Control parameter adjustment system

Abstract

To provide a control parameter adjustment system that identifies the robot to be controlled and optimally adjusts the parameter settings related to control commands. [Solution] A control parameter adjustment system according to one aspect of the present disclosure comprises a storage unit, an image acquisition unit, a whole image generation unit, a identification unit, a parameter generation unit, and an output unit. The storage unit stores images and specification information of multiple candidate robots in association. The image acquisition unit acquires images showing a part of the robot to be controlled. The whole image generation unit automatically generates a whole image of the robot to be controlled from the images. The identification unit compares the whole image with images of multiple candidate robots and identifies the robot corresponding to the robot to be controlled from among the multiple candidate robots. The parameter generation unit acquires specification information of the robot and generates parameter information based on the specification information. The output unit outputs the parameter information.

Description

Technical Field

[0001] The present invention relates to a control parameter adjustment system.

Background Art

[0002] When there are multiple robots used at a site, management becomes easier by controlling them with the same system. However, in this case, every time the robots used change depending on the scene, the administrator must change the settings and parameters of the control system to those suitable for the robots. Patent Document 1 describes a parameter setting method for performing image processing with parameters adapted based on an identification class.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the parameter setting method described in Patent Document 1, image processing is performed on an image signal obtained by an array sensor by an image processing unit, and the image processing parameters are set based on the class identification of the detected object in the image signal. However, the parameter setting method described in Patent Document 1 cannot be applied unless the image signal contains the detected object to such an extent that the class can be identified. Therefore, parameters cannot be set from an image signal that shows only a part of the robot.

[0005] In view of the above problems, the present disclosure provides a control parameter adjustment system that identifies a robot to be controlled and suitably adjusts parameter settings related to control commands.

Means for Solving the Problems

[0006] A control parameter adjustment system according to one aspect of this disclosure comprises a storage unit, an image acquisition unit, a whole image generation unit, a identification unit, a parameter generation unit, and an output unit. The storage unit stores images and specification information of multiple candidate robots in association. The image acquisition unit acquires images showing a part of the robot to be controlled. The whole image generation unit automatically generates a whole image of the robot to be controlled from the images. The identification unit compares the whole image with images of multiple candidate robots and identifies the robot corresponding to the robot to be controlled from among the multiple candidate robots. The parameter generation unit acquires specification information of the robot and generates parameter information based on the specification information. The output unit outputs the parameter information.

[0007] In other words, the control parameter adjustment system automatically generates a complete image from a captured image showing only a part of the robot to be controlled, using image generation AI (Artificial Intelligence), etc. This allows the control parameter adjustment system to suitably identify the robot to be controlled from among multiple candidate robots and generate parameter information. [Effects of the Invention]

[0008] According to this disclosure, a control parameter adjustment system can be provided that identifies the robot to be controlled and suitably adjusts the parameter settings related to control commands. [Brief explanation of the drawing]

[0009] [Figure 1] This is a block diagram of the control parameter adjustment system according to Embodiment 1. [Figure 2] This is a flowchart of the control parameter adjustment system according to Embodiment 1. [Figure 3] This is a block diagram illustrating the hardware configuration of a computer. [Modes for carrying out the invention]

[0010] The present invention will be described below through embodiments of the invention, but the invention claimed is not limited to the following embodiments. Furthermore, not all of the configurations described in the embodiments are necessarily essential as means of solving the problem. For clarity of explanation, the following descriptions and drawings have been omitted and simplified as appropriate. In each drawing, the same elements are denoted by the same reference numerals, and redundant explanations have been omitted where necessary.

[0011] <Embodiment 1> Referring to Figure 1, the control parameter adjustment system 1 according to Embodiment 1 will be described. Figure 1 is a block diagram of the control parameter adjustment system 1 according to Embodiment 1. The control parameter adjustment system 1 comprises a storage unit 11, an image acquisition unit 12, a whole image generation unit 13, a specification unit 14, a parameter generation unit 15, and an output unit 16. The control parameter adjustment system 1 generates a whole image of the robot to be controlled from an image showing a part of the robot to be controlled, and outputs parameter information related to control commands based on the generated whole image.

[0012] Here, the controlled robot is the robot currently being controlled by the control system, among several candidate robots that the control system can control. Candidate robots include, but are not limited to, multi-axis robots for processing machines, welding robots, or automated guided vehicles. Note that the candidate robots may also be commercially available robots.

[0013] The memory unit 11 stores images and specification information of multiple candidate robots in association. The images of the candidate robots are those that allow the entire candidate robot to be seen. For example, the images of the candidate robots may be actual photographs of the candidate robots. The images of the candidate robots may also be computer graphics (CG) images created from design data. The specification information includes information related to the specifications of the candidate robots. For example, the specification information includes design information of the candidate robots, the lengths of each part, the range of motion, or the settings of control parameters.

[0014] Here, the memory unit 11 may store information that has been pre-entered as a database. Alternatively, the memory unit 11 may connect to an external network as needed and store specification information by searching for the specification information of candidate robots. The memory unit 11 may also store information in URDF (Unified Robot Description Format) or USD (Universal Scene Description) format as specification information. The memory unit 11 may also extract and store design information from the URDF or USD format information.

[0015] The image acquisition unit 12 acquires an image showing a part of the controlled robot. For example, the image acquisition unit 12 acquires an image showing only the arm portion of the controlled robot. The image is captured by a camera mounted on the controlled robot, the control system, or the control parameter adjustment system 1. The image does not have to include identification information of the controlled robot. Identification information may be, for example, a product number, barcode, or 2D code.

[0016] The overall image generation unit 13 automatically generates an overall image of the controlled robot from a part of the controlled robot captured in the image. For example, the overall image generation unit 13 identifies the arm portion of the controlled robot captured in the image and generates an overall image of the controlled robot from the arm portion. The overall image generation unit 13 generates an overall image of the controlled robot using image generation software or image generation AI (Artificial Intelligence), etc. It is preferable that the image generation software or image generation AI used for overall image generation be pre-trained based on images of candidate robots, but it is not limited to this, and general-purpose software may also be used.

[0017] The specific part 14 compares the generated overall image with the images of a plurality of candidate robots stored in the storage part 11, and identifies the corresponding robot corresponding to the control target robot from the plurality of candidate robots. For example, the specific part 14 may use image recognition software, image recognition AI, etc. to compare the overall image with the images of the plurality of candidate robots, and identify the corresponding robot based on the image similarity. Alternatively, the specific part 14 may cause the images of the plurality of candidate robots to be learned by image recognition software or image recognition AI, and identify the corresponding robot.

[0018] The parameter generation part 15 acquires the specification information of the corresponding robot identified by the specific part 14 from the storage part 11, and generates parameter information based on the specification information. The parameter information is information for tuning various parameters related to the control command for the control target robot. Here, the control command may be paraphrased as a program.

[0019] The parameter information may, for example, indicate the optimal values of various parameters, or may indicate the adjustment values of various parameters. Alternatively, the parameter information may indicate the specification information. In this case, the control system that acquires the parameter information and determines the control command determines various parameters based on the specification information indicated by the parameter information.

[0020] The output part 16 outputs the parameter information. According to this, the control parameter adjustment system 1 can suitably adjust the parameters related to the control command for the control target robot for each robot in an environment where the robot used changes depending on the scene.

[0021] FIG. 2 is a flowchart of the control parameter adjustment system according to Embodiment 1. The flowchart of the control parameter adjustment system 1 includes steps S11 to S17.

[0022] In step S11, the control parameter adjustment system 1 acquires a captured image of a part of the controlled robot. The captured image may not include the identification information of the controlled robot. In step S12, the control parameter adjustment system 1 inputs the captured image into the image generation AI.

[0023] In step S13, the image generation AI automatically generates an overall image of the controlled robot. In step S14, the image recognition AI collates the overall image generated by the image generation AI with the images of a plurality of candidate robots stored in the control parameter adjustment system 1.

[0024] In step S15, the image recognition AI identifies the images of the candidate robots whose image similarity to the overall image is equal to or greater than the threshold value. The threshold value may be set to any value, for example, 90%. If the images of the candidate robots whose image similarity is equal to or greater than the threshold value can be identified, the control parameter adjustment system 1 starts step S16. If not, the control parameter adjustment system 1 resumes the process from step S13.

[0025] In step S16, the control parameter adjustment system 1 acquires the specification information of the identified corresponding robot. Here, the corresponding robot refers to the candidate robot in the image whose image similarity to the overall image is equal to or greater than the threshold value. The specification information is stored in association with the images of the candidate robots by the control parameter adjustment system 1. The control parameter adjustment system 1 may connect to an external network as needed to search for and acquire the specification information of the corresponding robot.

[0026] In step S17, the control parameter adjustment system 1 generates and outputs parameter information based on the specification information. Here, the parameter information is information used for tuning the parameters included in the control command to the controlled robot.

[0027] As explained above, the control parameter adjustment system 1 acquires specification information of the controlled robot and generates parameter information based on captured images of a part of the controlled robot. This allows the control parameter adjustment system 1 to suitably adjust the parameter settings based on the controlled robot. Therefore, by using the control parameter adjustment system 1, operators can eliminate the need to manually identify the robot, collect specification information, and manually tune the parameters of the control system.

[0028] The control parameter adjustment system 1 may also include a processor and a memory device, although these are not shown in the diagram. The memory device of the control parameter adjustment system 1 may include, for example, a non-volatile memory such as flash memory or an SSD (Solid State Drive). In this case, the memory device stores a computer program (hereinafter also simply referred to as a program) for executing the above-described method. The processor loads the computer program from the memory device into a buffer memory such as DRAM (Dynamic Random Access Memory) and executes the program.

[0029] Each component of the control parameter adjustment system 1 may be implemented with dedicated hardware. Furthermore, some or all of each component may be implemented by general-purpose or dedicated circuits, processors, etc., or combinations thereof. These may be implemented by a single chip or by multiple chips connected via a bus. Some or all of each component of each device may be implemented by a combination of the aforementioned circuits, etc., and programs. Processors include CPUs (Central Processing Units), GPUs (Graphics Processing Units), FPGAs (Field-Programmable Gate Arrays), etc. Also, at least a portion of the processing performed by the control parameter adjustment system 1 may be provided as SaaS (Software as a Service). The descriptions of the configurations described herein may also apply to other devices or systems described below in this disclosure.

[0030] <Example hardware configuration> The following describes examples of how each functional configuration of the information processing device in this disclosure is realized through a combination of hardware and software.

[0031] Figure 3 is a block diagram illustrating the hardware configuration of a computer. The information processing device in this disclosure can realize the above-described functions using a computer 500 including the hardware configuration shown in the figure. The computer 500 may be a portable computer such as a smartphone or tablet terminal, or a stationary computer such as a PC. The computer 500 may be a dedicated computer designed to realize each device, or it may be a general-purpose computer. The computer 500 can realize the desired functions by installing a predetermined application.

[0032] Computer 500 includes a bus 502, a processor 504, memory 506, a storage device 508, an input / output interface (I / F) 510, and a network interface (I / F) 512. Bus 502 is a data transmission path for the processor 504, memory 506, storage device 508, input / output interface 510, and network interface 512 to send and receive data to and from each other. However, the method of connecting the processor 504 and other components to each other is not limited to bus connection.

[0033] Processor 504 is a processor such as a CPU, GPU, or FPGA. Memory 506 is main memory implemented using RAM (Random Access Memory), etc.

[0034] The storage device 508 is an auxiliary storage device implemented using a hard disk, SSD, memory card, or ROM (Read Only Memory). The storage device 508 stores a program for realizing a desired function. The processor 504 reads this program into memory 506 and executes it to realize each functional component of each device.

[0035] The input / output interface 510 is an interface for connecting the computer 500 to input / output devices. For example, input devices such as keyboards and output devices such as display devices are connected to the input / output interface 510. The network interface 512 is an interface for connecting the computer 500 to a network.

[0036] It should be noted that the present invention is not limited to the embodiments described above, and can be modified as appropriate without departing from the spirit of the invention. For example, the memory unit may store images of candidate robots linked to identification information, and acquire specification information of candidate robots from an external network each time based on the identification information. [Explanation of Symbols]

[0037] 1. Control parameter adjustment system 11 Storage section 12 Image acquisition unit 13 Overall Image Generation Unit 14 Specific section 15 Parameter generation unit 16 Output section 500 Computers Bus 502 504 Processors 506 memory 508 Storage Devices 510 Input / Output Interfaces 512 Network Interfaces

Claims

[Claim 1] A memory unit that stores images and specification information of multiple candidate robots in a linked manner, An image acquisition unit that acquires a captured image showing a part of the controlled robot, A whole image generation unit that automatically generates a whole image of the controlled robot from the captured image, A selection unit that compares the overall image with the images of the plurality of candidate robots and identifies the robot corresponding to the robot to be controlled from the plurality of candidate robots, A parameter generation unit that acquires the specification information of the robot in question and generates parameter information based on the specification information, The system includes an output unit that outputs the parameter information, Control parameter adjustment system.

Images