Manipulator operation positioning method

Abstract

The invention relates to a manipulator operation positioning method, which comprises an initialization step, a manipulator obtains a relation between an actual distance B and a pixel distance A of a positioning element on a positioning identifier between X and Y directions according to a certain shooting focal length and different operation distances Z in an initialization scene, namely, a set of a ratio C of B to A is obtained, or a function relation f (Z) = C of C and Z is obtained; when a task is executed, the distance between the manipulator and the target object is the operation distance Z, the operation distance Z is directly measured through the distance measuring device, and the displacement between the manipulator and the target object in the X direction and the Y direction is calculated through the relation between C and Z. Finally, the manipulator and the target object are subjected to multi-time translation correction in the XY direction to meet the precision requirement range of task execution of the manipulator, a multi-time translation positioning mode is adopted, accurate and efficient positioning is achieved, the manipulator application scene with the high precision requirement can be met, and it is ensured that the manipulator executes related tasks accurately and reliably.

Description

[Technical field]

[0001] The present invention relates to the field of robot technology, and in particular to a manipulator operation positioning method. [Background Technology]

[0002] Existing robots are mainly divided into two types. One is installed in a fixed position and operates on a specific target according to a fixed process. The operating steps are determined by program programming, such as ordinary industrial robots. The other is a manually controlled robot, such as drones and robot dogs, which can only operate on the corresponding target object through real-time human control intervention.

[0003] In the process of robot control, the positioning of the target object is particularly critical. How to accurately and efficiently position the target object is the prerequisite for the robot to perform tasks. In the prior art, robots usually use binocular vision or laser radar for positioning. Whether it is binocular vision positioning or laser radar positioning, the positioning method is based on angle positioning calculation, and angle positioning has the defects of magnification error and uncorrectable defects, and its error accuracy is greater than 5cm. For some application scenarios with high precision requirements, robots using the above positioning method cannot be used.

[0004] The present invention is developed and proposed in view of the deficiencies in the prior art. [Summary of the invention]

[0005] The present invention overcomes the shortcomings of the prior art and provides a manipulator operation positioning method, comprising an initialization step. During initialization, the manipulator obtains the relationship between the actual distance B between the positioning elements on the positioning mark in the X and Y directions and the pixel distance A according to a certain shooting focal length and at different operating distances Z in the initialization scene, that is, a set of B-A ratios C is obtained, or a functional relationship f(Z)=C between C and Z; when used to perform a specific task, the distance between the manipulator and the target is the operating distance Z, and the operating distance Z is directly measured by a distance measuring device, and the displacement between the manipulator and the target in the XY direction is obtained by the relationship between the C value obtained by initialization and the operating distance Z, and is calculated according to the principle of visual calibration. Finally, the manipulator and the target are corrected by multiple translations in the XY direction to meet the accuracy requirement range of the manipulator to perform the task, and a positioning method of multiple translations is adopted to achieve accurate and efficient positioning, which can meet the application scenarios of the manipulator with high precision requirements and ensure that the manipulator is accurate and reliable when performing related tasks.

[0006] To achieve the above object, the present invention provides a manipulator operation positioning method, wherein the manipulator is provided with a visual shooting device and a distance measuring device, comprising the steps of:

[0007] S1. Setting an initialization scene including a positioning mark, the positioning mark having a plurality of positioning elements, and the actual distance between two adjacent positioning elements in the X and Y directions is a constant B, and the manipulator is configured to shoot the initialization scene at different operating distances Z;

[0008] S2, the visual shooting device takes a picture of the collection range containing the positioning mark to obtain an image containing the positioning mark;

[0009] S3, identifying the positioning mark in the image to obtain the pixel distance A between the positioning elements in the image in the X and Y directions;

[0010] S4. Under the operation distance Z, determine that the ratio of the actual distance B to the pixel distance A is C;

[0011] S5, repeat S1-S4 to obtain a set of ratios C of the actual distance B to the pixel distance A at different operation distances Z, or obtain a functional relationship f(Z)=C between C and Z at different operation distances Z;

[0012] The above-mentioned robot operation positioning method further includes the following steps after step S4 or S5:

[0013] S6, the robot accepts the work task;

[0014] S7, the manipulator goes to the working position and determines the collection range;

[0015] S8, sending a detection signal to the collection range, and obtaining the operating distance Z between the manipulator and the collection range after feedback;

[0016] S9, the visual shooting device takes a picture of the acquisition range containing the positioning mark to obtain an image containing the positioning mark and the target object, identifies the positioning mark in the image and obtains the pixel coordinates (X 0 , Y 0 ), and identify the target in the image and obtain its pixel coordinates (X 1 , Y 1 ), according to the pixel coordinates (X 0 , Y 0 ) and the pixel coordinates of the target object (X 1 , Y 1 ), calculate the relative pixel coordinates of the target object between the positioning element of the positioning mark in the image and the target object (X 2 , Y 2 ), and then according to the ratio C corresponding to the corresponding operation distance Z and the relative target pixel coordinates (X 2 , Y 2 ), calculate the physical displacement S of the manipulator relative to the target in the XY direction;

[0017] Or the visual shooting device takes a picture of the collection range containing the target object to obtain an image containing the target object and the center coordinates (X 3 , Y 3 ), and identify the target in the image and obtain its pixel coordinates (X 1 , Y 1 ), according to the center coordinates of the image (X 3 , Y 3 ) and the pixel coordinates of the target object (X 1 , Y 1 ), calculate the relative image center pixel coordinates (X 4 , Y 4 ), and then according to the ratio C corresponding to the corresponding operation distance Z and the relative image center pixel coordinate (X 4 , Y 4 ), calculate the physical displacement S of the manipulator relative to the target in the XY direction;

[0018] S10, according to the physical displacement S, the manipulator moves toward the target object accordingly;

[0019] S11, looping step S8 to step S10 until the relative displacement between the manipulator and the target object is within a preset accuracy range of the manipulator operation;

[0020] S12. Complete the robot operation positioning and perform corresponding work tasks.

[0021] In the above-mentioned robot operation positioning method, the visual shooting device is a monocular camera, and the distance measuring device is a laser rangefinder or a radar rangefinder.

[0022] As described above, a robot operation positioning method, the robot initialization setting includes steps S1-S5, and the set of ratios C in step S5 is stored in the robot system in the form of a data table for subsequent operation calls, or the corresponding C values ​​under different Z values ​​are obtained according to the functional relationship between C and Z f(Z)=C.

[0023] In the above-mentioned robot operation positioning method, the robot is provided with a projection device for projecting a positioning mark onto an initialization scene. In step S1, the projection device projects a positioning mark onto the initialization scene at different operation distances Z.

[0024] In the above-mentioned robot operation positioning method, in step S1, a positioning mark is manually set in an initialization scene.

[0025] In the above-mentioned robot operation positioning method, in steps S1-S4, the robot moves relative to the positioning mark to automatically obtain a set of ratios C of the actual distance B to the pixel distance A at different operation distances Z.

[0026] In the above-mentioned robot operation positioning method, in step 8, if a detection signal is sent to the collection range and no feedback is obtained after obtaining the operation distance Z between the robot and the collection range, the operation distance is assigned as Z n , according to the set C at the operating distance Z n Next, we get the corresponding C n , and then calculate the physical displacement S of the manipulator relative to the target object. The manipulator moves toward the target object accordingly according to the physical displacement S, and then sends a detection signal to the collection range. After feedback, the operating distance Z between the manipulator and the collection range is obtained.

[0027] In the above-mentioned robot operation positioning method, in step S10, if the robot moves beyond the target object in the XY direction, the movement value in the XY direction is calculated according to the C value corresponding to the current Z and the robot moves in the reverse direction; if the robot moves beyond the target object in the XY direction in the reverse direction, the movement value in the XY direction is continued to be calculated according to the C value corresponding to the current Z and the robot moves forward;

[0028] Alternatively, in step S10, if the robot moves beyond the target in the XY direction, it moves in the reverse direction by a value smaller than the last XY direction movement; if the robot moves in the reverse direction beyond the target, it continues to move forward by a value smaller than the last XY direction movement.

[0029] Compared with the prior art, the robot operation positioning method of the present invention has the following advantages:

[0030] 1. The distance between the manipulator and the target in the Z direction is directly measured by the distance measuring device, and the displacement between the manipulator and the target in the XY direction is calculated by the relationship between the C value obtained by initialization and the operating distance Z, and according to the principle of visual calibration. The manipulator undergoes multiple translation corrections in the XY direction to meet the accuracy requirements of the manipulator's task execution, thereby achieving accurate and high-precision positioning of the target.

[0031] 2. The present invention can obtain a set of ratios C of the actual distance B to the pixel distance A at different operating distances Z through an initialization step, or obtain a functional relationship f(Z)=C between C and Z at different operating distances Z, which lays a foundation for achieving accurate positioning results through multiple translation calculations of the manipulator.

[0032] 3. The method of the present invention calculates the physical displacement S of the manipulator relative to the target object, and then the manipulator translates in the XY direction relative to the target object to achieve accurate positioning. This method avoids the defects of angle positioning that cannot be corrected and errors that are magnified. Therefore, the method of the present invention can be used for the manipulator to position the target object in scenes with high precision requirements.

[0033] 4. Using visual calibration, at different operating distances Z, the physical displacement S of the manipulator relative to the target object is calculated using the positioning mark as a reference. Therefore, the manipulator can obtain multiple translation corrections in the XY direction to ensure accurate positioning of the target object. [Drawings]

[0034] Figure 1 It is a schematic diagram of a positioning mark containing a positioning element in the present invention.

[0035] Figure 2 This is a schematic diagram of another positioning mark containing positioning elements in the present invention.

[0036] Figure 3 This is a logical schematic diagram for initializing the present invention.

[0037] Figure 4 The working logic principle diagram for positioning of the present invention. [Specific implementation method]

[0038] The technical solutions in the embodiments of the present invention will be described clearly and completely below in conjunction with the accompanying drawings.

[0039] The present invention provides a manipulator operation positioning method, wherein the manipulator is configured to be movable in a working environment, and is provided with a visual shooting device and a distance measuring device, wherein the visual shooting device is a monocular camera, such as the monocular camera of Hikvision, model DS-2CD6B45DWD-U400w; and the distance measuring device is a laser rangefinder or a radar distance measuring device, such as the laser distance measuring sensor of Tianjin Yike, model OSM40-KL800CB6 / 485. When initializing, such as Figure 3 As shown, the steps include:

[0040] S1. Set an initialization scene including a positioning mark. The positioning mark has several positioning elements, and the actual distance between two adjacent positioning elements in the X and Y directions is a constant B. The manipulator is configured to shoot the initialization scene at different operating distances Z. In this step, a projection device is set on the manipulator, such as the projection device disclosed in Chinese Patent 202211204537.0. The projection device automatically projects the positioning mark to the initialization scene at different operating distances Z. During the process of the projection device automatically projecting the positioning mark at different operating distances Z in the initialization scene, its parameters remain unchanged. Or in this step, manually set the positioning mark in the initialization scene. For the graphics of the positioning mark, such as Figure 1 or Figure 2 shown.

[0041] S2. Adjust the shooting focal length of the visual shooting device and set it to remain unchanged. The visual shooting device takes a picture of the collection range containing the automatically placed or manually set positioning mark to obtain an image containing the positioning mark.

[0042] S3. Identify the positioning mark in the image to obtain the pixel distance A between the positioning elements in the image in the X and Y directions.

[0043] S4. Under the operating distance Z, determine that the ratio of the actual distance B to the pixel distance A is C.

[0044] S5. Repeat S1-S4 to obtain a set of ratios C of the actual distance B to the pixel distance A at different operating distances Z, or obtain a functional relationship f(Z)=C between C and Z at different operating distances Z; in this step, the set of ratios C is stored in the manipulator system in the form of a data table for subsequent operation calls, or the corresponding C values ​​at different Z values ​​are obtained according to the functional relationship f(Z)=C between C and Z, thereby completing the manipulator initialization.

[0045] In the above steps S1-S4, the manipulator moves relative to the positioning mark to automatically obtain a set of ratios C of the actual distance B to the pixel distance A at different operating distances Z.

[0046] like Figure 4 As shown, the manipulator operation positioning method described in the present invention, when the manipulator completes the above initialization steps to operate and position, includes the steps of:

[0047] S6. The robot accepts the work task.

[0048] S7. The robot moves to the working position and determines the collection range.

[0049] S8, send a detection signal to the collection range, and get the operating distance Z between the manipulator and the collection range after feedback; in this step, if a detection signal is sent to the collection range, and there is no feedback to get the operating distance Z between the manipulator and the collection range, then the operating distance is assigned as Z n , according to the set C at the operating distance Z n Next, we get the corresponding C n According to the visual calibration, the physical displacement S of the manipulator relative to the target object in the XY direction is calculated. The manipulator moves toward the target object according to the physical displacement S, and then sends a detection signal to the collection range. After feedback, the operating distance Z between the manipulator and the collection range is obtained.

[0050] S9, the visual shooting device takes a picture of the acquisition range containing the positioning mark to obtain an image containing the positioning mark and the target object, wherein the positioning mark is relatively fixedly arranged on the manipulator, and the visual shooting device can take a picture of the target object in the acquisition range together with the positioning mark; recognize the positioning mark in the image to obtain the pixel coordinates (X 0 , Y 0 ), and identify the target in the image and obtain its pixel coordinates (X 1 , Y 1 ), according to the pixel coordinates (X 0 , Y 0 ) and the pixel coordinates of the target object (X 1 , Y 1 ), calculate the relative pixel coordinates of the target object between the positioning element of the positioning mark in the image and the target object (X 2 , Y 2 ), and then according to the ratio C corresponding to the corresponding operation distance Z and the relative target pixel coordinates (X 2 , Y 2 ), calculate the physical displacement S of the manipulator relative to the target in the XY direction; or the visual shooting device takes a picture of the collection range containing the target to obtain an image containing the target and the center coordinates of the image (X 3 , Y 3 ), and identify the target in the image and obtain its pixel coordinates (X 1 , Y 1 ), according to the center coordinates of the image (X 3 , Y 3 ) and the pixel coordinates of the target object (X 1 , Y 1 ), calculate the relative image center pixel coordinates (X 4 , Y 4 ), and then according to the ratio C corresponding to the corresponding operation distance Z and the relative image center pixel coordinate (X 4, Y 4 ), and calculate the physical displacement S of the manipulator relative to the target object in the XY direction.

[0051] S10, according to the physical displacement S, the manipulator moves in the XY direction toward the target object. In this step, if the manipulator moves beyond the target object in the XY direction, the movement value in the XY direction is calculated according to the C value corresponding to the current Z and moves in the reverse direction. If the manipulator moves in the XY direction in the reverse direction and exceeds the target object, the movement value in the XY direction is continued to be calculated according to the C value corresponding to the current Z and moves forward; or in step S10, if the manipulator moves beyond the target object in the XY direction, the movement value in the XY direction is taken to be less than the last movement value in the XY direction and moves in the reverse direction. If the manipulator moves in the XY direction in the reverse direction and exceeds the target object, the movement value in the XY direction is continued to be less than the last movement value in the XY direction and moves forward.

[0052] S11, looping step S8 to step S10, the manipulator translates in the XY direction relative to the target object for multiple times until the relative displacement between the manipulator and the target object is within a preset accuracy range of the manipulator operation.

[0053] S12. Complete the robot operation positioning and perform corresponding work tasks.

[0054] Therefore, when the manipulator positions the target object, the method of the present invention first directly measures the operating distance Z, and uses the relationship between the operating distance Z and C to calculate the physical displacement S of the manipulator relative to the target object in the XY direction according to visual calibration. The manipulator then translates in the XY direction relative to the target object to achieve accurate positioning. This method avoids the defects of angle positioning that cannot be corrected and errors can be amplified. Therefore, the method of the present invention can be used for the manipulator to position the target object in scenarios with high precision requirements.

[0055] It should be noted that for the method of the present invention, in order to ensure normal and reliable use, when the manipulator performs and completes initialization, the shooting focal length of the visual shooting device on the manipulator is set, and when shooting in subsequent tasks, the same shooting focal length as that of initialization is used. If the shooting focal length of the visual shooting device is adjusted, the manipulator needs to be reinitialized. In addition, during the execution of the task by the manipulator, such as when its projection device automatically projects the positioning mark to the acquisition range at different operating distances Z, the projection device parameters are also consistent with the parameters adjusted and set during initialization.

Claims

1. A manipulator operation positioning method, characterized in that The manipulator is provided with a visual shooting device and a distance measuring device, including the following steps: S1. Setting an initialization scene including a positioning mark, the positioning mark having a plurality of positioning elements, and the actual distance between two adjacent positioning elements in the X and Y directions is a constant B, and the manipulator is configured to shoot the initialization scene at different operating distances Z; S2, the visual shooting device takes a picture of the collection range containing the positioning mark to obtain an image containing the positioning mark; S3, identifying the positioning mark in the image to obtain the pixel distance A between the positioning elements in the image in the X and Y directions; S4. Under the operation distance Z, determine that the ratio of the actual distance B to the pixel distance A is C; S5. Repeat S1-S4 to obtain a set of ratios C of the actual distance B to the pixel distance A at different operation distances Z, or obtain a functional relationship f(Z)=C between C and Z at different operation distances Z.

2. A manipulator operation positioning method according to claim 1, characterized in that The method further comprises the following steps after step S4 or S5: S6, the robot accepts the work task; S7, the manipulator goes to the working position and determines the collection range; S8, sending a detection signal to the collection range, and obtaining the operating distance Z between the manipulator and the collection range after feedback; S9, the visual shooting device takes a picture of the acquisition range containing the positioning mark to obtain an image containing the positioning mark and the target object, identifies the positioning mark in the image and obtains the pixel coordinates (X 0 ,Y 0 ), and identify the target in the image and obtain its pixel coordinates (X 1 ,Y 1 ), according to the pixel coordinates (X 0 ,Y 0 ) and the pixel coordinates of the target object (X 1 ,Y 1 ), calculate the relative pixel coordinates of the target object between the positioning element of the positioning mark in the image and the target object (X 2 ,Y 2 ), and then according to the ratio C corresponding to the corresponding operation distance Z and the relative target pixel coordinates (X 2 ,Y 2 ), calculate the physical displacement S of the manipulator relative to the target in the XY direction; Or the visual shooting device takes a picture of the collection range containing the target object to obtain an image containing the target object and the center coordinates (X 3 ,Y 3 ), and identify the target in the image and obtain its pixel coordinates (X 1 ,Y 1 ), according to the center coordinates of the image (X 3 ,Y 3 ) and the pixel coordinates of the target object (X 1 ,Y 1 ), calculate the relative image center pixel coordinates (X 4 ,Y 4 ), and then according to the ratio C corresponding to the corresponding operation distance Z and the relative image center pixel coordinates (X 4 ,Y 4 ), calculate the physical displacement S of the manipulator relative to the target in the XY direction; S10, according to the physical displacement S, the manipulator moves toward the target object accordingly; S11, looping step S8 to step S10 until the relative displacement between the manipulator and the target object is within a preset accuracy range of the manipulator operation; S12. Complete the robot operation positioning and perform corresponding work tasks.

3. A manipulator operation positioning method according to claim 1, characterized in that The visual shooting device is a monocular camera, and the distance measuring device is a laser rangefinder or a radar rangefinder.

4. A manipulator operation positioning method according to claim 1, characterized in that The robot initialization setting includes steps S1-S5. In step S5, the set of ratios C is stored in the robot system in the form of a data table for subsequent operation calls, or the corresponding C values ​​under different Z values ​​are obtained according to the functional relationship between C and Z f(Z)=C.

5. A manipulator operation positioning method according to claim 1, characterized in that The robot is provided with a projection device for projecting a positioning mark onto the initialization scene. In step S1, the projection device projects a positioning mark onto the initialization scene at different operating distances Z.

6. A manipulator operation positioning method according to claim 1, characterized in that In step S1, a positioning mark is manually set in the initialization scene.

7. A manipulator operation positioning method according to claim 1, characterized in that In steps S1-S4, the manipulator moves relative to the positioning mark to automatically obtain a set of ratios C of the actual distance B to the pixel distance A at different operating distances Z.

8. A manipulator operation positioning method according to claim 2, characterized in that In step 8, if a detection signal is sent to the collection range and no feedback is obtained after obtaining the operating distance Z between the manipulator and the collection range, the assigned operating distance is Z n , according to the set C at the operating distance Z n Next, we get the corresponding C n ,,Then the physical displacement S of the manipulator relative to the target object is calculated. The manipulator moves toward the target object accordingly according to the physical displacement S, and then sends a detection signal to the collection range. After feedback, the operating distance Z between the manipulator and the collection range is obtained.

9. A manipulator operation positioning method according to claim 2, characterized in that In step S10, if the manipulator moves beyond the target object in the XY direction, the movement value in the XY direction is calculated according to the C value corresponding to the current Z and the manipulator moves in the reverse direction. If the manipulator moves beyond the target object in the XY direction in the reverse direction, the movement value in the XY direction is calculated according to the C value corresponding to the current Z and the manipulator moves forward. Alternatively, in step S10, if the robot moves beyond the target in the XY direction, it moves in the reverse direction by a value smaller than the last XY direction movement; if the robot moves in the reverse direction beyond the target, it continues to move forward by a value smaller than the last XY direction movement.

Images