A method and system for automatic visual correction of tube selection in low-temperature environments

Abstract

This invention provides a method and system for automatic visual correction of tube picking in low-temperature environments, relating to the field of data processing technology. It involves controlling a tube picking fixture carrying a calibration pattern at room temperature to move to a cryogenic container holder, ensuring the plane of the calibration pattern is flush with the bottom surface of the cryogenic container during tube picking, thus obtaining the fixture's position information at room temperature. Based on this position information, the fixture is moved within the field of view of a visual sensor, and the movement position and image are recorded. The fixture is then calibrated at room temperature using self-calibration software to obtain a hand-eye conversion matrix. This invention can determine sample position information in real time, improving the stability of tube picking during long-term use in low-temperature environments, while reducing manual adjustment intensity, minimizing the impact of personnel adjustment skills and competence on product quality, and improving product consistency.

Description

Technical Field

[0001] This invention relates to the field of biobank technology, and more specifically to a visual automatic correction tube picking system for low-temperature environments. Background Technology

[0002] Biobanks are typically used to preserve valuable biological samples such as blood, genes, and metabolites. These samples are stored in cryovials within cryovial boxes, kept at extremely low temperatures of -80°C or even -196°C. When a user needs to retrieve a sample, automated equipment removes the cryovial containing the target sample, and a sample-picking gripper transfers the sample into an empty cryovial. Under these cryogenic conditions, the surface of the cryovials gradually frosts over. With repeated movement, positioning, and retrieving / retrieving processes, the frost thickens, potentially leading to decreased positioning accuracy during sample retrieval over time.

[0003] In addition, the automated sample library requires a lot of debugging work when it is delivered. Usually, during debugging, each tube picking point is fine-tuned at room temperature first, and then cooled to the working temperature. On-site debugging personnel find it difficult to maintain a high level of concentration under high-intensity labor, and the low-temperature deformation of materials further reduces the positioning accuracy during actual operation.

[0004] The above situations ultimately lead to increased errors in the gripper's pick-up and drop-off positions, resulting in a decrease in the success rate of tube picking, and in severe cases, may damage the sample, causing significant losses. Summary of the Invention

[0005] The technical problem this invention aims to solve is to provide a visual automatic correction method and system for tube picking under low-temperature conditions. This addresses the issue of decreased system accuracy due to low-temperature deformation in the tube picking area, improving system stability, reducing the likelihood of malfunctions, and enhancing sample safety. Furthermore, the proposed self-calibration method optimizes the system calibration process, eliminating the need for calibration in low-temperature environments, improving the working environment for personnel debugging, and significantly reducing the workload of equipment deployment and debugging, thus contributing to improved equipment performance consistency.

[0006] To solve the above-mentioned technical problems, the technical solution of the present invention is as follows:

[0007] In a first aspect, a method and system for automatic visual correction in tube picking under low-temperature conditions, the method comprising:

[0008] Place the cryopreservation box on the cryopreservation box holder, capture an image of the cryopreservation box using a vision sensor, and process the image to obtain the center coordinates of the hole position in the cryopreservation box.

[0009] Based on the center coordinates of the holes in the cryopreservation box, move the tube-picking clamp to the corresponding gripping position and record the corresponding position. Combining the center coordinates of the holes and the position information of the tube-picking clamp, calibrate the tube-picking position of the cryopreservation box at room temperature to obtain the room temperature tube-picking position transformation matrix.

[0010] By controlling the pipe-picking clamp to carry the calibration pattern at low temperature and moving it to the cryopreservation box bracket, the position information of the pipe-picking clamp at low temperature is obtained. The pipe-picking clamp is moved within the field of view of the vision sensor, and the self-calibration software is used to calculate and calibrate the pipe-picking clamp at low temperature to obtain the hand-eye conversion matrix at low temperature.

[0011] Images of the cryopreservation box are acquired using a visual sensor to locate the coordinates of the hole. Based on the hand-eye conversion matrix at room temperature, the tube picking position conversion matrix at room temperature, and the hand-eye conversion matrix at low temperature, the tube picking position after correction is calculated.

[0012] Furthermore, before placing the cryopreservation box on the cryopreservation box holder, capturing an image of the cryopreservation box using a vision sensor, and processing the image to obtain the center coordinates of the cryopreservation box aperture, the process also includes:

[0013] By controlling the tube-picking clamp to carry the calibration pattern at room temperature and moving it to the cryogenic box bracket, and ensuring that the plane where the calibration pattern is located is the same plane as the bottom surface of the cryogenic box when picking the tube, the position information of the tube-picking clamp at room temperature can be obtained.

[0014] Based on the position information of the pipe-picking clamp at room temperature, the pipe-picking clamp is moved within the field of view of the vision sensor, the movement position and image are recorded, and the pipe-picking clamp is calibrated at room temperature by self-calibration software to obtain the hand-eye conversion matrix H1 at room temperature.

[0015] Furthermore, by controlling the tube-picking clamp at room temperature to carry the calibration pattern and move it to the cryogenic container tray, ensuring that the plane of the calibration pattern is on the same plane as the bottom surface of the cryogenic container during tube picking, the position information of the tube-picking clamp at room temperature is obtained, including:

[0016] By installing the pipe-picking fixture on the robotic arm, fixing the calibration pattern on the pipe-picking fixture, and turning on and initializing the vision positioning system, the robotic arm control system is in a ready state.

[0017] Based on the robotic arm control system in the ready state, the tube-picking clamp is moved to the vicinity of the cryopreservation box tray. The robotic arm is used to adjust the position and posture of the tube-picking clamp so that the plane where the calibration pattern is located is completely parallel and coincident with the expected bottom surface of the cryopreservation box on the cryopreservation box tray, so as to obtain the position information of the tube-picking clamp at room temperature.

[0018] Furthermore, the cryopreservation box is placed on the cryopreservation box holder, and an image of the cryopreservation box is captured using a vision sensor. The image is then processed to obtain the center coordinates of the cryopreservation box aperture, including:

[0019] Place the cryopreservation box on the cryopreservation box holder, adjust the position and focus of the vision sensor, activate the vision sensor, and capture an image of the cryopreservation box to obtain an image of the cryopreservation box;

[0020] The image of the cryopreservation box is preprocessed by using an image segmentation algorithm to separate the holes from the background, extracting the image contour using an edge extraction method, and then locating the pixel coordinates H of the holes using contour matching. i2 = [u,v], to obtain the center coordinates of the hole position in the cryopreservation box.

[0021] Furthermore, based on the center coordinates of the orifice in the cryopreservation box, the tube-picking fixture is moved to the corresponding gripping position and the corresponding position is recorded. Combining the center coordinates of the orifice and the position information of the tube-picking fixture, the tube-picking position of the cryopreservation box is calibrated at room temperature to obtain the room temperature tube-picking position transformation matrix, including:

[0022] Based on the center coordinates of the holes in the cryopreservation box, select nine different holes on the cryopreservation box: the holes at the four corners, the holes at the centers of the four sides, and the hole at the center of the box. Move the pipe-picking fixture to the corresponding gripping position and record the corresponding robotic arm position to obtain the recorded robotic arm position information H. r2 ;

[0023] Based on the recorded robotic arm position information, combined with the hole center coordinates and the pipe-picking fixture position information, through... Construct a least-squares problem to obtain the position transformation matrix of the tube picking at room temperature.

[0024] Furthermore, by controlling the pipe-picking clamp to carry the calibration pattern and move it to the cryogenic container bracket under low temperature, the position information of the pipe-picking clamp under low temperature is obtained. The clamp is then moved within the field of view of the vision sensor, and self-calibration software is used to calculate and calibrate the clamp under low temperature to obtain the hand-eye conversion matrix under low temperature, including:

[0025] Based on the position information of the tube-picking clamp at low temperature, the tube-picking clamp is moved to 9 positions Pr=[x,y,z] within the field of view of the visual sensor according to a 3×3 rectangular dot matrix to cover the cryopreservation box area. The moving position and the image of the end of the tube-picking clamp are recorded to obtain the moving position and image of the tube-picking clamp.

[0026] Based on the movement position of the pipe-carrying fixture and the image, edge extraction methods such as Sobel and Canny operators are used to extract the contour of the fixture. A contour matching algorithm is then used to locate the pixel coordinates of the fixture's center. The obtained nine robot positions and nine pixel coordinates are organized into a matrix to obtain the robot position matrix. and the center pixel coordinate matrix of the pipe-picking fixture

[0027] Based on the robot's position matrix and the center pixel coordinate matrix of the pipe-picking fixture, construct a least-squares problem. To obtain the hand-eye calibration matrix H3 at low temperature, where in For H i The pseudo-inverse matrix.

[0028] Furthermore, images of the cryopreservation box are acquired using a visual sensor to locate the coordinates of the vias. Based on the hand-eye conversion matrix at room temperature, the tube-picking position conversion matrix at room temperature, and the hand-eye conversion matrix at low temperature, the corrected tube-picking position is calculated, including:

[0029] Images of the cryopreservation box are acquired using a visual sensor, and the features of the holes in the cryopreservation box are extracted. The pixel coordinates of the holes are located as p0 = [u, v, 1]. T ,

[0030] By calculating p1 = H1·p0, p2 = H2·p0, and p3 = H3·p0 respectively, and combining the hand-eye conversion matrix at room temperature, the tube-picking position conversion matrix at room temperature, and the hand-eye conversion matrix at low temperature, the final positioning result is obtained as p = p2 + (p3 - p1) to obtain the tube-picking position after calculation and correction.

[0031] Secondly, a method and system for automatic visual correction in tube picking under low-temperature conditions includes:

[0032] The tube picking execution module includes a cryopreservation box bracket, a robotic arm, and a tube picking clamp. The tube picking clamp is fixed on the robotic arm. The tube picking clamp is located above the cryopreservation box bracket and can move relative to the cryopreservation box bracket. Optionally, a cryopreservation box fixing device can be added to the tube picking execution module to hold the cryopreservation box and prevent it from falling or moving during the tube picking process.

[0033] The visual positioning module includes a visual sensor, an illumination device, and a visual positioning algorithm. The installation position of the visual information acquisition device ensures that its acquisition range can cover the space where at least one cryopreservation box is located. The illumination device ensures that uniform illumination is provided for the space where a cryopreservation box is located. The visual positioning module acquires cryopreservation box information through the visual sensor and processes it through the visual positioning algorithm to obtain the location information of the cryopreservation box.

[0034] The low-temperature self-calibration module includes a calibration pattern and self-calibration software. The calibration pattern is a template pattern that can be used for matching, identification, and positioning. The calibration pattern can be fixed on the pipe picker fixture by means including but not limited to milling, printing, engraving, pasting, and gripping.

[0035] Thirdly, a computing device includes:

[0036] One or more processors;

[0037] A storage device for storing one or more programs that, when executed by one or more processors, cause the one or more processors to implement the method.

[0038] Fourthly, a computer-readable storage medium storing a program that, when executed by a processor, implements the method.

[0039] The above-described solution of the present invention has at least the following beneficial effects.

[0040] This study addresses the issue of decreased system accuracy in tube picking area positioning due to low-temperature deformation under cryogenic conditions, improving system stability, reducing the likelihood of malfunctions, and enhancing sample safety. Furthermore, the proposed self-calibration method optimizes the system calibration process, eliminating the need for calibration in low-temperature environments, improving the working environment for personnel debugging, significantly reducing equipment deployment and debugging workload, and contributing to improved equipment performance consistency. Attached Figure Description

[0041] Figure 1 This is a schematic flowchart of a visual automatic correction tube picking method in a low-temperature environment provided by an embodiment of the present invention.

[0042] Figure 2 This is a schematic diagram of a visual automatic deviation correction tube picking system provided by an embodiment of the present invention in a low-temperature environment. Detailed Implementation

[0043] Exemplary embodiments of the present disclosure will now be described in more detail with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be implemented in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.

[0044] like Figure 1 As shown, embodiments of the present invention propose a method and system for automatic visual correction of tube selection in low-temperature environments. The method includes the following steps:

[0045] Step 11: Under normal temperature, control the tube picking clamp to carry the calibration pattern and move it to the cryogenic box bracket, and make the plane where the calibration pattern is located the same plane as the bottom surface of the cryogenic box when picking the tube, so as to obtain the position information of the tube picking clamp under normal temperature.

[0046] Step 12: Based on the position information of the pipe-picking clamp at room temperature, move the pipe-picking clamp within the field of view of the vision sensor, record the movement position and image, and calculate the calibration of the pipe-picking clamp at room temperature using self-calibration software to obtain the hand-eye conversion matrix at room temperature.

[0047] Step 13: Place the cryopreservation box on the cryopreservation box holder, capture an image of the cryopreservation box using a vision sensor, and process the image to obtain the center coordinates of the hole position of the cryopreservation box.

[0048] Step 14: Based on the center coordinates of the hole in the cryopreservation box, move the tube picking clamp to the corresponding gripping position and record the corresponding position. Combine the center coordinates of the hole and the position information of the tube picking clamp to calibrate the tube picking position of the cryopreservation box at room temperature to obtain the room temperature tube picking position transformation matrix.

[0049] Step 15: Control the pipe-picking clamp to carry the calibration pattern and move it to the cryopreservation box bracket under low temperature to obtain the position information of the pipe-picking clamp under low temperature. Move the pipe-picking clamp within the field of view of the vision sensor and perform self-calibration software calculation to calibrate the pipe-picking clamp under low temperature to obtain the hand-eye conversion matrix under low temperature.

[0050] Step 16: Acquire images of the cryopreservation box using a vision sensor, locate the coordinates of the hole, and calculate the corrected tube picking position based on the hand-eye conversion matrix at room temperature, the tube picking position conversion matrix at room temperature, and the hand-eye conversion matrix at low temperature.

[0051] In this embodiment of the invention, at room temperature, the pipe-picking clamp is controlled to move the calibration pattern to the cryopreservation box holder, ensuring that the calibration pattern and the bottom surface of the cryopreservation box are on the same plane, thereby obtaining accurate position information of the pipe-picking clamp. The pipe-picking clamp is moved within the field of view of the vision sensor, and its movement position and image are recorded. This data is processed using self-calibration software to calculate the hand-eye conversion matrix at room temperature. The cryopreservation box is placed on the cryopreservation box holder, and its image is captured by the vision sensor. The image is processed to identify and locate each hole in the cryopreservation box, thereby obtaining the center coordinates of the hole. Based on the obtained center coordinates of the hole, the pipe-picking clamp is moved to the corresponding gripping position, and its position information is recorded. Combining the center coordinates of the hole and the position information of the pipe-picking clamp, the self-calibration software is used to calculate the pipe-picking position conversion matrix at room temperature. This process is repeated in a low-temperature environment. Similar to the calibration process at room temperature, the tube-picking fixture is controlled to move with the calibration pattern to the cryogenic container bracket. The position information of the tube-picking fixture at low temperature is obtained. The hand-eye conversion matrix at low temperature is obtained through movement within the field of view of the vision sensor and calculations by the self-calibration software. In actual operation, the image of the cryogenic container is acquired through the vision sensor, and the coordinates of the hole are located. Using the hand-eye conversion matrix at room temperature, the tube-picking position conversion matrix at room temperature, and the hand-eye conversion matrix at low temperature, the corrected tube-picking position is calculated to ensure the accuracy of the tube-picking operation. Through a detailed calibration process, the position information of the tube-picking fixture at different temperatures and the accurate coordinates of the cryogenic container holes can be accurately obtained, thus significantly improving the accuracy of the tube-picking operation. By calibrating at different temperatures, the system can better adapt to deviations caused by temperature changes, ensuring high accuracy under various operating conditions.

[0052] Figure 1 As shown, embodiments of the present invention propose a visual automatic correction method and system for tube picking in low-temperature environments. The method involves controlling a tube picking clamp to carry a calibration pattern at room temperature and move it to the cryopreservation box holder, ensuring that the plane containing the calibration pattern is flush with the bottom surface of the cryopreservation box during tube picking. This allows for obtaining the position information of the tube picking clamp at room temperature. The method includes:

[0053] By installing the pipe-picking fixture on the robotic arm, fixing the calibration pattern on the pipe-picking fixture, and turning on and initializing the vision positioning system, the robotic arm control system is in a ready state.

[0054] Based on the robotic arm control system in the ready state, the tube-picking clamp is moved to the vicinity of the cryopreservation box tray. The robotic arm is used to adjust the position and posture of the tube-picking clamp so that the plane where the calibration pattern is located is completely parallel and coincident with the expected bottom surface of the cryopreservation box on the cryopreservation box tray, so as to obtain the position information of the tube-picking clamp at room temperature.

[0055] In this embodiment of the invention, the pipe-picking fixture is mounted on a robotic arm, and the calibration pattern is fixed on the fixture. The vision positioning system is turned on and initialized to ensure that all system components are in a ready state. Based on the ready state of the robotic arm control system, the pipe-picking fixture is moved to the vicinity of the cryopreservation box tray. Using the fine-tuning function of the robotic arm, the position and posture of the pipe-picking fixture are precisely adjusted to ensure that the plane where the calibration pattern is located is completely parallel and coincident with the expected bottom surface of the cryopreservation box on the cryopreservation box tray. This position is captured and verified by the vision positioning system to obtain the precise position information of the pipe-picking fixture at room temperature. With the precise control of the robotic arm and the assistance of the vision positioning system, the position of the pipe-picking fixture and the calibration pattern it carries in three-dimensional space can be ensured to be extremely accurate, thereby improving the positioning accuracy of subsequent pipe-picking operations. Due to the accurate positioning of the pipe-picking fixture, pipe-picking errors caused by human operation or system errors can be greatly reduced. Through a rigorous calibration process, the stability and reliability of the system under different operating conditions can be ensured.

[0056] Figure 1 As shown, embodiments of the present invention propose a method and system for automatic visual correction of pipe picking in low-temperature environments. Based on the position information of the pipe picking clamp at room temperature, the clamp is moved within the field of view of a visual sensor, the movement position and image are recorded, and the clamp is calibrated at room temperature using self-calibration software to obtain the hand-eye conversion matrix at room temperature, including:

[0057] Based on the position information of the tube picker at room temperature, the tube picker is moved to 9 positions Pr=[x,y,z] within the field of view of the vision sensor according to a 3×3 rectangular dot matrix to cover the cryopreservation box area. The moving position and the image of the end of the tube picker are recorded to obtain the moving position and image of the tube picker.

[0058] Based on the movement position of the pipe-carrying fixture and the image, edge extraction methods such as Sobel and Canny operators are used to extract the contour of the fixture. A contour matching algorithm is then used to locate the pixel coordinates of the fixture's center. The obtained nine robot positions and nine pixel coordinates are organized into a matrix to obtain the robot position matrix. and the center pixel coordinate matrix of the pipe-picking fixture

[0059] Based on the robot's position matrix and the center pixel coordinate matrix of the pipe-picking fixture, construct a least-squares problem. To obtain the hand-eye calibration matrix H1 at room temperature, where in For H i The pseudo-inverse matrix.

[0060] In this embodiment of the invention, based on the known position information of the pipe-picking clamp at room temperature, the clamp is controlled to move within the field of view of the vision sensor. Edge extraction algorithms such as Sobel and Canny are used to accurately extract the contour of the clamp from the image. Through contour matching algorithms, the pixel coordinates of the clamp's center are precisely located. The physical positions of the nine clamps and the nine pixel coordinates are organized into a matrix. The robot position matrix describes the position of the clamp in physical space, while the pixel coordinate matrix reflects its position in image space. Based on the robot position matrix and the pixel coordinate matrix, a least-squares problem is constructed. By solving this least-squares problem, the... The hand-eye calibration matrix at room temperature is obtained. By moving the pipe-picking fixture according to a 3×3 rectangular dot matrix within the field of view of the visual sensor and recording the position and image, the position of the pipe-picking fixture can be calibrated in all directions with high precision. The pixel coordinates of the center of the pipe-picking fixture are accurately located using edge extraction methods such as Sobel and Canny and contour matching algorithms, which further improves the accuracy of position recognition. The hand-eye calibration matrix at room temperature is obtained by constructing a least squares problem and solving the pseudo-inverse matrix, which handles noise and uncertainty in the data, thereby enhancing the robustness of the system. The accurate hand-eye conversion matrix enables the system to maintain high performance when facing slight environmental changes or mechanical errors.

[0061] Figure 1 As shown, embodiments of the present invention propose a method and system for automatic visual correction of pipe selection in low-temperature environments. The method involves placing the cryopreservation box on a cryopreservation box holder, capturing an image of the cryopreservation box using a visual sensor, and processing the image to obtain the center coordinates of the hole positions in the cryopreservation box. The method includes:

[0062] Place the cryopreservation box on the cryopreservation box holder, adjust the position and focus of the vision sensor, activate the vision sensor, and capture an image of the cryopreservation box to obtain an image of the cryopreservation box;

[0063] The image of the cryopreservation box is preprocessed. Image segmentation algorithms are used to separate the holes from the background. Edge extraction methods such as Sobel and Canny operators are used to extract the image contours of the cryopreservation box. Finally, contour matching is used to locate the pixel coordinates H of the holes in the cryopreservation box. i2 = [u,v], to obtain the center coordinates of the hole position in the cryopreservation box.

[0064] In this embodiment of the invention, the cryopreservation box is gently placed on the bracket, ensuring that the bottom surface of the cryopreservation box is in complete contact with the bracket. Based on the size and shape of the cryopreservation box and the limitations of the working environment, the optimal installation position of the vision sensor is determined. The focal length of the vision sensor is adjusted to ensure that the entire surface of the cryopreservation box can be clearly captured. The vision sensor is then activated and calibrated and initialized. Through a software or hardware trigger mechanism, the vision sensor is activated to capture an image of the cryopreservation box. The captured image data is acquired from the vision sensor, processed for grayscale conversion, noise reduction, and contrast enhancement. An image segmentation algorithm is used to separate the holes of the cryopreservation box from the background. Edge extraction operators such as Sobel and Canny are applied to extract edge information from the cryopreservation box image. The system performs contour matching and hole location based on the outline edges of the holes. The center coordinates of each hole are calculated based on its pixel coordinates and shape information. By adjusting the position and focal length of the vision sensor, clear, high-resolution images of the cryopreservation box are obtained, improving the accuracy of subsequent hole location. Image segmentation algorithms are used to effectively separate the holes from the background. Combined with edge extraction methods such as Sobel and Canny, the outlines of the holes are accurately captured, ensuring accurate location. Automated image preprocessing and hole recognition reduce human intervention. Precise hole recognition and location algorithms enable the system to adapt to different specifications and types of cryopreservation boxes, enhancing its versatility and scalability.

[0065] Figure 1 As shown, embodiments of the present invention propose a visual automatic correction method and system for tube picking in low-temperature environments. Based on the center coordinates of the holes in the cryopreservation box, the tube picking fixture is moved to the corresponding gripping position and the corresponding position is recorded. Combining the center coordinates of the holes and the position information of the tube picking fixture, the tube picking position of the cryopreservation box is calibrated at room temperature to obtain a room-temperature tube picking position transformation matrix, including:

[0066] Based on the center coordinates of the holes in the cryopreservation box, select nine different holes on the cryopreservation box: the holes at the four corners, the holes at the centers of the four sides, and the hole at the center of the box. Move the pipe-picking fixture to the corresponding gripping position and record the corresponding robotic arm position to obtain the recorded robotic arm position information H. r2 ;

[0067] Based on the recorded robotic arm position information, combined with the hole center coordinates and the pipe-picking fixture position information, through... Construct a least-squares problem to obtain the position transformation matrix of the tube picking at room temperature.

[0068] In this embodiment of the invention, based on the center coordinates of the holes in the cryopreservation box, holes are selected from the four corners of the cryopreservation box. Along each side of the cryopreservation box, a hole located at the center of the side is selected. A hole is then selected at the center of the cryopreservation box. For each selected hole, the pipe-picking fixture is moved and the position of the robotic arm is recorded, obtaining nine sets of robotic arm position information corresponding to the holes. The recorded robotic arm position information, hole center coordinates, and pipe-picking fixture position information are organized and used to construct a least-squares problem. The goal is to find the optimal room-temperature pipe-picking position transformation matrix, minimizing the error between the robotic arm position predicted by this matrix and the actual recorded robotic arm position. The least-squares problem is solved to obtain the transformation matrix. By selecting nine specific holes on the cryopreservation box, different areas of the cryopreservation box can be more comprehensively covered, thereby improving the overall accuracy of the pipe-picking operation. The transformation matrix obtained using the least-squares method can more accurately map the hole coordinates to the actual position of the robotic arm, reducing errors and improving the accuracy of pipe picking.

[0069] Figure 1 As shown, embodiments of the present invention propose a method and system for automatic visual correction of pipe picking in low-temperature environments. The method involves controlling a pipe picking clamp to carry a calibration pattern and move it to the cryopreservation box bracket at low temperatures. The position information of the pipe picking clamp at low temperatures is obtained, and the clamp is moved within the field of view of the visual sensor. Self-calibration software calculations are performed to calibrate the pipe picking clamp at low temperatures, resulting in a hand-eye conversion matrix at low temperatures. This includes:

[0070] Based on the position information of the tube-picking clamp at low temperature, the tube-picking clamp is moved to 9 positions Pr=[x,y,z] within the field of view of the visual sensor according to a 3×3 rectangular dot matrix to cover the cryopreservation box area. The moving position and the image of the end of the tube-picking clamp are recorded to obtain the moving position and image of the tube-picking clamp.

[0071] Based on the movement position of the pipe-carrying fixture and the image, edge extraction methods such as Sobel and Canny operators are used to extract the contour of the fixture. A contour matching algorithm is then used to locate the pixel coordinates of the fixture's center. The obtained nine robot positions and nine pixel coordinates are organized into a matrix to obtain the robot position matrix. and the center pixel coordinate matrix of the pipe-picking fixture

[0072] Based on the robot's position matrix and the center pixel coordinate matrix of the pipe-picking fixture, construct a least-squares problem. To obtain the hand-eye calibration matrix H3 at low temperature, where in Let be the pseudo-inverse matrix of Hi.

[0073] In this embodiment of the invention, within the field of view of the vision sensor, a 3×3 rectangular dot matrix covering the cryopreservation box area is selected as the moving position of the pipe-picking fixture. The pipe-picking fixture is moved and the position and image are recorded. The captured image is preprocessed as necessary, such as grayscale conversion and noise reduction. Edge extraction is performed using Sobel, Canny, etc., to extract the contour of the pipe-picking fixture in the image. The contour matching algorithm is used to locate the pixel coordinates of the center of the pipe-picking fixture, resulting in 9 robot positions. The 9 robot positions and 9 pixel coordinate positions are organized into a robot position matrix and a pipe-picking fixture center pixel coordinate matrix, respectively. A least squares problem is constructed and the hand-eye calibration matrix is ​​solved. By solving the least squares problem, the hand-eye calibration matrix under low temperature is obtained. The matrix describes the transformation relationship between the robot's position and the pixel coordinates of the vision sensor. A 3×3 rectangular dot matrix is ​​used to cover the cryopreservation box area, ensuring precise positioning of the pipe-picking fixture at different locations. Edge extraction methods such as Sobel and Canny, along with contour matching algorithms, accurately locate the pixel coordinates of the fixture's center, thus improving the accuracy of visual positioning. By constructing a least-squares problem and solving the hand-eye calibration matrix, the system can better adapt to minor deviations and inconsistencies between the robot and the vision sensor, enhancing its robustness. Recording the pipe-picking fixture's movement position and image data provides a rich data source for subsequent data analysis and operation optimization. The stored robot position matrix and pipe-picking fixture center pixel coordinate matrix facilitate the tracing and analysis of any problems or deviations during operation.

[0074] Figure 1 As shown, embodiments of the present invention propose a visual automatic correction method and system for tube picking in low-temperature environments. The method involves acquiring images of cryopreservation boxes using a visual sensor, locating the coordinates of the holes, and calculating the corrected tube picking position based on the hand-eye conversion matrix at room temperature, the tube picking position conversion matrix at room temperature, and the hand-eye conversion matrix at low temperatures. The process includes:

[0075] Images of the cryopreservation box are acquired using a visual sensor, and the features of the holes in the cryopreservation box are extracted. The pixel coordinates of the holes are located as p0 = [u, v, 1]. T ,

[0076] By calculating p1 = H1·p0, p2 = H2·p0, and p3 = H3·p0 respectively, and combining the hand-eye conversion matrix at room temperature, the tube-picking position conversion matrix at room temperature, and the hand-eye conversion matrix at low temperature, the final positioning result is obtained as p = p2 + (p3 - p1) to obtain the tube-picking position after calculation and correction.

[0077] In this embodiment of the invention, the pixel coordinates of the hole positions obtained from positioning are combined with the hand-eye transformation matrix at room temperature, the tube-picking position transformation matrix at room temperature, and the hand-eye transformation matrix at low temperature to perform coordinate transformation. The positional relationship between the robot arm and the vision sensor has slight deviations under different temperature environments. The above matrices are used to correct the tube-picking position. After correction calculation, the corrected tube-picking position is obtained. This position should be the accurate position that the robot arm needs to move to in order to successfully perform the tube-picking operation. By using the vision sensor to acquire high-resolution images of the cryopreservation box, the hole position features can be accurately extracted, thereby accurately locating the pixel coordinates of each hole position. The calculation is performed by combining multiple transformation matrices, taking into account the impact of temperature changes during teaching and actual use, effectively reducing positioning errors. By calculating the corrected tube-picking position, the system can automatically adapt to possible slight deviations between the robot arm, the vision sensor, and the cryopreservation box, improving the robustness of operation. By acquiring images of the cryopreservation box by the vision sensor and combining multiple transformation matrices to calculate the corrected tube-picking position, not only is the positioning accuracy and operational efficiency improved, but the adaptability and scalability of the system are also enhanced.

[0078] like Figure 2 As shown, embodiments of the present invention also provide a visual automatic deviation correction tube picking system for low-temperature environments, comprising:

[0079] The tube picking execution module includes a cryopreservation box bracket, a robotic arm, and a tube picking clamp. The tube picking clamp is fixed on the robotic arm. The tube picking clamp is located above the cryopreservation box bracket and can move relative to the cryopreservation box bracket. Optionally, a cryopreservation box fixing device can be added to the tube picking execution module to hold the cryopreservation box and prevent it from falling or moving during the tube picking process.

[0080] The visual positioning module includes a visual sensor, an illumination device, and a visual positioning algorithm. The installation position of the visual information acquisition device ensures that its acquisition range can cover the space where at least one cryopreservation box is located. The illumination device ensures that uniform illumination is provided for the space where a cryopreservation box is located. The visual positioning module acquires cryopreservation box information through the visual sensor and processes it through the visual positioning algorithm to obtain the location information of the cryopreservation box.

[0081] The low-temperature self-calibration module includes a calibration pattern and self-calibration software. The calibration pattern is a template pattern that can be used for matching, identification, and positioning. The calibration pattern can be fixed on the pipe picker fixture by means including but not limited to milling, printing, engraving, pasting, and gripping.

[0082] In this embodiment of the invention, the tube-picking execution module includes a cryopreservation box bracket 3, a robotic arm 1, and a tube-picking clamp 2. The tube-picking clamp 2 is fixed to the end of the robotic arm 1. The tube-picking clamp 2 is located above the cryopreservation box bracket 3, and the robotic arm 1 can move in the horizontal and vertical three-dimensional directions. Optionally, after the cryopreservation box 7 is placed on the cryopreservation box bracket 3, a cryopreservation box fixing device is pressed against the upper edge of the cryopreservation box 7 around it to fix the cryopreservation box 7 and prevent the cryopreservation box 7 from falling or moving during the process of picking up the cryopreservation tube 8. A 2D camera 4 and a light source 5 are installed directly below the cryopreservation box bracket 3; its field of view can cover the bottom area of ​​the cryopreservation box. The end of the tube-picking clamp has a unique calibration pattern 6, which can be a calibration pattern made by means of printing, engraving, etc., or the outline and grayscale image of the clamp end itself can be used directly as the calibration pattern 6.

[0083] Optionally, the tube-picking clamp is controlled at room temperature to carry the calibration pattern and move it to the cryogenic box bracket, so that the plane where the calibration pattern is located is the same plane as the bottom surface of the cryogenic box when picking the tube, so as to obtain the position information of the tube-picking clamp at room temperature.

[0084] Based on the position information of the pipe-picking clamp at room temperature, the pipe-picking clamp is moved within the field of view of the vision sensor, the movement position and image are recorded, and the pipe-picking clamp is calibrated at room temperature by self-calibration software to obtain the hand-eye conversion matrix at room temperature.

[0085] Place the cryopreservation box on the cryopreservation box holder, capture an image of the cryopreservation box using a vision sensor, and process the image to obtain the center coordinates of the hole position in the cryopreservation box.

[0086] Based on the center coordinates of the holes in the cryopreservation box, move the tube-picking clamp to the corresponding gripping position and record the corresponding position. Combining the center coordinates of the holes and the position information of the tube-picking clamp, calibrate the tube-picking position of the cryopreservation box at room temperature to obtain the room temperature tube-picking position transformation matrix.

[0087] By controlling the pipe-picking clamp to carry the calibration pattern at low temperature and moving it to the cryopreservation box bracket, the position information of the pipe-picking clamp at low temperature is obtained. The pipe-picking clamp is moved within the field of view of the vision sensor, and the self-calibration software is used to calculate and calibrate the pipe-picking clamp at low temperature to obtain the hand-eye conversion matrix at low temperature.

[0088] The image of the cryopreservation box is acquired by a vision sensor, the coordinates of the hole are located, and the corrected tube picking position is calculated based on the hand-eye conversion matrix at room temperature, the tube picking position conversion matrix at room temperature, and the hand-eye conversion matrix at low temperature.

[0089] Optionally, the tube-picking clamp is controlled at room temperature to carry the calibration pattern and move it to the cryogenic container tray, ensuring that the plane of the calibration pattern is on the same plane as the bottom surface of the cryogenic container during tube picking, in order to obtain the position information of the tube-picking clamp at room temperature, including:

[0090] By installing the pipe-picking fixture on the robotic arm, fixing the calibration pattern on the pipe-picking fixture, and turning on and initializing the vision positioning system, the robotic arm control system is in a ready state.

[0091] Based on the robotic arm control system in the ready state, the tube-picking clamp is moved to the vicinity of the cryopreservation box tray. The robotic arm is used to adjust the position and posture of the tube-picking clamp so that the plane where the calibration pattern is located is completely parallel and coincident with the expected bottom surface of the cryopreservation box on the cryopreservation box tray, so as to obtain the position information of the tube-picking clamp at room temperature.

[0092] Optionally, based on the position information of the pipe-picking clamp at room temperature, the clamp is moved within the field of view of the vision sensor, the movement position and image are recorded, and the clamp is calibrated at room temperature using self-calibration software to obtain the hand-eye conversion matrix at room temperature, including:

[0093] Based on the position information of the tube picker at room temperature, the tube picker is moved to 9 positions Pr=[x,y,z] within the field of view of the vision sensor according to a 3×3 rectangular dot matrix to cover the cryopreservation box area. The moving position and the image of the end of the tube picker are recorded to obtain the moving position and image of the tube picker.

[0094] Based on the movement position of the pipe-carrying fixture and the image, edge extraction methods such as Sobel and Canny operators are used to extract the contour of the fixture. A contour matching algorithm is then used to locate the pixel coordinates of the fixture's center. The obtained nine robot positions and nine pixel coordinates are organized into a matrix to obtain the robot position matrix. and the center pixel coordinate matrix of the pipe-picking fixture

[0095] Based on the robot's position matrix and the center pixel coordinate matrix of the pipe-picking fixture, construct a least-squares problem. To obtain the hand-eye calibration matrix H1 at room temperature, where in For H i The pseudo-inverse matrix.

[0096] Optionally, the cryopreservation box is placed on a cryopreservation box holder, an image of the cryopreservation box is captured by a vision sensor, and the image is processed to obtain the center coordinates of the cryopreservation box hole positions, including:

[0097] Place the cryopreservation box on the cryopreservation box holder, adjust the position and focus of the vision sensor, activate the vision sensor, and capture an image of the cryopreservation box to obtain an image of the cryopreservation box;

[0098] The image of the cryopreservation box is preprocessed. Image segmentation algorithms are used to separate the holes from the background. Edge extraction methods such as Sobel and Canny operators are used to extract the image contours of the cryopreservation box. Finally, contour matching is used to locate the pixel coordinates H of the holes in the cryopreservation box.i2 = [u,v], to obtain the center coordinates of the hole position in the cryopreservation box.

[0099] Optionally, based on the center coordinates of the holes in the cryopreservation box, the tube-picking fixture is moved to the corresponding gripping position and the corresponding position is recorded. Combining the center coordinates of the holes and the position information of the tube-picking fixture, the tube-picking position of the cryopreservation box is calibrated at room temperature to obtain a room temperature tube-picking position transformation matrix, including:

[0100] Based on the center coordinates of the holes in the cryopreservation box, select nine different holes on the cryopreservation box: the holes at the four corners, the holes at the centers of the four sides, and the hole at the center of the box. Move the pipe-picking fixture to the corresponding gripping position and record the corresponding robotic arm position to obtain the recorded robotic arm position information H. r2 ;

[0101] Based on the recorded robotic arm position information, combined with the hole center coordinates and the pipe-picking fixture position information, through... Construct a least-squares problem to obtain the position transformation matrix of the tube picking at room temperature.

[0102] Optionally, the pipe-picking clamp, carrying a calibration pattern, is moved to the cryogenic container tray under cryogenic conditions to obtain the clamp's position information. The clamp is then moved within the field of view of a vision sensor, and self-calibration software calculates and calibrates the clamp under cryogenic conditions to obtain the hand-eye conversion matrix, including:

[0103] Based on the position information of the tube-picking clamp at low temperature, the tube-picking clamp is moved to 9 positions Pr=[x,y,z] within the field of view of the visual sensor according to a 3×3 rectangular dot matrix to cover the cryopreservation box area. The moving position and the image of the end of the tube-picking clamp are recorded to obtain the moving position and image of the tube-picking clamp.

[0104] Based on the movement position of the pipe-carrying fixture and the image, edge extraction methods such as Sobel and Canny operators are used to extract the contour of the fixture. A contour matching algorithm is then used to locate the pixel coordinates of the fixture's center. The obtained nine robot positions and nine pixel coordinates are organized into a matrix to obtain the robot position matrix. and the center pixel coordinate matrix of the pipe-picking fixture

[0105] Based on the robot's position matrix and the center pixel coordinate matrix of the pipe-picking fixture, construct a least-squares problem. To obtain the hand-eye calibration matrix H3 at low temperature, where in For H i The pseudo-inverse matrix.

[0106] Optionally, an image of the cryopreservation box is acquired using a vision sensor to locate the coordinates of the hole. Based on the hand-eye conversion matrix at room temperature, the tube-picking position conversion matrix at room temperature, and the hand-eye conversion matrix at low temperature, the corrected tube-picking position is calculated, including:

[0107] Images of the cryopreservation box are acquired using a visual sensor, and the features of the holes in the cryopreservation box are extracted. The pixel coordinates of the holes are located as p0 = [u, v, 1]. T ,

[0108] By calculating p1 = H1·p0, p2 = H2·p0, and p3 = H3·p0 respectively, and combining the hand-eye conversion matrix at room temperature, the tube-picking position conversion matrix at room temperature, and the hand-eye conversion matrix at low temperature, the final positioning result is obtained as p = p2 + (p3 - p1) to obtain the tube-picking position after calculation and correction.

[0109] It should be noted that this system is a system corresponding to the above method. All implementation methods in the above method embodiments are applicable to this embodiment and can achieve the same technical effect.

[0110] Embodiments of the present invention also provide a computing device, including: a processor and a memory storing a computer program, wherein the computer program, when executed by the processor, performs the method described above. All implementations in the above method embodiments are applicable to this embodiment and can achieve the same technical effects.

[0111] Embodiments of the present invention also provide a computer-readable storage medium storing instructions that, when executed on a computer, cause the computer to perform the method described above. All implementations in the above method embodiments are applicable to this embodiment and can achieve the same technical effects.

[0112] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this invention.

[0113] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0114] In the embodiments provided by this invention, it should be understood that the disclosed apparatus and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative. For instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between devices or units may be electrical, mechanical, or other forms.

[0115] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0116] In addition, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0117] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, essentially, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, ROM, RAM, magnetic disks, or optical disks.

[0118] Furthermore, it should be noted that in the apparatus and method of the present invention, it is obvious that the components or steps can be decomposed and / or recombined. These decompositions and / or recombinations should be considered equivalent solutions of the present invention. Moreover, the steps performing the above-described series of processes can naturally be executed in the order described, but are not necessarily required to be executed in chronological order; some steps can be executed in parallel or independently of each other. Those skilled in the art will understand that all or any step or component of the method and apparatus of the present invention can be implemented in any computing device (including processors, storage media, etc.) or network of computing devices, in hardware, firmware, software, or a combination thereof. This can be achieved by those skilled in the art using basic programming skills after reading the description of the present invention.

[0119] Therefore, the object of the present invention can also be achieved by running a program or a set of programs on any computing device. The computing device can be a known general-purpose device. Therefore, the object of the present invention can also be achieved simply by providing a program product containing program code implementing the method or apparatus. That is, such a program product also constitutes the present invention, and the storage medium storing such a program product also constitutes the present invention. Obviously, the storage medium can be any known storage medium or any storage medium developed in the future. It should also be noted that in the apparatus and method of the present invention, it is obvious that the components or steps can be decomposed and / or recombined. These decompositions and / or recombinations should be considered equivalent to the present invention. Furthermore, the steps performing the above series of processes can naturally be performed in the order described, but are not necessarily required to be performed in chronological order. Some steps can be performed in parallel or independently of each other.

[0120] The above description represents the preferred embodiments of the present invention. It should be noted that those skilled in the art can make various improvements and modifications without departing from the principles of the present invention, and these improvements and modifications should also be considered within the scope of protection of the present invention.

Claims

1. A method for automatically correcting pipe selection based on visual perception under low-temperature conditions, characterized in that, The method includes: By controlling the tube-picking clamp at room temperature to carry the calibration pattern and move it to the cryogenic container tray, ensuring that the plane of the calibration pattern is on the same plane as the bottom surface of the cryogenic container during tube picking, the position information of the tube-picking clamp at room temperature is obtained, including: By installing the pipe-picking fixture on the robotic arm, fixing the calibration pattern on the pipe-picking fixture, and turning on and initializing the vision positioning system, the robotic arm control system is in a ready state. According to the robotic arm control system in the ready state, the tube picking clamp is moved to the vicinity of the cryopreservation box tray. The robotic arm is used to adjust the position and posture of the tube picking clamp so that the plane where the calibration pattern is located is completely parallel and coincident with the expected bottom surface of the cryopreservation box on the cryopreservation box tray, so as to obtain the position information of the tube picking clamp at room temperature. Based on the position information of the pipe-picking clamp at room temperature, the pipe-picking clamp is moved within the field of view of the vision sensor, the movement position and image are recorded, and the pipe-picking clamp is calibrated at room temperature by calculation through self-calibration software to obtain the hand-eye conversion matrix H1 at room temperature. The cryopreservation box is placed on the cryopreservation box holder, and an image of the cryopreservation box is captured using a vision sensor. The image is then processed to obtain the center coordinates of the cryopreservation box apertures, including: Place the cryopreservation box on the cryopreservation box holder, adjust the position and focus of the vision sensor, activate the vision sensor, and capture an image of the cryopreservation box to obtain an image of the cryopreservation box; The image of the cryopreservation box is preprocessed by using an image segmentation algorithm to separate the holes from the background, extracting the image contour using an edge extraction method, and then locating the pixel coordinates of the holes using contour matching. To obtain the center coordinates of the holes in the cryopreservation box; Based on the center coordinates of the holes in the cryopreservation box, move the tube-picking clamp to the corresponding gripping position and record the corresponding position. Combining the center coordinates of the holes and the position information of the tube-picking clamp, calibrate the tube-picking position of the cryopreservation box at room temperature to obtain the room temperature tube-picking position transformation matrix. By controlling the pipe-picking clamp to carry the calibration pattern at low temperature and moving it to the cryopreservation box bracket, the position information of the pipe-picking clamp at low temperature is obtained. The pipe-picking clamp is moved within the field of view of the vision sensor, and the self-calibration software is used to calculate and calibrate the pipe-picking clamp at low temperature to obtain the hand-eye conversion matrix at low temperature. Images of the cryopreservation box are acquired using a visual sensor to locate the coordinates of the hole. Based on the hand-eye conversion matrix at room temperature, the tube picking position conversion matrix at room temperature, and the hand-eye conversion matrix at low temperature, the tube picking position after correction is calculated.

2. The method for automatically correcting pipe selection under low-temperature conditions according to claim 1, characterized in that, Based on the center coordinates of the holes in the cryopreservation box, move the tube-picking clamp to the corresponding gripping position and record the position. Combining the center coordinates of the holes and the position information of the tube-picking clamp, calibrate the tube-picking position of the cryopreservation box at room temperature to obtain the room temperature tube-picking position transformation matrix, including: Based on the center coordinates of the holes in the cryopreservation box, select nine different holes on the cryopreservation box: the holes at the four corners, the holes at the centers of the four sides, and the hole at the center of the box. Move the pipe-picking fixture to the corresponding gripping position and record the corresponding robotic arm position to obtain the recorded robotic arm position information. ; Based on the recorded robotic arm position information, combined with the hole center coordinates and the pipe-picking fixture position information, through... Construct a least-squares problem to obtain the position transformation matrix of the tube picking at room temperature. .

3. The method for automatically correcting pipe selection under low-temperature conditions according to claim 2, characterized in that, By controlling a pipe-picking clamp to carry a calibration pattern and move it to the cryogenic container rack under cryogenic conditions, the position information of the pipe-picking clamp under cryogenic conditions is obtained. The clamp is then moved within the field of view of a vision sensor, and self-calibration software calculates and calibrates the clamp under cryogenic conditions to obtain the hand-eye conversion matrix, including: Based on the position information of the pipe-lifting clamp at low temperature, the device moves to 9 positions within the field of view of the vision sensor according to a 3×3 rectangular dot matrix. Move the tube-picking clamp to cover the cryopreservation box area, record the movement position and record the image of the end of the tube-picking clamp to obtain the movement position and image of the tube-picking clamp; Based on the movement position of the pipe-carrying fixture and the image, edge extraction methods such as Sobel and Canny operators are used to extract the contour of the fixture. A contour matching algorithm is then used to locate the pixel coordinates of the fixture's center. The obtained nine robot positions and nine pixel coordinates are organized into a matrix to obtain the robot position matrix. and the center pixel coordinate matrix of the pipe-picking fixture ; Based on the robot's position matrix and the center pixel coordinate matrix of the pipe-picking fixture, construct a least-squares problem. To obtain the hand-eye calibration matrix at low temperature ,in ,in for The pseudo-inverse matrix.

4. The method for automatically correcting pipe selection under low-temperature conditions according to claim 3, characterized in that, Images of the cryopreservation box are acquired using a vision sensor to locate the coordinates of the perforation. Based on the hand-eye conversion matrix at room temperature, the tube picking position conversion matrix at room temperature, and the hand-eye conversion matrix at low temperature, the corrected tube picking position is calculated, including: Images of the cryopreservation box are acquired using a vision sensor, and the features of the holes in the cryopreservation box are extracted. The pixel coordinates of the holes are then located. By calculating separately , , By combining the hand-eye conversion matrix at room temperature, the tube-picking position conversion matrix at room temperature, and the hand-eye conversion matrix at low temperature, the final positioning result is obtained as follows: To obtain the calculated and corrected pipe picking position.

5. A visual automatic correction tube picking system for low-temperature environments, characterized in that, The system is used to perform the method as described in any one of claims 1 to 4, comprising: The tube picking execution module includes a cryopreservation box bracket, a robotic arm, and a tube picking clamp. The tube picking clamp is fixed on the robotic arm. The tube picking clamp is located above the cryopreservation box bracket and can move relative to the cryopreservation box bracket. A cryopreservation box fixing device is added to the tube picking execution module to hold the cryopreservation box in place to prevent the cryopreservation box from falling or moving during the tube picking process. The visual positioning module includes a visual sensor, an illumination device, and a visual positioning algorithm. The visual information acquisition device covers the space where at least one cryopreservation box is located. The illumination device provides uniform illumination to the space where a cryopreservation box is located. The visual positioning module acquires cryopreservation box information through the visual sensor and processes it through the visual positioning algorithm to obtain the location information of the cryopreservation box. The low-temperature self-calibration module includes calibration patterns and self-calibration software; the calibration patterns are templates used for matching, identification, and positioning.

6. A computing device, characterized in that, include: One or more processors; A storage device for storing one or more programs that, when executed by one or more processors, cause the one or more processors to implement the method as described in any one of claims 1 to 4.

7. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a program that, when executed by a processor, implements the method as described in any one of claims 1 to 4.

Images