Lifting appliance attitude determination method, device and equipment, readable storage medium and product

Abstract

The invention provides a lifting appliance attitude determination method, device and equipment, a readable storage medium and a product, and the method comprises the steps: obtaining a template point cloud associated with a target lifting appliance, the template point cloud being a point cloud when the target lifting appliance is in a normal pose; determining a fitting plane of the target lifting appliance in a normal pose based on the template point cloud; acquiring a real-time point cloud acquired by at least one preset laser radar, and determining distance information between the real-time point cloud and the fitting plane; maximum posteriori estimation information corresponding to the target lifting appliance is constructed according to the distance information, and current pose information of the target lifting appliance is determined based on the maximum posteriori estimation information. Therefore, the current pose information of the target lifting appliance can be accurately identified on the basis of not arranging a flag bit on the target lifting appliance.

Description

Technical Field

[0001] The present disclosure relates to the field of data processing, and in particular to a method, device, equipment, readable storage medium and product for determining a hanger posture. Background Art

[0002] The sling includes the device for lifting heavy objects in the lifting machinery. In order to improve the safety and stability of the sling in the process of grabbing and placing heavy objects, it is necessary to predict the real-time posture of the sling.

[0003] In the related art, a marker is generally set on the sling, and the position information of the marker is identified by a laser radar to determine the position information of the sling.

[0004] However, the use of the above method for posture recognition requires setting a marker on the sling, which is often cumbersome to operate and has a high recognition cost. Summary of the invention

[0005] The present invention provides a method, device, equipment, readable storage medium and product for determining the posture of a sling, which are used to solve the technical problems that the existing sling posture recognition methods are complicated to operate and have high recognition costs.

[0006] A first aspect of the present disclosure is to provide a method for determining a hanger posture, comprising:

[0007] Acquire a template point cloud associated with a target lifting device, wherein the template point cloud is a point cloud when the target lifting device is in a normal posture;

[0008] Determine a fitting plane of the target lifting device in a normal posture based on the template point cloud;

[0009] Acquire a real-time point cloud collected by at least one preset laser radar, and determine distance information between the real-time point cloud and the fitting plane;

[0010] Maximum a posteriori estimation information corresponding to the target hoist is constructed according to the distance information, and current position information of the target hoist is determined based on the maximum a posteriori estimation information.

[0011] A second aspect of the present disclosure is to provide a device for determining a hanger posture, comprising:

[0012] An acquisition module, used for acquiring a template point cloud associated with a target sling, wherein the template point cloud is a point cloud when the target sling is in a normal posture;

[0013] A determination module, used to determine a fitting plane of the target lifting device in a normal posture based on the template point cloud;

[0014] A calculation module, used to obtain a real-time point cloud collected by at least one preset laser radar, and determine the distance information between the real-time point cloud and the fitting plane;

[0015] A processing module is used to construct maximum a posteriori estimation information corresponding to the target lifting device according to the distance information, and determine the current position and posture information of the target lifting device based on the maximum a posteriori estimation information.

[0016] A third aspect of the present disclosure is to provide an electronic device, comprising: a memory, a processor;

[0017] The memory stores computer-executable instructions;

[0018] The processor executes the computer-executable instructions stored in the memory, so that the processor performs the method for determining the posture of the spreader as described in the first aspect.

[0019] The fourth aspect of the present disclosure is to provide a computer-readable storage medium, wherein the computer-readable storage medium stores computer-executable instructions. When a processor executes the computer-executable instructions, the method for determining the posture of the sling as described in the first aspect is implemented.

[0020] A fifth aspect of the present disclosure is to provide a computer program product, comprising a computer program, wherein when the computer program is executed by a processor, the method for determining the posture of the spreader as described in the first aspect is implemented.

[0021] The method, device, equipment, readable storage medium and product for determining the posture of the sling provided by the present invention pre-set the template point cloud of the target sling in the normal posture, so that after the real-time point cloud is acquired, the real-time point cloud can be matched with the template point cloud, and the maximum a posteriori estimation problem about the posture of the sling is constructed based on the matching result, and the solution is optimized by the bundle adjustment method. Therefore, the current posture information of the target sling can be accurately identified without setting a marker on the target sling. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] In order to more clearly illustrate the embodiments of the present disclosure or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present disclosure, and a person skilled in the art can also obtain other drawings based on these drawings.

[0023] Figure 1 A schematic diagram of the system architecture on which the present disclosure is based;

[0024] Figure 2 A schematic diagram of a flow chart of a method for determining a hanger posture provided in an embodiment of the present disclosure;

[0025] Figure 3 A schematic flow chart of a method for determining a hanger posture provided by another embodiment of the present disclosure;

[0026] Figure 4 A schematic diagram of a trolley platform provided in an embodiment of the present disclosure;

[0027] Figure 5 A schematic diagram of a template point cloud provided in an embodiment of the present disclosure;

[0028] Figure 6 A schematic flow chart of a method for determining a hanger posture provided by another embodiment of the present disclosure;

[0029] Figure 7 A schematic flow chart of a method for determining a hanger posture provided by another embodiment of the present disclosure;

[0030] Figure 8 A schematic diagram of the structure of a device for determining the posture of a sling provided in an embodiment of the present disclosure;

[0031] Fig. 9 A schematic diagram of the structure of an electronic device provided in an embodiment of the present disclosure. DETAILED DESCRIPTION

[0032] In order to make the purpose, technical solution and advantages of the embodiments of the present disclosure clearer, the technical solution in the embodiments of the present disclosure will be clearly and completely described below in conjunction with the drawings in the embodiments of the present disclosure. Obviously, the described embodiments are part of the embodiments of the present disclosure, rather than all the embodiments. All other embodiments obtained based on the embodiments in the present disclosure belong to the scope of protection of the present disclosure.

[0033] In response to the above-mentioned technical problems that the existing methods for identifying the posture of a sling are complicated to operate and have high identification costs, the present disclosure provides a method, device, equipment, readable storage medium and product for determining the posture of a sling.

[0034] It should be noted that the method, device, equipment, readable storage medium and product for determining the posture of the sling provided by the present disclosure can be used in scenarios for testing various application software.

[0035] In the related art, in order to realize the recognition operation of the spreader's posture, it is generally necessary to set four markers on the spreader. Two 2D laser radars installed on the frame and a 3D radar pair consisting of two 2D radars plus a rotating mechanism are used to scan different markers to obtain the position information of the markers. Then, based on the position information of the markers, the left and right offset posture, left and right rotation amplitude posture, front and back offset posture, front and back tilt posture and left and right tilt amplitude posture (5DF) of the spreader are determined.

[0036] However, the above method often requires setting a marker on the spreader to identify the spreader's posture, which is cumbersome. In addition, only the spreader's posture with five degrees of freedom can be identified, and the recognition range is small. The recognition cost is high and the reproducibility is low.

[0037] In the process of solving the above technical problems, the inventors found through research that in order to quickly and accurately recognize the position and posture of the spreader without setting a marker, two laser radars can be installed at the diagonal of the spreader in advance. The point clouds of the spreader in normal posture collected by the two laser radars are obtained respectively, and the template point cloud is obtained by switching the point cloud coordinate system collected by the laser radar to the spreader coordinate system, and splicing and cropping the two converted point clouds.

[0038] Acquire at least one real-time point cloud collected by a laser radar, match the real-time point cloud with the template point cloud, construct a maximum a posteriori estimation problem about the spreader's posture based on the matching result, and optimize the solution through the bundle adjustment method. Therefore, the current posture information of the target spreader can be accurately identified without setting a marker on the target spreader.

[0039] Figure 1 This is a schematic diagram of the system architecture based on which the present disclosure is based. Figure 1 As shown, the system architecture based on the present disclosure includes at least: at least one laser radar 11 installed on the target sling and a server 12. The server 12 can determine the template point cloud corresponding to the target sling based on the point cloud of the target sling in a normal posture collected by the laser radar. And identify the posture information of the target sling based on the real-time point cloud collected by at least one laser radar and the template point cloud.

[0040] Figure 2 A flow chart of a method for determining the posture of a sling provided in an embodiment of the present disclosure is shown in FIG. Figure 2 As shown, the method includes:

[0041] Step 201: Acquire a template point cloud associated with a target lifting device, wherein the template point cloud is a point cloud when the target lifting device is in a normal posture.

[0042] Therefore, in order to realize the recognition of the posture information of the target lifting device, the template point cloud associated with the target lifting device can be obtained.

[0043] Step 202: Determine a fitting plane of the target lifting device in a normal position based on the template point cloud.

[0044] Step 203: Obtain a real-time point cloud collected by at least one preset laser radar, and determine distance information between the real-time point cloud and the fitting plane.

[0045] Step 204: construct maximum a posteriori estimation information corresponding to the target lifting device according to the distance information, and determine the current position and posture information of the target lifting device based on the maximum a posteriori estimation information.

[0046] The execution subject of this embodiment is a device for determining the posture of a sling, and the device for determining the posture of a sling can be coupled to a server.

[0047] In this embodiment, a laser radar can be pre-installed under the trolley platform of the field bridge. The number of the laser radars can be two, which can be installed on the diagonal line of the trolley platform.

[0048] Optionally, the point clouds collected by the two laser radars can be obtained respectively, and the coordinate system can be converted, spliced ​​and cropped to obtain a template point cloud, wherein the template point cloud is the point cloud when the target spreader is in a normal posture. Therefore, after obtaining the real-time point cloud, the real-time point cloud can be matched with the template point cloud, and the posture information of the target spreader can be identified based on the matching result.

[0049] Furthermore, after obtaining the template point cloud associated with the target sling, the fitting plane of the target sling in the normal posture can be determined based on the template point cloud. The real-time point cloud collected by at least one preset laser radar is obtained to determine the distance information between the real-time point cloud and the fitting plane. The maximum a posteriori estimation information corresponding to the target sling is constructed according to the distance information, and the maximum a posteriori estimation information is optimized and solved to minimize the distance between the real-time point cloud and the fitting plane, so as to obtain the current posture information of the target sling.

[0050] The method for determining the posture of the sling provided by the present invention pre-sets a template point cloud of the target sling in a normal posture, so that after the real-time point cloud is acquired, the real-time point cloud can be matched with the template point cloud, and a maximum a posteriori estimation problem about the posture of the sling is constructed based on the matching result, and the solution is optimized by the bundle adjustment method. Therefore, the current posture information of the target sling can be accurately identified without setting a marker on the target sling.

[0051] Figure 3 This is a flow chart of a method for determining the posture of a sling provided by another embodiment of the present disclosure. Based on any of the above embodiments, the laser radar includes a first radar and a second radar. Figure 3 As shown, step 201 includes:

[0052] Step 301: Acquire a first point cloud collected by the first radar and a second point cloud collected by the second radar respectively.

[0053] Step 302: convert the first point cloud and the second point cloud in the radar coordinate system to the target hanger coordinate system based on a preset external parameter conversion matrix to obtain the processed first point cloud and the second point cloud.

[0054] Step 303: perform data stitching operation on the processed first point cloud and the second point cloud to obtain a template point cloud associated with the target lifting device.

[0055] In this embodiment, the laser radar includes a first radar and a second radar. The first radar and the second radar are respectively arranged on the diagonal lines of the trolley platform of the field bridge. They can collect point clouds of the target hoist in normal posture.

[0056] Optionally, the point cloud collected by the laser radar is data in the laser radar coordinate system. In order to facilitate subsequent calculation operations, the point cloud can be converted to the target sling coordinate system. Therefore, the first radar and the second radar can be calibrated in time and space to obtain the external parameter matrix of the first radar and the second radar to the center of the target sling. The external parameter matrix can realize the unification and panoramic stitching of multiple radar coordinate systems to eliminate the limited field of view of a single radar.

[0057] Furthermore, a first point cloud collected by the first radar and a second point cloud collected by the second radar can be obtained respectively. The first point cloud and the second point cloud in the radar coordinate system are converted to the target sling coordinate system based on a preset external parameter conversion matrix to obtain the processed first point cloud and the second point cloud. The processed first point cloud and the second point cloud are subjected to data splicing operation to obtain a template point cloud associated with the target sling.

[0058] Among them, Formula 1 can be used to realize the coordinate system conversion and splicing operation of the template point cloud.

[0059] (1)

[0060] in, is the point cloud in the radar coordinate system before conversion, is the converted point cloud, is the stitched panoramic point cloud, R is the three-dimensional rotation matrix, and t is the 3×1 translation vector.

[0061] Figure 4 A schematic diagram of a trolley platform provided in an embodiment of the present disclosure, such as Figure 4As shown, two laser radars 42 can be installed in the diagonal position of the trolley platform 41 in the manner of sensor installation. The direction with the larger field of view of the laser radar can be set as the main direction, and the laser radar mirror is parallel to the ground, and the main direction of one of the laser radars in one corner is parallel to the long side of the sling, and the other main direction is parallel to the short side of the sling. The laser radars in the other corner are arranged in a mirror image.

[0062] The method for determining the posture of the spreader provided by the present disclosure can eliminate the problem of field of view obstruction by respectively setting two laser radars, and converting the point cloud collected by the laser radar from the laser radar coordinate system to the target spreader coordinate system after calibrating the external parameters of the laser radar. In addition, by splicing the point clouds collected by the two laser radars, a panoramic point cloud that is unobstructed and covers the entire target spreader can be obtained, and then the posture of the target spreader can be more accurately identified based on the panoramic template point cloud.

[0063] Further, based on any of the above embodiments, step 303 includes:

[0064] A data stitching operation is performed on the processed first point cloud and the second point cloud to obtain a panoramic point cloud.

[0065] The associated information of the target lifting device is obtained, wherein the associated information includes height information and size information of the target lifting device in a normal posture.

[0066] The panoramic point cloud is cropped according to the associated information to obtain the template point cloud.

[0067] In this embodiment, a data splicing operation may be performed on the first point cloud and the second point cloud after the coordinate system conversion to obtain a panoramic point cloud.

[0068] Furthermore, in order to make the template point cloud more consistent with the actual parameters of the target sling, the associated information of the target sling can be obtained, wherein the associated information includes the height information and size information of the target sling in the normal position. The height information can be determined by a preset programmable logic controller (PLC). The PLC can use a programmable memory to store instructions for performing logical operations, sequential control, timing, counting and arithmetic operations, and control various types of mechanical equipment or production processes through digital or analog input and output. The height information and size information of the target sling in the normal position can be pre-stored.

[0069] Optionally, the panoramic point cloud may be cropped according to the associated information to obtain a template point cloud.

[0070] Figure 5A schematic diagram of a template point cloud provided in an embodiment of the present disclosure, such as Figure 5 As shown, after the first point cloud and the second point cloud are spliced ​​to obtain the panoramic point cloud, the panoramic point cloud can be cropped based on the height information and size information of the target hoist in the normal posture to obtain the template point cloud 51.

[0071] The method for determining the posture of the sling provided in the present disclosure performs a cropping operation on the panoramic point cloud based on the height information and size information of the target sling in a normal posture, thereby making the template point cloud more consistent with the actual parameters of the target sling and improving the accuracy of the template point cloud.

[0072] Figure 6 A flow chart of a method for determining a hanger posture according to another embodiment of the present disclosure is provided. Based on any of the above embodiments, Figure 6 As shown, step 202 includes:

[0073] Step 601: construct a tree data structure based on the three-dimensional coordinate information associated with the template point cloud.

[0074] Step 602: Segment the template point cloud according to the height information of the target lifting tool to obtain a segmented point cloud, wherein the height information of the target lifting tool is determined by a preset programmable logic controller.

[0075] Step 603: Determine the nearest point associated with the template point cloud in the tree data structure according to the segmented point cloud, the height information and a preset search condition.

[0076] Step 604: Perform a plane fitting operation based on the nearest point to obtain a fitting plane of the target lifting device in a normal posture.

[0077] In this embodiment, after the template point cloud is obtained by splicing and clipping the point clouds collected by the two laser radars, a tree data structure (k-dimensionalTree, kd-tree for short) can be constructed based on the three-dimensional coordinate information associated with the template point cloud. It is a tree data structure that stores instance points in k-dimensional space for fast retrieval.

[0078] Furthermore, the template point cloud may be segmented according to the height information of the target spreader to obtain a segmented point cloud, wherein the height information of the target spreader is determined by a preset programmable logic controller.

[0079] In addition, search conditions may be pre-set, wherein the search conditions include a search range and the number of closest points. During the closest point search process, when the search conditions are met, the search operation is stopped.

[0080] Optionally, the nearest point associated with the template point cloud can be determined in the tree data structure according to the segmented point cloud, the height information and the preset search condition. A plane fitting operation is performed based on the nearest point to obtain a fitting plane of the target lifting device in a normal posture.

[0081] The method for determining the posture of a sling provided by the present invention constructs a tree data structure based on the three-dimensional coordinate information associated with the template point cloud, and performs a nearest point recognition operation based on the tree data structure, so as to more accurately construct a fitting plane of the target sling in a normal posture based on the nearest point, so that the real-time posture of the target sling can be determined based on the fitting plane subsequently.

[0082] Among them, the fitting method is to calculate the three eigenvalues ​​of the point cloud variance matrix A and the corresponding eigenvector, when the eigenvalue Greater than the other two eigenvalues , When , the fitting is successful, and its corresponding eigenvector is the normal vector n. The point cloud variance matrix A can be calculated as formula 2:

[0083] (2)

[0084] in, is a 3×1 template point cloud coordinate matrix, q is the coordinate of the centroid of the template point cloud, and N is the number of template point clouds.

[0085] Further, based on any of the above embodiments, step 203 includes:

[0086] The real-time point cloud in the radar coordinate system is converted to the target hanger coordinate system based on a preset external parameter conversion matrix to obtain a converted point cloud.

[0087] Determine the distance information between the converted point cloud and the fitting plane.

[0088] In this embodiment, a real-time point cloud collected by at least one laser radar can be obtained. Since the real-time point cloud is data in the laser radar coordinate system, in order to facilitate subsequent calculations, the real-time point cloud in the radar coordinate system can be converted to the target sling coordinate system based on a preset external parameter conversion matrix to obtain a converted point cloud. Among them, the external parameter conversion matrix is ​​used to convert the real-time point cloud in the radar coordinate system to the target sling coordinate system, which can be determined by any external parameter calibration method, and the present disclosure does not limit this. Therefore, the distance information between the converted point cloud and the fitting plane can be determined later.

[0089] Further, based on any of the above embodiments, the determining the distance information between the converted point cloud and the fitting plane includes:

[0090] A normal vector of the fitted plane is determined.

[0091] The distance information between the transformed point cloud and the fitting plane is calculated by a cross product method of the normal vector and a vector corresponding to the transformed point cloud.

[0092] In this embodiment, after the coordinate system conversion operation of the real-time point cloud is completed, the plane distance from the real-time point cloud of the target spreader to the template point cloud can be calculated by using the cross product method of the plane normal vector and the vector.

[0093] Optionally, a normal vector of the fitting plane may be determined, and distance information between the transformed point cloud and the fitting plane may be calculated by a cross product method of the normal vector and a vector corresponding to the transformed point cloud.

[0094] The distance information may be expressed as Formula 3:

[0095] (3)

[0096] Where d is the plane distance between the real-time point cloud and the template point cloud. n is the normal vector of the fitting plane. is the transformed point cloud after the coordinate system transformation, is the center of mass of the fitted plane, and R,t is the rotation matrix and translation matrix of the estimated pose.

[0097] The method for determining the posture of the spreader provided by the present disclosure can improve the accuracy and efficiency of subsequent calculations by converting the coordinate system of the real-time point cloud after acquiring it. In addition, by calculating the distance information between the converted point cloud and the fitting plane, the real-time posture of the target spreader can be accurately determined based on the distance information.

[0098] Further, based on any of the above embodiments, step 204 includes:

[0099] The maximum a posteriori estimation information is solved by a preset bundle adjustment method to minimize the plane distance between the real-time point cloud and the template point cloud, thereby obtaining the current position and posture information of the target hoist.

[0100] In this embodiment, after constructing the maximum a posteriori estimation information about the target sling posture, the maximum a posteriori estimation information can be solved by a preset bundle adjustment method to minimize the planar distance between the real-time point cloud and the template point cloud, and obtain the optimal solution of the 6DF target sling posture, and the optimal solution is determined as the current posture information of the target sling.

[0101] Among them, the optimal solution of the target spreader can be shown as formula 4:

[0102] (4)

[0103] Where d is the plane distance between the real-time point cloud and the template point cloud, R is the three-dimensional rotation matrix, and t is the 3×1 translation vector.

[0104] The method for determining the posture of a spreader provided by the present disclosure performs a matching operation on a real-time point cloud and a template point cloud, and constructs a least square equation for the matching. Finally, the equation is solved by a bundle adjustment method, thereby obtaining an optimal solution for the position and posture of a target spreader.

[0105] Figure 7 This is a flow chart of a method for determining the posture of a spreader provided by another embodiment of the present disclosure. Based on any of the above embodiments, the laser radar includes a first radar and a second radar. Figure 7 As shown, the method also includes:

[0106] Step 701: Determine the current first position information of the target lifting device based on the first real-time point cloud collected by the first radar and the template point cloud.

[0107] Step 702: Determine current second position information of the target lifting device based on the second real-time point cloud collected by the second radar and the template point cloud.

[0108] Step 703: determine whether the distance between the first posture information and the second posture information meets a preset redundancy condition, and obtain a processing result.

[0109] Step 704: Determine the current position and posture information of the target lifting device according to the processing result.

[0110] In this embodiment, the laser radar includes a first radar and a second radar. By setting up multiple radars, on the one hand, the accuracy of posture recognition can be improved, and on the other hand, the purpose of data redundancy can be achieved.

[0111] Optionally, two posture recognition operations can be performed based on the real-time point clouds and template point clouds collected by the two radars to obtain two recognition results. Then, more accurate posture information can be calculated based on the two recognition results, or, based on the two recognition results, it can be determined whether the current laser radar is operating normally, and the posture information obtained by the real-time point cloud recognition collected by the faulty radar can be discarded.

[0112] Further, the current first pose information of the target sling can be determined based on the first real-time point cloud collected by the first radar and the template point cloud. The current second pose information of the target sling can be determined based on the second real-time point cloud collected by the second radar and the template point cloud. The recognition method of the first pose information and the second pose information can be the same as the above embodiment, which will not be described in detail here.

[0113] Determine whether the distance between the first pose information and the second pose information meets a preset redundancy condition, and obtain a processing result. Determine the current pose information of the target hoist according to the processing result. The redundancy condition may be that the distance between the first pose information and the second pose information is less than a preset distance threshold.

[0114] Further, based on any of the above embodiments, step 704 includes:

[0115] If the distance between the first posture information and the second posture information meets a preset redundancy condition, an average value of the first posture information and the second posture information is calculated, and the average value is determined as the current posture information of the target hoist.

[0116] If the distance between the first posture information and the second posture information does not meet the preset redundancy condition, an error posture is determined based on the historical estimated posture in the first posture information and the second posture information, and the error posture is discarded to obtain the current posture information of the target hoist.

[0117] In this embodiment, when the first radar and the second radar are operating normally, the position and posture information of the target sling identified based on the real-time point cloud collected by the two radars should be the same or similar. Therefore, after determining the current first position and posture information of the target sling based on the first real-time point cloud and the current second position and posture information of the target sling based on the second real-time point cloud, the distance between the first position and posture information can be calculated to determine whether the two radars are currently operating normally, and further data verification operations can be performed.

[0118] Optionally, if the distance between the first posture information and the second posture information meets a preset redundancy condition, it indicates that the first radar and the second radar are operating normally. In order to improve the accuracy of the recognized posture information, the average value of the first posture information and the second posture information can be calculated, and the average value is determined as the current posture information of the target sling. The redundant condition can be a preset distance threshold. If the distance between the first posture information and the second posture information is less than the distance threshold, it indicates that the redundant condition is met. Otherwise, it indicates that the redundant condition is not met.

[0119] If the distance between the first pose information and the second pose information does not meet the preset redundancy condition, it indicates that one of the laser radars is faulty. At this time, one of the recognition results can be discarded.

[0120] Furthermore, during the use of the target sling, its moving position and moving trajectory are known, so data verification operations can be performed based on the historical estimated posture of the target sling. Therefore, the error posture can be determined based on the first posture information and the second posture information of the historical estimated posture, and the error posture can be discarded to obtain the current posture information of the target sling.

[0121] For example, after determining multiple historical estimated poses, it can be determined whether the first pose information and the second pose information match the historical estimated pose information and the moving position and moving trajectory of the target hoist, and the mismatching pose information is determined as an error pose.

[0122] The method for determining the posture of the spreader provided by the present disclosure can improve the accuracy of posture recognition by setting multiple radars, and can achieve the purpose of data redundancy. In addition, when one laser radar fails, the current posture information of the target spreader can also be recognized based on only one laser radar.

[0123] Further, based on any of the above embodiments, after step 204, the method further includes:

[0124] If the posture information meets the preset adjustment condition, the posture adjustment parameter is determined based on the posture information.

[0125] The current posture of the target lifting device is adjusted according to the posture adjustment parameters.

[0126] In this embodiment, adjustment conditions can be set in advance. Among them, when the posture information meets the adjustment conditions, it indicates that the target sling may shake or twist, resulting in unstable grasping and placing of heavy objects. As an implementable method, the adjustment condition can be the posture parameter interval of the target sling when it is in a posture such as shaking or twisting. If the current posture information of the target sling falls within this parameter interval, it indicates that the target sling may shake or twist, and a posture adjustment operation is required.

[0127] Further, if the posture information satisfies a preset adjustment condition, a posture adjustment parameter is determined based on the posture information, wherein the posture adjustment parameter may be a parameter for adjusting the target lifting device to a normal posture.

[0128] Therefore, after determining the posture adjustment parameters that can adjust the target spreader to a normal posture based on the posture information, the current posture of the target spreader can be adjusted according to the posture adjustment parameters to ensure stability and safety during the process of grabbing and releasing boxes.

[0129] The method for determining the posture of a sling provided in the present disclosure adjusts the target sling based on the current posture information, thereby providing accurate posture feedback for the anti-sway and anti-twist of the target sling, thereby ensuring stability and safety during the process of grabbing and releasing boxes.

[0130] Figure 8 A schematic diagram of the structure of the apparatus for determining the posture of a sling provided in an embodiment of the present disclosure, as shown in FIG. Figure 8 As shown, the device includes: an acquisition module 81, a determination module 82, a calculation module 83 and a processing module 84. The acquisition module 81 is used to acquire a template point cloud associated with a target sling, wherein the template point cloud is a point cloud when the target sling is in a normal posture. The determination module 82 is used to determine a fitting plane of the target sling in a normal posture based on the template point cloud. The calculation module 83 is used to acquire a real-time point cloud collected by at least one preset laser radar, and determine the distance information between the real-time point cloud and the fitting plane. The processing module 84 is used to construct the maximum a posteriori estimation information corresponding to the target sling according to the distance information, and determine the current posture information of the target sling based on the maximum a posteriori estimation information.

[0131] Further, based on any of the above embodiments, the laser radar includes a first radar and a second radar. The acquisition module is used to: respectively acquire a first point cloud collected by the first radar and a second point cloud collected by the second radar. Based on a preset external parameter conversion matrix, the first point cloud and the second point cloud in the radar coordinate system are converted to the target sling coordinate system to obtain the processed first point cloud and the second point cloud. Data splicing operation is performed on the processed first point cloud and the second point cloud to obtain a template point cloud associated with the target sling.

[0132] Further, based on any of the above embodiments, the acquisition module is used to: perform data stitching operations on the processed first point cloud and the second point cloud to obtain a panoramic point cloud. Acquire the associated information of the target sling, wherein the associated information includes height information and size information of the target sling in a normal posture. Perform a cropping operation on the panoramic point cloud according to the associated information to obtain the template point cloud.

[0133] Further, based on any of the above embodiments, the determination module is used to: construct a tree data structure based on the three-dimensional coordinate information associated with the template point cloud. Perform a segmentation operation on the template point cloud according to the height information of the target sling to obtain a segmented point cloud, wherein the height information of the target sling is determined by a preset programmable logic controller. Determine the nearest point associated with the template point cloud in the tree data structure according to the segmented point cloud, the height information and the preset search condition. Perform a plane fitting operation based on the nearest point to obtain a fitting plane of the target sling in a normal posture.

[0134] Further, based on any of the above embodiments, the calculation module is used to: transform the real-time point cloud in the radar coordinate system to the target sling coordinate system based on a preset external parameter transformation matrix to obtain a transformed point cloud, and determine the distance information between the transformed point cloud and the fitting plane.

[0135] Further, based on any of the above embodiments, the calculation module is used to: determine the normal vector of the fitting plane and calculate the distance information between the transformed point cloud and the fitting plane by a cross product method of the normal vector and a vector corresponding to the transformed point cloud.

[0136] Further, based on any of the above embodiments, the processing module is used to: solve the maximum a posteriori estimation information through a preset bundle adjustment method to minimize the plane distance between the real-time point cloud and the template point cloud, and obtain the current posture information of the target hoist.

[0137] Further, on the basis of any of the above embodiments, the laser radar includes a first radar and a second radar. The device also includes: a determination module, used to determine the current first pose information of the target sling based on the first real-time point cloud collected by the first radar and the template point cloud. A determination module, used to determine the current second pose information of the target sling based on the second real-time point cloud collected by the second radar and the template point cloud. A processing module, used to determine whether the distance between the first pose information and the second pose information meets a preset redundancy condition and obtain a processing result. A calculation module, used to determine the current pose information of the target sling according to the processing result.

[0138] Further, based on any of the above embodiments, the calculation module is used to: if the distance between the first posture information and the second posture information meets the preset redundancy condition, then calculate the average value of the first posture information and the second posture information, and determine the average value as the current posture information of the target sling. If the distance between the first posture information and the second posture information does not meet the preset redundancy condition, then determine the error posture based on the historical estimated posture in the first posture information and the second posture information, discard the error posture, and obtain the current posture information of the target sling.

[0139] Further, based on any of the above embodiments, the device further comprises: a determination module, for determining a posture adjustment parameter based on the posture information if the posture information meets a preset adjustment condition; and an adjustment module, for adjusting the current posture of the target sling according to the posture adjustment parameter.

[0140] The device provided in this embodiment can be used to execute the technical solution of the above method embodiment. Its implementation principle and technical effect are similar, and this embodiment will not be repeated here.

[0141] In order to implement the above embodiments, the embodiments of the present disclosure further provide a computer-readable storage medium, in which computer-executable instructions are stored. When a processor executes the computer-executable instructions, the method for determining the posture of the sling as described in any of the above embodiments is implemented.

[0142] In order to implement the above embodiments, the embodiments of the present disclosure further provide a computer program product, including a computer program, which, when executed by a processor, implements the method for determining the posture of a spreader as described in any of the above embodiments.

[0143] In order to implement the above embodiment, the present disclosure also provides an electronic device, including: a processor and a memory;

[0144] The memory stores computer-executable instructions;

[0145] The processor executes the computer-executable instructions stored in the memory, so that the processor executes the method for determining the posture of the spreader as described in any of the above embodiments.

[0146] Fig. 9 The electronic device 900 is a schematic diagram of the structure of an electronic device provided in an embodiment of the present disclosure, and the electronic device 900 may be a terminal device or a server. The terminal device may include but is not limited to mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, personal digital assistants (PDAs), tablet computers, portable multimedia players (PMPs), vehicle terminals (such as vehicle navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Fig. 9 The electronic device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present disclosure.

[0147] like Fig. 9As shown, the electronic device 900 may include a processing device (e.g., a central processing unit, a graphics processing unit, etc.) 901, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 902 or a program loaded from a storage device 908 to a random access memory (RAM) 903. Various programs and data required for the operation of the electronic device 900 are also stored in the RAM 903. The processing device 901, the ROM 902, and the RAM 903 are connected to each other via a bus 904. An input / output (I / O) interface 905 is also connected to the bus 904.

[0148] Typically, the following devices may be connected to the I / O interface 905: input devices 906 including, for example, a touch screen, a touch pad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; output devices 907 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; storage devices 908 including, for example, a magnetic tape, a hard disk, etc.; and communication devices 909. The communication device 909 may allow the electronic device 900 to communicate with other devices wirelessly or by wire to exchange data. Although Fig. 9 The electronic device 900 is shown with various devices, but it should be understood that it is not required to implement or possess all the devices shown. More or fewer devices may be implemented or possessed instead.

[0149] In particular, according to an embodiment of the present disclosure, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present disclosure includes a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program contains program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication device 909, or installed from a storage device 908, or installed from a ROM 902. When the computer program is executed by the processing device 901, the above-mentioned functions defined in the method of the embodiment of the present disclosure are executed.

[0150] It should be noted that the computer-readable medium mentioned above in the present disclosure may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, device or device. In the present disclosure, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, which carries a computer-readable program code. This propagated data signal may take a variety of forms, including but not limited to an electromagnetic signal, an optical signal, or any suitable combination of the above. Computer readable signal media may also be any computer readable medium other than computer readable storage media, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. The program code contained on the computer readable medium may be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination of the above.

[0151] The computer-readable medium may be included in the electronic device, or may exist independently without being incorporated into the electronic device.

[0152] The computer-readable medium carries one or more programs. When the one or more programs are executed by the electronic device, the electronic device executes the method shown in the above embodiment.

[0153] Computer program code for performing the operations of the present disclosure may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0154] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present disclosure. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some implementations as replacements, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0155] The units involved in the embodiments described in the present disclosure may be implemented by software or hardware. The name of a unit does not limit the unit itself in some cases. For example, the first acquisition unit may also be described as a "unit for acquiring at least two Internet Protocol addresses".

[0156] The functions described above herein may be performed at least in part by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that may be used include: field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), and the like.

[0157] In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or device, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0158] The above description is only a preferred embodiment of the present disclosure and an explanation of the technical principles used. Those skilled in the art should understand that the scope of disclosure involved in the present disclosure is not limited to the technical solutions formed by a specific combination of the above technical features, but should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the above disclosed concept. For example, the above features are replaced with the technical features with similar functions disclosed in the present disclosure (but not limited to) by each other to form a technical solution.

[0159] In addition, although each operation is described in a specific order, this should not be understood as requiring these operations to be performed in the specific order shown or in a sequential order. Under certain circumstances, multitasking and parallel processing may be advantageous. Similarly, although some specific implementation details are included in the above discussion, these should not be interpreted as limiting the scope of the present disclosure. Some features described in the context of a separate embodiment can also be implemented in a single embodiment in combination. On the contrary, the various features described in the context of a single embodiment can also be implemented in multiple embodiments individually or in any suitable sub-combination mode.

Claims

1. A method for determining a hanger posture, characterized in that: include: Acquire a template point cloud associated with a target lifting device, wherein the template point cloud is a point cloud when the target lifting device is in a normal posture; Determine a fitting plane of the target lifting device in a normal posture based on the template point cloud; Acquire a real-time point cloud collected by at least one preset laser radar, and determine distance information between the real-time point cloud and the fitting plane; Maximum a posteriori estimation information corresponding to the target hoist is constructed according to the distance information, and current position information of the target hoist is determined based on the maximum a posteriori estimation information.

2. The method according to claim 1, characterized in that The laser radar includes a first radar and a second radar; The step of obtaining a template point cloud associated with the target spreader includes: Acquire a first point cloud collected by the first radar and a second point cloud collected by the second radar respectively; Based on a preset external parameter conversion matrix, the first point cloud and the second point cloud in the radar coordinate system are converted to the target spreader coordinate system to obtain the processed first point cloud and the second point cloud; A data splicing operation is performed on the processed first point cloud and the second point cloud to obtain a template point cloud associated with the target spreader.

3. The method according to claim 2, characterized in that The step of performing a data stitching operation on the processed first point cloud and the second point cloud to obtain a template point cloud associated with the target spreader includes: Performing a data stitching operation on the processed first point cloud and the second point cloud to obtain a panoramic point cloud; Acquire the associated information of the target lifting device, wherein the associated information includes the height information and the size information of the target lifting device in a normal posture; The panoramic point cloud is cropped according to the associated information to obtain the template point cloud.

4. The method according to claim 1, characterized in that: The step of determining the fitting plane of the target lifting device in a normal posture based on the template point cloud comprises: Constructing a tree data structure based on the three-dimensional coordinate information associated with the template point cloud; Performing a segmentation operation on the template point cloud according to the height information of the target spreader to obtain a segmented point cloud, wherein the height information of the target spreader is determined by a preset programmable logic controller; Determining the nearest point associated with the template point cloud in the tree data structure according to the segmented point cloud, the height information and a preset search condition; A plane fitting operation is performed based on the nearest point to obtain a fitting plane of the target lifting device in a normal posture.

5. The method according to claim 1, characterized in that The step of acquiring a real-time point cloud collected by at least one preset laser radar and determining distance information between the real-time point cloud and the fitting plane includes: Based on a preset external parameter conversion matrix, the real-time point cloud in the radar coordinate system is converted to the target hanger coordinate system to obtain a converted point cloud; Determine the distance information between the converted point cloud and the fitting plane.

6. The method according to claim 5, characterized in that The determining the distance information between the converted point cloud and the fitting plane includes: Determining a normal vector of the fitting plane; The distance information between the transformed point cloud and the fitting plane is calculated by a cross product method of the normal vector and a vector corresponding to the transformed point cloud.

7. The method according to claim 1, characterized in that The determining the current position and posture information of the target lifting device based on the maximum a posteriori estimation information includes: The maximum a posteriori estimation information is solved by a preset bundle adjustment method to minimize the plane distance between the real-time point cloud and the template point cloud, thereby obtaining the current position and posture information of the target hoist.

8. The method according to any one of claims 1 to 7, characterized in that: The laser radar includes a first radar and a second radar; the method further includes: Determine the current first pose information of the target hoist based on the first real-time point cloud collected by the first radar and the template point cloud; Determine the second current position information of the target lifting device based on the second real-time point cloud collected by the second radar and the template point cloud; Determine whether the distance between the first posture information and the second posture information meets a preset redundancy condition, and obtain a processing result; The current position and posture information of the target lifting device is determined according to the processing result.

9. The method according to claim 8, characterized in that Determining the current position and posture information of the target lifting device according to the processing result includes: If the distance between the first posture information and the second posture information meets a preset redundancy condition, then calculating an average value of the first posture information and the second posture information, and determining the average value as the current posture information of the target hoist; If the distance between the first posture information and the second posture information does not meet the preset redundancy condition, an error posture is determined based on the historical estimated posture in the first posture information and the second posture information, and the error posture is discarded to obtain the current posture information of the target hoist.

10. The method according to any one of claims 1 to 7, characterized in that: After determining the current position and posture information of the target lifting device based on the maximum a posteriori estimation information, the method further includes: If the posture information satisfies a preset adjustment condition, determining a posture adjustment parameter based on the posture information; The current posture of the target lifting device is adjusted according to the posture adjustment parameters.

11. A device for determining the posture of a sling, characterized in that: include: An acquisition module, used for acquiring a template point cloud associated with a target sling, wherein the template point cloud is a point cloud when the target sling is in a normal posture; A determination module, used to determine a fitting plane of the target lifting device in a normal posture based on the template point cloud; A calculation module, used to obtain a real-time point cloud collected by at least one preset laser radar, and determine the distance information between the real-time point cloud and the fitting plane; A processing module is used to construct maximum a posteriori estimation information corresponding to the target lifting device according to the distance information, and determine the current position and posture information of the target lifting device based on the maximum a posteriori estimation information.

12. An electronic device, characterized in that: include: Memory, processor; The memory stores computer-executable instructions; The processor executes the computer-executable instructions stored in the memory, so that the processor executes the method for determining the posture of the spreader according to any one of claims 1 to 10.

13. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-executable instructions. When the processor executes the computer-executable instructions, the method for determining the posture of the sling according to any one of claims 1 to 10 is implemented.

14. A computer program product, characterized in that The method comprises a computer program, which, when executed by a processor, implements the method for determining the posture of a spreader according to any one of claims 1 to 10.

Images