A goods positioning method and system for an automated stereoscopic warehouse

Abstract

This invention provides a method and system for cargo positioning in an automated storage and retrieval system (AS / RS). The method includes acquiring point cloud data of stacked goods; preprocessing the point cloud data to obtain preprocessed point cloud data; performing iterative plane fitting on the preprocessed point cloud data to obtain a fitting plane; projecting the preprocessed point cloud data onto the fitting plane to obtain a projected point cloud; extracting edges from the projected point cloud to obtain point cloud edges; performing line fitting and matrix determination based on the point cloud edges to obtain a transformation matrix; and outputting the coordinates of the target cargo based on the transformation matrix and the projected point cloud. This invention effectively improves the processing efficiency and accuracy of point cloud data by performing a series of processing steps on the original point cloud data, while effectively capturing the edge information of the cargo, thus improving the accuracy of subsequent positioning and recognition. A coordinate system is then established based on the boundaries, and the size and pose information of the target cargo are determined through affine transformation.

Description

Technical Field

[0001] This invention belongs to the technical field of data writing, and specifically relates to a method and system for locating goods in an automated storage and retrieval system. Background Technology

[0002] Automated storage and retrieval systems (AS / RS) are a core component of modern logistics and intelligent manufacturing, with stacker cranes being key equipment for automated storage and retrieval of goods. The accuracy, stability, and efficiency of their operation directly determine the overall effectiveness of the warehousing system.

[0003] Currently, especially in areas with long service life or unstable geological conditions, stacker crane systems generally face the following severe technical challenges: the warehouse floor may experience irregular settlement due to geological changes and long-term loads, causing the stacker crane's running track (ground rail) to exhibit wavy deformation. Simultaneously, the racks supporting the goods will also experience height and forward / backward deviations, resulting in significant discrepancies between the actual and intended positions of the goods.

[0004] If the position of the goods deviates significantly, it will cause a significant positional shift when the goods are stored. When the offset exceeds the safety threshold, the wooden pallet will detach from the storage position support on one side, causing the goods to be suspended in the air. This not only easily leads to serious malfunctions such as jamming of the fork extension mechanism and equipment shutdown, but also poses a safety hazard of goods tipping over.

[0005] Meanwhile, the deviation in the position of the goods makes it impossible for the stacker crane to accurately identify or pick up the goods, resulting in a large number of "problem storage locations". Operators must frequently intervene manually, and each intervention takes about 3 minutes. Abnormal situations such as the stacker crane "having a work instruction but not moving" also occur from time to time, requiring repeated checks by personnel, which further reduces the utilization rate of equipment and the reliability of the system. Summary of the Invention

[0006] To address the aforementioned technical problems, this invention provides a method and system for cargo positioning in automated storage and retrieval systems (AS / RS), thereby resolving the technical issues in the prior art.

[0007] In a first aspect, the present invention provides the following technical solution: a method for positioning goods in an automated storage and retrieval system (AS / RS), comprising: Collect point cloud data of stacked goods, and preprocess the point cloud data to obtain preprocessed point cloud data; The preprocessed point cloud data is iteratively fitted to a plane to obtain a fitted plane, and the preprocessed point cloud data is projected onto the fitted plane to obtain a projected point cloud. Edge extraction is performed on the projected point cloud to obtain the point cloud edges; Based on the point cloud edges, straight line fitting and matrix determination are performed to obtain a transformation matrix. Based on the transformation matrix and the projected point cloud, the coordinates of the target cargo are output.

[0008] Compared with existing technologies, the beneficial effects of this invention are as follows: This invention collects point cloud data of stacked goods, preprocesses the point cloud data to obtain preprocessed point cloud data; iteratively fits the preprocessed point cloud data to obtain a fitting plane, projects the preprocessed point cloud data onto the fitting plane to obtain a projected point cloud; extracts edges from the projected point cloud to obtain point cloud edges; performs line fitting and matrix determination based on the point cloud edges to obtain a transformation matrix; and outputs the coordinates of the target goods based on the transformation matrix and the projected point cloud. This invention, through a series of processing steps on the original point cloud data, can effectively improve the processing efficiency and accuracy of point cloud data, while effectively capturing the edge information of the goods, improving the accuracy of subsequent positioning and recognition. Then, a coordinate system is established based on the boundary, and the size and pose information of the target goods are determined through affine transformation. Preferably, the step of preprocessing the point cloud data to obtain preprocessed point cloud data includes: Obtain environmental point cloud data of the environment where the goods are stacked, and perform differential operations on the environmental point cloud data and the point cloud data to obtain the first processed point cloud data; The point cloud space containing the first processed point cloud data is divided into several grids of the same size, and the first processed point cloud data within the grid is weighted and averaged to output the average point cloud. The point cloud closest to the average point cloud in the grid is selected as the target point cloud, and the target point clouds in all the grids are combined to obtain the second processed point cloud data; Traverse all point clouds in the second processed point cloud data In the neighborhood The first parameter inside With the second parameter : ; ; Based on the first parameter With the second parameter Determine the filtering range Point clouds that are not within the filtering range are removed from the second processed point cloud to obtain preprocessed point cloud data, wherein, It is a fixed multiple.

[0009] Preferably, the step of iteratively fitting the preprocessed point cloud data to obtain a fitting plane, and projecting the preprocessed point cloud data onto the fitting plane to obtain a projected point cloud includes: Select a subset containing three point clouds from the preprocessed point cloud data, and fit a target plane using the least squares method with the three point clouds in the subset; Calculate the distance from each point in the preprocessed point cloud data to the target plane; If the distance from the point cloud to the target plane is less than a preset distance threshold, then the point cloud is a first type of point cloud; if the distance from the point cloud to the target plane is not less than the preset distance threshold, then the point cloud is a second type of point cloud. The process of subset selection, distance calculation and point cloud classification is repeated iteratively, and the target plane corresponding to the largest number of first-class point clouds is selected as the fitting plane from all iteration results. Each point cloud in the preprocessed point cloud data Projected onto the fitting plane to obtain a projected point cloud. : ; ; ; In the formula, The normal vector of the fitted plane, To fit the distance from the plane to the origin, Normal vector The square of the modulus.

[0010] Preferably, the step of extracting edges from the projected point cloud to obtain point cloud edges includes: Calculate the projected point cloud at a preset distance Point cloud density on the plane : ; In the formula, For near-end field of view size, For resolution size, The distance from the camera to the near-end of the field of view; Based on the point cloud density Determine the number of point clouds within the range : ; In the formula, The preset radius; The number of range point clouds corresponding to each point cloud in the projected point cloud is determined. If the number of range point clouds corresponding to a point cloud is less than a preset number, the point cloud is an edge point cloud. All edge point clouds are combined to obtain the point cloud edge.

[0011] Preferably, the step of performing line fitting and matrix determination based on the point cloud edges to obtain a transformation matrix, and outputting the coordinates of the target cargo based on the transformation matrix and the projected point cloud includes: Iterative line fitting is performed on the edge of the point cloud until the angle between the two fitted lines is close to 1. Output two straight lines; Determine the origin of the cargo stacking coordinate system. And based on two straight lines and the origin Determine the transformation matrix : ; In the formula, , These are the unit direction vectors of the two lines, respectively. The unit normal vector of the fitted plane; Based on the transformation matrix All point clouds in the projected point cloud are converted into coordinate positions in the cargo stacking coordinate system to obtain the coordinates of the target cargo.

[0012] Secondly, the present invention provides the following technical solution: a cargo positioning system for an automated storage and retrieval system, the system comprising: The preprocessing module is used to collect point cloud data of stacked goods and preprocess the point cloud data to obtain preprocessed point cloud data. The fitting module is used to perform iterative plane fitting on the preprocessed point cloud data to obtain a fitting plane, and to project the preprocessed point cloud data onto the fitting plane to obtain a projected point cloud. An extraction module is used to extract the edges of the projected point cloud to obtain the point cloud edges; The transformation module is used to perform line fitting and matrix determination based on the edge of the point cloud to obtain a transformation matrix, and output the coordinates of the target cargo based on the transformation matrix and the projected point cloud.

[0013] Preferably, the preprocessing module is specifically used for: Obtain environmental point cloud data of the environment where the goods are stacked, and perform differential operations on the environmental point cloud data and the point cloud data to obtain the first processed point cloud data; The point cloud space containing the first processed point cloud data is divided into several grids of the same size, and the first processed point cloud data within the grid is weighted and averaged to output the average point cloud. The point cloud closest to the average point cloud in the grid is selected as the target point cloud, and the target point clouds in all the grids are combined to obtain the second processed point cloud data; Traverse all point clouds in the second processed point cloud data In the neighborhood The first parameter inside With the second parameter : ; ; Based on the first parameter With the second parameter Determine the filtering range Point clouds that are not within the filtering range are removed from the second processed point cloud to obtain preprocessed point cloud data, wherein, It is a fixed multiple.

[0014] Preferably, the fitting module is specifically used for: Select a subset containing three point clouds from the preprocessed point cloud data, and fit a target plane using the least squares method with the three point clouds in the subset; Calculate the distance from each point in the preprocessed point cloud data to the target plane; If the distance from the point cloud to the target plane is less than a preset distance threshold, then the point cloud is a first type of point cloud; if the distance from the point cloud to the target plane is not less than the preset distance threshold, then the point cloud is a second type of point cloud. The process of subset selection, distance calculation and point cloud classification is repeated iteratively, and the target plane corresponding to the largest number of first-class point clouds is selected as the fitting plane from all iteration results. Each point cloud in the preprocessed point cloud data Projected onto the fitting plane to obtain a projected point cloud. : ; ; ; In the formula, The normal vector of the fitted plane, To fit the distance from the plane to the origin, Normal vector The square of the modulus.

[0015] Thirdly, the present invention provides the following technical solution: a computer, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the above-described method for positioning goods in an automated storage and retrieval system.

[0016] Fourthly, the present invention provides the following technical solution: a storage medium storing a computer program, wherein the computer program, when executed by a processor, implements the above-described method for locating goods in an automated storage and retrieval system. Attached Figure Description

[0017] To more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0018] Figure 1 A flowchart of a cargo positioning method for an automated storage and retrieval system provided in Embodiment 1 of the present invention; Figure 2 This is a structural block diagram of a cargo positioning system for an automated storage and retrieval system provided in Embodiment 2 of the present invention; Figure 3 This is a schematic diagram of the hardware structure of a computer provided for another embodiment of the present invention.

[0019] The embodiments of the present invention will be further described below with reference to the accompanying drawings. Detailed Implementation

[0020] Embodiments of the present invention are described in detail below, examples of which are illustrated in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and intended to explain embodiments of the present invention, and should not be construed as limiting the present invention.

[0021] Example 1 In Embodiment 1 of the present invention, as Figure 1 As shown, a method for goods positioning in an automated storage and retrieval system (AS / RS) includes: S1. Collect point cloud data of the stacked goods, and preprocess the point cloud data to obtain preprocessed point cloud data; Specifically, step S1 includes: S11. Obtain environmental point cloud data of the environment where the goods are stacked, and perform differential operations on the environmental point cloud data and the point cloud data to obtain first processed point cloud data. Specifically, in actual shooting, an environmental point cloud without cargo is first acquired as a reference. Then, a differentiation operation is performed between the point cloud containing cargo and the reference point cloud, that is, the two are compared point by point. Points in the captured point cloud that match the reference point cloud within a certain radius are identified as environmental background points and removed from the point cloud. If a small-radius search is performed on the background point cloud in the cargo area, the number of background point clouds within the radius of the cargo area points is 0. Similarly, the number of points obtained by a radius search on the cargo point cloud in the background area is also 0. Only when searching in a consistent region, points exist within the radius of both the background and cargo point clouds, thus the consistent region can be removed.

[0022] S12. Divide the point cloud space where the first processed point cloud data is located into several grids of the same size, and perform a weighted average on the first processed point cloud data within the grids to output an average point cloud. S13. Select the point cloud in the grid that is closest to the average point cloud as the target point cloud, and combine all the target point clouds in the grid to obtain the second processed point cloud data; Specifically, for traditional point cloud sampling, the points in each grid are usually averaged or weighted and the new points obtained are used to replace the points in the original grid. Since the new points are not necessarily points in the original point cloud, some small features of the original point cloud may be lost. However, this application selects the point cloud that is closest to the average point cloud in the grid as the target point cloud, which reduces the amount of data while preserving the shape features of the original point cloud as much as possible.

[0023] S14. Traverse all point clouds in the second processed point cloud data. In the neighborhood The first parameter inside With the second parameter : ; ; S15, Based on the first parameter With the second parameter Determine the filtering range Point clouds that are not within the filtering range are removed from the second processed point cloud to obtain preprocessed point cloud data, wherein, It is a fixed multiple; Specifically, factors such as unstable lighting conditions, complex surface characteristics of objects, and camera movement or vibration can all lead to outliers in point cloud data. These outliers are usually data points that deviate extremely from their surroundings or have large abnormal values. Therefore, outliers are removed by determining the filtering range.

[0024] S2. Perform iterative plane fitting on the preprocessed point cloud data to obtain a fitting plane, and project the preprocessed point cloud data onto the fitting plane to obtain a projected point cloud. Step S2 includes: S21. Select a subset containing three point clouds from the preprocessed point cloud data, and fit a target plane using the least squares method with the three point clouds in the subset.

[0025] S22. Calculate the distance from each point cloud in the preprocessed point cloud data to the target plane.

[0026] S23. If the distance from the point cloud to the target plane is less than a preset distance threshold, then the point cloud is a first type of point cloud; if the distance from the point cloud to the target plane is not less than the preset distance threshold, then the point cloud is a second type of point cloud. Specifically, the first type of point cloud consists of interior points, and the second type of point cloud consists of exterior points.

[0027] S24. Repeat the process of subset selection, distance calculation and point cloud classification. Select the target plane corresponding to the largest number of first-class point clouds from all iteration results as the fitting plane.

[0028] S25. Each point cloud in the preprocessed point cloud data... Projected onto the fitting plane to obtain a projected point cloud. : ; ; ; In the formula, The normal vector of the fitted plane, To fit the distance from the plane to the origin, Normal vector The square of the modulus; Specifically, due to factors such as extrusion deformation and manufacturing, the edges of goods may have a certain curvature, which results in the length and width of the carton not being consistent with the length of the side of the top surface. Since the edge curvature can usually be captured by the camera, by projecting the point cloud onto the top surface, the largest rectangle formed by the side of the goods can be obtained, thus obtaining accurate length and width information.

[0029] S3. Extract the edges of the projected point cloud to obtain the point cloud edges; Step S3 includes: S31. Calculate the projected point cloud at a preset distance. Point cloud density on the plane : ; In the formula, For near-end field of view size, For resolution size, The distance from the camera to the near-end of the field of view; S32, Based on the point cloud density Determine the number of point clouds within the range : ; In the formula, The preset radius; S33. Determine the number of range point clouds corresponding to each point cloud in the projected point cloud. If the number of range point clouds corresponding to a point cloud is less than a preset number, then the point cloud is an edge point cloud. Combine all the edge point clouds to obtain the point cloud edge. Specifically, if a point is located in a non-edge region of a point cloud, the number of points within its radius will be close to the number of points within a theoretical circular region. In a non-edge region, most areas within a circular region contain points, so the number of points is roughly equal to the area of ​​the circle multiplied by the theoretical density of the point cloud. If a point is located at the edge of a point cloud, there may be some areas within its radius where no points exist, resulting in a point count lower than the product of density and the area of ​​the circle. Based on this principle, by analyzing the point cloud density around each point, the edges of the point cloud can be effectively extracted, thereby identifying edge regions in the point cloud. S4. Perform line fitting and matrix determination based on the edge of the point cloud to obtain a transformation matrix, and output the coordinates of the target cargo based on the transformation matrix and the projected point cloud.

[0030] Step S4 includes: S41. Iteratively fit straight lines to the edge of the point cloud until the angle between the two fitted straight lines is close to... Output two straight lines; S42. Determine the origin of the cargo stacking coordinate system. And based on two straight lines and the origin Determine the transformation matrix : ; In the formula, , These are the unit direction vectors of the two lines, respectively. The unit normal vector of the fitted plane; S43, Based on the transformation matrix All point clouds in the projected point cloud are converted into coordinate positions in the cargo stacking coordinate system to obtain the coordinates of the target cargo; Specifically, based on the obtained transformation matrix, the original point cloud in the camera coordinate system is transformed. The coordinates of the transformed point cloud are then its coordinates in the box coordinate system. Furthermore, the edges of the point cloud are parallel or perpendicular to the X and Y axes of the box coordinate system. Next, the minimum and maximum values ​​of the transformed point cloud along the X and Y axes of the box coordinate system are calculated. Based on these minimum and maximum values, the minimum bounding box of the transformed point cloud is obtained. The minimum bounding box is perpendicular or parallel to the coordinate axes. By transforming the minimum bounding box back to the camera coordinate system, the length, width, and pose of the box are obtained based on its size and rotation direction. It is worth noting that since the newly established coordinate system is not a standard Cartesian coordinate system, the transformation matrix is ​​not a rigid transformation but an affine transformation, but this does not affect the final result.

[0031] The first embodiment of this invention provides a method for cargo positioning in an automated storage and retrieval system (AS / RS). This invention collects point cloud data of stacked goods, preprocesses the point cloud data to obtain preprocessed point cloud data, performs iterative plane fitting on the preprocessed point cloud data to obtain a fitting plane, projects the preprocessed point cloud data onto the fitting plane to obtain a projected point cloud, extracts edges from the projected point cloud to obtain point cloud edges, performs line fitting and matrix determination based on the point cloud edges to obtain a transformation matrix, and outputs the coordinates of the target cargo based on the transformation matrix and the projected point cloud. This invention, through a series of processing steps on the original point cloud data, can effectively improve the processing efficiency and accuracy of point cloud data, while effectively capturing the edge information of the cargo, improving the accuracy of subsequent positioning and recognition. Then, a coordinate system is established based on the boundaries, and the size and pose information of the target cargo are determined through affine transformation.

[0032] Example 2 like Figure 2 As shown, in Embodiment 2 of the present invention, a goods positioning system for an automated storage and retrieval system is provided, the system comprising: Preprocessing module 1 is used to collect point cloud data of stacked goods and preprocess the point cloud data to obtain preprocessed point cloud data. Fitting module 2 is used to perform iterative plane fitting on the preprocessed point cloud data to obtain a fitting plane, and to project the preprocessed point cloud data onto the fitting plane to obtain a projected point cloud. Extraction module 3 is used to extract the edges of the projected point cloud to obtain the point cloud edges; The conversion module 4 is used to perform line fitting and matrix determination based on the edge of the point cloud to obtain a conversion matrix, and output the coordinates of the target cargo based on the conversion matrix and the projected point cloud.

[0033] Specifically, the preprocessing module 1 is used for: Obtain environmental point cloud data of the environment where the goods are stacked, and perform differential operations on the environmental point cloud data and the point cloud data to obtain the first processed point cloud data; The point cloud space containing the first processed point cloud data is divided into several grids of the same size, and the first processed point cloud data within the grid is weighted and averaged to output the average point cloud. The point cloud closest to the average point cloud in the grid is selected as the target point cloud, and the target point clouds in all the grids are combined to obtain the second processed point cloud data; Traverse all point clouds in the second processed point cloud data In the neighborhood The first parameter inside With the second parameter : ; ; Based on the first parameter With the second parameter Determine the filtering range Point clouds that are not within the filtering range are removed from the second processed point cloud to obtain preprocessed point cloud data, wherein, It is a fixed multiple.

[0034] Specifically, the fitting module 2 is used for: Select a subset containing three point clouds from the preprocessed point cloud data, and fit a target plane using the least squares method with the three point clouds in the subset; Calculate the distance from each point in the preprocessed point cloud data to the target plane; If the distance from the point cloud to the target plane is less than a preset distance threshold, then the point cloud is a first type of point cloud; if the distance from the point cloud to the target plane is not less than the preset distance threshold, then the point cloud is a second type of point cloud. The process of subset selection, distance calculation and point cloud classification is repeated iteratively, and the target plane corresponding to the largest number of first-class point clouds is selected as the fitting plane from all iteration results. Each point cloud in the preprocessed point cloud data Projected onto the fitting plane to obtain a projected point cloud. : ; ; ; In the formula, The normal vector of the fitted plane, To fit the distance from the plane to the origin, Normal vector The square of the modulus.

[0035] Specifically, the extraction module 3 is used for: Calculate the projected point cloud at a preset distance Point cloud density on the plane : ; In the formula, For near-end field of view size, For resolution size, The distance from the camera to the near-end of the field of view; Based on the point cloud density Determine the number of point clouds within the range : ; In the formula, The preset radius; The number of range point clouds corresponding to each point cloud in the projected point cloud is determined. If the number of range point clouds corresponding to a point cloud is less than a preset number, the point cloud is an edge point cloud. All edge point clouds are combined to obtain the point cloud edge.

[0036] Specifically, the conversion module 4 is used for: Iterative line fitting is performed on the edge of the point cloud until the angle between the two fitted lines is close to 1. Output two straight lines; Determine the origin of the cargo stacking coordinate system. And based on two straight lines and the origin Determine the transformation matrix : ; In the formula, , These are the unit direction vectors of the two lines, respectively. The unit normal vector of the fitted plane; Based on the transformation matrix All point clouds in the projected point cloud are converted into coordinate positions in the cargo stacking coordinate system to obtain the coordinates of the target cargo.

[0037] In other embodiments of the present invention, the present invention provides the following technical solution: a computer, including a memory 102, a processor 101, and a computer program stored in the memory 102 and executable on the processor 101, wherein the processor 101 executes the computer program to implement the goods positioning method for an automated storage and retrieval system as described above.

[0038] Specifically, the processor 101 may include a central processing unit (CPU), or an application specific integrated circuit (ASIC), or one or more integrated circuits that can be configured to implement the embodiments of the present invention.

[0039] The memory 102 may include a large-capacity memory for data or instructions. For example, and not limitingly, the memory 102 may include a hard disk drive (HDD), a floppy disk drive, a solid-state drive (SSD), flash memory, an optical disk drive, a magneto-optical disk drive, magnetic tape, or a Universal Serial Bus (USB) drive, or a combination of two or more of these. Where appropriate, the memory 102 may include removable or non-removable (or fixed) media. Where appropriate, the memory 102 may be internal or external to a data processing device. In a particular embodiment, the memory 102 is non-volatile memory. In a particular embodiment, the memory 102 includes read-only memory (ROM) and random access memory (RAM). Where appropriate, the ROM may be a mask-programmed ROM, a programmable read-only memory (PROM), an erasable read-only memory (EPROM), an electrically erasable read-only memory (EEPROM), an electrically alterable read-only memory (EAROM), or flash memory, or a combination of two or more of these. Where appropriate, the RAM can be Static Random-Access Memory (SRAM) or Dynamic Random-Access Memory (DRAM). DRAM can be Fast Page Mode Dynamic Random Access Memory (FPMDRAM), Extended Data Out Dynamic Random Access Memory (EDODRAM), Synchronous Dynamic Random-Access Memory (SDRAM), etc.

[0040] The memory 102 can be used to store or cache various data files that need to be processed and / or used for communication, as well as possible computer program instructions executed by the processor 101.

[0041] The processor 101 implements the above-described cargo positioning method for automated storage and retrieval systems by reading and executing computer program instructions stored in the memory 102.

[0042] In some embodiments, the computer may further include a communication interface 103 and a bus 100. For example, Figure 3 As shown, the processor 101, memory 102, and communication interface 103 are connected through bus 100 and complete communication with each other.

[0043] The communication interface 103 is used to enable communication between the various modules, devices, units, and / or equipment in the embodiments of the present invention. The communication interface 103 can also enable data communication with other components such as external devices, image / data acquisition devices, databases, external storage, and image / data processing workstations.

[0044] Bus 100 includes hardware, software, or both, that couples components of a computer device together. Bus 100 includes, but is not limited to, at least one of the following: data bus, address bus, control bus, expansion bus, and local bus. For example, and not as a limitation, bus 100 may include an Accelerated Graphics Port (AGP) or other graphics bus, an Extended Industry Standard Architecture (EISA) bus, a Front Side Bus (FSB), a Hyper Transport (HT) interconnect, an Industry Standard Architecture (ISA) bus, an InfiniBand interconnect, a Low Pin Count (LPC) bus, a memory bus, a Micro Channel Architecture (MCA) bus, a Peripheral Component Interconnect (PCI) bus, a PCI-Express (PCI-X) bus, a Serial Advanced Technology Attachment (SATA) bus, a Video Electronics Standards Association Local Bus (VLB) bus, or other suitable buses, or a combination of two or more of these. Where appropriate, bus 100 may include one or more buses. Although specific buses are described and illustrated in the embodiments of the present invention, the present invention is contemplated by any suitable bus or interconnect.

[0045] The computer can execute the cargo positioning method for automated storage and retrieval systems of the present invention based on the cargo positioning system acquired for automated storage and retrieval systems, thereby realizing cargo positioning for automated storage and retrieval systems.

[0046] In some further embodiments of the present invention, in conjunction with the above-described method for locating goods in an automated storage and retrieval system, the present invention provides the following technical solution: a storage medium storing a computer program, wherein the computer program, when executed by a processor, implements the above-described method for locating goods in an automated storage and retrieval system.

[0047] Those skilled in the art will understand that the logic and / or steps represented in the flowcharts or otherwise described herein, for example, can be considered as a ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a processor-included system, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can mean any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device.

[0048] More specific examples of readable media (a non-exhaustive list) include: electrical connections (electronic devices) with one or more wires, portable computer disk drives (magnetic devices), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). Furthermore, computer-readable media can even be paper or other suitable media on which the program can be printed, since the program can be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, interpreting, or otherwise processing as necessary, and then stored in computer memory.

[0049] It should be understood that various parts of the present invention can be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0050] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0051] The embodiments described above are merely illustrative of several implementations of the present invention, and while the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the invention patent. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of the present invention, and these all fall within the protection scope of the present invention. Therefore, the protection scope of this invention patent should be determined by the appended claims.

Claims

1. A method for goods positioning in an automated storage and retrieval system (AS / RS), characterized in that, include: Collect point cloud data of stacked goods, and preprocess the point cloud data to obtain preprocessed point cloud data; The preprocessed point cloud data is iteratively fitted to a plane to obtain a fitted plane, and the preprocessed point cloud data is projected onto the fitted plane to obtain a projected point cloud. Edge extraction is performed on the projected point cloud to obtain the point cloud edges; Based on the point cloud edges, straight line fitting and matrix determination are performed to obtain a transformation matrix. Based on the transformation matrix and the projected point cloud, the coordinates of the target cargo are output.

2. The cargo positioning method for an automated storage and retrieval system according to claim 1, characterized in that, The step of preprocessing the point cloud data to obtain preprocessed point cloud data includes: Obtain environmental point cloud data of the environment where the goods are stacked, and perform differential operations on the environmental point cloud data and the point cloud data to obtain the first processed point cloud data; The point cloud space containing the first processed point cloud data is divided into several grids of the same size, and the first processed point cloud data within the grid is weighted and averaged to output the average point cloud. The point cloud closest to the average point cloud in the grid is selected as the target point cloud, and the target point clouds in all the grids are combined to obtain the second processed point cloud data; Traverse all point clouds in the second processed point cloud data In the neighborhood The first parameter inside With the second parameter : ； ； Based on the first parameter With the second parameter Determine the filtering range Point clouds that are not within the filtering range are removed from the second processed point cloud to obtain preprocessed point cloud data, wherein, It is a fixed multiple.

3. The cargo positioning method for an automated storage and retrieval system according to claim 1, characterized in that, The steps of iteratively fitting the preprocessed point cloud data to obtain a fitting plane, and projecting the preprocessed point cloud data onto the fitting plane to obtain a projected point cloud include: Select a subset containing three point clouds from the preprocessed point cloud data, and fit a target plane using the least squares method with the three point clouds in the subset; Calculate the distance from each point in the preprocessed point cloud data to the target plane; If the distance from the point cloud to the target plane is less than a preset distance threshold, then the point cloud is a first type of point cloud; if the distance from the point cloud to the target plane is not less than the preset distance threshold, then the point cloud is a second type of point cloud. The process of subset selection, distance calculation and point cloud classification is repeated iteratively, and the target plane corresponding to the largest number of first-class point clouds is selected as the fitting plane from all iteration results. Each point cloud in the preprocessed point cloud data Projected onto the fitting plane to obtain a projected point cloud. : ； ； ； In the formula, The normal vector of the fitted plane, To fit the distance from the plane to the origin, Normal vector The square of the modulus.

4. The cargo positioning method for an automated storage and retrieval system according to claim 1, characterized in that, The step of extracting the edges of the projected point cloud to obtain the point cloud edges includes: Calculate the projected point cloud at a preset distance Point cloud density on the plane : ； In the formula, For near-end field of view size, For resolution size, The distance from the camera to the near-end of the field of view; Based on the point cloud density Determine the number of point clouds within the range : ； In the formula, The preset radius; The number of range point clouds corresponding to each point cloud in the projected point cloud is determined. If the number of range point clouds corresponding to a point cloud is less than a preset number, the point cloud is an edge point cloud. All edge point clouds are combined to obtain the point cloud edge.

5. The cargo positioning method for an automated storage and retrieval system according to claim 1, characterized in that, The step of performing line fitting and matrix determination based on the point cloud edges to obtain a transformation matrix, and outputting the coordinates of the target cargo based on the transformation matrix and the projected point cloud includes: Iterative line fitting is performed on the edge of the point cloud until the angle between the two fitted lines is close to 1. Output two straight lines; Determine the origin of the cargo stacking coordinate system. And based on two straight lines and the origin Determine the transformation matrix : ； In the formula, , These are the unit direction vectors of the two lines, respectively. The unit normal vector of the fitted plane; Based on the transformation matrix All point clouds in the projected point cloud are converted into coordinate positions in the cargo stacking coordinate system to obtain the coordinates of the target cargo.

6. A cargo positioning system for an automated storage and retrieval system (AS / RS), characterized in that, The system includes: The preprocessing module is used to collect point cloud data of stacked goods and preprocess the point cloud data to obtain preprocessed point cloud data. The fitting module is used to perform iterative plane fitting on the preprocessed point cloud data to obtain a fitting plane, and to project the preprocessed point cloud data onto the fitting plane to obtain a projected point cloud. An extraction module is used to extract the edges of the projected point cloud to obtain the point cloud edges; The transformation module is used to perform line fitting and matrix determination based on the edge of the point cloud to obtain a transformation matrix, and output the coordinates of the target cargo based on the transformation matrix and the projected point cloud.

7. The cargo positioning system for an automated storage and retrieval system according to claim 6, characterized in that, The preprocessing module is specifically used for: Obtain environmental point cloud data of the environment where the goods are stacked, and perform differential operations on the environmental point cloud data and the point cloud data to obtain the first processed point cloud data; The point cloud space containing the first processed point cloud data is divided into several grids of the same size, and the first processed point cloud data within the grid is weighted and averaged to output the average point cloud. The point cloud closest to the average point cloud in the grid is selected as the target point cloud, and the target point clouds in all the grids are combined to obtain the second processed point cloud data; Traverse all point clouds in the second processed point cloud data In the neighborhood The first parameter inside With the second parameter : ； ； Based on the first parameter With the second parameter Determine the filtering range Point clouds that are not within the filtering range are removed from the second processed point cloud to obtain preprocessed point cloud data, wherein, It is a fixed multiple.

8. The cargo positioning system for an automated storage and retrieval system according to claim 6, characterized in that, The fitting module is specifically used for: Select a subset containing three point clouds from the preprocessed point cloud data, and fit a target plane using the least squares method with the three point clouds in the subset; Calculate the distance from each point in the preprocessed point cloud data to the target plane; If the distance from the point cloud to the target plane is less than a preset distance threshold, then the point cloud is a first type of point cloud; if the distance from the point cloud to the target plane is not less than the preset distance threshold, then the point cloud is a second type of point cloud. The process of subset selection, distance calculation and point cloud classification is repeated iteratively, and the target plane corresponding to the largest number of first-class point clouds is selected as the fitting plane from all iteration results. Each point cloud in the preprocessed point cloud data Projected onto the fitting plane to obtain a projected point cloud. : ； ； ； In the formula, The normal vector of the fitted plane, To fit the distance from the plane to the origin, Normal vector The square of the modulus.

9. A computer comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the cargo positioning method for an automated storage and retrieval system as described in any one of claims 1 to 6.

10. A storage medium, characterized in that, The storage medium stores a computer program, which, when executed by a processor, implements the cargo positioning method for an automated storage and retrieval system as described in any one of claims 1 to 6.

Images