An intelligent control method and system based on a target calibration and positioning model

Abstract

The present invention discloses an intelligent control method and system based on a target calibration and positioning model, including: obtaining the pose of the end of the actuator under the main camera by using a target of an auxiliary camera, a main camera and a calibration actuator, obtaining the pose of the target part under the main camera, and the actuator is installed at the end of the robotic arm through a flange; calculating the pose of the target part under the screwdriver according to the pose and the pose; establishing a coordinate model of the target part in the reference coordinate system based on the pose of the target part under the screwdriver, the pose of the screwdriver under the flange of the robotic arm, and the pose of the flange in the reference coordinate system; controlling the movement of the robotic arm according to the coordinate model of the target part in the reference coordinate system, and driving the actuator to process the target part; simplifying the control process of the robotic arm and avoiding being restricted by environmental factors.

Description

Technical Field

[0001] The present invention belongs to the technical field of machine vision, and particularly relates to an intelligent control method and system based on a target calibration and positioning model. Background Art

[0002] In recent years, manipulator control, as a technology with great prospects and application value, has played an important role in fields such as automobile manufacturing, fruit picking, assembly line operations, and surgical operations, and is of great significance to the development of industry, agriculture, and manufacturing. Most multi-degree-of-freedom manipulator systems are essentially a semi-closed-loop control structure. The system can only accurately control the position of the joint servo motor, and the relationship between the motor position and the position of the end effector of the manipulator is determined by kinematics. At present, due to the influence of processing and assembly, the manipulators produced by domestic and foreign manipulator manufacturers cannot ensure the absolute fit of each module. Moreover, non-geometric factors such as motor wear and external noise directly affect the model parameters of the manipulator during operation, resulting in an inevitable error between the theoretical kinematic model and the actual model, thus leading to an error in the end position.

[0003] Under the current environment, the manipulator and the end of the actuator are usually calibrated based on monocular vision and binocular vision to assist in completing the control actions of the manipulator. However, the control method based on binocular vision is relatively cumbersome, and the control method based on monocular vision is restricted by environmental factors. Summary of the Invention

[0004] The present invention provides an intelligent control method and system based on a target calibration and positioning model, which simplifies the control process of the manipulator and avoids being restricted by environmental factors.

[0005] To achieve the above object, the technical solution adopted by the present invention is:

[0006] The first aspect of the present invention provides an intelligent control method based on a target calibration and positioning model, including:

[0007] Obtaining the pose of the end of the actuator under the main camera by using an auxiliary camera, a main camera, and a target for calibrating the actuator The auxiliary camera and the main camera form a binocular camera, and the auxiliary camera and the main camera are respectively arranged on both sides of the actuator;

[0008] Obtaining the pose of the target part under the main camera The actuator is installed at the end of the manipulator through a flange; according to the pose and the pose Calculating and obtaining the pose of the target part under the screwdriver;

[0009] Based on the pose of the target part under the screwdriver, the pose of the screwdriver under the flange of the robotic arm, and the pose of the flange in the reference coordinate system, establish the coordinate model of the target part in the reference coordinate system; control the movement of the robotic arm according to the coordinate model of the target part in the reference coordinate system, and drive the actuator to process the target part.

[0010] Preferably, use the auxiliary camera, the main camera, and the target for calibrating the actuator to obtain the pose of the end of the actuator under the main camera The method includes:

[0011] Obtain the relative pose relationship of the binocular cameras by mutual calibration between the auxiliary camera and the main camera;

[0012] Use the auxiliary camera to collect images of the positioning area of the target to establish a target template; use the deformable template matching algorithm to identify the target template to obtain the two-dimensional pixel coordinates of the target positioning points, and the target positioning points form the edge line of the target positioning area;

[0013] Convert the two-dimensional pixel coordinates of the target positioning points into three-dimensional coordinates in the world coordinate system; obtain the pose of the end of the actuator under the auxiliary camera according to the fixed position relationship between the target and the actuator;

[0014] Based on the pose of the end of the actuator under the auxiliary camera and the relative pose relationship of the binocular cameras, calculate the pose of the end of the actuator under the main camera Wherein, Represents the rotation matrix from the end of the actuator to the main camera, Represents the translation vector from the end of the actuator to the main camera.

[0015] Preferably, the method for obtaining the relative pose relationship of the binocular cameras by mutual calibration between the auxiliary camera and the main camera includes:

[0016] After installing the auxiliary camera and the main camera on both sides of the actuator respectively, establish an auxiliary camera coordinate system and a main camera coordinate system for the auxiliary camera and the main camera respectively, and calibrate the relative pose of the binocular cameras; the relative pose of the binocular cameras includes the rotation matrix from the auxiliary camera to the main camera And the translation vector from the auxiliary camera to the main camera

[0017] Preferably, the method for converting the two-dimensional pixel coordinates of the target positioning points into three-dimensional coordinates in the world coordinate system includes: converting the two-dimensional pixel coordinates of the target positioning points into three-dimensional coordinates in the auxiliary camera coordinate system through the PnP algorithm, and converting the three-dimensional coordinates of the target positioning points in the auxiliary camera coordinate system into three-dimensional coordinates in the world coordinate system through the ICP algorithm.

[0018] Preferably, the method for fixing the target of the calibration actuator includes:

[0019] Set the target at a set distance l from the flange of the robotic arm, and at the same time, set the target within the field of view of the auxiliary camera, with the target perpendicular to the axis of the actuator; Set the origin of the target coordinate system on the axis of the actuator; wherein, the axes of the actuator, the main camera, and the auxiliary camera are parallel to each other.

[0020] Preferably, based on the pose of the end of the actuator under the auxiliary camera and the relative pose relationship of the binocular cameras, calculate the pose of the end of the actuator under the main camera The method includes:

[0021]

[0022]

[0023] In the formula, t x is the coordinate of the origin of the target coordinate with respect to the auxiliary camera coordinate system in the x-axis direction; t y is the coordinate of the origin of the target coordinate with respect to the auxiliary camera in the y direction, and t z is the coordinate of the origin of the target coordinate with respect to the auxiliary camera coordinate system in the z-axis direction; represents the translation vector from the end of the actuator to the auxiliary camera; represents the rotation matrix from the end of the actuator to the auxiliary camera.

[0024] Preferably, the method for obtaining the pose of the target part under the main camera The method includes:

[0025] Use the main camera to collect images of the target part to establish a target part template; Use the deformable template matching algorithm to identify the target part template to obtain the two-dimensional pixel coordinates of the target part positioning points, and the edge lines of the target part are composed of each target part positioning point;

[0026] Convert the two-dimensional pixel coordinates of the target part positioning points to three-dimensional coordinates in the main camera coordinate system through the PnP algorithm, and convert the three-dimensional coordinates of the target part positioning points in the main camera coordinate system to three-dimensional coordinates in the world coordinate system through the ICP algorithm to obtain the pose of the target part under the main camera Wherein, represents the rotation matrix from the target part to the main camera; represents the translation vector from the target part to the main camera.

[0027] Preferably, the method for establishing the coordinate model of the target part in the reference coordinate system based on the lower pose of the target part in the screwdriver, the pose of the screwdriver under the flange of the robotic arm, and the pose of the flange in the reference coordinate system includes:

[0028]

[0029]

[0030]

[0031] In the formula, R hb represents the rotation matrix from the flange of the robotic arm to the origin of the reference coordinate system; T hb represents the translation vector from the flange of the robotic arm to the origin of the reference coordinate system; R th represents the rotation matrix from the actuator to the flange of the robotic arm; T th represents the translation vector from the actuator to the flange of the robotic arm; R final represents the rotation matrix from the actuator to the origin of the reference coordinate system; T final represents the translation vector from the actuator to the origin of the reference coordinate system.

[0032] The second aspect of the present invention provides an intelligent control system based on a target calibration and positioning model, including:

[0033] A calibration module for obtaining the pose of the end of the actuator under the main camera by using the target of the auxiliary camera, the main camera, and the calibration actuator The auxiliary camera and the main camera form a binocular camera, and the auxiliary camera and the main camera are respectively arranged on both sides of the actuator;

[0034] A processing and analysis module for obtaining the pose of the target part under the main camera The actuator is installed at the end of the robotic arm through a flange; according to the pose and the pose calculate to obtain the lower pose of the target part in the screwdriver;

[0035] A control module for establishing the coordinate model of the target part in the reference coordinate system based on the lower pose of the target part in the screwdriver, the pose of the screwdriver under the flange of the robotic arm, and the pose of the flange in the reference coordinate system; controlling the movement of the robotic arm according to the coordinate model of the target part in the reference coordinate system, and driving the actuator to process the target part.

[0036] Preferably, the actuator is set as an electric screwdriver.

[0037] In the third aspect of the present invention, a computer-readable storage medium is provided, on which a computer program is stored, and when the program is executed by a processor, the steps of the intelligent control method described in the first aspect are implemented.

[0038] Compared with the prior art, the beneficial effects of the present invention are as follows:

[0039] The present invention uses the targets of the auxiliary camera, the main camera and the calibration actuator to obtain the pose of the end of the actuator under the main camera. The auxiliary camera and the main camera form a binocular camera, and the auxiliary camera and the main camera are respectively arranged on both sides of the actuator; only the main camera and the actuator need to be calibrated through the auxiliary camera and the target. After the calibration of the end of the mechanism is completed, the auxiliary camera and the target are removed, and then it can be directly installed on the flange of the robotic arm for use. The process is simple and easy to operate, and is suitable for some occasions where calibration is inconvenient to carry out.

[0040] According to the pose of the present invention and the pose the pose of the target part under the screwdriver is calculated and obtained; based on the pose of the target part under the screwdriver, the pose of the screwdriver under the flange of the robotic arm, and the pose of the flange in the reference coordinate system, the coordinate model of the target part in the reference coordinate system is established; according to the coordinate model of the target part in the reference coordinate system, the robotic arm is controlled to move, and the actuator is driven to process the target part; only the main camera is needed to identify the target part and send the position information to the robotic arm, which simplifies the control process of the robotic arm and at the same time avoids being restricted by environmental factors. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] Figure 1 is a flowchart of the intelligent control method provided in Embodiment 1;

[0042] Figure 2 is a structural diagram of the binocular camera and the electric screwdriver provided in Embodiment 1;

[0043] Figure 3 is a structural diagram of the robotic arm and the electric screwdriver provided in Embodiment 1. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0044] The present invention will be further described below with reference to the drawings. The following embodiments are only used to more clearly illustrate the technical solutions of the present invention and cannot be used to limit the protection scope of the present invention.

[0045] Embodiment 1

[0046] As Figures 1 to 3 shown, this embodiment provides an intelligent control method based on a target calibration and positioning model, including:

[0047] Install the auxiliary camera and the main camera on both sides of the actuator respectively. In this embodiment, the actuator is set on an electric screwdriver, and the auxiliary camera and the main camera form a binocular camera; establish an auxiliary camera coordinate system and a main camera coordinate system for the auxiliary camera and the main camera, and calibrate the relative pose of the binocular camera; the relative pose of the binocular camera includes the rotation matrix from the auxiliary camera to the main camera and the translation vector from the auxiliary camera to the main camera

[0048] The fixed method of the target of the actuator calibration includes:

[0049] Set the target at a set distance l from the flange of the robotic arm, and at the same time set the target within the field of view of the auxiliary camera, and the target is perpendicular to the axis of the actuator; set the origin of the target coordinate system on the axis of the actuator; wherein, the axes of the actuator, the main camera, and the auxiliary camera are parallel to each other.

[0050] Use the auxiliary camera to collect images of the positioning area of the target to establish a target template; use the deformable template matching algorithm to identify the target template to obtain the two-dimensional pixel coordinates of the target positioning points, and each target positioning point forms the edge line of the target positioning area.

[0051] Convert the two-dimensional pixel coordinates of the target positioning points to three-dimensional coordinates in the auxiliary camera coordinate system through the PnP algorithm, convert the three-dimensional coordinates of the target positioning points in the auxiliary camera coordinate system to three-dimensional coordinates in the world coordinate system through the ICP algorithm, and obtain the pose of the end of the actuator under the auxiliary camera according to the fixed position relationship between the target and the actuator.

[0052] Based on the pose of the end of the actuator under the auxiliary camera and the relative pose relationship of the binocular camera, calculate the pose of the end of the actuator under the main camera The calculation formula is:

[0053]

[0054]

[0055] Among them, represents the rotation matrix from the end of the actuator to the main camera, represents the translation vector from the end of the actuator to the main camera; t x is the coordinate of the origin of the target coordinate relative to the auxiliary camera coordinate system in the x-axis direction; t y is the coordinate of the origin of the target coordinate relative to the auxiliary camera in the y direction, t z the coordinate of the origin of the target coordinate relative to the auxiliary camera coordinate system in the z-axis direction; represents the translation vector from the end of the actuator to the auxiliary camera; It is represented as the rotation matrix from the end of the actuator to the auxiliary camera.

[0056] After the calibration of the end of the mechanism is completed, the auxiliary camera and the target are removed. Then, the actuator can be directly installed on the flange of the robotic arm for use. The process is simple and easy to operate, and it is suitable for some occasions where calibration is inconvenient.

[0057] Obtain the pose of the target part under the main camera The method includes:

[0058] Use the main camera to collect images of the target part to establish a target part template; use the deformable template matching algorithm to identify the target part template to obtain the two-dimensional pixel coordinates of the target part positioning points, and the target part positioning points form the edge line of the target part;

[0059] Convert the two-dimensional pixel coordinates of the target part positioning points to three-dimensional coordinates in the main camera coordinate system through the PnP algorithm, and convert the three-dimensional coordinates of the target part positioning points in the main camera coordinate system to three-dimensional coordinates in the world coordinate system through the ICP algorithm to obtain the pose of the target part under the main camera Among them, It is represented as the rotation matrix from the target part to the main camera; It is represented as the translation vector from the target part to the main camera.

[0060] The actuator is installed on the end of the robotic arm through the flange; according to the pose and the pose Calculate to obtain the pose of the target part under the screwdriver;

[0061] The method for establishing the coordinate model of the target part in the reference coordinate system based on the pose of the target part under the screwdriver, the pose of the screwdriver under the flange of the robotic arm, and the pose of the flange in the reference coordinate system includes:

[0062]

[0063]

[0064] In the formula, R hb It is represented as the rotation matrix from the flange of the robotic arm to the origin of the reference coordinate system; T hb It is represented as the translation vector from the flange of the robotic arm to the origin of the reference coordinate system; R th It is represented as the rotation matrix from the actuator to the flange of the robotic arm; T th It is represented as the translation vector from the actuator to the flange of the robotic arm; R final It is represented as the rotation matrix from the actuator to the origin of the reference coordinate system; T final It is represented as the translation vector from the actuator to the origin of the reference coordinate system.

[0065] Control the movement of the robotic arm according to the coordinate model of the target part in the reference coordinate system, and drive the actuator to process the target part; only need to use the main camera to identify the target part and send the position information to the robotic arm, which simplifies the control process of the robotic arm and avoids being restricted by environmental factors at the same time.

[0066] Embodiment 2

[0067] This embodiment provides an intelligent control system based on a target calibration and positioning model. The intelligent control system in this embodiment can be applied to the intelligent control method described in Embodiment 1. The intelligent control system includes:

[0068] A calibration module, which is used to obtain the pose of the end of the actuator under the main camera by using the target of the auxiliary camera, the main camera and the calibration actuator The auxiliary camera and the main camera form a binocular camera, and the auxiliary camera and the main camera are respectively arranged on both sides of the actuator; the actuator is set as an electric screwdriver;

[0069] A processing and analysis module, which is used to obtain the pose of the target part under the main camera The actuator is installed at the end of the robotic arm through a flange; according to the pose and pose Calculate to obtain the pose of the target part under the screwdriver;

[0070] A control module, which is used to establish the coordinate model of the target part in the reference coordinate system based on the pose of the target part under the screwdriver, the pose of the screwdriver under the flange of the robotic arm, and the pose of the flange in the reference coordinate system; control the movement of the robotic arm according to the coordinate model of the target part in the reference coordinate system, and drive the actuator to process the target part.

[0071] Embodiment 3

[0072] This embodiment provides a computer-readable storage medium, which is characterized in that a computer program is stored thereon, and when the program is executed by a processor, the steps of the intelligent control method described in Embodiment 1 are realized.

[0073] Those skilled in the art should understand that the embodiments of the present application can be provided as a method, a system, or a computer program product. Therefore, the present application can take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0074] This application is described with reference to the flowcharts and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the present application. It should be understood that each flow and / or block in the flowchart and / or block diagram, and the combination of flows and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, such that the instructions executed by the processor of the computer or other programmable data processing device produce means for implementing the functions specified in the Figure 1 one or more flows and / or blocks Figure 1 means for implementing the functions specified in one or more blocks.

[0075] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, such that the instructions stored in the computer-readable memory produce a manufactured article including instruction means that implement the functions specified in the Figure 1 one or more flows and / or blocks Figure 1 one or more blocks.

[0076] These computer program instructions can also be loaded onto a computer or other programmable data processing device, such that a series of operational steps are performed on the computer or other programmable device to generate a computer-implemented process, and thus the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in the Figure 1 one or more flows and / or blocks Figure 1 one or more blocks.

[0077] The above is only the preferred embodiment of the present invention. It should be noted that for those of ordinary skill in the art of this technology, without departing from the technical principles of the present invention, several improvements and modifications can be made, and these improvements and modifications should also be regarded as the protection scope of the present invention.

Claims

1. An intelligent control method based on a target calibration and positioning model, characterized in that Including: Obtain the pose of the end of the actuator under the main camera by using an auxiliary camera, a main camera, and a calibration actuator , the auxiliary camera and the main camera form a binocular camera, the auxiliary camera and the main camera are respectively arranged on both sides of the actuator, and the actuator is an electric screwdriver, specifically including: Obtaining the relative pose relationship of the binocular camera through mutual calibration between the auxiliary camera and the main camera; Using the auxiliary camera to collect images of the positioning area of the target to establish a target template; using the deformable template matching algorithm to identify the target template to obtain the two-dimensional pixel coordinates of the target positioning points, and the edge lines of the target positioning area are formed by each target positioning point; Converting the two-dimensional pixel coordinates of the target positioning points into three-dimensional coordinates in the world coordinate system; obtaining the pose of the end of the actuator under the auxiliary camera according to the fixed position relationship between the target and the actuator; Calculate the pose of the end of the actuator under the main camera based on the pose of the end of the actuator under the auxiliary camera and the relative pose relationship between the binocular cameras. ; where represents the rotation matrix from the end of the actuator to the main camera, represents the translation vector from the end of the actuator to the main camera. Obtain the pose of the target part under the main camera ; The actuator is installed at the end of the robotic arm through a flange; According to the pose and pose Calculate and obtain the pose of the target part under the screwdriver; Based on the pose of the target part under the screwdriver, the pose of the screwdriver under the flange of the robotic arm, and the pose of the flange in the reference coordinate system, establishing a coordinate model of the target part in the reference coordinate system; controlling the movement of the robotic arm according to the coordinate model of the target part in the reference coordinate system, and driving the actuator to process the target part.

2. The intelligent control method based on the target calibration and positioning model according to claim 1, characterized in that The method for obtaining the relative pose relationship of the binocular camera through mutual calibration between the auxiliary camera and the main camera includes: After the auxiliary camera and the main camera are respectively installed on both sides of the actuator, an auxiliary camera coordinate system and a main camera coordinate system are respectively established for the auxiliary camera and the main camera, and the relative pose of the binocular camera is calibrated; the relative pose of the binocular camera includes the rotation matrix from the auxiliary camera to the main camera and the translation vector from the auxiliary camera to the main camera .

3. The intelligent control method based on the target calibration and positioning model according to claim 1, wherein, The method for converting the two-dimensional pixel coordinates of the target positioning points into three-dimensional coordinates in the world coordinate system includes: converting the two-dimensional pixel coordinates of the target positioning points into three-dimensional coordinates in the auxiliary camera coordinate system through the PnP algorithm, and converting the three-dimensional coordinates of the target positioning points in the auxiliary camera coordinate system into three-dimensional coordinates in the world coordinate system through the ICP algorithm.

4. The intelligent control method based on a target calibration and positioning model according to claim 2, wherein, The fixing method of the target for calibrating the actuator includes: Setting the target at a set distance l from the flange of the robotic arm, and at the same time setting the target within the field of view of the auxiliary camera, and the axis of the target is perpendicular to the axis of the actuator; setting the origin of the target coordinate system on the axis of the actuator; wherein, the axes of the actuator, the main camera, and the auxiliary camera are parallel to each other.

5. The intelligent control method based on the target calibration and positioning model according to claim 4, wherein, Calculate the pose of the end of the actuator under the main camera based on the pose of the end of the actuator under the auxiliary camera and the relative pose relationship between the binocular cameras. The method includes: ； ； In the formula, is the coordinate of the origin of the target coordinates in the x-axis direction relative to the secondary camera coordinate system; is the coordinate of the origin of the target coordinates in the y-direction relative to the secondary camera, the coordinate of the origin of the target coordinates in the z-axis direction relative to the secondary camera coordinate system; represents the translation vector from the end of the actuator to the secondary camera; represents the rotation matrix from the end of the actuator to the secondary camera.

6. The intelligent control method based on the target calibration and positioning model according to claim 1, wherein, Method for obtaining the pose of a target part under a main camera The method includes: Using the main camera to collect images of the target part to establish a target part template; using the deformable template matching algorithm to identify the target part template to obtain the two-dimensional pixel coordinates of the target part positioning points, and the edge lines of the target part are formed by each target part positioning point; Convert the two-dimensional pixel coordinates of the target part's positioning points into three-dimensional coordinates in the main camera coordinate system through the PnP algorithm, and convert the three-dimensional coordinates of the target part's positioning points in the main camera coordinate system into three-dimensional coordinates in the world coordinate system through the ICP algorithm to obtain the pose of the target part under the main camera. ; where represents the rotation matrix from the target part to the main camera; represents the translation vector from the target part to the main camera.

7. An intelligent control method based on a target calibration and positioning model according to claim 5, characterized in that, The method for establishing the coordinate model of the target part in the reference coordinate system based on the pose of the target part under the screwdriver, the pose of the screwdriver under the flange of the robotic arm, and the pose of the flange in the reference coordinate system includes: ； ； In the formula, represents the rotation matrix between the end of the actuator and the target part, represents the translation vector between the end of the actuator and the target part; represents the rotation matrix from the robot flange to the origin of the reference coordinate system; represents the translation vector from the robot flange to the origin of the reference coordinate system; represents the rotation matrix from the actuator to the robot flange; represents the translation vector from the actuator to the robot flange; represents the rotation matrix from the actuator to the origin of the reference coordinate system; represents the translation vector from the actuator to the origin of the reference coordinate system.

8. An intelligent control system based on a target calibration and positioning model, characterized in that, Including: The calibration module is used to obtain the pose of the end of the actuator under the main camera by using the targets of the auxiliary camera, the main camera and the calibration actuator ; the auxiliary camera and the main camera form a binocular camera, and the auxiliary camera and the main camera are respectively arranged on both sides of the actuator; the actuator is an electric screwdriver The processing and analysis module is used to obtain the pose of the target part under the main camera ; The actuator is installed at the end of the robotic arm through a flange; According to the pose and pose calculate the pose of the target part under the screwdriver; A control module, configured to establish a coordinate model of the target part in the reference coordinate system based on the pose of the target part under the screwdriver, the pose of the screwdriver under the flange of the robotic arm, and the pose of the flange in the reference coordinate system; controlling the movement of the robotic arm according to the coordinate model of the target part in the reference coordinate system, and driving the actuator to process the target part; The calibration module obtains the pose of the end of the actuator under the main camera by using the targets of the auxiliary camera, the main camera, and the calibration actuator , specifically including: Obtaining the relative pose relationship of the binocular camera through mutual calibration between the auxiliary camera and the main camera; Using the auxiliary camera to collect images of the positioning area of the target to establish a target template; using the deformable template matching algorithm to identify the target template to obtain the two-dimensional pixel coordinates of the target positioning points, and the edge lines of the target positioning area are formed by each target positioning point; Converting the two-dimensional pixel coordinates of the target positioning points into three-dimensional coordinates in the world coordinate system; obtaining the pose of the end of the actuator under the auxiliary camera according to the fixed position relationship between the target and the actuator; Calculate the pose of the end of the actuator under the main camera based on the pose of the end of the actuator under the auxiliary camera and the relative pose relationship between the binocular cameras. ; where represents the rotation matrix from the end of the actuator to the main camera, represents the translation vector from the end of the actuator to the main camera.

9. A computer-readable storage medium, characterized in that A computer program is stored thereon, and when the program is executed by a processor, it implements the steps of the intelligent control method described in any one of claims 1 to 7.

Images