Robot teaching method, teaching device and computer-readable storage medium

Abstract

The present application discloses a robot teaching method, a teaching device and a computer-readable storage medium. The method includes: receiving video data captured by an intelligent terminal during the movement relative to a teaching trajectory; when a trigger instruction is received, determining the point contacted by the free end of a tooling in the current frame of the video data as a teaching point until the intelligent terminal completes the shooting of the teaching trajectory; determining the first relative pose of all adjacent two teaching points on the teaching trajectory in the world coordinate system according to the video data; determining the poses of all teaching points on the teaching trajectory in the world coordinate system according to the pose of any teaching point on the teaching trajectory in the world coordinate system and the first relative poses of all adjacent two teaching points in the world coordinate system; controlling the movement of the robot according to the poses of all teaching points in the world coordinate system. The teaching method provided by the present application can achieve rapid teaching of the robot.

Description

Technical Field

[0001] This application relates to the technical field of robots, and in particular to a robot teaching method, a teaching sub-device, and a computer-readable storage medium. Background Art

[0002] In the application of industrial robots, the teaching work takes a lot of time. Therefore, how to teach faster during production change is a common problem faced by robot manufacturers and users.

[0003] Currently, one widely used method for shortening the teaching time is to import the processed workpiece through 3D modeling and then generate teaching points through computer-aided calculation. This method has two limitations. One is that 3D modeling is required, the operation is cumbersome, and in many cases, the conditions for such modeling are not available. The other is that generating teaching points through computer-aided calculation still requires specifying the trajectory, and the time saved is limited.

[0004] Therefore, how to achieve fast teaching of robots is a problem that urgently needs to be solved. Summary of the Invention

[0005] This application provides a robot teaching method, a teaching device, and a computer-readable storage medium, which can achieve fast teaching of robots.

[0006] In a first aspect of an embodiment of this application, a robot teaching method is provided. The method includes: receiving video data captured by an intelligent terminal during the movement along a relative teaching trajectory; when a trigger instruction is received, determining a point contacted by the free end of a tooling in the current frame of the video data as a teaching point until the intelligent terminal completes the shooting of the teaching trajectory, where one end of the tooling is fixedly connected to the intelligent terminal, and when the intelligent terminal moves within a preset range of the teaching point, an operator controls the free end of the tooling that is not connected to the intelligent terminal to contact the teaching point and inputs the trigger instruction; determining a first relative pose of all adjacent two teaching points on the teaching trajectory in a world coordinate system according to the video data; determining the poses of all teaching points on the teaching trajectory in the world coordinate system according to the pose of any one teaching point on the teaching trajectory in the world coordinate system and the first relative poses of all adjacent two teaching points in the world coordinate system; and controlling the movement of the robot according to the poses of all teaching points in the world coordinate system.

[0007] In a second aspect of the embodiments of the present application, a teaching device is provided. The teaching device includes a processor, a memory, and a communication circuit. The processor is respectively coupled to the memory and the communication circuit. Program data is stored in the memory, and the processor executes the program data in the memory to implement the steps in the above method.

[0008] In a third aspect of the embodiments of the present application, a computer-readable storage medium is provided. The computer-readable storage medium stores a computer program, and the computer program can be executed by a processor to implement the steps in the above method.

[0009] The beneficial effect is that the present application uses an intelligent terminal to capture a teaching trajectory, and during the capture process, a tooling fixedly connected to the intelligent terminal is used to clearly describe the teaching points, so as to determine the poses of all teaching points in the world coordinate system according to the video data captured by the intelligent terminal, realizing the teaching of the robot. Compared with the related art, the teaching efficiency can be improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the following drawings are only some embodiments of the present application. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained according to these drawings. Among them:

[0011] Figure 1 is a flowchart of an implementation manner of the robot teaching method of the present application;

[0012] Figure 2 is Figure 1 a flowchart of step S130 in an application scenario in ;

[0013] Figure 3 is Figure 1 a flowchart of step S130 in another application scenario in ;

[0014] Figure 4 is Figure 1 a flowchart of step S140 in an application scenario in ;

[0015] Figure 5 is a structural diagram of an implementation manner of the teaching device of the present application;

[0016] Figure 6 is a structural diagram of an implementation manner of the computer-readable storage medium of the present application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0017] Next, the technical solutions in the embodiments of the present application will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present application without creative efforts shall fall within the protection scope of the present application.

[0018] Refer to Figure 1 , Figure 1 which is a schematic flowchart of an implementation manner of the robot teaching method of the present application. The method includes:

[0019] S110: Receive video data captured by the intelligent terminal during the movement relative to the teaching trajectory.

[0020] Among them, the robot teaching method in the present application is executed by a teaching device. The teaching device can be an independent device or integrated on the robot, which is not limited herein. At the same time, the teaching device is communicatively connected to the intelligent terminal to receive the video data sent by the intelligent terminal. In an application scenario, the teaching device and the intelligent terminal can be the same device.

[0021] Among them, the intelligent terminal can be any device with a camera function, such as a mobile phone, a tablet computer, a camera, etc., which is not limited herein. Considering that almost everyone has a mobile phone in modern society and it has powerful functions, the intelligent terminal is set as a mobile phone in this implementation manner.

[0022] Among them, first, the operator controls the intelligent terminal to move relative to the teaching trajectory on the workpiece. During the movement, the intelligent terminal captures the teaching trajectory to form video data.

[0023] S120: When a trigger instruction is received, determine the point where the free end of the tooling contacts in the current frame of the video data until the intelligent terminal completes the capture of the teaching trajectory. One end of the tooling is fixedly connected to the intelligent terminal. When the intelligent terminal moves within the preset range of the teaching point, the operator controls the free end of the tooling that is not connected to the intelligent terminal to contact the teaching point and inputs a trigger instruction.

[0024] Among them, the current frame refers to the frame being displayed in the video data when the trigger instruction is received, that is, the moment of the current frame in the video data is the same as the moment of receiving the trigger instruction.

[0025] A fixture is fixedly connected to the intelligent terminal, and the fixture moves relative to the teaching trajectory along with the intelligent terminal. When the intelligent terminal moves to the preset range of each teaching point in sequence, the operator will control the free end of the fixture that is not connected to the intelligent terminal to contact the teaching point and input a trigger instruction to inform the teaching device that the point pointed by the free end of the fixture is the teaching point at present, so that the teaching device can determine which points on the teaching trajectory are teaching points. In an application scenario, in order to better identify the teaching points, the free end of the fixture is a tip, for example, the fixture is a needle.

[0026] When the teaching point is in the preset area in the picture captured by the intelligent terminal, it is determined that the intelligent terminal moves to the preset range of the teaching point. For example, when the teaching point is in the central preset area of the captured picture, it is determined that the intelligent terminal moves to the preset range of the teaching point.

[0027] It should be noted that during the process of the intelligent terminal moving from one teaching point to the adjacent teaching point, the free end of the fixture may not contact the teaching trajectory. That is to say, as long as it is ensured that when the intelligent terminal moves to the preset range of the teaching point, the free end of the fixture contacts the teaching point.

[0028] S130: According to the video data, determine the first relative pose of all adjacent two teaching points on the teaching trajectory in the world coordinate system.

[0029] Specifically, the first relative pose of two adjacent teaching points in the world coordinate system represents the rotation and translation relationship of overlapping one of the two teaching points with the other teaching point among the two adjacent teaching points.

[0030] Refer to Figure 2 , in an application scenario, step S130 includes:

[0031] S131: According to the video data and based on the principle of epipolar geometry, determine the relative pose of all adjacent two teaching points on the teaching trajectory in the pixel coordinate system.

[0032] If the same object is photographed at different positions by two cameras and there is an overlapping part of the scenery in the two photos, the corresponding relationship between the two photos can be determined through the principle of epipolar geometry. That is to say, the epipolar geometry describes the visual geometric relationship between two images of the same scene. Therefore, after obtaining two images that simultaneously include two scenes but have different shooting angles, by applying the principle of epipolar geometry, the relative pose of the two scenes can be determined.

[0033] Among them, when the distance between the camera and the scene is unknown, the relative pose determined by using the epipolar geometry is a dimensionless relative pose, that is, the relative pose of the two scenes in the pixel coordinate system.

[0034] In this application scenario, without knowing the distance between the intelligent terminal and the teaching trajectory, the dimensionless relative poses of two adjacent teaching points are determined, that is, the relative poses of two adjacent teaching points in the pixel coordinate system.

[0035] Among them, step S131 specifically includes:

[0036] First, define two adjacent teaching points as the first teaching point and the second teaching point. When the intelligent terminal moves within the preset range of the first teaching point, the operator controls the free end of the tooling to contact the teaching point and inputs a trigger command. At this time, the teaching device determines the point contacted by the free end of the tooling in the current frame as the first teaching point. When the trigger command is received again, the teaching device determines the point contacted by the free end of the tooling in the current frame as the second teaching point.

[0037] After determining the first teaching point, the teaching device extracts two adjacent or prespecified-frame-interval images from the video data after the first teaching point. Both of these two images include the first teaching point. Then, select the same point as the first feature point in these two images, and then use the principle of epipolar geometry to process these two images to obtain the dimensionless relative pose of the first feature point and the first teaching point, that is, the relative pose in the pixel coordinate system.

[0038] Then, extract two more images after these two images. Both of these two images include the first feature point, and select the same point as the second feature point in these two images. Then, use the principle of epipolar geometry to process these two images to obtain the relative pose of the second feature point and the first feature point in the pixel coordinate system.

[0039] And so on, obtain the relative pose of the third feature point and the second feature point in the pixel coordinate system, the relative pose of the fourth feature point and the third feature point in the pixel coordinate system, …… and the relative pose of the second teaching point and the previous feature point in the pixel coordinate system.

[0040] Among them, the number of feature points selected between the first teaching point and the second teaching point can be set by the designer according to the actual scenario. For example, 9 feature points are selected.

[0041] According to the relative pose of the first feature point and the first teaching point in the pixel coordinate system, the relative pose of the second feature point and the first feature point in the pixel coordinate system, the relative pose of the third feature point and the second feature point in the pixel coordinate system, …… and the relative pose of the second teaching point and the previous feature point in the pixel coordinate system, the relative pose of the second teaching point and the first teaching point in the pixel coordinate system can be determined, that is, the relative pose of two adjacent teaching points in the pixel coordinate system is obtained.

[0042] S132: Determine the conversion relationship between the pixel coordinate system and the world coordinate system.

[0043] In an application scenario, first, based on the relative poses of all adjacent two teaching points in the pixel coordinate system, determine the relative pose of the starting teaching point and the ending teaching point on the teaching trajectory in the pixel coordinate system. Then, obtain the poses of the starting teaching point and the ending teaching point in the world coordinate system. Next, based on the poses of the starting teaching point and the ending teaching point in the world coordinate system, determine the relative pose of the starting teaching point and the ending teaching point in the world coordinate system. Finally, based on the relative pose of the starting teaching point and the ending teaching point in the pixel coordinate system and the relative pose of the starting teaching point and the ending teaching point in the world coordinate system, determine the conversion relationship between the pixel coordinate system and the world coordinate system.

[0044] Among them, the robot can be taught the starting teaching point and the ending teaching point, so as to obtain the poses of the starting teaching point and the ending teaching point in the world coordinate system. Specifically, pull the end of the robot to the starting teaching point and the ending teaching point in turn, so as to obtain the poses of the starting teaching point and the ending teaching point in the teaching coordinate system. That is, only need to teach the starting teaching point and the ending teaching point to the robot.

[0045] S133: Based on the relative poses of all adjacent two teaching points in the pixel coordinate system and the conversion relationship, determine the first relative pose of all adjacent two teaching points in the world coordinate system.

[0046] Among them, after determining the conversion relationship between the pixel coordinate system and the world coordinate system, the relative pose of adjacent two teaching points in the pixel coordinate system can be converted into the first relative pose of adjacent two teaching points in the world coordinate system.

[0047] Refer to Figure 3 , in another application scenario, step S130 includes:

[0048] S134: Use the length of the tooling as the distance from the intelligent terminal to the teaching trajectory, and based on the video data and the principle of epipolar geometry, determine the first relative pose of all adjacent two teaching points in the world coordinate system.

[0049] The difference in the above application scenarios is that in this application scenario, the tooling is a columnar tooling. For example, the tooling is a needle, and at this time, the tooling is vertically installed on the intelligent terminal. It can be understood that the length of the tooling at this time is the distance from the intelligent terminal to the teaching trajectory.

[0050] After knowing the distance from the intelligent terminal to the teaching trajectory, the relative pose with dimensions of adjacent two teaching points, that is, the first relative pose of adjacent two teaching points in the world coordinate system, can be directly determined by using the principle of epipolar geometry.

[0051] Among them, the process of determining the first relative pose of adjacent two teaching points in the world coordinate system in this application scenario specifically includes:

[0052] First, define two adjacent teaching points as the first teaching point and the second teaching point. When the intelligent terminal moves within the preset range of the first teaching point, the operator controls the free end of the tooling to contact the teaching point and inputs a trigger command. At this time, the teaching device determines the point contacted by the free end of the tooling in the current frame as the first teaching point. When the trigger command is received again, the teaching device determines the point contacted by the free end of the tooling in the current frame as the second teaching point.

[0053] After determining the first teaching point, the teaching device extracts two adjacent or preset-frame-spaced images from the video data after the first teaching point. These two images both include the first teaching point. Then, select the same point in these two images as the first feature point. Then, use the length of the tooling as the distance from the intelligent terminal to the teaching trajectory, and use the principle of epipolar geometry to process these two images to obtain the dimensional relative pose of the first feature point and the first teaching point, that is, the first relative pose in the world coordinate system.

[0054] Then, extract two more images after these two images. These two images both include the first feature point. And select the same point in these two images as the second feature point. Then, use the length of the tooling as the distance from the intelligent terminal to the teaching trajectory, and use the principle of epipolar geometry to process these two images to obtain the first relative pose of the second feature point and the first feature point in the world coordinate system.

[0055] And so on, obtain the first relative pose of the third feature point and the second feature point in the world coordinate system, the first relative pose of the fourth feature point and the third feature point in the world coordinate system, …… and the first relative pose of the second teaching point and the previous feature point in the world coordinate system.

[0056] Finally, according to the first relative pose of the first feature point and the first teaching point in the world coordinate system, the first relative pose of the second feature point and the first feature point in the world coordinate system, the first relative pose of the third feature point and the second feature point in the world coordinate system, …… and the first relative pose of the second teaching point and the previous feature point in the world coordinate system, the first relative pose of the second teaching point and the first teaching point in the world coordinate system can be determined, that is, the first relative pose of two adjacent teaching points in the world coordinate system is obtained.

[0057] The above has introduced step S130 in detail. Next, introduce the steps after step S130.

[0058] S140: Determine the poses of all teaching points on the teaching trajectory in the world coordinate system according to the pose of any teaching point on the teaching trajectory in the world coordinate system and the first relative poses of all adjacent two teaching points in the world coordinate system.

[0059] The determination of the pose of the starting teaching point on the teaching trajectory in the world coordinate system is described as follows:

[0060] After determining the pose of the starting teaching point in the world coordinate system, based on the pose of the starting teaching point in the world coordinate system and the first relative pose of the starting teaching point and the teaching point adjacent to the starting teaching point in the world coordinate system, the pose of the teaching point adjacent to the starting teaching point in the world coordinate system can be determined. By analogy, the poses of all teaching points in the world coordinate system can be determined.

[0061] Refer to Figure 4 , in an application scenario, in order to reduce errors, step S140 specifically includes:

[0062] S141: Obtain the acquisition data sent by the inertial sensor on the intelligent terminal during the movement of the intelligent terminal relative to the teaching trajectory.

[0063] The inertial sensor is integrated on the intelligent terminal. The inertial sensor is also called IMU (Inertial Measurement Unit), which is a sensor used to measure acceleration and rotational motion. During the movement of the intelligent terminal relative to the teaching trajectory, the inertial sensor continuously collects data.

[0064] S142: According to the acquisition data, determine the second relative pose of all adjacent two teaching points on the teaching trajectory in the world coordinate system.

[0065] Specifically, the inertial sensor is mainly used to detect and measure the acceleration, tilt, shock, vibration, rotation and multi-degree-of-freedom (DoF) motion of the intelligent terminal. The acquisition data it sends includes the linear acceleration, angular acceleration, rotation angle, etc. of the intelligent terminal.

[0066] Among them, specifically, according to parameters such as the rotation angle and angular acceleration in the acquisition data, the second relative pose of two adjacent teaching points in the world coordinate system can be determined.

[0067] Each time the teaching device receives a trigger instruction, it determines the second relative pose of the current teaching point relative to the previous teaching point in the world coordinate system according to the acquisition data sent by the current inertial sensor. Thus, after the movement of the intelligent terminal relative to the teaching trajectory ends, the second relative poses of all adjacent teaching points in the world coordinate can be obtained.

[0068] S143: Fuse the first relative pose and the corresponding second relative pose of all adjacent two teaching points respectively to obtain the final relative pose of all adjacent two teaching points in the world coordinate system.

[0069] S144: Determine the poses of all the teaching points on the teaching trajectory in the world coordinate system based on the pose of any teaching point on the teaching trajectory in the world coordinate system and the final relative poses of all adjacent pairs of teaching points in the world coordinate system.

[0070] Specifically, for a pair of adjacent teaching points, fuse their corresponding first relative pose and second relative pose to obtain the final relative pose of this pair of adjacent teaching points in the world coordinate system, and this final relative pose is the relative pose of the adjacent two teaching points in the world coordinate system.

[0071] When obtaining the first relative pose based on the video data, although the accuracy of the relative position can be guaranteed, there is still room for further improvement in the accuracy of the relative pose. And the process of obtaining the second relative pose based on the acquisition data sent by the inertial sensor is opposite to the process of obtaining the first relative pose based on the video data. It can guarantee the accuracy of the relative pose, but there is still room for further improvement in the accuracy of the relative position. Therefore, during the process of fusing the first relative pose and the second relative pose, the complementarity of the two relative poses can be realized, ensuring the accuracy of the finally determined relative pose.

[0072] Among them, when fusing the corresponding first relative pose and second relative pose, corresponding weights can be set for the first relative pose and the second relative pose, and then weighted summation is performed according to the weights to obtain the final relative pose of the adjacent two teaching points in the world coordinate system.

[0073] S150: Control the movement of the robot according to the poses of all the teaching points in the world coordinate system.

[0074] The principle of robot teaching is to describe the poses of the teaching points in the world coordinate system. Therefore, after obtaining the poses of all the teaching points in the world coordinate system, the teaching of the robot can be realized.

[0075] It can be seen from the above content that this embodiment uses the intelligent terminal to take pictures of the teaching trajectory, and during the shooting process, the tooling fixedly connected to the intelligent terminal is used to clearly describe the teaching points, so that the teaching device can determine which points on the teaching trajectory are teaching points, and then determine the poses of all the teaching points in the world coordinate system according to the video data taken by the intelligent terminal, realizing the teaching of the robot. Compared with the related technology, there is no need to teach each teaching point on the teaching trajectory, thus improving the teaching efficiency.

[0076] Refer to Figure 5 , Figure 5It is a schematic structural diagram of an embodiment of the teaching device of the present application. The teaching device 200 includes a processor 210, a memory 220, and a communication circuit 230. The processor 210 is respectively coupled to the memory 220 and the communication circuit 230. Program data is stored in the memory 220. The processor 210 realizes the steps in the method of any of the above embodiments by executing the program data in the memory 220. For the detailed steps, reference can be made to the above embodiments and will not be elaborated here.

[0077] Refer to Figure 6 , Figure 6 It is a schematic structural diagram of an embodiment of the computer-readable storage medium of the present application. The computer-readable storage medium 300 stores a computer program 310, and the computer program 310 can be executed by a processor to realize the steps in any of the above methods.

[0078] Among them, the computer-readable storage medium 300 can specifically be a USB flash drive, a mobile hard disk, a read-only memory (ROM, Read-Only Memory), a random access memory (RAM, Random Access Memory), a magnetic disk, or an optical disc, etc., which can store the computer program 310, or it can also be a server storing the computer program 310. The server can send the stored computer program 310 to other devices for running, or it can also run the stored computer program 310 by itself.

[0079] The above are only the embodiments of the present application and do not limit the patent scope of the present application. Any equivalent structural or equivalent process transformation made by using the content of the specification and drawings of the present application, or directly or indirectly applied in other related technical fields, shall be equally included in the patent protection scope of the present application.

Claims

1. A robot teaching method, characterized in that, the method includes: Receiving video data captured by the intelligent terminal during the movement along the teaching trajectory; When receiving a trigger instruction, determining the points contacted by the free end of the tooling in the current frame of the video data as teaching points until the intelligent terminal completes the shooting of the teaching trajectory, wherein one end of the tooling is fixedly connected to the intelligent terminal, and when the intelligent terminal moves within the preset range of the teaching point, the operator controls the free end of the tooling that is not connected to the intelligent terminal to contact the teaching point and inputs the trigger instruction; According to the video data, determining the first relative pose of all adjacent two teaching points on the teaching trajectory in the world coordinate system; According to the pose of any one of the teaching points on the teaching trajectory in the world coordinate system and the first relative poses of all adjacent two teaching points in the world coordinate system, determining the poses of all the teaching points on the teaching trajectory in the world coordinate system; Controlling the movement of the robot according to the poses of all the teaching points in the world coordinate system.

2. The method according to claim 1, characterized in that, the step of determining the first relative pose of all adjacent two teaching points on the teaching trajectory in the world coordinate system according to the video data includes: According to the video data and based on the principle of epipolar geometry, determining the relative poses of all adjacent two teaching points on the teaching trajectory in the pixel coordinate system; Determining the conversion relationship between the pixel coordinate system and the world coordinate system; According to the relative poses of all adjacent two teaching points in the pixel coordinate system and the conversion relationship, determining the first relative poses of all adjacent two teaching points in the world coordinate system.

3. The method according to claim 2, characterized in that, the step of determining the conversion relationship between the pixel coordinate system and the world coordinate system includes: According to the relative poses of all adjacent two teaching points in the pixel coordinate system, determining the relative pose of the starting teaching point and the ending teaching point on the teaching trajectory in the pixel coordinate system; Obtaining the poses of the starting teaching point and the ending teaching point in the world coordinate system; According to the poses of the starting teaching point and the ending teaching point in the world coordinate system, determining the relative pose of the starting teaching point and the ending teaching point in the world coordinate system; According to the relative pose of the starting teaching point and the ending teaching point in the pixel coordinate system and the relative pose of the starting teaching point and the ending teaching point in the world coordinate system, determining the conversion relationship between the pixel coordinate system and the world coordinate system.

4. The method according to claim 3, characterized in that, the step of obtaining the poses of the starting teaching point and the ending teaching point in the world coordinate system includes: Teach the robot at the starting teaching point and the ending teaching point, so as to obtain the poses of the starting teaching point and the ending teaching point in the world coordinate system.

5. The method according to claim 1, wherein, the tooling is in a columnar structure, and the tooling is vertically installed on the intelligent terminal. The step of determining the first relative poses of all adjacent two of the teaching points on the teaching trajectory in the world coordinate system according to the video data includes: Taking the length of the tooling as the distance from the intelligent terminal to the teaching trajectory, and determining the first relative poses of all adjacent two of the teaching points in the world coordinate system according to the video data and the principle of epipolar geometry.

6. The method according to claim 1, wherein, the step of determining the poses of all the teaching points on the teaching trajectory in the world coordinate system according to the pose of any one of the teaching points on the teaching trajectory in the world coordinate system and the first relative poses of all adjacent two of the teaching points in the world coordinate system includes: Obtaining the acquisition data sent by the inertial sensor on the intelligent terminal during the movement of the intelligent terminal relative to the teaching trajectory; Determining the second relative poses of all adjacent two of the teaching points on the teaching trajectory in the world coordinate system according to the acquisition data; Respectively fusing the first relative poses of all adjacent two of the teaching points with the corresponding second relative poses to obtain the final relative poses of all adjacent two of the teaching points in the world coordinate system; Determining the poses of all the teaching points on the teaching trajectory in the world coordinate system according to the pose of any one of the teaching points on the teaching trajectory in the world coordinate system and the final relative poses of all adjacent two of the teaching points in the world coordinate system.

7. The method according to claim 6, wherein, the step of respectively fusing the first relative poses of all adjacent two of the teaching points with the corresponding second relative poses to obtain the final relative poses of all adjacent two of the teaching points in the world coordinate system includes: Respectively performing weighted summation on the first relative poses of all adjacent two of the teaching points and the corresponding second relative poses to obtain the final relative poses of all adjacent two of the teaching points in the world coordinate system.

8. The method according to claim 1, wherein, the intelligent terminal is a mobile phone.

9. A teaching device, wherein, the teaching device includes a processor, a memory, and a communication circuit. The processor is respectively coupled to the memory and the communication circuit. Program data is stored in the memory, and the processor realizes the steps in the method according to any one of claims 1-8 by executing the program data in the memory.

10. A computer-readable storage medium, wherein, The computer-readable storage medium stores a computer program that can be executed by a processor to implement the steps in the method according to any one of claims 1-8.

Images