Object pose adjustment method and apparatus

Abstract

The application provides an object posture adjustment method and device. The object posture adjustment method comprises the following steps: collecting an object image; determining the marker point three-dimensional coordinates of each target marker point according to the marker point pixel coordinates of each target marker point in the object image, and determining the tool three-dimensional coordinates of each tool target ball according to the target ball pixel coordinates in the object image; determining the bush three-dimensional coordinates corresponding to each bush according to the positional relationship between each target marker point and at least three bushes on the object to be adjusted and the three-dimensional coordinates of each marker point; determining the current posture information of the object to be adjusted according to the three-dimensional coordinates of each bush and the three-dimensional coordinates of each tool, and adjusting the posture of the object to be adjusted according to the current posture information and target posture information. The method provided in the application converts the traditional posture adjustment process which depends on manual interpretation and single measurement into a digital and synchronous measurement mode. The posture adjustment efficiency is significantly improved, and reliable technical support is provided for the precise assembly of spacecraft structures.

Description

Technical Field

[0001] This application relates to the field of spacecraft manufacturing technology, and in particular to a method for adjusting the attitude of an object. This application also relates to an object attitude adjustment device, a computing device, a computer-readable storage medium, and a computer program product. Background Technology

[0002] In the aerospace manufacturing field, solar panels are crucial components in satellite operation. Rigid folding solar panels, with their high power density and reliable mechanical structure, are the most widely used type. They mainly consist of solar panels, inter-panel hinges, and positioning sleeves. Among these, inter-panel hinge failure is one of the key factors leading to solar panel deployment failure. Therefore, before installing the inter-panel hinges, the roll and pitch attitudes of each panel must be adjusted to 90° relative to the ground level, ensuring that the hinge driving force and the panel suspending force are orthogonal, achieving dynamic decoupling and preventing the hinges from bearing additional loads that could cause damage or jamming.

[0003] Currently, windsurfing attitude adjustment relies heavily on manual visual inspection, calculation, or evaluation, leading to measurement accuracy being affected by personnel experience, resulting in unstable accuracy and low digitalization. Secondly, the measuring instruments require frequent manual adjustments during the measurement process, making the steps cumbersome and inefficient. Furthermore, the current method can only measure either roll or pitch at a time, requiring retesting of the other after each adjustment, creating redundancy in the process. Therefore, a new windsurfing attitude adjustment method is urgently needed to solve these problems. Summary of the Invention

[0004] In view of this, embodiments of this application provide an object posture adjustment method. This application also relates to an object posture adjustment apparatus, a computing device, a computer-readable storage medium, and a computer program product, to solve the aforementioned problems existing in the prior art.

[0005] According to a first aspect of the embodiments of this application, an object pose adjustment method is provided, including: Acquire an image of an object including the object to be adjusted and a reference tooling, wherein the object to be adjusted includes at least three target marker points and the reference tooling includes at least three tooling target balls; The three-dimensional coordinates of each target marker point are determined based on the pixel coordinates of each target marker point in the object image, and the three-dimensional coordinates of each tooling target ball are determined based on the pixel coordinates of each tooling target ball in the object image. Based on the positional relationship between each target marker point on the object to be adjusted and at least three bushings, and the three-dimensional coordinates of each marker point, determine the three-dimensional coordinates of each bushing; The current posture information of the object to be adjusted is determined based on the three-dimensional coordinates of each bushing and the three-dimensional coordinates of each tooling, and the posture of the object to be adjusted is adjusted based on the current posture information and the target posture information.

[0006] According to a second aspect of the embodiments of this application, an object posture adjustment device is provided, comprising: The acquisition module is configured to acquire an object image including the object to be adjusted and a reference tooling, wherein the object to be adjusted includes at least three target marker points and the reference tooling includes at least three tooling target balls; The determination module is configured to determine the three-dimensional coordinates of each target marker point based on the pixel coordinates of each target marker point in the object image, and to determine the three-dimensional coordinates of each tooling target ball based on the pixel coordinates of each tooling target ball in the object image. The calibration module is configured to determine the three-dimensional coordinates of each bushing based on the positional relationship between each target marker point on the object to be adjusted and at least three bushings and the three-dimensional coordinates of each marker point. The adjustment module is configured to determine the current posture information of the object to be adjusted based on the three-dimensional coordinates of each bushing and the three-dimensional coordinates of each tooling, and to adjust the posture of the object to be adjusted based on the current posture information and the target posture information.

[0007] According to a third aspect of the embodiments of this application, a computing device is provided, comprising: Memory and processor; The memory is used to store computer programs / instructions, and the processor is used to execute the computer programs / instructions, which, when executed by the processor, implement the steps of the above-described object pose adjustment method.

[0008] According to a fourth aspect of the embodiments of this application, a computer-readable storage medium is provided that stores a computer program / instructions, which, when executed by a processor, implement the steps of the above-described object posture adjustment method.

[0009] According to a fifth aspect of the embodiments of this application, a computer program product is provided, including a computer program / instructions that, when executed by a processor, implement the steps of the above-described object pose adjustment method.

[0010] The object posture adjustment method provided in this application includes acquiring an object image including an object to be adjusted and a reference tooling reference, wherein the object to be adjusted includes at least three target marker points, and the reference tooling reference includes at least three tooling target balls; determining the three-dimensional coordinates of each target marker point based on the pixel coordinates of the marker points in the object image, and determining the tooling three-dimensional coordinates of each tooling target ball based on the pixel coordinates of the target balls in the object image; determining the bushing three-dimensional coordinates corresponding to each bushing based on the positional relationship between each target marker point on the object to be adjusted and at least three bushings and the three-dimensional coordinates of each marker point; determining the current posture information of the object to be adjusted based on the three-dimensional coordinates of each bushing and each tooling three-dimensional coordinate, and adjusting the posture of the object to be adjusted based on the current posture information and the target posture information.

[0011] One embodiment of this application achieves high-precision, non-contact measurement of the object to be adjusted, fundamentally avoiding interference with the object during the measurement process. Furthermore, the process of determining the current attitude information in this method requires no human intervention and eliminates visual errors. Pre-calibrated information is applied to the object to be adjusted using a reference fixture, and feature-based proxy measurement is employed to convert the difficult-to-obtain bushing center coordinates into the coordinates of the target marker point. This further improves the final measurement accuracy and ensures that the attitude of the object to be adjusted under gravity unloading is not affected by the measurement process itself. Attached Figure Description

[0012] Figure 1 This is a flowchart of an object pose adjustment method provided in an embodiment of this application; Figure 2 This is a schematic diagram of a scenario provided by an embodiment of this application for calculating the positional relationship between each target marker point and at least three bushings; Figure 3 This is a schematic diagram of the structure of an object posture adjustment device provided in an embodiment of this application; Figure 4 This is a structural block diagram of a computing device provided in one embodiment of this application. Detailed Implementation

[0013] Many specific details are set forth in the following description to provide a full understanding of this application. However, this application can be implemented in many other ways different from those described herein, and those skilled in the art can make similar extensions without departing from the spirit of this application; therefore, this application is not limited to the specific embodiments disclosed below.

[0014] The terminology used in one or more embodiments of this application is for the purpose of describing particular embodiments only and is not intended to limit the scope of one or more embodiments of this application. The singular forms “a,” “the,” and “the” used in one or more embodiments of this application and in the appended claims are also intended to include the plural forms unless the context clearly indicates otherwise. It should also be understood that the term “and / or” used in one or more embodiments of this application refers to and includes any or all possible combinations of one or more associated listed items.

[0015] It should be understood that although the terms first, second, etc., may be used to describe various information in one or more embodiments of this application, such information should not be limited to these terms. These terms are only used to distinguish information of the same type from one another. For example, first may also be referred to as second without departing from the scope of one or more embodiments of this application, and similarly, second may also be referred to as first. Depending on the context, the word "if" as used herein may be interpreted as "when," "when," or "in response to a determination."

[0016] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties. Furthermore, the collection, use and processing of the relevant data must comply with the relevant laws, regulations and standards of the relevant regions, and corresponding operation entry points are provided for users to choose to authorize or refuse.

[0017] First, the terms and concepts involved in one or more embodiments of this application will be explained.

[0018] Solar array: Also known as a solar panel or solar cell array, it is the core energy device of a spacecraft that converts solar energy into electrical energy through the photoelectric effect. It is mainly used to power satellites, spacecraft, and other spacecraft. Its surface is covered with solar cells made of semiconductor materials, which can be folded and stored outside the cabin. After the satellite enters orbit, it unfolds to increase the area for receiving sunlight.

[0019] With the rapid development of advanced spacecraft platforms such as high-resolution Earth observation and large communication satellites, extremely stringent requirements have been placed on the deployment accuracy, energy stability, and overall satellite dynamics of solar arrays. This trend directly impacts the manufacturing process, demanding unprecedentedly high standards for attitude adjustment accuracy and assembly efficiency during the solar array assembly stage, as well as for digitalization and traceability throughout the entire assembly and final assembly process. Achieving seamless integration of solar arrays from assembly to final assembly with high precision, high efficiency, and high consistency has become a key core element in improving the manufacturing level and reliability of modern spacecraft.

[0020] Currently, the aerospace manufacturing industry is undergoing a profound transformation from a traditional model relying on human experience to an advanced manufacturing model characterized by data-driven and intelligent decision-making. Against this industry backdrop, solar array assembly, as a crucial upstream process affecting subsequent assembly procedures and even final on-orbit performance, directly determines the efficiency and quality ceiling of the entire spacecraft assembly chain through upgrades in its technological capabilities—especially the digitalization of attitude measurement. This represents a technological high ground that the industry urgently needs to break through and improve.

[0021] Currently, in the field of ground attitude adjustment for solar panels, the suspended plumb line method and the theodolite method remain the mainstream technologies widely used. Both methods rely on manual operation and share common technical bottlenecks such as cumbersome procedures, limited efficiency, and difficulty in achieving synchronous and accurate measurements.

[0022] The operational procedure for the plumb line suspension method is as follows: After the sailboard is suspended, a plumb bob is suspended through the uppermost screw hole on its side to form a stable gravity baseline. The operator visually observes the relative positional deviation between the plumb bob suspension line and the center of the lowermost screw hole on the side of the sailboard in two spatial dimensions (i.e., roll and pitch directions) and judges the sailboard attitude based on this. Subsequently, the center of gravity of the sailboard needs to be repeatedly and independently adjusted in the roll and pitch directions to align the suspension line with the center of the target screw hole, thereby theoretically ensuring that the sailboard is perpendicular to the horizontal plane.

[0023] The theodolite method operates as follows: First, the theodolite is leveled to ensure that the horizontal lines of its crosshairs are strictly parallel to the horizontal plane and the vertical lines are strictly perpendicular to the horizontal plane, thus establishing the measurement benchmark for the windsurfing's roll and pitch attitudes. Then, with auxiliary lighting, the operator visually observes the two horizontal positioning sleeves on the windsurfing and fine-tunes the theodolite's vertical angle until the horizontal lines of the crosshairs are sequentially tangent to the lower edge of the target sleeve. Based on the deviation of the vertical angle readings at the two tangency points, the windsurfing's roll attitude is calculated. Similarly, the observation position is changed to observe the two vertical positioning sleeves from the side of the windsurfing, and the windsurfing's pitch attitude is calculated based on the deviation of their horizontal angles. Because the two attitudes cannot be measured and decoupled simultaneously, after adjusting the pitch attitude, the roll attitude often needs to be re-measured and readjusted. This process needs to be repeated until both the roll and pitch attitudes meet the maximum allowable attitude adjustment error requirements.

[0024] Analysis reveals the following main problems with existing manual windsurfing attitude adjustment methods: Measurement accuracy is constrained by human factors and has a low degree of digitization: the measurement results of existing methods rely heavily on manual visual interpretation and calculation by operators. Their accuracy is directly affected by the operator's experience, skill level, and subjective state, resulting in poor consistency and weak traceability. The entire measurement process lacks objective digital recording and processing, making precise quality control difficult.

[0025] The measurement process is cumbersome and lacks automation: whether it's the centering, leveling, and auxiliary lighting of the theodolite, or the plumb line method involving plumb bob suspension and manual alignment and observation, all involve a large number of repetitive manual operations and preparation steps. These cumbersome procedures result in long measurement cycles, low automation levels, and difficulty in improving overall attitude adjustment efficiency.

[0026] Multi-dimensional attitude cannot be measured and decoupled synchronously, resulting in redundant attitude adjustment processes: Existing methods cannot simultaneously acquire attitude data in both roll and pitch dimensions in a single setup. Adjusting any one dimension of attitude will disrupt the adjusted state of the other dimension, forcing the attitude adjustment process into an iterative loop of "measurement-adjustment-retest," causing severe redundancy and poor synchronization.

[0027] Based on this, this application provides an object posture adjustment method. This application also relates to an object posture adjustment device, a computing device, a computer-readable storage medium, and a computer program product, which will be described in detail in the following embodiments.

[0028] Figure 1 A flowchart of an object pose adjustment method according to an embodiment of this application is shown, which specifically includes the following steps: Step 102: Acquire an object image including the object to be adjusted and a reference tooling object, wherein the object to be adjusted includes at least three target marker points, and the reference tooling object includes at least three tooling target balls.

[0029] The object attitude adjustment method provided in this application can be understood as a digital adjustment method for the attitude of a solar panel. Its main processing flow involves acquiring image information of the solar panel and image information of a reference fixture, using this two image information to calculate the attitude of the solar panel, and adjusting the attitude of the solar panel to achieve the target attitude.

[0030] Based on this, in the method provided in this application embodiment, the object to be adjusted can be understood as a solar panel, and the reference tooling reference can be understood as an object used to provide a reference for the object to be adjusted. The object image can be understood as an image that simultaneously includes the object to be adjusted and the reference tooling reference. In the method provided in this application, by calibrating and comparing the object to be adjusted and the reference tooling reference in the object image, the attitude of the solar panel can be calculated, and the solar panel can be adjusted accordingly.

[0031] In practical applications, at least three target markers are set on the object to be adjusted, and these three target markers are non-collinear with each other. The reference fixture includes at least three tooling target balls, which are auxiliary tools used in industrial measurement, typically in conjunction with high-precision measuring equipment such as laser trackers. The reference fixture serves as a standard to provide the basis for adjustment.

[0032] A reference tooling can also be understood as a reference fixture. Reference fixtures are specialized auxiliary devices used in various stages of industrial production to provide precise reference standards. They are applicable to multiple technical fields, and their core function is to ensure the accuracy and efficiency of production, measurement, and assembly. They can provide precise positioning to ensure machining and assembly accuracy; stable support to reduce workpiece deformation and loss; and simplified processes to improve production and measurement efficiency.

[0033] In practical applications, image acquisition devices are typically used for image acquisition. In the method provided in this application embodiment, a binocular vision device is used for image acquisition. Specifically, in a specific embodiment provided in this application, acquiring an object image including the object to be adjusted and a reference tooling is included, comprising: The image of an object, including the object to be adjusted and a reference tool, is acquired using a binocular vision device, wherein the reference tool is located between the binocular vision device and the object to be adjusted.

[0034] Among them, binocular vision acquisition equipment is also known as binocular measurement equipment. Binocular measurement equipment is a type of measurement instrument based on binocular vision technology. It imitates the principle of human binocular parallax, uses two cameras with the same parameters to acquire target images from different angles, and then uses algorithms to calculate image parallax to obtain the target's three-dimensional spatial information. It has advantages such as low cost and simple structure.

[0035] The binocular measurement device, as the core data acquisition tool in this method, adopts a working principle based on stereo vision. The device consists of two precisely calibrated high-resolution industrial cameras. It synchronously acquires images of the target object and uses triangulation to calculate the three-dimensional spatial coordinates of the target points.

[0036] In one specific embodiment provided in this application, the binocular vision acquisition device is equipped with two 25-megapixel industrial cameras with a field of view of 40°×50°×65°; at a standard working distance of 3-4 meters, its measurement expanded uncertainty is 0.020 mm, ensuring high accuracy of coordinate acquisition.

[0037] In practical applications, the volume of the object to be adjusted is larger than the volume of the reference fixture. To acquire images of it using a binocular vision device, the reference fixture can be positioned between the binocular vision device and the object to be adjusted. Simultaneously, the binocular vision device is directed towards both the reference fixture and the object to be adjusted to capture images. The binocular vision device can then obtain an image of the object including both the object to be adjusted and the reference fixture.

[0038] It should be noted that binocular vision devices are one specific implementation of the method described in this application. In practical applications, tri-vision or multi-vision devices can also be used as alternatives. By increasing the number of devices, the overall observation angle can be expanded, reducing blind spots in measurement. Furthermore, more views can be provided for verification when ambiguity arises in binocular matching, thereby improving the robustness and accuracy of 3D reconstruction.

[0039] In this method, the number of cameras, resolution, and lens focal length of the vision system can be adjusted according to specific measurement distance and accuracy requirements. For example, for larger sailboards, multiple binocular subsystems can be distributed and data fusion can be performed through unified global calibration. The camera mounting baseline (i.e., the distance between cameras) can be flexibly designed according to the measurement scenario; a long baseline can be used to improve depth measurement accuracy, while a short baseline is suitable for confined spaces. The method in this application relies on ambient light or ordinary lighting. Specific wavelength active light sources (such as infrared LEDs) can also be added, along with synchronized filters, to suppress ambient light interference and improve the signal-to-noise ratio of the marker point images. Furthermore, the feature point recognition and extraction algorithms are alternative; besides ellipse fitting, deep learning-based feature point detection algorithms (such as Keypoint Detection Network) can be used, which have better robustness to changes in illumination and partial occlusion.

[0040] Step 104: Determine the three-dimensional coordinates of each target marker point based on the pixel coordinates of each target marker point in the object image, and determine the three-dimensional coordinates of each tooling target ball based on the pixel coordinates of each tooling target ball in the object image.

[0041] Once the object image is obtained, the 3D coordinates of each target marker can be further determined based on the pixel coordinates of each marker in the object image. Similarly, the 3D coordinates of each tooling target ball can be determined based on its pixel coordinates in the object image.

[0042] The object image determined in the above steps is acquired using a binocular measurement device, which has two cameras. At the same time, the two cameras can simultaneously capture two images. These two images form a pair of conjugate image points on the imaging plane. Conjugate image points are a core concept in stereo vision and photogrammetry. They refer to the two two-dimensional projection points formed by a three-dimensional point in space on imaging planes from two different viewpoints. These two two-dimensional projection points correspond to the same physical point in space, and there is a strict geometric constraint relationship between them.

[0043] Based on this, the three-dimensional coordinates of the target marker point and the tooling target ball can be statistically determined through conjugate image points.

[0044] Specifically, the object image includes a first object image and a second object image; Determining the three-dimensional coordinates of each target marker point based on the pixel coordinates of each marker point in the object image includes: Select a target marker point to be processed, wherein the target marker point to be processed is any one of the target marker points; Determine the first pixel information of the target marker point to be processed in the first image of the object, and determine the second pixel information of the target marker point to be processed in the second image of the object; The three-dimensional coordinates of the marker point corresponding to the target marker point to be processed are calculated based on the first pixel information, the second pixel information, and the device parameter information.

[0045] When processing target markers, we can use any one of multiple target markers as an example for explanation, that is, to determine the target marker to be processed from multiple target markers. The same processing can be performed on each target marker.

[0046] Once the target marker point to be processed is determined, it can be used as a conjugate image point to obtain the first pixel information of the target marker point in the first image and the second pixel information of the target marker point in the second image.

[0047] The first image and the second image are images acquired by the binocular vision acquisition device. The first image can be acquired by the left device in the binocular vision acquisition device, and the second image can be acquired by the right device in the binocular vision acquisition device. In another specific embodiment provided in this application, the two can also be interchanged, with the first image acquired by the right device and the second image acquired by the left device.

[0048] After obtaining the information of the first and second pixels, the 3D coordinates of the marker point corresponding to the target marker point can be calculated by further combining the device parameter information. In the implementation provided in this application embodiment, the device parameter information specifically includes the intrinsic parameters (such as focal length, principal point, and distortion coefficient) and extrinsic parameters (rotation matrix, translation vector, and baseline distance between the two devices) of the binocular vision device. The disparity can be calculated based on these two pixel information using a stereo matching algorithm, and 3D reconstruction can be performed based on the disparity to obtain the 3D coordinates of the reconstructed marker point.

[0049] The object image includes a first object image and a second object image; Determining the tooling three-dimensional coordinates of each tooling target ball based on the target ball pixel coordinates in the object image includes: Select a tooling target ball to be processed, wherein the tooling target ball to be processed is any one of the tooling target balls; Determine the coordinates of the first tooling target ball in the first image of the object, and determine the coordinates of the second tooling target ball in the second image of the object; The three-dimensional coordinates of the tooling target ball to be processed are calculated based on the coordinates of the first tooling target ball, the coordinates of the second tooling target ball, and the equipment parameter information.

[0050] In practical applications, the processing of each tooling target ball in the reference tooling is the same as the operation of the target marker points to be processed described above. Specifically, any one of the tooling target balls can be selected as the tooling target ball to be processed. The coordinates of the first tooling target ball in the first image of the object and the coordinates of the second tooling target ball in the second image of the object are determined. The tooling target ball coordinates corresponding to the tooling target ball are obtained by processing the first tooling target ball coordinates, the second tooling target ball coordinates, and the intrinsic parameters (such as focal length, principal point, distortion coefficient) and extrinsic parameters (rotation matrix, translation vector, baseline distance between the two devices) of the binocular vision device.

[0051] This processing method obtains the coordinate information of each target marker point in the object image, as well as the coordinate information of each tooling target ball. Using the three-dimensional coordinates of the target marker points and the tooling target balls, the posture information of the object to be adjusted can be determined in subsequent processing, and then used to adjust it to achieve the target posture.

[0052] Step 106: Determine the three-dimensional coordinates of each bushing based on the positional relationship between each target marker point on the object to be adjusted and at least three bushings, and the three-dimensional coordinates of each marker point.

[0053] In the specific embodiments provided in this application, the object to be adjusted is the solar array liner, which can be deployed in space to begin operation. The bushing is the clamping bushing within the solar array liner, a core adapter component in the clamping and release mechanism of the satellite solar array. It is a multi-dimensional hollow columnar structure, often used in conjunction with clamping rods and clamping seats, and is a key component ensuring the stability of the solar array during launch and its smooth deployment in orbit. The core function of each target marker point is to act as a "non-contact agent" for the bushing's measurement characteristics.

[0054] During ground-based adjustments to the solar panels, it's crucial to ensure the panels are in a gravity-unloaded state. This means that clamping rods cannot be placed on the clamping bushings for attitude adjustment (if clamping rods are present, their weight would affect the panels, impacting attitude adjustment accuracy). This makes it impossible to directly identify the center position of the clamping bushings. Consequently, during feature recognition, the coordinates of the clamping bushing center cannot be directly identified by the binocular vision system, resulting in the inability to directly obtain the coordinate information of the clamping bushing center.

[0055] Based on this, the method provided in this application proposes a measurement feature proxy concept. Multiple lightweight target markers are set on the surface of the sailboard. These markers are so light that they will not affect the sailboard's attitude adjustment due to gravity. First, a corresponding positional relationship is established between the target markers and each bushing. Then, by measuring the marker information of each target marker and combining it with the positional relationship between the target markers and each bushing, the bushing coordinate information of the center of each bushing can be obtained. In the method provided in this application, this is called the two-step calibration proxy method.

[0056] In a specific embodiment provided in this application, the positional relationship between each target marker point on the object to be adjusted and at least three bushings is determined through the following steps: With the target ball installed in each bushing of the object to be adjusted, an initial object image of the object to be adjusted is obtained; The initial coordinates of each target marker point and the initial coordinates of each target ball are identified based on the initial object image. The positional relationship between each target marker and at least three bushings is generated based on the initial coordinates of each marker point and each target ball.

[0057] In this embodiment, the above two-step calibration proxy method will be further explained.

[0058] In the first stage (initial calibration stage), the positional calibration between the clamping bushing and each target marker point is performed. Specifically, the calibration target ball is installed in the clamping bushing of the object to be adjusted, and lightweight target markers are attached near the target ball. Images of the current state are acquired using a binocular vision device, and the initial coordinates of each target marker point and each target ball are measured simultaneously. The positional relationship between the target marker points and each bushing is established using the initial coordinates of each marker point and each target ball.

[0059] In practical applications, the shape of the target marker is not limited to circular, diamond, cross, or other specific patterned coded markers. Alternatively, high-contrast natural features inherent to the sailboard (such as rivets, seams, etc.) can be used as proxy features instead of manually set target markers.

[0060] See Figure 2 , Figure 2 This illustration shows a scenario diagram illustrating the calculation of the positional relationship between each target marker point and at least three bushings according to an embodiment of this application. Figure 2 As shown, the solar panel has multiple clamping bushings, and a target ball is added to at least three of the non-collinear bushings, with eight target marker points set. The target balls and target marker points are measured using a binocular vision device to obtain their respective coordinate values. See Table 1 below, which shows the coordinate values ​​between the three bushings and the eight target marker points according to an embodiment of this application.

[0061] Table 1

[0062] In the second stage (i.e., the actual measurement stage), the target ball that introduced load interference in the first stage is removed, leaving only the target marker points. During actual measurement, it is only necessary to capture the marker coordinates of the target marker points. Based on the established positional relationship between the target marker points and each bushing, the marker coordinates of the target marker points can be converted into the corresponding three-dimensional coordinates of each bushing.

[0063] The two-step calibration proxy method proposed in this embodiment sets lightweight target markers near the clamping bushing. The coordinates of each target marker and the bushing coordinates of the clamping bushing are established through calibration to establish a corresponding spatial correspondence. This allows the binocular measuring device to indirectly and undisturbedly obtain the bushing position of the clamping bushing simply by observing the target markers and obtaining their information. This information can then be used to calculate the current attitude of the solar panel.

[0064] In practical applications, a 3D scanner can be used to directly obtain a precise 3D model of the compression bushing and its surrounding area. The conversion relationship between the marker point and the bushing center can be virtually defined in the model, thus eliminating the need for physically pasting the marker point. Alternatively, a dedicated calibration fixture integrating the marker point and bushing positioning features can be designed and installed on the bushing as a whole during calibration, improving calibration efficiency.

[0065] In one specific embodiment provided in this application, the three-dimensional coordinates of each bushing are determined based on the positional relationship between each target marker point on the object to be adjusted and at least three bushings, and the three-dimensional coordinates of each marker point, including: Based on the three-dimensional coordinates of each marker point and the positional relationship between each target marker point and at least three bushings, determine the attitude offset information between each target marker point and each bushing; The three-dimensional coordinates of each bushing are calculated based on the attitude offset information and the three-dimensional coordinates of each marker point.

[0066] Specifically, in the method provided in this application embodiment, the attitude offset information between each target marker point and each bushing can be further determined based on the three-dimensional coordinates of each marker point and the positional relationship between each target marker point and at least three bushings. The attitude offset information can be specifically understood as a rotation matrix and a translation vector. The positional relationship specifically includes the calibration coordinate data of the target marker point in the marking scene.

[0067] Then, based on the attitude offset information and the three-dimensional coordinates of each marker point, the three-dimensional coordinates of each bushing are calculated.

[0068] In a specific embodiment provided in this application, taking eight target markers as an example for explanation, the above steps can measure the position of each target marker in the binocular coordinate system. The coordinates below are respectively In the above steps, the calibration coordinate data of each target marker point in the marking scene were obtained and recorded as follows: The attitude offset information from the calibration binocular coordinate system to the measurement binocular coordinate system can be calculated by taking the 3D coordinates and positional relationships of the target markers obtained from the measurement.

[0069] Specifically, the solution from the calibrated binocular coordinate system can be obtained through least squares fitting. To measure the binocular coordinate system rotation matrix Translation vector The calculation method is shown in Formula 1 below: Formula 1 After determining the rotation matrix Translation vector Then, the three-dimensional coordinates of each bushing can be further calculated using Formula 2 below. : Formula 2 in, To calibrate the three-dimensional coordinates of the bushing's corresponding position in the scene.

[0070] Step 108: Determine the current posture information of the object to be adjusted based on the three-dimensional coordinates of each bushing and the three-dimensional coordinates of each tooling, and adjust the posture of the object to be adjusted based on the current posture information and the target posture information.

[0071] Having obtained the three-dimensional coordinates of each bushing and each tooling, the current attitude information of the object to be adjusted can be further calculated based on the known information. In practical applications, each bushing and each tooling target ball consists of three non-collinear points. A plane can be further defined through these three non-collinear points, and the current attitude information of the object to be adjusted can then be determined through this plane.

[0072] Specifically, in one embodiment provided in this application, determining the current posture information of the object to be adjusted based on the three-dimensional coordinates of each bushing and the three-dimensional coordinates of each tooling includes: Determine at least two bushing three-dimensional vectors based on the three-dimensional coordinates of each bushing, and determine the calibration normal information based on the three-dimensional coordinates of each tooling and the tooling calibration data. The current pose information of the object to be adjusted is calculated based on at least two bushing three-dimensional vectors and the calibration normal information.

[0073] In the method provided in the embodiments of this specification, at least two bushing three-dimensional vectors can be further determined based on the three-dimensional coordinates of each bushing. For example, assuming three bushing three-dimensional coordinates... They are respectively , , Then, at least two bushing three-dimensional vectors can be calculated according to the following formula 3.

[0074] Formula 3 Furthermore, calibration normal information is determined based on the three-dimensional coordinates of each tooling and the tooling calibration data obtained by the method described above in this application. In the method provided in the embodiments of this application, the three-dimensional coordinates of each tooling are used as... The following example will be used for explanation. In the method provided in this application, calibration data from pre-calibrated tooling is used. To determine the calibration normal information. The calibration normal information refers to the normals perpendicular to the horizontal plane of the earth in a binocular coordinate system. The calculation method is shown in Formula 4 below: Formula 4 in, This is the representation matrix of the reference tooling coordinate system constructed in a binocular coordinate system. This refers to the pre-calibrated tooling calibration data. For a detailed representation, please refer to Formula 5 below: Formula 5 in, The rotation matrix representing the rotation from the reference fixture's measurement coordinates to the reference fixture's coordinate system in the calibration scenario. The tooling coordinates characterize the tooling target ball in three dimensions.

[0075] The role of the reference fixture in this application will be further explained below. To ensure simplicity and speed in the attitude adjustment process of the object to be adjusted, this application provides a reference fixture. It is used to establish, maintain, and transfer a geodetic horizontal reference. It transfers the geodetic horizontal reference calibrated by a high-precision laser tracker to the binocular vision coordinate system, thereby enabling the binocular vision device to measure the attitude of the object to be adjusted relative to the geodetic horizontal plane.

[0076] Specifically, the tooling calibration data is generated through the following steps: A reference tooling object is determined, wherein the reference tooling object includes at least three tooling target balls; Based on the preset measuring instrument, measure the tooling measurement coordinate information of each tooling target ball in the measuring instrument coordinate system; Determine the measurement tooling transformation matrix from the measuring instrument coordinate system to the tooling coordinate system based on the measurement coordinate information of each tooling; The tooling calibration data corresponding to the reference tooling is determined based on the measurement tooling transformation matrix and the measurement normal information corresponding to the preset measuring instrument.

[0077] In the method provided in this application, a special reference tooling is designed, which includes a measurement module and an attitude adjustment module.

[0078] The measurement module, a reference-establishing unit for a reference tooling, primarily functions to establish and transfer a stable and accurate reference coordinate system. This module constructs the reference tooling coordinate system using at least three tooling target spheres. During initial calibration, this coordinate system is precisely calibrated using a laser tracker, thus establishing a fixed transformation relationship between it and the laser tracker's measurement coordinate system. This provides a reliable reference for the binocular vision coordinate system, achieving effective transfer from the high-precision laser tracker reference to the binocular vision coordinate system. The measurement module is mainly used for binocular measurement and laser tracker calibration.

[0079] After the reference fixture is assembled, it cannot be immediately used for the high-precision measurement requirements of the solar panel assembly and adjustment. Calibration of the reference fixture is necessary. The purpose of calibration is to establish the relationship between the reference attitude and the high-precision horizontal coordinate system of the laser tracker.

[0080] During the calibration process, a preset measuring instrument (laser tracker) can be used to accurately measure the center coordinates of the three tooling target balls. The tooling measurement coordinates of the target balls in the measuring instrument's coordinate system are obtained by averaging multiple samples. See Table 2 below, which shows the reference tooling calibration data provided in an embodiment of this application: Table 2

[0081] To further illustrate this point, in the method provided in this application, it can be assumed that the tooling target ball is in the coordinate system of the measuring instrument. The corresponding tooling measurement coordinate information are as follows: , , .

[0082] Once the coordinate information of each tooling has been determined, the tooling transformation matrix from the measuring instrument coordinate system to the tooling coordinate system can be determined based on the coordinate information of each tooling.

[0083] Specifically, the first step is to solve for the normal to the plane formed by the three target spheres. And the direction relative to the plane is upward. For the specific solution method, please refer to Formula 6 below: Formula 6 In obtaining the normal After normalization, the reference tooling coordinate system can be obtained. The unit vector along the Z-axis For the specific calculation formula, please refer to Formula 7 below: Formula 7 Furthermore, regarding the above After normalization, the reference tooling coordinate system can be obtained. The unit vector in the X-axis direction below For the specific calculation formula, please refer to Formula 8 below: Formula 8 By performing a cross product operation on the Z-axis unit vector and the X-axis unit vector, the reference tooling coordinate system can be obtained. unit vector in the Y-axis direction below .

[0084] Based on this, the coordinate system of the measuring instrument can be obtained. To the reference tooling coordinate system rotation matrix ,in, For the specific calculation method, please refer to Formula 9 below: Formula 9 in, This is the rotation matrix in Formula 5 that represents the measurement coordinates of the reference tooling to the coordinate system of the reference tooling in the calibration scenario.

[0085] Since the Z-axis of the laser tracker is perpendicular to the horizontal plane of the earth, the Z-axis vector in the coordinate system of the measuring instrument... The expression in is Then the tooling calibration data In the reference tooling coordinate system The following expression is shown in Formula 10: Formula 10 The tooling calibration data can be determined using the above method. The calibration normal information can be calculated based on Formula 4 above. Then, the current pose information of the object to be adjusted is calculated based on at least two bushing three-dimensional vectors and the calibration normal information. Specifically, see Formula 11 below: Formula 11 The current attitude information includes the roll angle of the object to be adjusted. and pitch angle Roll angle and pitch angle The calculation method is described in Formula 11 above.

[0086] At this point, the current pose information of the object to be adjusted can be calculated. In practical applications, the number of tooling target balls on the reference tooling is at least three non-collinear tooling target balls, and can be increased to four or more. By fitting the reference plane through multiple points, the robustness and accuracy of the reference establishment can be further improved. In addition, the tooling target balls can be replaced with high-precision optically coded targets, plane mirrors, or other standards with defined geometric features, as long as they can be recognized by binocular vision equipment and used to establish the corresponding coordinate system.

[0087] In another specific embodiment provided in this application, adjusting the posture of the object to be adjusted based on the current posture information and the target posture information includes: The target attitude range is determined based on the target attitude information and the preset attitude error value; Adjust the posture of the object to be adjusted until the current posture information is within the target posture range.

[0088] Once the current posture information of the object to be adjusted is obtained, adjustments can be made based on this information. The specific adjustment target can be the target posture information. In other words, the current posture information of the object to be adjusted is adjusted to bring it closer to the target posture information.

[0089] In practical applications, the target attitude information is ideal attitude information. To ensure smooth attitude adjustment, a target attitude range can be determined based on the target attitude information and a preset attitude error value. During the adjustment of the object to be adjusted, the current attitude information should be kept within this target attitude range.

[0090] In one specific embodiment provided in this application, taking a target posture information of 90° and a preset posture error value of ±0.003 as an example, when the current posture information of the object to be adjusted is detected to be within the target posture range of 90°±0.003, the posture adjustment operation of the object to be adjusted can be confirmed to be completed.

[0091] The process of comparing the current attitude information with the target attitude information can be displayed on the operation interface in a visual way. The operator can make corresponding adjustments to the attitude information of the object to be adjusted based on the displayed error information, thereby realizing the synchronous measurement and adjustment of the two degrees of freedom attitude. This overcomes the shortcomings of traditional methods that require single measurement and repeated verification, and significantly improves the attitude adjustment efficiency.

[0092] To verify the feasibility and reliability of the above method, technicians designed and conducted a series of experiments. The experiments mainly focused on two dimensions: measurement accuracy verification and measurement uncertainty assessment. By comparing and analyzing the measurement results with those of a high-precision laser tracker, the overall performance indicators of the method were evaluated.

[0093] In the measurement accuracy verification test, technicians randomly arranged five target balls in space, forming 10 different simulated windsurfing attitudes. A laser tracker was used to measure the roll and pitch angles of each attitude group, with each group measured three times and the average value taken as the reference value. Subsequently, the simulated windsurfing attitudes were measured using the methods described above, with each attitude measured ten times. Outliers were removed using the Grubbs criterion, and the arithmetic mean was taken as the measured value.

[0094] The test results show that the root mean square error of the roll angle and pitch angle obtained by this method is better than 0.003°, and the maximum single-point deviation does not exceed 0.005°, which fully meets the accuracy requirement of ±0.03° for solar panel attitude adjustment in aerospace scenarios.

[0095] In addition, technicians used the Monte Carlo method for statistical analysis. They selected 18 typical measurement locations within the actual windsurfing attitude adjustment range and performed 30 repeated measurements at each location using the aforementioned method. Based on the measurement data, they constructed probability density functions for each input quantity, setting the sampling number to 10. 6 The results show that when the coverage factor k=3, the expanded uncertainty is less than 0.0008°, and the corresponding confidence probability reaches 99.73%, indicating that the stability of the measurement results meets the requirements for use.

[0096] The method provided in this application transforms the traditional attitude adjustment process, which relies on manual interpretation and single-item measurement, into a digital, synchronous measurement method. This significantly improves attitude adjustment efficiency and provides reliable technical support for the precision assembly of spacecraft structural components.

[0097] The method provided in this application offers a reference fixture that combines measurement and attitude adjustment functions. It realizes the proxy representation of the earth plane through the reference fixture, which is the physical basis for solving the problem of the lack of absolute measurement reference in binocular vision using the above method.

[0098] Furthermore, this method proposes a two-step proxy measurement approach: first, calibration using a calibration target ball, followed by measurement using lightweight target markers. By establishing a fixed coordinate transformation relationship between the center of the clamping bushing and the target markers during the calibration stage, the coordinates of unmeasurable feature points can be obtained without contacting the sailboard in subsequent actual measurements. This achieves high-precision feature measurement without interfering with the sailboard's attitude.

[0099] Finally, images of the solarboard and the reference fixture are acquired simultaneously using a binocular vision device. By calculating the feature points in the images, the roll and pitch angles of the solarboard are calculated simultaneously. The attitude error is then calculated using the roll and pitch angles and fed back to the operator to guide adjustments. By integrating the reference fixture, binocular vision device, feature proxy, and data processing algorithms, and with each component working together to form a closed loop of measurement, calculation, display, adjustment, and verification, the digitalization of solarboard attitude adjustment is achieved, greatly improving the efficiency and consistency of attitude adjustment.

[0100] Corresponding to the above method embodiments, this application also provides an embodiment of an object posture adjustment device. Figure 3 A schematic diagram of an object posture adjustment device according to an embodiment of this application is shown. Figure 3 As shown, the device includes: The acquisition module 302 is configured to acquire an object image including the object to be adjusted and a reference tooling reference, wherein the object to be adjusted includes at least three target marker points and the reference tooling reference includes at least three tooling target balls; The determining module 304 is configured to determine the three-dimensional coordinates of each target marker point based on the pixel coordinates of each target marker point in the object image, and to determine the three-dimensional coordinates of each tooling target ball based on the pixel coordinates of each tooling target ball in the object image. The calibration module 306 is configured to determine the three-dimensional coordinates of each bushing based on the positional relationship between each target marker point on the object to be adjusted and at least three bushings and the three-dimensional coordinates of each marker point. The adjustment module 308 is configured to determine the current posture information of the object to be adjusted based on the three-dimensional coordinates of each bushing and the three-dimensional coordinates of each tooling, and to adjust the posture of the object to be adjusted based on the current posture information and the target posture information.

[0101] Optionally, the acquisition module 302 is further configured to: The image of an object, including the object to be adjusted and a reference tool, is acquired using a binocular vision device, wherein the reference tool is located between the binocular vision device and the object to be adjusted.

[0102] Optionally, the object image includes a first object image and a second object image; The determining module 304 is further configured as follows: Select a target marker point to be processed, wherein the target marker point to be processed is any one of the target marker points; Determine the first pixel information of the target marker point to be processed in the first image of the object, and determine the second pixel information of the target marker point to be processed in the second image of the object; The three-dimensional coordinates of the marker point corresponding to the target marker point to be processed are calculated based on the first pixel information, the second pixel information, and the device parameter information.

[0103] Optionally, the object image includes a first object image and a second object image; The determining module 304 is further configured as follows: Select a tooling target ball to be processed, wherein the tooling target ball to be processed is any one of the tooling target balls; Determine the coordinates of the first tooling target ball in the first image of the object, and determine the coordinates of the second tooling target ball in the second image of the object; The three-dimensional coordinates of the tooling target ball to be processed are calculated based on the coordinates of the first tooling target ball, the coordinates of the second tooling target ball, and the equipment parameter information.

[0104] Optionally, the device further includes a position relationship determination module, configured to: With the target ball installed in each bushing of the object to be adjusted, an initial object image of the object to be adjusted is obtained; The initial coordinates of each target marker point and the initial coordinates of each target ball are identified based on the initial object image. The positional relationship between each target marker and at least three bushings is generated based on the initial coordinates of each marker point and each target ball.

[0105] Optionally, the calibration module 306 is further configured to: Based on the three-dimensional coordinates of each marker point and the positional relationship between each target marker point and at least three bushings, determine the attitude offset information between each target marker point and each bushing; The three-dimensional coordinates of each bushing are calculated based on the attitude offset information and the three-dimensional coordinates of each marker point.

[0106] Optionally, the adjustment module 308 is further configured to: Determine at least two bushing three-dimensional vectors based on the three-dimensional coordinates of each bushing, and determine the calibration normal information based on the three-dimensional coordinates of each tooling and the tooling calibration data. The current pose information of the object to be adjusted is calculated based on at least two bushing three-dimensional vectors and the calibration normal information.

[0107] Optionally, the adjustment module 308 is further configured to: A reference tooling object is determined, wherein the reference tooling object includes at least three tooling target balls; Based on the preset measuring instrument, measure the tooling measurement coordinate information of each tooling target ball in the measuring instrument coordinate system; Determine the measurement tooling transformation matrix from the measuring instrument coordinate system to the tooling coordinate system based on the measurement coordinate information of each tooling; The tooling calibration data corresponding to the reference tooling is determined based on the measurement tooling transformation matrix and the measurement normal information corresponding to the preset measuring instrument.

[0108] Optionally, the adjustment module 308 is further configured to: The target attitude range is determined based on the target attitude information and the preset attitude error value; Adjust the posture of the object to be adjusted until the current posture information is within the target posture range.

[0109] The apparatus provided in this application transforms the traditional attitude adjustment process, which relies on manual interpretation and single-item measurement, into a digital, synchronous measurement method. This significantly improves attitude adjustment efficiency and provides reliable technical support for the precision assembly of spacecraft structural components.

[0110] The device provided in this application offers a reference tool that combines measurement and attitude adjustment functions. It realizes the proxy representation of the ground plane through the reference tool, which is the physical basis for solving the problem of the lack of absolute measurement reference in binocular vision using the above-mentioned device.

[0111] Furthermore, this device proposes a two-step proxy measurement method: first, calibration using a calibration target ball, and then measurement using lightweight target markers. By establishing a fixed coordinate transformation relationship between the center of the clamping bushing and the target markers during the calibration stage, the coordinates of non-directly measurable feature points can be obtained without contacting the sailboard in subsequent actual measurements. This achieves high-precision feature measurement without interfering with the sailboard's attitude.

[0112] Finally, images of the solar panel and the reference fixture are acquired simultaneously using a binocular vision device. By calculating the feature points in the images, the roll and pitch angles of the solar panel are calculated simultaneously. The attitude error is then calculated using the roll and pitch angles and fed back to the operator to guide adjustments. The reference fixture, binocular vision device, feature proxy, and data processing algorithms are integrated, with each component working together to form a comprehensive measurement, calculation, display, adjustment, and verification system.

[0113] The above is a schematic scheme of an object posture adjustment device according to this embodiment. It should be noted that the technical solution of this object posture adjustment device and the technical solution of the object posture adjustment method described above belong to the same concept. For details not described in detail in the technical solution of the object posture adjustment device, please refer to the description of the technical solution of the object posture adjustment method described above.

[0114] Figure 4 A structural block diagram of a computing device 400 according to an embodiment of this application is shown. The components of the computing device 400 include, but are not limited to, a memory 410 and a processor 420. The processor 420 is connected to the memory 410 via a bus 430, and a database 450 is used to store data.

[0115] The computing device 400 also includes an access device 440, which enables the computing device 400 to communicate via one or more networks 460. Examples of these networks include Public Switched Telephone Network (PSTN), Local Area Network (LAN), Wide Area Network (WAN), Personal Area Network (PAN), or combinations of communication networks such as the Internet. The access device 440 may include one or more of any type of wired or wireless network interface (e.g., a network interface card (NIC)), such as an IEEE 802.11 Wireless Local Area Network (WLAN) wireless interface, a Wi-MAX (Worldwide Interoperability for Microwave Access) interface, an Ethernet interface, a Universal Serial Bus (USB) interface, a cellular network interface, a Bluetooth interface, a Near Field Communication (NFC) interface, and so on.

[0116] In one embodiment of this application, the aforementioned components of the computing device 400 and Figure 4 Other components, not shown, can also be connected to each other, for example, via a bus. It should be understood that... Figure 4 The block diagram of the computing device shown is for illustrative purposes only and is not intended to limit the scope of this application. Those skilled in the art can add or replace other components as needed.

[0117] The computing device 400 can be any type of stationary or mobile computing device, including mobile computers or mobile computing devices (e.g., tablet computers, personal digital assistants, laptop computers, notebook computers, netbooks, etc.), mobile phones (e.g., smartphones), wearable computing devices (e.g., smartwatches, smart glasses, etc.) or other types of mobile devices, or stationary computing devices such as desktop computers or personal computers (PCs). The computing device 400 can also be a mobile or stationary server.

[0118] The processor 420 is used to execute the following computer program / instructions, which, when executed by the processor, implement the steps of the above-described object pose adjustment method.

[0119] The above is a schematic representation of a computing device according to this embodiment. It should be noted that the technical solution of this computing device and the technical solution of the object posture adjustment method described above belong to the same concept. Details not described in detail in the technical solution of the computing device can be found in the description of the technical solution of the object posture adjustment method described above.

[0120] An embodiment of this application also provides a computer-readable storage medium storing a computer program / instructions that, when executed by a processor, implement the steps of the above-described object posture adjustment method.

[0121] The above is an illustrative scheme of a computer-readable storage medium according to this embodiment. It should be noted that the technical solution of this storage medium and the technical solution of the object posture adjustment method described above belong to the same concept. For details not described in detail in the technical solution of the storage medium, please refer to the description of the technical solution of the object posture adjustment method described above.

[0122] An embodiment of this application also provides a computer program product, including a computer program / instructions that, when executed by a processor, implement the steps of the above-described object pose adjustment method.

[0123] The above is an illustrative scheme of a computer program product according to this embodiment. It should be noted that the technical solution of this computer program product and the technical solution of the object posture adjustment method described above belong to the same concept. For details not described in detail in the technical solution of the computer program product, please refer to the description of the technical solution of the object posture adjustment method described above.

[0124] The foregoing has described specific embodiments of this application. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims may be performed in a different order than that shown in the embodiments and may still achieve the desired results. Furthermore, the processes depicted in the drawings do not necessarily require the specific or sequential order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0125] The computer instructions include computer program code, which may be in the form of source code, object code, executable file, or certain intermediate forms. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording media, USB flash drive, portable hard drive, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signals, telecommunication signals, and software distribution media, etc. It should be noted that the content included in the computer-readable medium may be appropriately added or removed according to the requirements of patent practice. For example, in some regions, according to patent practice, computer-readable media may not include electrical carrier signals and telecommunication signals.

[0126] It should be noted that, for the sake of simplicity, the foregoing method embodiments are all described as a series of actions. However, those skilled in the art should understand that this application is not limited to the described order of actions, as some steps may be performed in other orders or simultaneously according to this application. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are preferred embodiments, and the actions and modules involved are not necessarily essential to this application.

[0127] In the above embodiments, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions in other embodiments.

[0128] The preferred embodiments disclosed above are merely illustrative of this application. The optional embodiments do not exhaustively describe all details, nor do they limit the invention to the specific implementations described. Clearly, many modifications and variations can be made based on the content of this application. These embodiments are selected and specifically described in this application to better explain the principles and practical applications of this application, thereby enabling those skilled in the art to better understand and utilize this application. This application is limited only by the claims and their full scope and equivalents.

Claims

1. A method for adjusting the pose of an object, characterized in that, include: Acquire an image of an object including the object to be adjusted and a reference tooling, wherein the object to be adjusted includes at least three target marker points and the reference tooling includes at least three tooling target balls; The three-dimensional coordinates of each target marker point are determined based on the pixel coordinates of each target marker point in the object image, and the three-dimensional coordinates of each tooling target ball are determined based on the pixel coordinates of each tooling target ball in the object image. Based on the positional relationship between each target marker point on the object to be adjusted and at least three bushings, and the three-dimensional coordinates of each marker point, determine the three-dimensional coordinates of each bushing; The current posture information of the object to be adjusted is determined based on the three-dimensional coordinates of each bushing and the three-dimensional coordinates of each tooling, and the posture of the object to be adjusted is adjusted based on the current posture information and the target posture information.

2. The method as described in claim 1, characterized in that, Acquire object images including the object to be adjusted and the reference tooling, including: The image of an object, including the object to be adjusted and a reference tool, is acquired using a binocular vision device, wherein the reference tool is located between the binocular vision device and the object to be adjusted.

3. The method as described in claim 1, characterized in that, The object image includes a first object image and a second object image; Determining the three-dimensional coordinates of each target marker point based on the pixel coordinates of each marker point in the object image includes: Select a target marker point to be processed, wherein the target marker point to be processed is any one of the target marker points; Determine the first pixel information of the target marker point to be processed in the first image of the object, and determine the second pixel information of the target marker point to be processed in the second image of the object; The three-dimensional coordinates of the marker point corresponding to the target marker point to be processed are calculated based on the first pixel information, the second pixel information, and the device parameter information.

4. The method as described in claim 1, characterized in that, The object image includes a first object image and a second object image; Determining the tooling three-dimensional coordinates of each tooling target ball based on the target ball pixel coordinates in the object image includes: Select a tooling target ball to be processed, wherein the tooling target ball to be processed is any one of the tooling target balls; Determine the coordinates of the first tooling target ball in the first image of the object, and determine the coordinates of the second tooling target ball in the second image of the object; The three-dimensional coordinates of the tooling target ball to be processed are calculated based on the coordinates of the first tooling target ball, the coordinates of the second tooling target ball, and the equipment parameter information.

5. The method as described in claim 1, characterized in that, The positional relationship between each target marker point on the object to be adjusted and at least three bushings is determined through the following steps: With the target ball installed in each bushing of the object to be adjusted, an initial object image of the object to be adjusted is obtained; The initial coordinates of each target marker point and the initial coordinates of each target ball are identified based on the initial object image. The positional relationship between each target marker and at least three bushings is generated based on the initial coordinates of each marker point and each target ball.

6. The method as described in claim 1, characterized in that, Based on the positional relationship between each target marker point on the object to be adjusted and at least three bushings, and the three-dimensional coordinates of each marker point, determine the three-dimensional coordinates of each bushing, including: Based on the three-dimensional coordinates of each marker point and the positional relationship between each target marker point and at least three bushings, determine the attitude offset information between each target marker point and each bushing; The three-dimensional coordinates of each bushing are calculated based on the attitude offset information and the three-dimensional coordinates of each marker point.

7. The method as described in claim 1, characterized in that, The current attitude information of the object to be adjusted is determined based on the three-dimensional coordinates of each bushing and each tooling, including: Determine at least two bushing three-dimensional vectors based on the three-dimensional coordinates of each bushing, and determine the calibration normal information based on the three-dimensional coordinates of each tooling and the tooling calibration data. The current pose information of the object to be adjusted is calculated based on at least two bushing three-dimensional vectors and the calibration normal information.

8. The method as described in claim 7, characterized in that, The tooling calibration data is generated through the following steps: A reference tooling object is determined, wherein the reference tooling object includes at least three tooling target balls; Based on the preset measuring instrument, measure the tooling measurement coordinate information of each tooling target ball in the measuring instrument coordinate system; Determine the measurement tooling transformation matrix from the measuring instrument coordinate system to the tooling coordinate system based on the measurement coordinate information of each tooling; The tooling calibration data corresponding to the reference tooling is determined based on the measurement tooling transformation matrix and the measurement normal information corresponding to the preset measuring instrument.

9. The method according to any one of claims 1-8, characterized in that, Adjusting the posture of the object to be adjusted based on the current posture information and the target posture information includes: The target attitude range is determined based on the target attitude information and the preset attitude error value; Adjust the posture of the object to be adjusted until the current posture information is within the target posture range.

10. An object posture adjustment device, characterized in that, include: The acquisition module is configured to acquire an object image including the object to be adjusted and a reference tooling, wherein the object to be adjusted includes at least three target marker points and the reference tooling includes at least three tooling target balls; The determination module is configured to determine the three-dimensional coordinates of each target marker point based on the pixel coordinates of each target marker point in the object image, and to determine the three-dimensional coordinates of each tooling target ball based on the pixel coordinates of each tooling target ball in the object image. The calibration module is configured to determine the three-dimensional coordinates of each bushing based on the positional relationship between each target marker point on the object to be adjusted and at least three bushings and the three-dimensional coordinates of each marker point. The adjustment module is configured to determine the current posture information of the object to be adjusted based on the three-dimensional coordinates of each bushing and the three-dimensional coordinates of each tooling, and to adjust the posture of the object to be adjusted based on the current posture information and the target posture information.

11. A computing device, characterized in that, include: Memory and processor; The memory is used to store computer programs / instructions, and the processor is used to execute the computer programs / instructions, which, when executed by the processor, implement the steps of the method according to any one of claims 1 to 9.

12. A computer-readable storage medium storing a computer program / instructions, characterized in that, When the computer program / instructions are executed by the processor, they implement the steps of the method according to any one of claims 1 to 9.

13. A computer program product comprising a computer program / instructions, characterized in that, When the computer program / instructions are executed by the processor, they implement the steps of the method according to any one of claims 1 to 9.

Images