A pallet posture recognition method and system based on laser radar

Abstract

The present invention provides a pallet posture recognition method and system based on laser radar, which traverses the points in the leg space of the pallet, takes a point in the first quadrant of the laser coordinate system as the first coordinate point, takes a point in the second quadrant of the laser coordinate system as the second coordinate point, and takes the point when the angle between the second coordinate point and the first coordinate point relative to the laser coordinate system is less than a preset threshold as the first positioning coordinate point and the second positioning coordinate point; obtains the corresponding first center point and second center point according to the clustering clusters where the first coordinate point and the second coordinate point are located; takes the direction from the second center point to the first center point as the X-axis direction, obtains the Y-axis direction according to the right-hand rule, obtains the pallet coordinate system, and takes the posture angle of the pallet coordinate system as the pallet posture; translates a preset distance along the negative direction of the Y-axis to obtain the position of the pallet center point; the present invention realizes the recognition of pallet posture data and the repositioning of the pallet posture.

Description

Technical Field

[0001] The present invention relates to the technical field of high-precision positioning of logistics handling robots, and in particular to a method and system for recognizing the position and posture of a pallet based on a laser radar. Background Art

[0002] The statements in this section merely provide background art related to the present invention and do not necessarily constitute prior art.

[0003] Pallet posture recognition technology is the basis for realizing robotic cargo handling. As the application environment becomes increasingly complex, mobile robots still have many shortcomings in positioning accuracy, algorithm robustness and adaptability to complex scenarios, making it difficult to ensure that robots can complete tasks accurately and efficiently.

[0004] The inventors found that laser-based pallet position recognition technology is more adaptable to flexible working environments and has broad application prospects. However, in most actual working conditions, the position of the pallet needs to be accurately placed, and during the actual operation, the pallet cannot move or rotate at all, so the level of intelligence is low. Summary of the invention

[0005] In order to address the deficiencies in the prior art, the present invention provides a method and system for pallet posture recognition based on laser radar, which utilizes the curvature features of laser radar data to achieve the recognition of pallet posture data and the repositioning of the pallet posture through feature extraction and cluster analysis.

[0006] In order to achieve the above object, the present invention adopts the following technical solution:

[0007] A first aspect of the present invention provides a pallet posture recognition method based on laser radar.

[0008] A pallet posture recognition method based on laser radar includes the following processes:

[0009] According to the acquired laser radar data, spatial point cloud data is obtained;

[0010] Extract point cloud feature points according to curvature features, traverse the point cloud feature points, take a feature point in the first quadrant of the laser coordinate system as the first coordinate point, take a point in the second quadrant of the laser coordinate system as the second coordinate point, and take the point where the angle between the second coordinate point and the first coordinate point relative to the laser coordinate system is less than a preset threshold as the first positioning coordinate point and the second positioning coordinate point;

[0011] According to the clustering clusters where the first coordinate point and the second coordinate point are located, the corresponding first center point and second center point are obtained;

[0012] The direction from the second center point to the first center point is the X-axis direction, the Y-axis direction is obtained according to the right-hand rule, the pallet coordinate system is obtained according to the X-axis direction and the Y-axis direction, and the attitude angle of the pallet coordinate system is the pallet attitude;

[0013] Along the negative direction of the Y axis, translate the preset distance to obtain the center point position of the pallet;

[0014] According to the pallet posture and the position of the pallet center point, the pallet posture recognition result is obtained.

[0015] Furthermore, based on the acquired LiDAR data, the pallet leg space points are obtained, including:

[0016] The curvature of all laser points is calculated, and points with curvature greater than the preset curvature threshold are placed in the search space. Among all points in the search space, points with a curvature less than the angle threshold or exceeding the distance threshold are deleted to obtain the final pallet leg space point.

[0017] Furthermore, a point in the first quadrant of the laser coordinate system is used as the first coordinate point, and a point in the second quadrant of the laser coordinate system is used as the second coordinate point. If the direction angle of the line connecting the second coordinate point and the first coordinate point is greater than a preset threshold, the selection of the first coordinate point and the second coordinate point is repeated until the first coordinate point and the second coordinate point that meet the conditions are found.

[0018] Furthermore, the laser point cloud data is clustered based on Euclidean clustering to obtain the cluster clusters where the first coordinate point and the second coordinate point are located.

[0019] Furthermore, the preset distance is: 0.5 times the difference between the longitudinal dimension of the pallet and the diameter of the pallet leg.

[0020] Furthermore, the pallet posture is the relative posture of the pallet coordinate system with respect to the AGV coordinate system, and the pallet center point position is the position of the pallet center point with respect to the AGV coordinate system.

[0021] Furthermore, based on the posture data of the AGV, the center point of the pallet is transformed into the global coordinate system through rotation and translation, and the posture data of the target pallet is updated.

[0022] A second aspect of the present invention provides a pallet posture recognition system based on laser radar.

[0023] A pallet posture recognition system based on laser radar, comprising:

[0024] The data acquisition module is configured to: obtain spatial point cloud data according to the acquired laser radar data;

[0025] The positioning coordinate point acquisition module is configured to: extract point cloud feature points according to curvature features, traverse the point cloud feature points, take a feature point in the first quadrant of the laser coordinate system as the first coordinate point, take a point in the second quadrant of the laser coordinate system as the second coordinate point, and take the point where the angle between the second coordinate point and the first coordinate point relative to the laser coordinate system is less than a preset threshold as the first positioning coordinate point and the second positioning coordinate point;

[0026] A cluster center point acquisition module is configured to: obtain the corresponding first center point and second center point according to the cluster clusters where the first coordinate point and the second coordinate point are located;

[0027] The pallet posture acquisition module is configured to: take the direction from the second center point to the first center point as the X-axis direction, obtain the Y-axis direction according to the right-hand rule, obtain the pallet coordinate system according to the X-axis direction and the Y-axis direction, and take the posture angle of the pallet coordinate system as the pallet posture;

[0028] The pallet center point acquisition module is configured to: translate a preset distance along the negative direction of the Y axis to obtain the center point position of the pallet;

[0029] The posture data generation module is configured to obtain a pallet posture recognition result according to the posture of the pallet and the position of the center point of the pallet.

[0030] A third aspect of the present invention provides a computer-readable storage medium having a program stored thereon, which, when executed by a processor, implements the steps in the pallet posture recognition method based on laser radar as described in the first aspect of the present invention.

[0031] The fourth aspect of the present invention provides an electronic device, comprising a memory, a processor, and a program stored in the memory and executable on the processor, wherein when the processor executes the program, the steps in the pallet posture recognition method based on laser radar as described in the first aspect of the present invention are implemented.

[0032] Compared with the prior art, the present invention has the following beneficial effects:

[0033] 1. The laser radar-based pallet posture recognition method and system described in the present invention utilizes the curvature characteristics of the laser radar data and realizes the recognition of the pallet posture data and the repositioning of the pallet posture through feature extraction and cluster analysis.

[0034] 2. The laser radar-based pallet posture recognition method and system described in the present invention eliminates point cloud data based on the geometric curvature calculation of the laser radar point cloud data; extracts the pallet leg posture from the eliminated point cloud set; based on the pallet leg posture, corrects the actual spatial posture of the pallet; can reuse laser radar data to achieve pallet positioning, thereby improving the flexible operation performance of AGV operations. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] The accompanying drawings in the specification, which constitute a part of the present invention, are used to provide a further understanding of the present invention. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute improper limitations on the present invention.

[0036] Figure 1 A schematic flow chart of a method for recognizing a pallet posture based on laser radar provided in Example 1 of the present invention.

[0037] Figure 2 Schematic diagram of leg feature extraction provided in Example 1 of the present invention. DETAILED DESCRIPTION

[0038] The present invention will be further described below in conjunction with the accompanying drawings and embodiments.

[0039] It should be noted that the following detailed descriptions are all illustrative and intended to provide further explanation of the present invention. Unless otherwise specified, all technical and scientific terms used herein have the same meanings as those commonly understood by those skilled in the art to which the present invention belongs.

[0040] It should be noted that the terms used herein are only for describing specific embodiments and are not intended to limit exemplary embodiments according to the present invention. As used herein, unless the context clearly indicates otherwise, the singular form is also intended to include the plural form. In addition, it should be understood that when the terms "comprising" and / or "including" are used in this specification, it indicates the presence of features, steps, operations, devices, components and / or combinations thereof.

[0041] In the absence of conflict, the embodiments of the present invention and the features of the embodiments may be combined with each other.

[0042] Embodiment 1:

[0043] like Figure 1 As shown, Embodiment 1 of the present invention provides a method for recognizing a pallet posture based on a laser radar, comprising the following process:

[0044] S1: Get the feature point set ∑p of the pallet leg:

[0045] S1.1: Obtain the laser radar point cloud data, calculate the geometric curvature information of each point in the point cloud, and store the points greater than the curvature threshold into the list to be searched;

[0046] S1.2: Delete the points in the search list that are smaller than the angle threshold and larger than the distance threshold to obtain the final tray leg feature point set ∑p.

[0047] S2: Leg posture estimation

[0048] S2.1: Find the points p1 and p2 located in the first and second quadrants from the simplified list to be searched;

[0049] S2.2: If the direction angle of the line connecting p2p1 is greater than the set threshold, repeat the previous step until points p1 and p2 that meet the conditions are found;

[0050] S2.3: Cluster the LiDAR point cloud based on the Euclidean clustering method, find the clusters where p1 and p2 are located, and calculate the centers p1' and p2' of the two clusters as the leg poses;

[0051] S3: Pallet posture estimation:

[0052] S3.1: With the direction of p2'p1' as the X-axis and the center of p2' and p1' as the origin, a coordinate system is established according to the right-hand rule. The posture of the coordinate system is set as the relative posture of the pallet coordinate system with respect to the AGV coordinate system.

[0053] S3.2: From the origin of the coordinate system, translate along the negative direction of the y-axis by a distance: (l*0.5-r) (r: pallet leg diameter, l: pallet longitudinal dimension) to obtain the position of the pallet center relative to the AGV coordinate system.

[0054] After obtaining the position of the pallet center relative to the AGV coordinate system, the position and posture data of the target pallet is updated by transforming it to the global coordinate system through rotation and translation based on the AGV's position and posture.

[0055] In this embodiment, Figure 2 As shown, leg feature extraction includes:

[0056] By sorting the points in the point cloud according to the size of geometric curvature and judging by threshold, the points with larger curvature in the point cloud are obtained as the set of leg feature points; the feature points with the orientation and posture that meet the conditions are traversed and searched from the set. In a density-based way, the point cloud clusters near the feature points are obtained as leg points.

[0057] Embodiment 2:

[0058] Embodiment 2 of the present invention provides a pallet posture recognition system based on laser radar, comprising:

[0059] The data acquisition module is configured to: obtain spatial point cloud data according to the acquired laser radar data;

[0060] The positioning coordinate point acquisition module is configured to: extract point cloud feature points according to curvature features, traverse the point cloud feature points, take a feature point in the first quadrant of the laser coordinate system as the first coordinate point, take a point in the second quadrant of the laser coordinate system as the second coordinate point, and take the point where the angle between the second coordinate point and the first coordinate point relative to the laser coordinate system is less than a preset threshold as the first positioning coordinate point and the second positioning coordinate point;

[0061] A cluster center point acquisition module is configured to: obtain the corresponding first center point and second center point according to the cluster clusters where the first coordinate point and the second coordinate point are located;

[0062] The pallet posture acquisition module is configured to: take the direction from the second center point to the first center point as the X-axis direction, obtain the Y-axis direction according to the right-hand rule, obtain the pallet coordinate system according to the X-axis direction and the Y-axis direction, and take the posture angle of the pallet coordinate system as the pallet posture;

[0063] The pallet center point acquisition module is configured to: translate a preset distance along the negative direction of the Y axis to obtain the center point position of the pallet;

[0064] The posture data generation module is configured to obtain a pallet posture recognition result according to the posture of the pallet and the position of the center point of the pallet.

[0065] The working method of the system is the same as the pallet posture recognition method based on laser radar provided in Example 1, and will not be repeated here.

[0066] Embodiment 3:

[0067] Embodiment 3 of the present invention provides a computer-readable storage medium having a program stored thereon, which, when executed by a processor, implements the steps in the method for pallet posture recognition based on laser radar as described in Embodiment 1 of the present invention.

[0068] Embodiment 4:

[0069] Embodiment 4 of the present invention provides an electronic device, comprising a memory, a processor, and a program stored in the memory and executable on the processor, wherein when the processor executes the program, the steps in the method for recognizing a pallet posture based on laser radar as described in Embodiment 1 of the present invention are implemented.

[0070] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of hardware embodiments, software embodiments, or embodiments combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage and optical storage, etc.) containing computer-usable program code.

[0071] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0072] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0073] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0074] A person skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through a computer program, and the program can be stored in a computer-readable storage medium, and when the program is executed, it can include the processes of the embodiments of the above-mentioned methods. The storage medium can be a disk, an optical disk, a read-only memory (ROM) or a random access memory (RAM), etc.

[0075] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A pallet posture recognition method based on laser radar, characterized in that: The process includes: According to the acquired laser radar data, spatial point cloud data is obtained; Extract point cloud feature points according to curvature features, traverse the point cloud feature points, take a feature point in the first quadrant of the laser coordinate system as the first coordinate point, take a point in the second quadrant of the laser coordinate system as the second coordinate point, and take the point where the angle between the second coordinate point and the first coordinate point relative to the laser coordinate system is less than a preset threshold as the first positioning coordinate point and the second positioning coordinate point; According to the clustering clusters where the first coordinate point and the second coordinate point are located, the corresponding first center point and second center point are obtained; The direction from the second center point to the first center point is the X-axis direction, the Y-axis direction is obtained according to the right-hand rule, the pallet coordinate system is obtained according to the X-axis direction and the Y-axis direction, and the attitude angle of the pallet coordinate system is the pallet attitude; Along the negative direction of the Y axis, translate the preset distance to obtain the center point position of the pallet; According to the pallet posture and the position of the pallet center point, the pallet posture recognition result is obtained.

2. The method for recognizing a pallet posture based on laser radar according to claim 1, characterized in that: Based on the acquired LiDAR data, the pallet leg space points are obtained, including: The curvature of all laser points is calculated, and points with curvature greater than the preset curvature threshold are placed in the search space. Among all points in the search space, points with a curvature less than the angle threshold or exceeding the distance threshold are deleted to obtain the final pallet leg space point.

3. The method for recognizing the position and posture of a pallet based on laser radar according to claim 1, characterized in that: A point in the first quadrant of the laser coordinate system is used as the first coordinate point, and a point in the second quadrant of the laser coordinate system is used as the second coordinate point. If the direction angle of the line connecting the second coordinate point and the first coordinate point is greater than a preset threshold, the selection of the first coordinate point and the second coordinate point is repeated until the first coordinate point and the second coordinate point that meet the conditions are found.

4. The method for recognizing a pallet position based on laser radar according to claim 1, characterized in that: The laser point cloud data is clustered based on Euclidean clustering to obtain the cluster clusters where the first coordinate point and the second coordinate point are located.

5. The method for recognizing a pallet position based on laser radar according to claim 1, characterized in that: The preset distance is: 0.5 times the difference between the longitudinal dimension of the pallet and the diameter of the pallet leg.

6. The method for recognizing a pallet position based on laser radar according to claim 1, characterized in that: The pallet posture is the relative posture of the pallet coordinate system relative to the AGV coordinate system, and the pallet center point position is the position of the pallet center point relative to the AGV coordinate system.

7. The method for recognizing the position and posture of a pallet based on laser radar as claimed in claim 6, characterized in that: Based on the AGV's posture data, the center point of the pallet is transformed into the global coordinate system through rotation and translation, and the posture data of the target pallet is updated.

8. A pallet posture recognition system based on laser radar, characterized in that: include: The data acquisition module is configured to: obtain spatial point cloud data according to the acquired laser radar data; The positioning coordinate point acquisition module is configured to: extract point cloud feature points according to curvature features, traverse the point cloud feature points, take a feature point in the first quadrant of the laser coordinate system as the first coordinate point, take a point in the second quadrant of the laser coordinate system as the second coordinate point, and take the point where the angle between the second coordinate point and the first coordinate point relative to the laser coordinate system is less than a preset threshold as the first positioning coordinate point and the second positioning coordinate point; A cluster center point acquisition module is configured to: obtain the corresponding first center point and second center point according to the cluster clusters where the first coordinate point and the second coordinate point are located; The pallet posture acquisition module is configured to: take the direction from the second center point to the first center point as the X-axis direction, obtain the Y-axis direction according to the right-hand rule, obtain the pallet coordinate system according to the X-axis direction and the Y-axis direction, and take the posture angle of the pallet coordinate system as the pallet posture; The pallet center point acquisition module is configured to: translate a preset distance along the negative direction of the Y axis to obtain the center point position of the pallet; The posture data generation module is configured to obtain a pallet posture recognition result according to the posture of the pallet and the position of the center point of the pallet.

9. A computer-readable storage medium having a program stored thereon, characterized in that: When the program is executed by a processor, the steps in the pallet posture recognition method based on laser radar as described in any one of claims 1 to 7 are implemented.

10. An electronic device comprising a memory, a processor, and a program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the steps in the pallet posture recognition method based on laser radar as described in any one of claims 1 to 7 are implemented.

Images