Robot teaching method and robot teaching equipment
By selecting the reference robot and platform among multiple AMR robots, obtaining the reference position position information, and other robots imitate their actions to grab items, solving the problem of large and low teaching workload and improving the teaching efficiency and accuracy .
Patent Information
- Application Number
- CN202410833485.6
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-06-26
- Publication Date
- 2024-11-22
AI Technical Summary
In multiple AMR robot application scenarios, due to the deviation in the repeated positioning accuracy of each AMR, the teaching workload is huge and the efficiency is low.
By selecting the reference robot and the reference platform, the reference position information is obtained, and other robots are allowed to grab items based on the information, reducing the independent position correction of each robot for each platform, and improving teaching efficiency.
It greatly reduces the workload of robot teaching, improves teaching efficiency, and realizes more complex task allocation and execution.
Smart Images

Figure CN118990439A_ABST
Abstract
Description
Technical Field
[0001] The invention relates to a robot teaching method and a robot teaching device. Background Art
[0002] At present, in the application scenarios of multiple AMR robots, due to the deviation in the repeat positioning accuracy of each AMR, in order to achieve accurate grasping and positioning, each AMR needs to be taught one by one for each target position. If there are multiple AMR robots and the number of carriers is large, the teaching workload = number of AMR robots × number of carriers, and the teaching workload is huge. Summary of the invention
[0003] In order to solve the above technical problems, the present invention provides a robot teaching method and a robot teaching device to solve the problems of heavy workload and low efficiency of robot teaching.
[0004] In order to achieve the above-mentioned purpose, the technical solution adopted in the embodiment of the present invention is: a robot teaching method, applied to multiple robots grasping objects on multiple platforms, comprising the following steps:
[0005] Selecting a reference stage from the plurality of stages;
[0006] selecting a reference robot from among the plurality of robots;
[0007] Controlling the reference robot to grab the object on the reference platform and obtaining reference posture information of the reference robot;
[0008] Control other robots except the reference robot to grasp the objects on the plurality of platforms according to the reference posture information.
[0009] Optionally, each of the robots is provided with an image acquisition structure, and each of the platforms is provided with a calibration plate;
[0010] Controlling the reference robot to grab the object on the reference platform and obtaining the reference posture information of the reference robot specifically includes:
[0011] Controlling the reference robot to move so that the image acquisition structure of the reference robot acquires reference image information of the calibration plate on the reference stage and obtains the first position information of the reference robot;
[0012] According to the first posture information, control the reference robot to grab the object on the reference platform, and obtain second posture information of the reference robot;
[0013] The first posture information is compared with the second posture information to correct the second posture information, thereby obtaining the reference posture information.
[0014] Optionally, also include:
[0015] Controlling other robots except the reference robot to grasp the object on the reference platform according to the reference posture information and obtain actual posture information;
[0016] The actual position information is compared with the reference position information, and the actual position information is corrected.
[0017] Optionally, it further includes: controlling the reference robot to grab the object on each of the platforms and obtaining reference posture information of the reference robot relative to each of the platforms;
[0018] Control the other robots except the reference robot to grab the corresponding items on the platform according to the reference information.
[0019] Optionally, also include:
[0020] Dividing the plurality of carriers into M categories according to a preset condition, where M is greater than or equal to 2;
[0021] Selecting a reference stage from the plurality of stages specifically includes: selecting a reference stage from each type of the stages;
[0022] Controlling the reference robot to grasp the items on the reference platform and obtaining the reference posture information of the reference robot specifically includes: controlling the reference robot to grasp the items on M reference platforms and obtaining M reference posture information relative to the M reference platforms.
[0023] Optionally, controlling other robots except the reference robot to grasp the multiple objects on the platforms according to the reference posture information specifically includes:
[0024] Controlling the other robots except the reference robot to grasp the objects on the M reference platforms according to the M reference posture information, and obtaining the corresponding M actual posture information;
[0025] Comparing the M pieces of actual posture information with the corresponding M pieces of reference posture information, and correcting the M pieces of actual posture information;
[0026] Controlling the reference robot to grab objects on a plurality of the platforms to obtain reference posture information relative to all the platforms;
[0027] Control the other robots except the reference robot to grasp the objects on the corresponding platforms according to the reference posture information of all the platforms.
[0028] The embodiment of the present invention further provides a robot teaching device for implementing the above-mentioned robot teaching method, comprising a plurality of robots and a plurality of carriers, each of the robots being provided with an image acquisition structure, and each of the carriers being provided with a calibration plate;
[0029] The image acquisition structure is used to acquire image information of the corresponding calibration plate on the stage;
[0030] A first movement control structure, used to control the movement of the plurality of robots to grab the corresponding objects on the carrier;
[0031] A processing structure, used for acquiring reference position and posture information of a reference robot according to the image information;
[0032] The second movement processing structure is used to control other robots except the reference robot to grab the multiple objects on the carrier according to the reference posture information.
[0033] Optionally, the processing structure further includes:
[0034] A first processing unit is used to control the movement of the reference robot so that the image acquisition structure of the reference robot acquires the reference image information of the calibration plate on the reference stage and obtains the first pose information of the reference robot;
[0035] The second processing unit is used to control the reference robot to grab the object on the reference platform according to the first posture information, and obtain the reference posture information of the reference robot.
[0036] Optionally, a correction structure is also included, and the correction structure includes:
[0037] An acquisition unit, used for controlling other robots except the reference robot to grasp the object on the reference platform according to the reference posture information, and acquiring actual posture information;
[0038] A correction unit is used to compare the actual posture information with the reference posture information and correct the actual posture information.
[0039] An embodiment of the present invention further provides a computer device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the above-mentioned robot teaching method when executing the computer program.
[0040] An embodiment of the present invention further provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the steps of the above-mentioned robot teaching method are implemented.
[0041] The beneficial effects of the present invention are as follows: the robot teaching method provided by the present invention selects a reference robot from a plurality of the robots, and selects a reference platform from a plurality of the platforms, and obtains reference posture information relative to the reference platform through the reference robot. Robots other than the reference robot do not need to obtain corresponding posture information for each platform, but only need to grab the objects on the corresponding platform according to the reference posture information, which greatly reduces the workload of robot teaching and improves teaching efficiency. BRIEF DESCRIPTION OF THE DRAWINGS
[0042] Figure 1 A schematic diagram showing a flow chart of a robot teaching method according to an embodiment of the present invention;
[0043] Figure 2 A schematic diagram of a robot teaching device in an embodiment of the present invention is shown. DETAILED DESCRIPTION
[0044] In order to make the purpose, technical solution and advantages of the embodiments of the present disclosure clearer, the technical solution of the embodiments of the present disclosure will be clearly and completely described below in conjunction with the drawings of the embodiments of the present disclosure. Obviously, the described embodiments are part of the embodiments of the present disclosure, not all of the embodiments. Based on the described embodiments of the present disclosure, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present disclosure.
[0045] Unless otherwise defined, the technical terms or scientific terms used in the present disclosure should be understood by people with ordinary skills in the field to which the present disclosure belongs. The "first", "second" and similar words used in the present disclosure do not indicate any order, quantity or importance, but are only used to distinguish different components. Similarly, similar words such as "one", "one" or "the" do not indicate quantity restrictions, but indicate that there is at least one. Similar words such as "include" or "comprise" mean that the elements or objects appearing before the word cover the elements or objects listed after the word and their equivalents, without excluding other elements or objects. Similar words such as "connect" or "connected" are not limited to physical or mechanical connections, but can include electrical connections, whether direct or indirect. "Up", "down", "left", "right" and the like are only used to indicate relative positional relationships. When the absolute position of the described object changes, the relative positional relationship may also change accordingly.
[0046] refer to Figure 1 This embodiment provides a robot teaching method, which is applied to multiple robots grasping objects on multiple platforms, including the following steps:
[0047] Selecting a reference stage from the plurality of stages;
[0048] selecting a reference robot from among the plurality of robots;
[0049] Controlling the reference robot to grab the object on the reference platform and obtaining reference posture information of the reference robot;
[0050] Control other robots except the reference robot to grasp the objects on the plurality of platforms according to the reference posture information.
[0051] The robot teaching method provided by the present invention selects a reference robot from a plurality of the robots, and selects a reference platform from a plurality of the platforms, obtains reference posture information relative to the reference platform through the reference robot, and then transmits the obtained reference posture information to other robots. Robots other than the reference robot do not need to obtain corresponding posture information for each platform, but only need to grab items on the corresponding platform according to the reference posture information, that is, imitate the actions of the reference robot and grab items on multiple platforms. This method can improve the collaboration and efficiency between multiple robots, greatly reduce the workload of robot teaching, improve teaching efficiency, and realize more complex task allocation and execution.
[0052] In an exemplary embodiment, each of the robots is provided with an image acquisition structure, and each of the platforms is provided with a calibration plate;
[0053] Controlling the reference robot to grab the object on the reference platform and obtaining the reference posture information of the reference robot specifically includes:
[0054] Controlling the reference robot to move so that the image acquisition structure of the reference robot acquires reference image information of the calibration plate on the reference stage and obtains the first position information of the reference robot;
[0055] According to the first posture information, control the reference robot to grab the object on the reference platform, and obtain second posture information of the reference robot;
[0056] The first posture information is compared with the second posture information to correct the second posture information, thereby obtaining the reference posture information.
[0057] The image acquisition structure photographs the calibration plate to obtain image information of the calibration plate, and the first posture information of the reference robot can be accurately obtained based on the image information. The object on the reference platform is grasped based on the first posture information, and the second posture information of the actually grasped object is obtained. The first posture information and the second posture information are compared, and the second posture information is corrected to obtain the reference posture information with higher accuracy.
[0058] In an exemplary embodiment, the robot teaching method further includes:
[0059] Controlling other robots except the reference robot to grasp the object on the reference platform according to the reference posture information and obtain actual posture information;
[0060] The actual position information is compared with the reference position information, and the actual position information is corrected.
[0061] The relevant parameters of different robots have certain deviations. If other robots except the reference robot directly use the reference posture information to imitate the action of the reference robot to grab the object on the platform, there is actually a deviation. In this embodiment, by comparing the actual posture information obtained by other robots except the reference robot when actually grabbing the object on the reference platform with the reference posture information, the posture information of other robots except the reference robot is corrected, so that the posture information of other robots except the reference robot is consistent with the posture information of the reference robot, so as to improve the accuracy of object grabbing.
[0062] In an exemplary embodiment, the robot teaching method further includes: controlling the reference robot to grasp the object on each of the platforms and obtaining reference posture information of the reference robot relative to each of the platforms;
[0063] Control the other robots except the reference robot to grab the corresponding items on the platform according to the reference information.
[0064] It should be noted that the above steps are performed after the position and posture information of the robots other than the reference robot is corrected.
[0065] In an exemplary embodiment, the robot teaching method further includes:
[0066] Dividing the plurality of carriers into M categories according to a preset condition, where M is greater than or equal to 2;
[0067] Selecting a reference stage from the plurality of stages specifically includes: selecting a reference stage from each type of the stages;
[0068] Controlling the reference robot to grasp the items on the reference platform and obtaining the reference posture information of the reference robot specifically includes: controlling the reference robot to grasp the items on M reference platforms and obtaining M reference posture information relative to the M reference platforms.
[0069] There are a large number of carriers, and the relevant parameters of multiple carriers are not exactly the same. On this basis, in order to improve the accuracy of each robot in grasping objects, multiple carriers are classified according to preset conditions. The preset conditions can be set according to actual needs, which can be the appearance, size, height, and method of grasping objects of the carrier.
[0070] After the plurality of platforms are divided into M categories, one platform is selected from each category of platforms as the reference platform.
[0071] Each of the reference platforms is taught by the reference robot, that is, the reference robot grabs the objects on each of the reference platforms to obtain reference posture information relative to each of the reference platforms.
[0072] The other robots except the reference robot can grasp the items on the corresponding types of platforms according to the corresponding reference posture information. For example, the M types of platforms include the first type of platforms, and the first type of platforms include the first reference platform. The reference robot obtains the first reference posture information relative to the first reference platform, and the other robots except the reference robot grasp the items on each platform in the first type of platforms according to the first reference posture information, without the need to teach each platform in the first type of platforms.
[0073] Exemplarily, controlling other robots except the reference robot to grasp objects on each platform of the first type of platform according to the first reference posture information may specifically include:
[0074] Controlling other robots except the reference robot to grasp an object on a first reference platform of the first type of platform according to the first reference posture information to obtain first actual posture information;
[0075] The first actual posture information is compared with the first reference posture information to correct the first actual posture information.
[0076] Control the other robots except the reference robot to grab the objects on each of the first type of platforms according to the corrected posture information.
[0077] By adopting the above scheme, other robots except the reference robot do not need to teach each of the first type of platforms, but only need to teach the first reference platform in the first type of platforms.
[0078] In some embodiments, controlling the reference robot may obtain reference pose information relative to each platform in the first type of platform;
[0079] By controlling robots other than the reference robot to teach the first reference platform, the reference robot can grasp the objects on the corresponding platforms in the first type of platform according to the reference posture information relative to each platform in the first type of platform obtained by the reference robot, thereby improving the grasping accuracy.
[0080] In an exemplary embodiment, controlling other robots except the reference robot to grasp the multiple objects on the carrier according to the reference posture information specifically includes:
[0081] Controlling the other robots except the reference robot to grasp the objects on the M reference platforms according to the M reference posture information, and obtaining the corresponding M actual posture information;
[0082] Comparing the M pieces of actual posture information with the corresponding M pieces of reference posture information, and correcting the M pieces of actual posture information;
[0083] Controlling the reference robot to grab objects on a plurality of the platforms to obtain reference posture information relative to all the platforms;
[0084] Control the other robots except the reference robot to grasp the objects on the corresponding platforms according to the reference posture information of all the platforms.
[0085] In some specific embodiments, the robot teaching method comprises the following steps:
[0086] After the plurality of platforms are divided into M categories, one platform is selected from each category of platforms as the reference platform;
[0087] Selecting one of the plurality of robots as a reference robot;
[0088] Grasping the object on each of the reference platforms by the reference robot to obtain reference posture information relative to each reference platform;
[0089] Control the other robots except the reference robot to grab the objects on the corresponding reference platforms among the M types of platforms according to the M reference posture information to obtain actual posture information;
[0090] Comparing the M pieces of actual posture information with the M pieces of reference posture information to correct the M pieces of actual posture information so that the posture information of robots other than the reference robot relative to the M reference platforms is consistent with the posture information of the reference robot relative to the M reference platforms;
[0091] Controlling the reference robot to grab the object on each of the platforms to obtain reference posture information relative to each platform;
[0092] Control the other robots except the reference robot to grab the objects on the corresponding platform according to the reference posture information.
[0093] refer to Figure 2 The embodiment of the present invention further provides a robot teaching device for implementing the above-mentioned robot teaching method, comprising a plurality of robots 1 and a plurality of carriers 2, each of the robots 1 being provided with an image acquisition structure 3, each of the carriers 2 being provided with a calibration plate 4, and a mechanical arm 11 of the robot 1 being used for grabbing a film box 5 on the carrier 2;
[0094] The image acquisition structure 3 is used to acquire image information of the corresponding calibration plate 4 on the stage 2;
[0095] A first movement control structure, used to control the movement of the plurality of robots to grab the corresponding objects on the carrier;
[0096] A processing structure, used for acquiring reference position and posture information of a reference robot according to the image information;
[0097] The second movement processing structure is used to control other robots except the reference robot to grab the multiple objects on the carrier according to the reference posture information.
[0098] In an exemplary embodiment, the processing structure further includes:
[0099] A first processing unit is used to control the movement of the reference robot so that the image acquisition structure of the reference robot acquires the reference image information of the calibration plate on the reference stage and obtains the first pose information of the reference robot;
[0100] The second processing unit is used to control the reference robot to grab the object on the reference platform according to the first posture information, and obtain the reference posture information of the reference robot.
[0101] In an exemplary embodiment, a correction structure is further included, and the correction structure includes:
[0102] An acquisition unit, used for controlling other robots except the reference robot to grasp the object on the reference platform according to the reference posture information, and acquiring actual posture information;
[0103] A correction unit is used to compare the actual posture information with the reference posture information and correct the actual posture information.
[0104] An embodiment of the present invention further provides a computer device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the above-mentioned robot teaching method when executing the computer program.
[0105] An embodiment of the present invention further provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the steps of the above-mentioned robot teaching method are implemented.
[0106] An embodiment of the present invention further provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the above-mentioned HRTF measurement method when executing the computer program.
[0107] An embodiment of the present invention further provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the steps of the above-mentioned HRTF measurement method are implemented.
[0108] Among them, the processor may include one or more processing cores, such as a 4-core processor, an 8-core processor, etc. The processor may be implemented in at least one hardware form of DSP (Digital Signal Processing), FPGA (Field-Programmable Gate Array), and PLA (Programmable Logic Array). The processor may also include a main processor and a coprocessor. The main processor is a processor for processing data in the awake state, also known as CPU (Central Processing Unit); the coprocessor is a low-power processor for processing data in the standby state. In some embodiments, the processor may be integrated with a GPU (Graphics Processing Unit), which is responsible for rendering and drawing the content to be displayed on the display screen. In some embodiments, the processor may also include an I (Artificial Intelligence) processor, which is used to process computing operations related to machine learning. The memory may include one or more computer-readable storage media, which may be non-transitory. The memory may also include a high-speed random access memory, and a non-volatile memory, such as one or more disk storage devices and flash storage devices. In this embodiment, the memory is used to store at least the following computer program, wherein after the computer program is loaded and executed by the processor, the computer program is executed by the processor to implement the steps of a portable HRTF measurement method as described in any of the above items. In addition, the resources stored in the memory may also include an operating system and data, etc., and the storage method may be temporary storage or permanent storage. Among them, the operating system may include Windows, Unix, Linux, etc. The data may include but is not limited to data corresponding to the test results, etc.
[0109] There are a few points to note:
[0110] (1) The drawings of the embodiments of the present disclosure only relate to the structures related to the embodiments of the present disclosure, and other structures may refer to the general design.
[0111] (2) For the sake of clarity, in the drawings used to describe the embodiments of the present disclosure, the thickness of layers or regions is exaggerated or reduced, that is, these drawings are not drawn according to the actual scale. It is understood that when an element such as a layer, film, region or substrate is referred to as being "on" or "under" another element, the element may be "directly" "on" or "under" the other element or there may be intermediate elements.
[0112] (3) In the absence of conflict, the embodiments of the present disclosure and the features therein may be combined with each other to obtain new embodiments.
[0113] It is to be understood that the above embodiments are merely exemplary embodiments used to illustrate the principles of the present invention, but the present invention is not limited thereto. For those of ordinary skill in the art, various modifications and improvements can be made without departing from the spirit and essence of the present invention, and these modifications and improvements are also considered to be within the scope of protection of the present invention.
Claims
1. A robot teaching method, applied to multiple robots grasping objects on multiple platforms, It is characterized in that The following steps are involved: Selecting a reference stage from the plurality of stages; selecting a reference robot from among the plurality of robots; Controlling the reference robot to grab the object on the reference platform and obtaining reference posture information of the reference robot; Control other robots except the reference robot to grasp the objects on the plurality of platforms according to the reference posture information.
2. The robot teaching method according to claim 1, It is characterized in that Each of the robots is provided with an image acquisition structure, and each of the platforms is provided with a calibration plate; Controlling the reference robot to grab the object on the reference platform and obtaining the reference posture information of the reference robot specifically includes: Controlling the reference robot to move so that the image acquisition structure of the reference robot acquires reference image information of the calibration plate on the reference stage and obtains the first position information of the reference robot; According to the first posture information, control the reference robot to grab the object on the reference platform, and obtain second posture information of the reference robot; The first posture information is compared with the second posture information to correct the second posture information, thereby obtaining the reference posture information.
3. The robot teaching method according to claim 1, It is characterized in that Also includes: Controlling other robots except the reference robot to grasp the object on the reference platform according to the reference posture information and obtain actual posture information; The actual position information is compared with the reference position information, and the actual position information is corrected.
4. The robot teaching method according to claim 1, It is characterized in that Also includes: Controlling the reference robot to grab the object on each of the platforms and obtaining reference posture information of the reference robot relative to each of the platforms; Control the other robots except the reference robot to grasp the corresponding objects on the platform according to the reference posture information.
5. The robot teaching method according to claim 1, It is characterized in that Also includes: Dividing the plurality of carriers into M categories according to a preset condition, where M is greater than or equal to 2; Selecting a reference stage from the plurality of stages specifically includes: selecting a reference stage from each type of the stages; Controlling the reference robot to grasp the items on the reference platform and obtaining the reference posture information of the reference robot specifically includes: controlling the reference robot to grasp the items on M reference platforms and obtaining M reference posture information relative to the M reference platforms.
6. The robot teaching method according to claim 5, It is characterized in that Controlling other robots except the reference robot to grab the objects on the plurality of platforms according to the reference posture information specifically includes: Controlling the other robots except the reference robot to grasp the objects on the M reference platforms according to the M reference posture information, and obtaining the corresponding M actual posture information; Comparing the M pieces of actual posture information with the corresponding M pieces of reference posture information, and correcting the M pieces of actual posture information; Controlling the reference robot to grab objects on a plurality of the platforms to obtain reference posture information relative to all the platforms; Control the other robots except the reference robot to grasp the objects on the corresponding platforms according to the reference posture information of all the platforms.
7. A robot teaching device, used to implement the robot teaching method according to any one of claims 1 to 6, It is characterized in that It comprises a plurality of robots and a plurality of carriers, each of the robots is provided with an image acquisition structure, and each of the carriers is provided with a calibration plate; The image acquisition structure is used to acquire image information of the corresponding calibration plate on the stage; A first movement control structure, used to control the movement of the plurality of robots to grab the corresponding objects on the carrier; A processing structure, used for acquiring reference position and posture information of a reference robot according to the image information; The second movement processing structure is used to control other robots except the reference robot to grab the multiple objects on the carrier according to the reference posture information.
8. The robot teaching device according to claim 7, It is characterized in that The processing structure also includes: A first processing unit is used to control the movement of the reference robot so that the image acquisition structure of the reference robot acquires the reference image information of the calibration plate on the reference stage and obtains the first pose information of the reference robot; The second processing unit is used to control the reference robot to grab the object on the reference platform according to the first posture information, and obtain the reference posture information of the reference robot.
9. The robot teaching device according to claim 7, It is characterized in that Also included is a correction structure, the correction structure comprising: An acquisition unit, used for controlling other robots except the reference robot to grasp the object on the reference platform according to the reference posture information, and acquiring actual posture information; A correction unit is used to compare the actual posture information with the reference posture information and correct the actual posture information.
10. A computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, It is characterized in that When the processor executes the computer program, the steps of the robot teaching method according to any one of claims 1 to 6 are implemented.
11. A computer-readable storage medium having a computer program stored thereon, It is characterized in that When the computer program is executed by a processor, the steps of the robot teaching method according to any one of claims 1 to 6 are implemented.
Citation Information
Patent Citations
Robot system, calibration method, and method for producing to-be-processed material
CN104044143A
Robot system, robot controller, and method for controlling robot
CN108453785A
Tool center point calibration method and system for robot vision tool
CN109900207A
Migration method of composite robot 2D visual guide teaching
CN110815177A
Production system capable of realizing automatic stacking of multi-level battery modules and production method thereof
CN118099503A
