjusting system of the fifth aspect of the present invention, the computer has a problem in the position of the work robot based on the image data transmitted from the robot side transmitting unit using the learned neural network. It is determined whether or not there is a problem with the position of the work robot as a result of this determination, and control is performed to send an instruction command for adjusting the position of the work robot to the robot control unit. Then, the robot controller moves the work robot based on the instruction command received from the computer to adjust the position of the work robot. As a result, even if the stop position of the trolley deviates from a predetermined predetermined stop position, whether or not the position deviation of the work robot due to the deviation of the stop position of the dolly is at a problematic level (work It is possible to adjust the position of the work robot when there is a problem in the position of the work robot as a result of this determination. Therefore, it is possible to prevent a work trouble caused by the work robot.

  According to the robot position adjusting system of the sixth aspect of the present invention, the robot control unit uses the learned neural network to perform the work operation based on the image data taken by the camera at each work position of the work robot. It is determined whether or not there is a problem with the position of the robot, and as a result of this determination, when there is a problem with the position of the work robot, control is performed to adjust the position of the work robot. As a result, even if the stop position of the trolley deviates from a predetermined predetermined stop position, whether or not the position deviation of the work robot due to the deviation of the stop position of the dolly is at a problematic level (work It is possible to adjust the position of the work robot when there is a problem in the position of the work robot as a result of this determination. Therefore, it is possible to prevent a work trouble caused by the work robot.

FIG. 3 is a side view of the mobile robot in the learning/robot position adjusting system according to the first embodiment of the present invention. (A) and (b) are the electric block block diagram of the automatic guided vehicle of the same mobile robot, and the electrical block block diagram of the rotary laser radar of this automatic guided vehicle, respectively. The electric block block diagram of the said learning / robot position adjustment system. The functional block block diagram of CPU of the server in FIG. The figure which shows the mode of operation of the robot in the facility (machining center) arrange|positioned at the factory line. Explanatory drawing at the time of using the said mobile robot in common in several lines in a factory. Explanatory drawing at the time of using the said mobile robot in common in the some line in which the equipment is arrange|positioned at the both sides of a traveling path. The electric block block diagram of the robot position adjustment system which stored the learned arm position correctness determination NN and the arm position adjustment program in the memory of the centralized control operation panel. The electric block block diagram of the robot position adjustment system which stored the learned arm position correctness determination NN and the arm position adjustment program in the memory of the robot controller. The electrical block block diagram of the robot position adjustment system which stored the learned arm position correctness determination NN and the arm position adjustment program in the memory of the robot controller mounted in the robot. The side view of the robot with a trolley|bogie in the learning / robot position adjustment system of the 2nd Embodiment of this invention. The electric block block diagram of the learning and robot position adjustment system. Explanatory drawing at the time of using the said robot with a trolley|bogie commonly in several lines in a factory. Explanatory drawing of the operation|work in the factory which has several conventional lines.

  Hereinafter, a learning system and a robot position adjusting system according to embodiments embodying the present invention will be described with reference to the drawings.

  First, a learning system according to a first embodiment of the present invention and a mobile robot in a robot position adjusting system will be described with reference to FIG. The mobile robot 1 includes a robot 2 which is a work robot in a factory line, and an automatic guided vehicle 3 which moves the robot 2. As shown in FIG. 1, the robot 2 is mounted on the pedestal 15 of the automated guided vehicle 3, and along with the movement and stop of the automated guided vehicle 3, each work position on the line (position of each facility on the line). ), and then stop. The robot 2 described above includes a camera 4, an arm 5, and a hand 6. The camera 4 has a built-in image sensor, takes images of the periphery of the robot 2 every moment, and the centralized control operation panel 7 and server shown in FIG. 3 are taken via the robot controller 9 (see FIG. 3). Send to 8. The arm 5 is, for example, a vertical articulated robot arm or a horizontal articulated robot arm.

  The camera 4 of the mobile robot 1 may be attached to the side of the hand 6 as shown by the solid line in FIG. 1, or may be attached on the base 2a of the robot 2 as shown by the broken line in FIG. Alternatively, it may be attached to the pole 16 installed on the pedestal 15 of the automated guided vehicle 3. In FIG. 1, the camera mounted on the base 2a of the robot 2 is denoted by 4', and the camera mounted on the pole 16 is denoted by 4".

  The automated guided vehicle 3 includes a rotary laser radar 11, front wheels 13a, rear wheels 13b, front and rear wheel encoder-equipped motor units 12a and 12b, a handle 14, and a pedestal 15. The number of the front wheels 13a is one or two, and the number of the rear wheels 13b is two. The handle 14 is gripped by the user when moving the mobile robot 1 from one line to another line (see FIG. 6). The pedestal 15 is a base on which the robot 2 is placed.

  Next, with reference to FIGS. 2A and 2B in addition to FIG. 1, the electrical block configuration of the automatic guided vehicle 3 will be described. As shown in FIG. 2B, the rotary laser radar 11 described above includes a laser projector 11a that emits a laser beam and a reflector R (see FIG. 2A) for the laser beam emitted from the laser projector 11a. A laser receiver 11b formed of a photodiode for receiving the reflected light, a rotary base 11d for rotatably supporting the radar main body 11c including the laser projector 11a and the laser receiver 11b, and a rotary base 11d are rotated. And a motor unit 11e with an encoder for.

  Further, the automatic guided vehicle 3 includes an AGV controller 20 that controls and calculates the entire apparatus. The AGV controller 20 controls, for example, the rotation of the rotary base 11d by the motor unit 11e with an encoder, controls the laser projector 11a and the laser receiver 11b, and drives circuits 21a and 21b and steering circuits 22a and 22b described later. And the detection (calculation) of the distance and direction to each reflector R described later.

  The automated guided vehicle 3 (the AGV controller 20 of the automated guided vehicle) is arranged on the traveling path (see 76a to 76c in FIG. 6) in the factory line from the rotary laser radar 11 by using the rotary laser radar 11 described above. The distance and direction to each reflector R is detected. The AGV controller 20 obtains the distance to each of the reflectors R based on the time from the emission of the laser light by the laser projector 11a to the reception of the reflected light from each reflector R by the laser receiver 11b. Further, the AGV controller 20 obtains the rotation angle of the rotary base 11d based on the output value from the encoder incorporated in the motor unit 11e with an encoder, so that the reflector R from the laser receiver 11b is output from each reflector R. The direction of each reflector R is detected when the reflected light is received.

  The AGV controller 20 arranges the reflectors R along the traveling path (of the automatic guided vehicle 3) in the factory line, and the AGV controller 20 detects the distance and the direction to each of the reflectors R, thereby performing the automatic transfer. The vehicle 3 can be driven at an appropriate position on the road.

  The motor units with encoders 12a and 12b shown in FIG. 1 and FIG. 2A drive and steer the front wheels 13a and the rear wheels 13b, respectively. Further, the drive circuit 21a and the steering circuit 22a shown in FIG. 2A are circuits for driving and steering the front wheels 13a, and the drive circuit 21b and the steering circuit 22b are for driving and steering the rear wheels 13b. Circuit.

  Next, an electrical block configuration of the learning/robot position adjusting system 10 according to the first embodiment will be described with reference to FIG. The learning/robot position adjusting system 10 includes the constituent elements of both the learning system according to claims 1 and 2 and the robot position adjusting system according to claims 5 to 7. That is, the learning/robot position adjusting system 10 corresponds to both the learning system according to claims 1 and 2 and the robot position adjusting system according to claims 5 to 7. As shown in FIG. 3, the learning/robot position adjusting system 10 includes a mobile robot 1, a robot controller 9 (robot controller) that is a controller for controlling the robot 2 in the mobile robot 1, and a centralized control operation panel. 7, a server 8 on the cloud (“computer” in the claims) that communicates with the centralized control operation panel 7 via a network (Internet 17), and an auxiliary operation panel 18.

  The robot 2 of the mobile robot 1 includes a transmission/reception line 31 (robot side transmission unit) in addition to the camera 4, the arm 5, and the hand 6. The transmission/reception line 31 is a circuit for wired or wireless communication with the robot controller 9. The transmission/reception line 31 transmits the image data taken by the camera 4 at each stop position of the automatic guided vehicle 3 to the server 8 via the robot controller 9 and the centralized control operation panel 7.

  The robot controller 9 is configured by using a micro controller, and controls the operation of the arm 5 and the hand 6 of the robot 2 by using a program for robot work. Further, the robot controller 9 moves the robot 2 based on the instruction command received from the server 8 via the Internet 17 and the centralized control operation panel 7. The robot controller 9 includes a CPU 33, a transmission/reception line 34, and a memory 35. The CPU 33 controls and calculates the entire robot controller 9. The transmission/reception line 34 is a circuit for wired or wireless communication with (the transmission/reception line 31 of) the robot 2 and (the transmission/reception line 42 of) the centralized control operation panel 7. The memory 35 stores data such as the above-mentioned robot work program.

  The centralized control operation panel 7 is used for controlling various devices on the line and for inputting instructions to various devices. The central control operation panel 7 includes a CPU 41, a transmission/reception line 42, a memory 43, an operation unit 44 (position correct/incorrect information input unit in claims), and a monitor 45. The operation unit 44 of the centralized control operation panel 7 performs an input instruction operation to the robot controller 9 for setting the operation of the robot 2 and an arm position correctness determination neural network (hereinafter, referred to as “arm position correctness determination” on the server 8 side described later). "NN") 55 for inputting position correctness information to create a training (learning) data set for machine learning. This position correctness information indicates whether or not there is a problem in the position of the robot 2 (more accurately, the position of the arm 5 of the robot 2) when the robot 2 is working at each facility on the line. This is information (so-called annotation data) to be shown.

  The operator on the centralized control operation panel 7 sees on the monitor 45 the images around the robot 2 in operation, which are sent from the camera 4 of the robot 2 at each stop position of the automatic guided vehicle 3 (each work position of the robot 2). If it is determined that there is no problem in the position of the robot 2 (more precisely, the position of the arm 5 of the robot 2), the position indicating that there is no problem in the position of the robot 2 using the operation unit 44. If correctness information is input and it is determined that there is a problem in the position of the robot 2, the position correctness information indicating that there is a problem in the position of the robot 2 is input using the operation unit 44. The above-mentioned "there is a problem with the position of the robot 2" means that the position of the robot 2 (more accurately, the position of the arm 5 of the robot 2) is deviated, so that the work of the robot 2 is stopped, This means a case where work troubles such as a failure of a work such as machining or assembly by the robot 2 actually occur, and a case where these troubles are not unusual.

  The server 8 includes a CPU 51, a transmission/reception line 52 (“computer-side transmission unit” in claims), a hard disk 53 (“neural network storage unit” in claims), an operation unit 58, and a memory 59. There is. The CPU 51 controls/calculates the entire server 8. The hard disk 53 stores a training data set 54, an arm position correctness determination NN 55, a learning program 56, and an arm position adjusting program 57.

  The above-mentioned arm position correctness determination NN55 is image data taken by the camera 4 of the robot 2 at each stop position of the automated guided vehicle 3 (each work position of the robot 2) transmitted from (the transmission/reception line 31 of) the robot 2. Is a neural network that determines whether or not there is a problem with the position of the arm 5 of the (current) robot 2 based on the above. The arm position correctness determination NN55 is a type of neural network that performs object recognition (classification of images), and is preferably based on, for example, a convolutional neural network (Convolutional Neural Network).

  The training data set 54 is an image when the above position correctness information is input from the images around the robot 2 in operation, which is sent from the camera 4 of the robot 2 at each stop position of the automatic guided vehicle 3. (Data of image) and position correctness information corresponding to this image data. The learning program 56 is a program for machine learning the arm position correctness determination NN55 based on the image data and the position correctness information stored in the training data set 54. The arm position adjustment program 57 is a program for adjusting the position of the arm 5 of the robot 2 when there is a problem in the position of the arm 5 of the robot 2 as a result of the determination using the arm position correctness determination NN55. Is.

  FIG. 4 shows functional blocks of the CPU 51 on the server 8 side. The CPU 51 on the server 8 side includes a machine learning unit 61, a position correctness determination unit 62, and a command transmission control unit 63. The machine learning unit 61 inputs the above-mentioned image data stored in the training data set 54 and position correctness information (image data transmitted from the transmission/reception line 31 of the robot 2 and the operation unit 44 of the centralized control operation panel 7 by the user. The machine learning of the arm position correctness determination NN55 is performed based on the obtained position correctness information). The position correctness determination unit 62 uses the learned arm position correctness determination NN55 to the image data (taken by the camera 4 at each stop position of the automated guided vehicle 3) transmitted from the transmission/reception line 31 of the robot 2. Based on this, it is determined whether or not there is a problem with the position of the arm 5 of the robot 2. When the position correctness determination unit 62 determines that the position of the arm 5 of the robot 2 has a problem, the command transmission control unit 63 uses the transmission/reception line 52 to inform the robot controller 9 of the position of the arm 5 of the robot 2. Control so as to send an instruction command for adjusting.

  Next, referring to FIG. 5 in addition to FIGS. 3 and 4 described above, the adjustment of the position of the arm 5 of the robot 2 will be further described. FIG. 5 shows how the robot 2 works when the equipment arranged on the factory line is the machining center 71. In FIG. 5, the robot 2 holds a work 72 in the hand 6, and when the position of the arm 5 of the robot 2 at the time of work is correct, the work 72 has a fixed position corresponding to the jig 73 of the machining center 71. It is set at (the position shown by the broken line in the figure) and cut by the cutting tool 74. However, when there is a problem in the position of the arm 5 of the robot 2 during work when the stop position of the automated guided vehicle 3 deviates from a predetermined stop position, the work of the robot 2 is stopped or the robot 2 is stopped. There is a possibility of causing work troubles such as failure of work such as cutting by 2.

  In the learning/robot position adjusting system 10 of the present embodiment, when the arm position correctness determination NN55 is learned, as described above, when there is a problem in the position of the arm 5 of the robot 2 (when a trouble in work actually occurs). , And in the case where these troubles would have occurred), the operator of the centralized control operation panel 7 uses the operation unit 44 to indicate whether the position of the arm 5 of the robot 2 is incorrect. Enter the information. On the contrary, when there is no problem in the position of the arm 5 of the robot 2, the operator inputs the position correctness information indicating that there is no problem in the position of the arm 5 of the robot 2 using the operation unit 44. Then, the server 8 (the machine learning unit 61 thereof) uses the image data transmitted from the camera 4 on the robot 2 side and the operator (from the operation unit 44 of the centralized control operation panel 7) when the robot 2 is working. Machine learning of the arm position correctness determination NN55 is performed based on the position correctness information input by the user). At this point, even if there is a problem in the position of the arm 5 of the robot 2, the position of the arm 5 of the robot 2 using the arm position correctness determination NN 55 on the server 8 side and the arm position adjustment program 57 ( (Automatic) adjustment is not performed.

  When the machine learning of the arm position correctness determination NN55 by the server 8 has progressed to some extent and the arm position correctness determination NN55 can be regarded as a learned neural network, for example, the system administrator of the server 8 side The operation unit 58 instructs to start (automatic) adjustment processing of the position of the arm 5 of the robot 2 using the arm position correctness determination NN 55 on the server 8 side and the arm position adjustment program 57.

  When the (automatic) adjustment processing of the position of the arm 5 of the robot 2 described above is started, the CPU 51 of the server 8 (the position correctness determination unit 62 thereof) uses the learned arm position correctness determination NN55 to detect the robot 2 Based on the image data transmitted from the transmission/reception line 31 (image data around the robot 2 transmitted from the camera 4 when the robot 2 is working), it is determined whether or not there is a problem in the position of the arm 5 of the robot 2. .. Then, the CPU 51 of the server 8 (the command transmission control unit 63 thereof) uses the transmission/reception line 52 when the position of the arm 5 of the robot 2 has a problem as a result of the determination using the learned arm position correctness determination NN55. Then, the robot controller 9 is controlled to transmit an instruction command for adjusting the position of the arm 5 of the robot 2. Then, the robot controller 9 moves the robot 2 based on the instruction command received from the server 8 to adjust the position of the arm 5 of the robot 2. As a result, even if the stop position of the automatic guided vehicle 3 deviates from a predetermined predetermined stop position, the positional deviation of the arm 5 of the robot 2 due to the deviation of the stopped position of the automatic guided vehicle 3 causes a problem. If there is a problem with the position of the arm 5 of the robot 2, it is determined whether there is a problem with the position of the arm 5 of the robot 2 or not. The position of 5 can be adjusted. Therefore, even if the stop position of the automatic guided vehicle 3 deviates from a predetermined stop position, it is possible to prevent a trouble in working by the robot 2.

  During the position adjustment process of the arm 5 of the robot 2, the learned arm position correctness determination NN55 determines that there is no problem in the position of the arm 5 of the robot 2 based on the image data transmitted from the transmission/reception line 31 of the robot 2. Until then, the position of the arm 5 of the robot 2 is repeatedly adjusted.

  In this embodiment, as shown in FIG. 6, the mobile robot 1 is commonly used in a plurality of lines in a factory. Specifically, the operator grips the handle 14 of the mobile robot 1 shown in FIG. 5, and moves the mobile robot 1 that was performing the work on the line A shown in FIG. 6 from the line A to the line B, for example. Then, the mobile robot 1 is caused to perform the work on the line B. In this way, the mobile robot 1 is alternately used in the lines A to C according to the operation schedule of each line of the day.

  In FIG. 6, reference numerals 79a to 79f indicate facilities such as machining centers arranged on the lines A to C, and reference numerals 76a to 76c indicate running paths on the respective lines A to C. Further, reference numerals 77a to 77c indicate parts feed devices in the respective lines A to C, reference numerals 78a to 78c respectively indicate finished product discharging conveyors in the respective lines A to C, and reference numerals 18a to 18c respectively. , Respectively show the auxiliary operation panel in each of the lines A to C. The parts feed devices 77a to 77c are devices for supplying a work to the mobile robot 1. Further, the finished product discharge conveyors 78a to 78c are conveyors for discharging finished products after the processing or assembling process by the facilities 79a to 79f such as machining centers.

  Further, (1) to (4) in FIG. 6 are respective stop positions of the automated guided vehicle 3 on the lines A to C. The above (1) is the position where the robot 2 receives the work (part), and (2) and (3) are the positions where the robot 2 performs the first and second work in each line, ( 4) is the position at which the robot 2 places the finished product on the finished product discharge conveyors 78a to 78c (or inside the cardboard on the finished product discharge conveyors 78a to 78c).

  As shown in FIG. 6, when the mobile robot 1 is used in common in a plurality of lines in a factory, compared with the case where it is used in only one line, the stop position of the automated guided vehicle 3 on the line and Since there are many types and types of equipment (equipment 79a to 79f in FIG. 6), the stop position of the automated guided vehicle 3 is likely to deviate from a predetermined stop position. The above troubles are likely to occur.

  However, according to the learning/robot position adjustment system 10 of the present embodiment, when the machine learning of the arm position correctness determination NN55 progresses to some extent and the arm position correctness determination NN55 becomes a state in which it can be regarded as a learned neural network, The CPU 51 of the server 8 (the position correctness determination unit 62 thereof) uses the learned arm position correctness determination NN55 to determine whether the mobile robot 1 is located on any of the plurality of lines. Based on the image data transmitted from the transmission/reception line 31, it is determined whether or not there is a problem in the position of the arm 5 of the robot 2. The CPU 51 of the server 8 (the command transmission control unit 63 thereof) uses the transmission/reception line 52 when there is a problem in the position of the arm 5 of the robot 2 as a result of the determination using the learned arm position correctness determination NN55. Then, the robot controller 9 is controlled to transmit an instruction command for adjusting the position of the arm 5 of the robot 2. Therefore, even when the mobile robot 1 is commonly used in a plurality of lines in a factory, the position of the arm 5 of the robot 2 can be adjusted if there is a problem in the position of the arm 5 of the robot 2. .

  The learning/robot position adjusting system 10 of the present embodiment and a factory line to which the mobile robot 1 can be applied are lines in which the facilities 79a to 79f are arranged on one side of the traveling paths 76a to 76c as shown in FIG. However, the line may be a line in which the facilities 79g to 79n are arranged on both sides of the traveling paths 76d and 76e as shown in FIG.

  In FIG. 7, reference numerals 79g to 79n indicate facilities such as machining centers arranged on the lines A and B, and reference numerals 76d and 76e indicate traveling paths on the lines A and B, respectively. In addition, reference numerals 77d to 77g indicate parts feed devices in the respective lines A and B, reference numerals 78d to 78g indicate finished product discharge conveyors in the respective lines A and B, and reference numerals 18d and 18e respectively. , And auxiliary operation panels on lines A and B, respectively.

  When the machine learning of the arm position correctness determination NN55 by the server 8 described above progresses and the arm position correctness determination NN55 becomes a state in which it can be regarded as a learned neural network, as shown in FIG. 8 and FIG. The arm position correctness determination NN81 may be stored in the memory 43 of the centralized control operation panel 7 or the memory 35 of the robot controller 9 together with the arm position adjustment program 57. As shown in FIG. 8, in the robot position adjustment system 80 in which the learned arm position correctness determination NN81 and the arm position adjustment program 57 are stored in the memory 43 of the centralized control operation panel 7, the central control operation panel 7 is a Corresponds to the "computer" of the robot position adjustment system in. Further, as shown in FIG. 9, the robot position adjusting system 83 is a robot position adjusting system in which the learned arm position correctness determination NN81 and the arm position adjusting program 57 are stored in the memory 35 of the robot controller 9. In these FIG. 8 and FIG. 9, the same reference numerals are given to the electrical blocks equivalent to those in FIG.

  Further, as in the robot position adjusting system 85 shown in FIG. 10, the robot 2 itself is provided with a robot controller 86 constituted by a processor such as a micro controller, and a memory 88 in the robot controller 86 is provided with a learned arm. The position correctness determination NN81 and the arm position adjustment program 57 may be stored. In FIG. 10 as well, electrical blocks equivalent to those in FIG. 3 are assigned the same reference numerals and explanations thereof are omitted.

  However, if there are many changes in the type, arrangement, number, etc. of equipment in the factory line to which the learning/robot position adjustment system 10 is applied, the arm position correctness determination NN55 stored in the hard disk 53 of the server 8 shown in FIG. While constantly continuing the machine learning described above, it is determined whether or not there is a problem in the position of the arm 5 of the robot 2 by using the arm position correctness determination NN 55 and the arm position adjustment program 57 of the server 8 and the arm of the robot 2 It is desirable to perform the position adjustment processing of No. 5.

  As described above, according to the learning/robot position adjusting system 10 of the first embodiment, image data transmitted from the transmission/reception line 31 of the robot 2 (taken by the camera 4 at each stop position of the automatic guided vehicle 3). Machine learning of the arm position correctness determination NN55 can be performed based on the image data) and the position correctness information input by the operator (user) from the operation unit 44 of the centralized control operation panel 7.

  Further, according to the learning/robot position adjusting system 10 of the first embodiment, the machine learning of the arm position correctness determination NN55 is advanced to some extent, and the arm position correctness determination NN55 is considered to be a learned neural network. After that, the server 8 determines whether or not there is a problem in the position of the arm 5 of the robot 2 based on the image data transmitted from the transmission/reception line 31 of the robot 2 by using the learned arm position correctness determination NN55. If there is a problem with the position of the arm 5 of the robot 2 as a result of the determination, the robot controller 9 is controlled to transmit an instruction command for adjusting the position of the arm 5 of the robot 2. . Then, the robot controller 9 moves the robot 2 based on the instruction command received from the server 8 to adjust the position of the arm 5 of the robot 2. As a result, even if the stop position of the automatic guided vehicle 3 deviates from a predetermined predetermined stop position, the positional deviation of the arm 5 of the robot 2 due to the deviation of the stopped position of the automatic guided vehicle 3 causes a problem. If there is a problem with the position of the arm 5 of the robot 2, it is determined whether there is a problem with the position of the arm 5 of the robot 2 or not. The position of 5 can be adjusted. Therefore, it is possible to prevent a trouble in the work performed by the robot 2.

  Even when the learned arm position correctness determination NN81 and the arm position adjustment program 57 shown in FIG. 8 are stored in the memory 43 of the centralized control operation panel 7, the arm position correctness determination NN55 is a learned neural network. It is possible to obtain the same actions and effects as those of the learning/robot position adjusting system 10 after the state that can be regarded as. Specifically, whether the centralized control operation panel 7 has a problem in the position of the arm 5 of the robot 2 based on the image data transmitted from the transmission/reception line 31 of the robot 2 using the learned arm position correctness determination NN81. It is determined whether or not there is a problem with the position of the arm 5 of the robot 2 as a result of this determination, and the robot controller 9 is controlled to transmit an instruction command for adjusting the position of the robot 2. Then, the robot controller 9 moves the robot 2 based on the instruction command received from the centralized control operation panel 7 to adjust the position of the arm 5 of the robot 2. As a result, even if the stop position of the automatic guided vehicle 3 deviates from a predetermined predetermined stop position, the positional deviation of the arm 5 of the robot 2 due to the deviation of the stopped position of the automatic guided vehicle 3 causes a problem. It is possible to adjust the position of the arm 5 of the robot 2 when there is a problem in the position of the arm 5 of the robot 2 as a result of this judgment. Therefore, it is possible to prevent a trouble in the work performed by the robot 2.

  Also in the robot position adjusting system 83 shown in FIG. 9 and the robot position adjusting system 85 shown in FIG. 10, the robot controller 9 or the robot controller 86 uses the learned arm position correctness determination NN81 to detect the automatic guided vehicle 3. Based on the image data taken by the camera 4 at each stop position, it is determined whether or not there is a problem with the position of the arm 5 of the robot 2, and as a result of this determination, there is a problem with the position of the arm 5 of the robot 2. At some times, control is performed to adjust the position of the arm 5 of the robot 2. As a result, even if the stop position of the automatic guided vehicle 3 deviates from a predetermined predetermined stop position, the positional deviation of the arm 5 of the robot 2 due to the deviation of the stopped position of the automatic guided vehicle 3 causes a problem. It is possible to adjust the position of the robot 2 when there is a problem in the position of the robot 2 as a result of this determination by determining whether or not there is a certain level (whether or not there is a problem in the position of the robot 2). . Therefore, it is possible to prevent a trouble in the work performed by the robot 2.

  Next, a learning/robot position adjusting system 95 according to a second embodiment of the present invention and a trolley-equipped robot 91 in the learning/robot position adjusting system 95 will be described with reference to FIGS. 11 to 13. 11 and 13, the same members as those in FIGS. 1 and 6 are designated by the same reference numerals, and the description thereof will be omitted. Further, in FIG. 12, electrical blocks equivalent to those in FIG. 3 are designated by the same reference numerals, and description thereof will be omitted.

  FIG. 11 shows a robot with a trolley 91 in the learning/robot position adjusting system 95 of the second embodiment. The learning/robot position adjusting system 10 of the first embodiment includes the mobile robot 1 in which the robot 2 is mounted (mounted) on the pedestal 15 of the automatic guided vehicle 3. The robot position adjustment system 95 includes a trolley-equipped robot 91 in which the robot 2 is mounted (mounted) on the pedestal 96 of the trolley 92 instead of the mobile robot 1 described above. Other than this, the learning/robot position adjusting system 10 of the first embodiment is the same as the learning/robot position adjusting system 95 of the second embodiment.

  The trolley 92 includes front and rear wheels 93 and a handle 97 in addition to the pedestal 96 to which the robot 2 is attached. Similar to the handle 14 of the automated guided vehicle 3 according to the first embodiment, the handle 97 is gripped by the user when moving the robot 91 with a carriage from one line to another line (see FIG. 13). It In the second embodiment, as shown in FIG. 13, rails 94 (rails 94a to 94c in the example of FIG. 13) are provided on the travel routes (traveling paths 76a to 76c in the example of FIG. 13) in each line of the factory. ) Is provided, and wheels 93 on the front and rear of the carriage 92 are fitted into the rail 94 and move on the rail 94.

  Also in this embodiment, as shown in FIG. 13, the robot 2 attached to the carriage-equipped robot 91 is commonly used in a plurality of lines in a factory. Specifically, the operator grips the handle 97 of the trolley-equipped robot 91 shown in FIG. 11, and, for example, the trolley-equipped robot 91 that was performing the work on the line A shown in FIG. The robot 2 of the trolley-equipped robot 91 to the respective work positions on the line B by moving the wheels 93 to and from the front and rear wheels 93 of the trolley 92 by removing them from the rails 94a on the line A and fitting them on the rails 94b on the line B. It is made to move and it is made to work using each equipment of line B. As described above, the carriage-equipped robot 91 is alternately used in the lines A to C according to the operation schedule of each line of the day.

  FIG. 12 shows an electrical block configuration of the learning/robot position adjusting system 95 of the second embodiment. This electrical block configuration is the same as the electrical block configuration of the learning/robot position adjusting system 10 of the first embodiment shown in FIG. 3 except that the mobile robot 1 is replaced by the trolley-equipped robot 91.

  According to the learning/robot position adjusting system 95 of the second embodiment, similar to the learning/robot position adjusting system 10 of the first embodiment, image data transmitted from the transmission/reception line 31 of the robot 2 (of the robot 2). At each work position on the line, the arm position correctness determination is made based on the image data taken by the camera 4) and the position correctness information input by the operator (user) from the operation unit 44 of the centralized control operation panel 7. Machine learning of NN55 can be performed.

  Further, according to the learning/robot position adjustment system 95 of the second embodiment, the machine learning of the arm position correctness determination NN55 is advanced to some extent, and the arm position correctness determination NN55 is considered to be a learned neural network. After that, the server 8 determines whether or not there is a problem in the position of the arm 5 of the robot 2 based on the image data transmitted from the transmission/reception line 31 of the robot 2 using the learned arm position correctness determination NN55. If there is a problem with the position of the arm 5 of the robot 2 as a result of the determination, the robot controller 9 is controlled to transmit an instruction command for adjusting the position of the arm 5 of the robot 2. .. Then, the robot controller 9 moves the robot 2 based on the instruction command received from the server 8 to adjust the position of the arm 5 of the robot 2. As a result, even if the stop position of the carriage 92 deviates from a predetermined stop position, whether the position deviation of the arm 5 of the robot 2 caused by the deviation of the stop position of the carriage 92 has a problematic level. Whether or not there is a problem with the position of the arm 5 of the robot 2 is determined. As a result of this determination, when there is a problem with the position of the arm 5 of the robot 2, the position of the arm 5 of the robot 2 is determined. Can be adjusted. Therefore, it is possible to prevent a trouble in the work performed by the robot 2.

  Also in the second embodiment, if the machine learning of the arm position correctness determination NN55 by the server 8 progresses to some extent and the arm position correctness determination NN55 becomes a state in which it can be regarded as a learned neural network, the first embodiment is performed. Similarly to the robot position adjusting system 80 and the robot position adjusting system 83 (see FIGS. 8 and 9) in the embodiment, the learned arm position correctness determination NN81 and the arm position adjusting program 57 are stored in the memory 43 of the central control operation panel 7, Alternatively, it may be stored in the memory 35 of the robot controller 9. Further, similarly to the robot position adjusting system 85 (see FIG. 10) in the first embodiment, the robot controller 86 is mounted on the robot 2 itself, and the learned arm position correct/incorrect is stored in the memory 88 in the robot controller 86. The determination NN81 and the arm position adjustment program 57 may be stored.

  Also in the second embodiment, as in the robot position adjustment system 80 in the first embodiment shown in FIG. 8, the learned arm position correctness determination NN81 and the arm position adjustment program 57 are stored in the memory of the centralized control operation panel 7. When stored in 43, it is possible to obtain the same operation and effect as the learning/robot position adjusting system 95 after the arm position correctness determination NN55 becomes a state in which it can be regarded as a learned neural network.

  Further, also in the second embodiment, similarly to the robot position adjusting system 83 and the robot position adjusting system 85 in the first embodiment shown in FIGS. 9 and 10, the learned arm position correctness determination NN81 and the arm position adjusting program are performed. When 57 is stored in the memory 35 of the robot controller 9 or the memory 88 of the robot controller 86, the robot controller 9 or the robot controller 86 uses the learned arm position correctness determination NN81 to detect the camera at each work position of the robot 2. It is determined whether there is a problem in the position of the arm 5 of the robot 2 based on the image data captured by the robot 4, and when the result of this determination is that there is a problem in the position of the arm 5 of the robot 2, the robot 2 The arm 5 is controlled so as to adjust its position. As a result, even if the stop position of the carriage 92 deviates from a predetermined stop position, whether the position deviation of the arm 5 of the robot 2 caused by the deviation of the stop position of the carriage 92 has a problematic level. It is possible to determine whether or not there is a problem with the position of the robot 2, and as a result of this determination, when there is a problem with the position of the robot 2, the position of the robot 2 can be adjusted. Therefore, it is possible to prevent work troubles caused by the robot 2.

Modification:
The present invention is not limited to the configurations of the above-described embodiments, and various modifications can be made without departing from the spirit of the invention. Next, a modified example of the present invention will be described.

Modification 1:
In each of the above embodiments, the image data transmitted from the transmission/reception line 31 on the robot 2 side and the position correctness information input by the operator from the operation unit 44 of the centralized control operation panel 7 are transmitted via the Internet 17. The data is transmitted to the server 8 on the cloud, and the machine learning of the arm position correctness determination NN55 stored in the hard disk 53 of the server 8 is performed. However, a neural network that determines whether or not there is a problem in the position of the robot arm is stored in the hard disk of the computer installed in the factory premises, and the neural network stored in the computer installed in this factory premises. Machine learning of the network may be performed.

Modification 2:
In each of the above embodiments, the “learned neural network” in the claims is a neural network that determines whether or not there is a problem with the position of the arm 5 of the robot 2. When the position of the arm 5 of the robot 2 has a problem as a result of the determination using “. However, the learning system and the robot position adjusting system of the present invention are not limited to this. For example, the “learned neural network” is a neural network that determines whether or not there is a problem in the position of the robot hand, As a result of the determination using the learned neural network, when there is a problem in the position of the robot hand, the position of the robot hand may be adjusted. Further, the "learned neural network" is a neural network that determines whether or not there is a problem in the position of the front end, the center, or the rear end of the robot, and the result of the determination using this learned neural network, The position of the front, center, or rear end of the robot may be adjusted when there is a problem in the position of the front, center, or rear end of the robot.

Modification 3:
Further, in the above-described first embodiment, an example in which the robot 2 is mounted (mounted) on the pedestal 15 of the automatic guided vehicle 3 is shown, but the present invention is not limited to this, and for example, wheels are mounted on the robot itself. Then, the automatic guided vehicle may move the robot by pushing the back surface of the robot. Further, the robot may be attached to the front part of the automatic guided vehicle.

Modification 4:
Further, in the above-described first embodiment, an example in which the automatic guided vehicle 3 is a so-called laser guided automatic guided vehicle is shown, but the guided system of the automatic guided vehicle is not limited to this, and, for example, a magnetic The induction method may be used, or the multi-induction method using both magnetic induction and laser induction may be used.

1 Mobile robot 2 Robot (working robot)
3 Automated guided vehicle 4 Camera 7 Centralized control operation panel (computer)
8 servers (computers)
9,86 Robot controller (robot controller)
10, 95 Learning and robot position adjustment system (learning system and robot position adjustment system)
31 Transmission/reception line (robot side transmitter)
44 Operation part (position correctness information input part)
52 Transmission/reception line (transmission unit on computer side)
53 Hard Disk (Neural Network Storage)
55 Arm Position Correctness Judgment NN (Neural network for judging whether or not there is a problem in position of work robot, and learned neural network)
61 machine learning unit 62 position correctness determination unit 63 command transmission control units 80, 83, 85 robot position adjustment system 81 learned arm position correctness determination NN (learned neural network)
92 trolley A, B, C line

Claims (14)

A work robot in a factory line having a camera, and a mobile robot having an automatic guided vehicle for moving the work robot,
A position correctness information input unit for inputting position correctness information indicating whether or not there is a problem in the position of the work robot,
A learning system comprising a computer that communicates with the mobile robot,
The mobile robot includes a robot-side transmitter that transmits image data captured by the camera at each stop position of the automatic guided vehicle to the computer.
The computer is
A neural network storage unit that stores a neural network that determines whether or not there is a problem in the position of the work robot based on the image data transmitted from the robot-side transmission unit,
Learning including a machine learning unit that performs machine learning of the neural network based on the image data transmitted from the robot side transmission unit and the position correctness information input by the user from the position correctness information input unit system. The mobile robot is commonly used in a plurality of lines in the factory,
The machine learning unit, when the mobile robot is located on any line of the plurality of lines, the image data transmitted from the robot side transmission unit and the user from the position correctness information input unit. The learning system according to claim 1, wherein machine learning of the neural network is performed based on the position correctness information input by. A robot for working in a factory line, which has a camera,
A dolly equipped with the work robot,
A position correctness information input unit for inputting position correctness information indicating whether or not there is a problem in the position of the work robot,
A learning system comprising a computer that communicates with the work robot,
The work robot includes a robot-side transmitter that transmits image data captured by the camera to the computer at each work position on the line.
The computer is
A neural network storage unit that stores a neural network that determines whether or not there is a problem in the position of the work robot based on the image data transmitted from the robot-side transmission unit,
Learning including a machine learning unit that performs machine learning of the neural network based on the image data transmitted from the robot side transmission unit and the position correctness information input by the user from the position correctness information input unit system. The work robot is commonly used in a plurality of lines in the factory,
The machine learning unit, when the work robot is located on any line of the plurality of lines, the image data transmitted from the robot side transmission unit and the position correctness information input unit. The learning system according to claim 3, wherein machine learning of the neural network is performed based on the position correctness information input by the user. A work robot in a factory line having a camera, and a mobile robot having an automatic guided vehicle for moving the work robot,
A robot controller that controls the work robot;
A robot position adjusting system comprising a computer that communicates with the mobile robot,
The mobile robot includes a robot-side transmitter that transmits image data captured by the camera at each stop position of the automatic guided vehicle to the computer.
The robot controller moves the work robot based on an instruction command received from the computer,
The computer is
A computer-side transmitter that transmits the instruction command to the robot controller,
Using a learned neural network, based on the image data transmitted from the robot side transmission unit, a position correctness determination unit that determines whether there is a problem in the position of the work robot,
When there is a problem with the position of the work robot as a result of the determination by the position correctness determination unit, the computer-side transmission unit is used to instruct the robot control unit to adjust the position of the work robot. A robot position adjustment system, comprising: a command transmission control unit that controls to transmit a command. The mobile robot is commonly used in a plurality of lines in the factory,
The position correctness determination unit, based on the image data transmitted from the robot side transmission unit, when the mobile robot is located on any line of the plurality of lines, based on the image data of the work robot, The robot position adjusting system according to claim 5, wherein it is determined whether or not there is a problem in position. The position correctness determination unit, based on the image data transmitted from the robot side transmission unit, determines whether there is a problem in the position of the arm of the work robot,
The robot position according to claim 5 or 6, wherein the instruction command that the command transmission control unit controls to transmit is an instruction command for adjusting the position of the arm of the work robot. Adjustment system. A work robot having a camera in a factory line, and a mobile robot having an automatic guided vehicle for moving the work robot;
A robot position adjusting system comprising a robot control unit for controlling the work robot,
The robot controller is
Using a learned neural network, a position correctness determination unit that determines whether or not there is a problem in the position of the work robot based on image data taken by the camera at each stop position of the automatic guided vehicle. Prepare,
A robot position adjusting system that controls so as to adjust the position of the work robot when there is a problem in the position of the work robot as a result of the determination by the position correctness determination unit. The mobile robot is commonly used in a plurality of lines in the factory,
The position correctness determination unit, when the mobile robot is located on any line of the plurality of lines, based on the image data taken by the camera at each stop position of the automatic guided vehicle, 9. The robot position adjusting system according to claim 8, wherein it is determined whether or not there is a problem in the position of the work robot. A robot for working in a factory line, which has a camera,
A dolly equipped with the work robot,
A robot controller that controls the work robot;
A robot position adjusting system comprising a computer that communicates with the work robot,
The work robot includes a robot-side transmitter that transmits image data captured by the camera at each work position on the line to the computer.
The robot controller moves the work robot based on an instruction command received from the computer,
The computer is
A computer-side transmitter that transmits the instruction command to the robot controller,
Using a learned neural network, based on the image data transmitted from the robot side transmission unit, a position correctness determination unit that determines whether there is a problem in the position of the work robot,
When there is a problem with the position of the work robot as a result of the determination by the position correctness determination unit, the computer-side transmission unit is used to instruct the robot control unit to adjust the position of the work robot. A robot position adjustment system, comprising: a command transmission control unit that controls to transmit a command. The work robot is commonly used in a plurality of lines in the factory,
The position correctness determination unit, based on the image data transmitted from the robot side transmission unit, when the work robot is located on any line of the plurality of lines, the work robot. 11. The robot position adjusting system according to claim 10, wherein it is determined whether or not there is a problem with the position. The position correctness determination unit, based on the image data transmitted from the robot side transmission unit, determines whether there is a problem in the position of the arm of the work robot,
The robot position according to claim 10 or 11, wherein the instruction command that the command transmission control unit controls to transmit is an instruction command for adjusting the position of the arm of the work robot. Adjustment system. A robot for working in a factory line, which has a camera,
A dolly equipped with the work robot,
A robot position adjusting system comprising a robot control unit for controlling the work robot,
The robot controller is
Using a learned neural network, a position correctness determination unit that determines whether or not there is a problem in the position of the work robot based on image data taken by the camera at each work position of the work robot. Prepare,
A robot position adjusting system that controls so as to adjust the position of the work robot when there is a problem in the position of the work robot as a result of the determination by the position correctness determination unit. The work robot is commonly used in a plurality of lines in the factory,
The position correctness determination unit, when the work robot is located on any line of the plurality of lines, based on image data taken by the camera at each work position of the work robot, The robot position adjusting system according to claim 13, wherein it is determined whether or not there is a problem in the position of the work robot.

Images