CN104827474A - Intelligent programming method and auxiliary device of virtual teaching robot for learning person - Google Patents

Abstract

The invention provides a virtual teaching robot intelligent programming auxiliary device for learning human beings. The end of the robot is equipped with working tools, including: the teaching tool is the same as the working tool set at the end of the robot and has a first feature point, which is captured in time order And record the movement track of the feature points on the teaching tool, the joint angle information of the teaching tool and the camera unit of the operation point of the operation target, and the robot controller that generates the robot work order; A second feature point corresponding to a feature point.

Description

Intelligent programming method and auxiliary device for learning human virtual teaching robot

technical field

The invention relates to an intelligent programming technology of an industrial robot, in particular to an intelligent programming method and an auxiliary device for learning a virtual teaching robot.

Background technique

With the development of science and technology, more and more industrial robots have been widely used in various industrial fields, such as robot painting, robot handling, robot assembly, etc. Now, in these fields, industrial robots can replace humans to complete repeatable and precise work, thus ensuring product quality. When a robot is used to replace a human to perform operations, it is necessary to issue instructions to the robot in advance, specifying the actions that the robot should complete and the specific content of the operation. Along with the development of industrial robots, robot programming technology has also been developed and improved; robot programming has become an important part of robot technology; in addition to relying on the support of robot hardware, a considerable part of robot functions depends on robot language.

There are many methods of robot programming, divided into online programming and offline programming according to location:

Online programming controls the movement of the robot through the manual operation box of the robot. The process of online teaching includes moving the end of the tool installed on the robot to its operating position, and recording the coordinates of the robot at this position, and then the robot records along the teaching path. The track autonomously moves to complete a specific operation task. The accuracy of the teaching is completely determined by the experience and visual inspection of the teaching operator. The hand-held teaching cannot achieve the expected effect, and it may hurt the teaching personnel, which is very dangerous.

The accuracy of off-line programming is high, the robot can be used for programming without the robot, and the robot can perform other work, and the operation plan and operation cycle time can be pre-optimized through the simulation test program, and the previously completed process or subroutine can be combined into the program to be programmed to avoid injury to the operator. Compared with teaching and reproducing programming, the off-line programming system has higher requirements for operators, and requires specialized robot knowledge and programming ability, and it is not very convenient to use, especially in the description of robot tasks. If the teaching and reproduction function can be introduced into the robot offline programming system, the operator can guide the online teaching robot on the computer screen through the corresponding human-machine interface, generate the robot's operation trajectory, and then generate the robot motion program and perform simulation and simulation. Optimization will undoubtedly greatly enhance the operability of robot offline programming and the friendliness of the user interface, make robot programming more convenient and simple, and help promote the application and promotion of robot technology in actual production.

Contents of the invention

The purpose of the present invention is to provide a robot intelligent programming method for learning human virtual operation, which has the advantages of simple operation, high flexibility and intelligence.

The invention relates to an intelligent programming auxiliary device for a virtual teaching robot for learning human beings. A working tool is arranged at the end of the robot, including a teaching tool, a robot controller and a robot controller. The teaching tool is the same as the operating tool set at the end of the robot and has a first feature point; the camera unit captures and records the movement track of the feature points on the teaching tool and the joint angle information of the teaching tool in time sequence; the A robot controller that generates robot work instructions. The working tool is provided with a second feature point corresponding to the first feature point of the teaching tool.

Using the above-mentioned device to realize the method for intelligent programming of a virtual teaching robot for learning people, including:

The teaching tool performs virtual work, and the camera unit captures the motion trajectory and joint angle of the first feature point in time order and generates the two-dimensional coordinates of the camera space of the first feature point.

The robot controller obtains an instruction program including the robot space three-dimensional coordinates and joint angles of the first feature point according to the camera space coordinates and joint angles of the first feature point,

The robot controller inputs the instruction program into the robot;

The robot controller controls the motion track of the second feature point on the working tool according to the robot space three-dimensional coordinate information of the first feature point in the instruction program.

Before the teaching tool performs virtual operations, first establish the mapping relationship between the robot space and the camera space. The specific method is:

The camera unit captures more than three sets of images of the second feature points in the work and obtains the two-dimensional coordinates of the camera space of the second feature points;

Record the robot joint angle parameters, and obtain the robot space three-dimensional coordinates of the second feature point through the forward kinematics of the robot;

Establish the mapping relationship between robot space and camera space

${\mathrm{<span\; class="notranslate">\; x</span>}}_{\mathrm{<span\; class="notranslate">\; c</span>}}<span\; class="notranslate">\; =</span><span\; class="notranslate">\; (</span>{\mathrm{<span\; class="notranslate">\; C</span>}}_{\mathrm{<span\; class="notranslate">\; 1</span>}}^{\mathrm{<span\; class="notranslate">\; 2</span>}}<span\; class="notranslate">\; +</span>{\mathrm{<span\; class="notranslate">\; C</span>}}_{\mathrm{<span\; class="notranslate">\; 2</span>}}^{\mathrm{<span\; class="notranslate">\; 2</span>}}<span\; class="notranslate">\; -</span>{\mathrm{<span\; class="notranslate">\; C</span>}}_{\mathrm{<span\; class="notranslate">\; 3</span>}}^{\mathrm{<span\; class="notranslate">\; 2</span>}}<span\; class="notranslate">\; -</span>{\mathrm{<span\; class="notranslate">\; C</span>}}_{\mathrm{<span\; class="notranslate">\; 4</span>}}^{\mathrm{<span\; class="notranslate">\; 2</span>}}<span\; class="notranslate">\; )</span>{\mathrm{<span\; class="notranslate">\; p</span>}}_{\mathrm{<span\; class="notranslate">\; x</span>}}<span\; class="notranslate">\; +</span>\mathrm{<span\; class="notranslate">\; 2</span>}<span\; class="notranslate">\; (</span>{\mathrm{<span\; class="notranslate">\; C</span>}}_{\mathrm{<span\; class="notranslate">\; 2</span>}}{\mathrm{<span\; class="notranslate">\; C</span>}}_{\mathrm{<span\; class="notranslate">\; 3</span>}}<span\; class="notranslate">\; +</span>{\mathrm{<span\; class="notranslate">\; C</span>}}_{\mathrm{<span\; class="notranslate">\; 1</span>}}{\mathrm{<span\; class="notranslate">\; C</span>}}_{\mathrm{<span\; class="notranslate">\; 4</span>}}<span\; class="notranslate">\; )</span>{\mathrm{<span\; class="notranslate">\; p</span>}}_{\mathrm{<span\; class="notranslate">\; the\; y</span>}}<span\; class="notranslate">\; +</span>\mathrm{<span\; class="notranslate">\; 2</span>}<span\; class="notranslate">\; (</span>{\mathrm{<span\; class="notranslate">\; C</span>}}_{\mathrm{<span\; class="notranslate">\; 2</span>}}{\mathrm{<span\; class="notranslate">\; C</span>}}_{\mathrm{<span\; class="notranslate">\; 4</span>}}<span\; class="notranslate">\; -</span>{\mathrm{<span\; class="notranslate">\; C</span>}}_{\mathrm{<span\; class="notranslate">\; 1</span>}}{\mathrm{<span\; class="notranslate">\; C</span>}}_{\mathrm{<span\; class="notranslate">\; 3</span>}}<span\; class="notranslate">\; )</span>{\mathrm{<span\; class="notranslate">\; p</span>}}_{\mathrm{<span\; class="notranslate">\; z</span>}}<span\; class="notranslate">\; +</span>{\mathrm{<span\; class="notranslate">\; C</span>}}_{\mathrm{<span\; class="notranslate">\; 5</span>}}$

${\mathrm{<span\; class="notranslate">\; the\; y</span>}}_{\mathrm{<span\; class="notranslate">\; c</span>}}<span\; class="notranslate">\; =</span>\mathrm{<span\; class="notranslate">\; 2</span>}<span\; class="notranslate">\; (</span>{\mathrm{<span\; class="notranslate">\; C</span>}}_{\mathrm{<span\; class="notranslate">\; 2</span>}}{\mathrm{<span\; class="notranslate">\; C</span>}}_{\mathrm{<span\; class="notranslate">\; 3</span>}}<span\; class="notranslate">\; -</span>{\mathrm{<span\; class="notranslate">\; C</span>}}_{\mathrm{<span\; class="notranslate">\; 1</span>}}{\mathrm{<span\; class="notranslate">\; C</span>}}_{\mathrm{<span\; class="notranslate">\; 4</span>}}<span\; class="notranslate">\; )</span>{\mathrm{<span\; class="notranslate">\; p</span>}}_{\mathrm{<span\; class="notranslate">\; x</span>}}<span\; class="notranslate">\; +</span><span\; class="notranslate">\; (</span>{\mathrm{<span\; class="notranslate">\; C</span>}}_{\mathrm{<span\; class="notranslate">\; 1</span>}}^{\mathrm{<span\; class="notranslate">\; 2</span>}}<span\; class="notranslate">\; -</span>{\mathrm{<span\; class="notranslate">\; C</span>}}_{\mathrm{<span\; class="notranslate">\; 2</span>}}^{\mathrm{<span\; class="notranslate">\; 2</span>}}<span\; class="notranslate">\; +</span>{\mathrm{<span\; class="notranslate">\; C</span>}}_{\mathrm{<span\; class="notranslate">\; 3</span>}}^{\mathrm{<span\; class="notranslate">\; 2</span>}}<span\; class="notranslate">\; -</span>{\mathrm{<span\; class="notranslate">\; C</span>}}_{\mathrm{<span\; class="notranslate">\; 4</span>}}^{\mathrm{<span\; class="notranslate">\; 2</span>}}<span\; class="notranslate">\; )</span>{\mathrm{<span\; class="notranslate">\; p</span>}}_{\mathrm{<span\; class="notranslate">\; the\; y</span>}}<span\; class="notranslate">\; +</span>\mathrm{<span\; class="notranslate">\; 2</span>}<span\; class="notranslate">\; (</span>{\mathrm{<span\; class="notranslate">\; C</span>}}_{\mathrm{<span\; class="notranslate">\; 3</span>}}{\mathrm{<span\; class="notranslate">\; C</span>}}_{\mathrm{<span\; class="notranslate">\; 4</span>}}<span\; class="notranslate">\; +</span>{\mathrm{<span\; class="notranslate">\; C</span>}}_{\mathrm{<span\; class="notranslate">\; 1</span>}}{\mathrm{<span\; class="notranslate">\; C</span>}}_{\mathrm{<span\; class="notranslate">\; 2</span>}}<span\; class="notranslate">\; )</span>{\mathrm{<span\; class="notranslate">\; p</span>}}_{\mathrm{<span\; class="notranslate">\; z</span>}}<span\; class="notranslate">\; +</span>{\mathrm{<span\; class="notranslate">\; C</span>}}_{\mathrm{<span\; class="notranslate">\; 6</span>}}$

Among them, (x _c , y _c ) are the two-dimensional coordinates of the camera space of the second feature point (11), (p _x , p _y , p _z ) are the three-dimensional coordinates of the second feature point in the robot space, C=[C ₁ , C ₂ , C ₃ , C ₄ , C ₅ , C ₆ ] are mapping relationship parameters.

Compared with the prior art, the present invention has the following advantages: (1) In the past, it was necessary for the operator to hold the end of the robot hand in hand for teaching, and it required great effort to simulate the posture of the operation and it was not easy to teach in place. Now, it is easy and dexterous without effort ;(2) There will be an "immersive" feeling in the process of human-computer interaction between the operator and the robot, providing users with a new and harmonious human-computer interaction environment; (3) Hand-held teaching device equipment Setting several feature point arrangements can uniquely determine the posture, and the feature points can be LEDs, which solves the problem of working environment restrictions.

The present invention will be further described below in conjunction with the accompanying drawings.

Description of drawings

Fig. 1 is a schematic diagram of the system structure of the present invention.

Fig. 2 is a schematic structural diagram of the handheld virtual teaching tool of the present invention.

Fig. 3 is a schematic diagram of the present invention for welding a car door.

Fig. 4 is a flowchart of the method of the present invention.

Detailed ways

Referring to FIG. 1 and FIG. 2 , a virtual teaching robot intelligent programming auxiliary device for learning people includes: a teaching tool 2 , a camera unit 3 and a robot controller 4 . The teaching tool 2 is the same as the working tool 1 set at the end of the robot and is provided with a first feature point 21; the camera unit 3 captures and records the movement trajectory of the feature points on the teaching tool 2 and the joints of the teaching tool 2 in time sequence. Angle information; the robot controller 4 generates robot work instructions. The working tool 1 is provided with a second feature point 11 corresponding to the first feature point 21 of the teaching tool 2 .

1 and 2, the robot used in the present invention is a six-degree-of-freedom industrial robot 6 with a welding tool at its end, which includes a welding tool upper jaw 12 and a movable welding tool lower jaw 13 . What the hand-held teaching tool 2 simulates is the upper jaw 12 of the welding tool, and its shape and size are the same as the upper jaw 12 of the welding tool, but the weight of the teaching tool 2 is very light, and the operator can operate flexibly and facilitate posture adjustment.

Referring to FIG. 2 , there are several first feature points 21 on the teaching tool 2 , and the first feature points 21 can be located on a feature point mounting block protruding from the rear end of the upper jaw of the simulation welding tool. The 21-column combination of the first feature point row should conform to the posture that uniquely identifies the teaching tool 2 . The present invention takes an L-shaped arrangement as an example. There are three first feature points 21, and the connection line A between the first first feature point and the second first feature point is perpendicular to the second first feature point and the second first feature point. A connection line B between the three first feature points, and the length of the connection line A is twice the length of the connection line B. The front port of the teach pendant 2 simulates a welding torch head.

Three second feature points 11 corresponding to the three first feature points 21 are also provided on the upper jaw 12 of the welding tool. The distance from the corresponding first feature point 21 to the front end of the teaching tool to simulate the welding torch head is equal to the distance from the corresponding second feature point 11 of the welding tool on the end of the robot to the welding torch head at the front end of the upper jaw 12 of the welding tool.

As shown in FIG. 3 , the field of view of the camera unit 3 covers the working area of the teaching tool 2 , so as to realize shooting of the teaching tool 2 in all directions without blind spots. The camera unit 3 is composed of more than two cameras 31, and the distance between the cameras and the angle between the cameras do not have to be determined. Take welding the car door 51 as an example, there is a welding spot 52 on the car door 51, and the teaching tool 2 reaches the position of the welding spot 52 in an operating posture. It only needs to be observed by some of the cameras 31 .

Referring to FIG. 4 , an intelligent programming method for a human-learning virtual teaching robot includes the following steps.

Step 1, establish the mapping relationship between robot space and camera space.

The field of view of the camera unit 3 covers the working area, collects images of the second feature point 11 of the welding tool on the end of the robot in multiple groups of working areas, obtains the coordinates of the feature point in the camera space through image recognition, records the corresponding robot joint angle information, and passes The forward kinematics of the robot obtains the robot space coordinates of the feature points, and establishes the mapping relationship between the robot space and the camera space. The mapping relationship is as follows:

${\mathrm{<span\; class="notranslate">\; x</span>}}_{\mathrm{<span\; class="notranslate">\; c</span>}}<span\; class="notranslate">\; =</span><span\; class="notranslate">\; (</span>{\mathrm{<span\; class="notranslate">\; C</span>}}_{\mathrm{<span\; class="notranslate">\; 1</span>}}^{\mathrm{<span\; class="notranslate">\; 2</span>}}<span\; class="notranslate">\; +</span>{\mathrm{<span\; class="notranslate">\; C</span>}}_{\mathrm{<span\; class="notranslate">\; 2</span>}}^{\mathrm{<span\; class="notranslate">\; 2</span>}}<span\; class="notranslate">\; -</span>{\mathrm{<span\; class="notranslate">\; C</span>}}_{\mathrm{<span\; class="notranslate">\; 3</span>}}^{\mathrm{<span\; class="notranslate">\; 2</span>}}<span\; class="notranslate">\; -</span>{\mathrm{<span\; class="notranslate">\; C</span>}}_{\mathrm{<span\; class="notranslate">\; 4</span>}}^{\mathrm{<span\; class="notranslate">\; 2</span>}}<span\; class="notranslate">\; )</span>{\mathrm{<span\; class="notranslate">\; p</span>}}_{\mathrm{<span\; class="notranslate">\; x</span>}}<span\; class="notranslate">\; +</span>\mathrm{<span\; class="notranslate">\; 2</span>}<span\; class="notranslate">\; (</span>{\mathrm{<span\; class="notranslate">\; C</span>}}_{\mathrm{<span\; class="notranslate">\; 2</span>}}{\mathrm{<span\; class="notranslate">\; C</span>}}_{\mathrm{<span\; class="notranslate">\; 3</span>}}<span\; class="notranslate">\; +</span>{\mathrm{<span\; class="notranslate">\; C</span>}}_{\mathrm{<span\; class="notranslate">\; 1</span>}}{\mathrm{<span\; class="notranslate">\; C</span>}}_{\mathrm{<span\; class="notranslate">\; 4</span>}}<span\; class="notranslate">\; )</span>{\mathrm{<span\; class="notranslate">\; p</span>}}_{\mathrm{<span\; class="notranslate">\; the\; y</span>}}<span\; class="notranslate">\; +</span>\mathrm{<span\; class="notranslate">\; 2</span>}<span\; class="notranslate">\; (</span>{\mathrm{<span\; class="notranslate">\; C</span>}}_{\mathrm{<span\; class="notranslate">\; 2</span>}}{\mathrm{<span\; class="notranslate">\; C</span>}}_{\mathrm{<span\; class="notranslate">\; 4</span>}}<span\; class="notranslate">\; -</span>{\mathrm{<span\; class="notranslate">\; C</span>}}_{\mathrm{<span\; class="notranslate">\; 1</span>}}{\mathrm{<span\; class="notranslate">\; C</span>}}_{\mathrm{<span\; class="notranslate">\; 3</span>}}<span\; class="notranslate">\; )</span>{\mathrm{<span\; class="notranslate">\; p</span>}}_{\mathrm{<span\; class="notranslate">\; z</span>}}<span\; class="notranslate">\; +</span>{\mathrm{<span\; class="notranslate">\; C</span>}}_{\mathrm{<span\; class="notranslate">\; 5</span>}}$

${\mathrm{<span\; class="notranslate">\; the\; y</span>}}_{\mathrm{<span\; class="notranslate">\; c</span>}}<span\; class="notranslate">\; =</span>\mathrm{<span\; class="notranslate">\; 2</span>}<span\; class="notranslate">\; (</span>{\mathrm{<span\; class="notranslate">\; C</span>}}_{\mathrm{<span\; class="notranslate">\; 2</span>}}{\mathrm{<span\; class="notranslate">\; C</span>}}_{\mathrm{<span\; class="notranslate">\; 3</span>}}<span\; class="notranslate">\; -</span>{\mathrm{<span\; class="notranslate">\; C</span>}}_{\mathrm{<span\; class="notranslate">\; 1</span>}}{\mathrm{<span\; class="notranslate">\; C</span>}}_{\mathrm{<span\; class="notranslate">\; 4</span>}}<span\; class="notranslate">\; )</span>{\mathrm{<span\; class="notranslate">\; p</span>}}_{\mathrm{<span\; class="notranslate">\; x</span>}}<span\; class="notranslate">\; +</span><span\; class="notranslate">\; (</span>{\mathrm{<span\; class="notranslate">\; C</span>}}_{\mathrm{<span\; class="notranslate">\; 1</span>}}^{\mathrm{<span\; class="notranslate">\; 2</span>}}<span\; class="notranslate">\; -</span>{\mathrm{<span\; class="notranslate">\; C</span>}}_{\mathrm{<span\; class="notranslate">\; 2</span>}}^{\mathrm{<span\; class="notranslate">\; 2</span>}}<span\; class="notranslate">\; +</span>{\mathrm{<span\; class="notranslate">\; C</span>}}_{\mathrm{<span\; class="notranslate">\; 3</span>}}^{\mathrm{<span\; class="notranslate">\; 2</span>}}<span\; class="notranslate">\; -</span>{\mathrm{<span\; class="notranslate">\; C</span>}}_{\mathrm{<span\; class="notranslate">\; 4</span>}}^{\mathrm{<span\; class="notranslate">\; 2</span>}}<span\; class="notranslate">\; )</span>{\mathrm{<span\; class="notranslate">\; p</span>}}_{\mathrm{<span\; class="notranslate">\; the\; y</span>}}<span\; class="notranslate">\; +</span>\mathrm{<span\; class="notranslate">\; 2</span>}<span\; class="notranslate">\; (</span>{\mathrm{<span\; class="notranslate">\; C</span>}}_{\mathrm{<span\; class="notranslate">\; 3</span>}}{\mathrm{<span\; class="notranslate">\; C</span>}}_{\mathrm{<span\; class="notranslate">\; 4</span>}}<span\; class="notranslate">\; +</span>{\mathrm{<span\; class="notranslate">\; C</span>}}_{\mathrm{<span\; class="notranslate">\; 1</span>}}{\mathrm{<span\; class="notranslate">\; C</span>}}_{\mathrm{<span\; class="notranslate">\; 2</span>}}<span\; class="notranslate">\; )</span>{\mathrm{<span\; class="notranslate">\; p</span>}}_{\mathrm{<span\; class="notranslate">\; z</span>}}<span\; class="notranslate">\; +</span>{\mathrm{<span\; class="notranslate">\; C</span>}}_{\mathrm{<span\; class="notranslate">\; 6</span>}}$

Among them, (x _c , y _c ) is the two-dimensional coordinates of the feature points in the camera space, (p _x , p _y , p _z ) is the three-dimensional coordinates of the feature points in the robot space, C=[C ₁ ,C ₂ ,C ₃ ,C ₄ ,C ₅ ,C ₆ ] are mapping relationship parameters. This process is a training step of the mapping relationship parameter, the more the captured second feature point groups, the more accurate the mapping relationship parameter C is.

Step 2, the teaching tool 2 performs virtual operations.

The operator holds the teaching tool 2 to reach the position of the welding spot 52 of the robot operation, simulates the robot's working posture and ensures that the welding torch head at the front port of the teaching tool is on the welding spot 52, and the first feature point 21 on the teaching tool can be captured by the camera unit 3 The camera 21 in the camera observes that the operator holds the teaching tool 2 and arrives at different welding spot positions in sequence.

Step 3, collect the virtual teaching tool information.

All the cameras in the camera unit 3 collect the first feature point 21 on the teaching tool 2 in step 2, save the image of each working position feature point in the camera space, and generate the two-dimensional coordinates of the first feature point 21 in the camera space.

Step 4, position coordinate calculation in robot space.

Based on the mapping relationship between the robot space and the camera space established in step 1, the camera space coordinates (obtained by the image recognition of the feature points) of the first feature point 21 on the teaching tool 2 in the camera space are converted to obtain the robot space coordinates. Three-dimensional coordinate information or joint angle information, and record the joint angle information.

Step 5, automatically generate the robot program.

After teaching, the robot controller 4 sequentially saves the joint angle information recorded in step 4, and generates an instruction program robot program including the three-dimensional robot space coordinates of the first feature point 21 and the joint angle.

Finally, the robot controller 4 executes the program generated in step 5, controls the robot to automatically move to all working positions at the position and posture taught by the operator, and completes the welding task. After the work is completed, the robot returns to the original position and waits for the operator. The next teaching will realize the intelligent programming of the robot.

Claims (6)

1. A virtual teaching robot intelligent programming auxiliary device for learning people, the end of the robot is provided with a working tool (1), it is characterized in that, comprising: A teaching tool (2) identical to the working tool (1) provided at the end of the robot and provided with a first feature point (21), A camera unit (3) that captures and records the movement trajectory of the feature points on the teaching tool (2), the joint angle information of the teaching tool (2) and the operating point of the operation target in chronological order, and A robot controller (4) generating robot work instructions; The working tool (1) is provided with a second feature point (11) corresponding to the first feature point (21) of the teaching tool (2). 2. The virtual teaching robot intelligent programming auxiliary device for learning people according to claim 1, the first feature point (22) includes more than two feature points, and the arrangement between the feature points meets the unique identification teaching tool (2) attitude. 3. the virtual teaching robot intelligent programming auxiliary device for learning people according to claim 2, the first feature point (22) has three, and the distance between the first first feature point and the second first feature point The connection line A is perpendicular to the connection line B between the second first feature point and the third first feature point, and the length of the connection line A is twice the length of the connection line B. 4. according to claim 2 or 3 described learning people's virtual teaching robot intelligent programming auxiliary device, the feature point in the first feature point (22) and the second feature point (11) is LED, black point or white point . 5. A virtual teaching robot intelligent programming method for learning people using the auxiliary device described in any one of the above claims, characterized in that it includes: The teaching tool (2) performs virtual operations, and the camera unit (3) captures the motion trajectory, joint angles, and operating points of the first feature point (21) according to time sequence and generates an image of the first feature point (21). 2D camera space coordinates, The robot controller (01) obtains an instruction program including the robot space three-dimensional coordinates and joint angles of the first feature point (21) according to the camera space coordinates, joint angles, and the operating point of the operation target of the first feature point (21), The robot controller (4) inputs the instruction program into the robot; The robot controller (4) controls the motion track of the second feature point (11) on the working tool (1) according to the robot space three-dimensional coordinate information of the first feature point (21) in the instruction program. 6. the robot intelligent programming method of learning people's virtual teaching according to claim 5 is characterized in that, before the teaching tool (2) carries out the virtual operation, the mapping relationship between the robot space and the camera space is first established, and the specific method is as follows: : The camera unit (3) captures more than three sets of images of the second feature point (11) in operation and obtains the two-dimensional coordinates of the second feature point (11) in camera space; Record the robot joint angle parameters, and obtain the robot space three-dimensional coordinates of the second feature point (11) through the forward kinematics of the robot; Establish the mapping relationship between robot space and camera space ${\mathrm{<span\; class="notranslate">\; x</span>}}_{\mathrm{<span\; class="notranslate">\; c</span>}}<span\; class="notranslate">\; =</span><span\; class="notranslate">\; (</span>{\mathrm{<span\; class="notranslate">\; C</span>}}_{\mathrm{<span\; class="notranslate">\; 1</span>}}^{\mathrm{<span\; class="notranslate">\; 2</span>}}<span\; class="notranslate">\; +</span>{\mathrm{<span\; class="notranslate">\; C</span>}}_{\mathrm{<span\; class="notranslate">\; 2</span>}}^{\mathrm{<span\; class="notranslate">\; 2</span>}}<span\; class="notranslate">\; -</span>{\mathrm{<span\; class="notranslate">\; C</span>}}_{\mathrm{<span\; class="notranslate">\; 3</span>}}^{\mathrm{<span\; class="notranslate">\; 2</span>}}<span\; class="notranslate">\; -</span>{\mathrm{<span\; class="notranslate">\; C</span>}}_{\mathrm{<span\; class="notranslate">\; 4</span>}}^{\mathrm{<span\; class="notranslate">\; 2</span>}}<span\; class="notranslate">\; )</span>{\mathrm{<span\; class="notranslate">\; p</span>}}_{\mathrm{<span\; class="notranslate">\; x</span>}}<span\; class="notranslate">\; +</span>\mathrm{<span\; class="notranslate">\; 2</span>}<span\; class="notranslate">\; (</span>{\mathrm{<span\; class="notranslate">\; C</span>}}_{\mathrm{<span\; class="notranslate">\; 2</span>}}{\mathrm{<span\; class="notranslate">\; C</span>}}_{\mathrm{<span\; class="notranslate">\; 3</span>}}<span\; class="notranslate">\; +</span>{\mathrm{<span\; class="notranslate">\; C</span>}}_{\mathrm{<span\; class="notranslate">\; 1</span>}}{\mathrm{<span\; class="notranslate">\; C</span>}}_{\mathrm{<span\; class="notranslate">\; 4</span>}}<span\; class="notranslate">\; )</span>{\mathrm{<span\; class="notranslate">\; p</span>}}_{\mathrm{<span\; class="notranslate">\; the\; y</span>}}<span\; class="notranslate">\; +</span>\mathrm{<span\; class="notranslate">\; 2</span>}<span\; class="notranslate">\; (</span>{\mathrm{<span\; class="notranslate">\; C</span>}}_{\mathrm{<span\; class="notranslate">\; 2</span>}}{\mathrm{<span\; class="notranslate">\; C</span>}}_{\mathrm{<span\; class="notranslate">\; 4</span>}}<span\; class="notranslate">\; -</span>{\mathrm{<span\; class="notranslate">\; C</span>}}_{\mathrm{<span\; class="notranslate">\; 1</span>}}{\mathrm{<span\; class="notranslate">\; C</span>}}_{\mathrm{<span\; class="notranslate">\; 3</span>}}<span\; class="notranslate">\; )</span>{\mathrm{<span\; class="notranslate">\; p</span>}}_{\mathrm{<span\; class="notranslate">\; z</span>}}<span\; class="notranslate">\; +</span>{\mathrm{<span\; class="notranslate">\; C</span>}}_{\mathrm{<span\; class="notranslate">\; 5</span>}}$ ${\mathrm{<span\; class="notranslate">\; the\; y</span>}}_{\mathrm{<span\; class="notranslate">\; c</span>}}<span\; class="notranslate">\; =</span>\mathrm{<span\; class="notranslate">\; 2</span>}<span\; class="notranslate">\; (</span>{\mathrm{<span\; class="notranslate">\; C</span>}}_{\mathrm{<span\; class="notranslate">\; 2</span>}}{\mathrm{<span\; class="notranslate">\; C</span>}}_{\mathrm{<span\; class="notranslate">\; 3</span>}}<span\; class="notranslate">\; -</span>{\mathrm{<span\; class="notranslate">\; C</span>}}_{\mathrm{<span\; class="notranslate">\; 1</span>}}{\mathrm{<span\; class="notranslate">\; C</span>}}_{\mathrm{<span\; class="notranslate">\; 4</span>}}<span\; class="notranslate">\; )</span>{\mathrm{<span\; class="notranslate">\; p</span>}}_{\mathrm{<span\; class="notranslate">\; x</span>}}<span\; class="notranslate">\; +</span><span\; class="notranslate">\; (</span>{\mathrm{<span\; class="notranslate">\; C</span>}}_{\mathrm{<span\; class="notranslate">\; 1</span>}}^{\mathrm{<span\; class="notranslate">\; 2</span>}}<span\; class="notranslate">\; -</span>{\mathrm{<span\; class="notranslate">\; C</span>}}_{\mathrm{<span\; class="notranslate">\; 2</span>}}^{\mathrm{<span\; class="notranslate">\; 2</span>}}<span\; class="notranslate">\; +</span>{\mathrm{<span\; class="notranslate">\; C</span>}}_{\mathrm{<span\; class="notranslate">\; 3</span>}}^{\mathrm{<span\; class="notranslate">\; 2</span>}}<span\; class="notranslate">\; -</span>{\mathrm{<span\; class="notranslate">\; C</span>}}_{\mathrm{<span\; class="notranslate">\; 4</span>}}^{\mathrm{<span\; class="notranslate">\; 2</span>}}<span\; class="notranslate">\; )</span>{\mathrm{<span\; class="notranslate">\; p</span>}}_{\mathrm{<span\; class="notranslate">\; the\; y</span>}}<span\; class="notranslate">\; +</span>\mathrm{<span\; class="notranslate">\; 2</span>}<span\; class="notranslate">\; (</span>{\mathrm{<span\; class="notranslate">\; C</span>}}_{\mathrm{<span\; class="notranslate">\; 3</span>}}{\mathrm{<span\; class="notranslate">\; C</span>}}_{\mathrm{<span\; class="notranslate">\; 4</span>}}<span\; class="notranslate">\; +</span>{\mathrm{<span\; class="notranslate">\; C</span>}}_{\mathrm{<span\; class="notranslate">\; 1</span>}}{\mathrm{<span\; class="notranslate">\; C</span>}}_{\mathrm{<span\; class="notranslate">\; 2</span>}}<span\; class="notranslate">\; )</span>{\mathrm{<span\; class="notranslate">\; p</span>}}_{\mathrm{<span\; class="notranslate">\; z</span>}}<span\; class="notranslate">\; +</span>{\mathrm{<span\; class="notranslate">\; C</span>}}_{\mathrm{<span\; class="notranslate">\; 6</span>}}$ Among them, (x _c , y _c ) are the two-dimensional coordinates of the camera space of the second feature point (11), (p _x , p _y , p _z ) are the three-dimensional coordinates of the second feature point (11) in the robot space, and C =[C ₁ , C ₂ , C ₃ , C ₄ , C ₅ , C ₆ ] are mapping relationship parameters.