Shelf posture recognition method, device, equipment and medium based on laser radar

Abstract

The present disclosure relates to the field of posture recognition technology, and provides a method, device, equipment and medium for shelf posture recognition based on laser radar. The method includes: obtaining the coordinates of each laser point in the first annular area formed by a circle with the center of the chassis as the first center, the first radius and the second radius in the target laser area at the bottom of the shelf, and obtaining a coordinate set; based on the coordinate set, grouping the laser points in the first annular area to obtain at least one point set group; based on the coordinate set, for each point set group in at least one point set group, selecting a target laser point; based on the coordinate set, determining the posture of the shelf. The method provided by the present disclosure utilizes the depth space at the bottom of the shelf, sets two identification objects that are parallel to the central longitudinal axis of the shelf, and calculates the shelf angle and horizontal coordinates in combination with the drooping objects in the direction of the central longitudinal axis, which can effectively reduce the influence of the laser point coordinate stability on the characteristic object angle calculation.

Description

Technical Field

[0001] The present disclosure relates to the technical field of posture recognition, and in particular to a method, device, equipment and medium for shelf posture recognition based on laser radar. Background Art

[0002] In recent years, my country's lidar technology has developed rapidly, and using lidar to identify the position and posture of objects is one of its current applications. Currently, there are two common methods for using single-line lidar to identify features and determine their position: the first involves attaching a reflective strip to a specific location on the feature. A frame of the lidar scan is filtered based on light intensity greater than that of the reflective strip to obtain a point set containing the reflective strip. The angle of the reflective strip is then calculated using segmentation and linear fitting, and the coordinates of the reflective strip's feature points are taken to calculate the reflective strip's position in the object's coordinate system. However, due to the physical properties of the reflective strip, the intensity of the reflected laser light decreases the further the laser deviates from the outer normal of the reflective strip. To achieve a wider range of recognition angles, this recognition method often requires reducing the light intensity threshold for filtering out the reflective strip. This inevitably filters out surfaces with higher reflectivity in the environment, increasing the data processing workload while making less use of the reflective strip's inherent high reflectivity and making it prone to misidentifying other similar surfaces in the environment. The second method is to shape the side of the feature facing the laser into a special geometric shape. The LiDAR scanned point set is then directly evaluated through segmentation and geometric feature matching to calculate the feature's position in the object's coordinate system. This method allows for a wider range of recognition angles, but shaping a unique shape requires the feature to provide a certain amount of space. For features with a limited depth within the LiDAR's visible height, there is no room for additional special geometric shapes. Therefore, how to minimize the addition of additional components within the limited structural space and fully utilize the inherent structural features to achieve object position recognition has become a pressing issue. Summary of the Invention

[0003] In view of this, an embodiment of the present disclosure provides a lidar-based shelf posture recognition method that utilizes the depth space at the bottom of the shelf to set up identification objects and hanging objects to calculate the shelf angle and horizontal coordinates, so as to solve the problems in the existing technology.

[0004] A first aspect of an embodiment of the present disclosure provides a shelf posture recognition method based on laser radar, including: obtaining the coordinates of each laser point in a first annular area formed by a circle with a first radius and a second radius and a center of the chassis as the first center within a target laser area at the bottom of the shelf, to obtain a coordinate set; based on the above coordinate set, grouping the laser points in the above first annular area to obtain at least one point set group; based on the above coordinate set, selecting a target laser point for each point set group in the above at least one point set group; and determining the posture of the above shelf based on the coordinates of the above target laser point.

[0005] According to a second aspect of an embodiment of the present disclosure, a laser radar-based shelf posture recognition device is provided, comprising: an acquisition unit, configured to acquire the coordinates of each laser point in a first annular area formed by a circle with a first radius and a second radius and a center of the chassis as the first center in a target laser area at the bottom of the shelf, to obtain a coordinate set; a grouping unit, configured to group the laser points in the first annular area based on the coordinate set to obtain at least one point set group; a selection unit, configured to select a target laser point for each point set group in the at least one point set group based on the coordinate set; and a determination unit, configured to determine the posture of the shelf based on the coordinates of the target laser point.

[0006] According to a third aspect of an embodiment of the present disclosure, an electronic device is provided, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the above method when executing the computer program.

[0007] According to a fourth aspect of the embodiments of the present disclosure, a computer-readable storage medium is provided, which stores a computer program. When the computer program is executed by a processor, the steps of the above method are implemented.

[0008] Compared with the prior art, the beneficial effects of the embodiments of the present disclosure are as follows: first, the coordinates of each laser point in the first annular area formed by a circle with the center of the chassis as the first center, the first radius and the second radius in the target laser area at the bottom of the shelf are obtained to obtain a coordinate set; then, based on the above coordinate set, the laser points in the above first annular area are grouped to obtain at least one point set group; thereafter, based on the above coordinate set, for each point set group in the above at least one point set group, a target laser point is selected; finally, based on the coordinates of the above target laser point, the posture of the above shelf is determined. The method provided by the present disclosure is based on a laser radar, and utilizes the depth space at the bottom of the shelf to set two identification objects parallel to the central longitudinal axis of the shelf. The shelf angle and horizontal coordinates are calculated in combination with the drooping objects in the direction of the central longitudinal axis, which can effectively reduce the influence of the laser point coordinate stability on the characteristic object angle calculation. At the same time, the light intensity feature is not used, which avoids the problem of misidentification, and does not require additional changes to the shelf structure, thereby reducing costs. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] In order to more clearly illustrate the technical solutions in the embodiments of the present disclosure, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present disclosure. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0010] Figure 1 is a schematic diagram of an application scenario of a shelf posture recognition method based on laser radar according to some embodiments of the present disclosure;

[0011] Figure 2 is a flowchart of some embodiments of the laser radar-based shelf posture recognition method according to the present disclosure;

[0012] Figure 3 is an example diagram of the target laser area of the shelf pose recognition method based on laser radar according to the present disclosure;

[0013] Figure 4 is a schematic structural diagram of some embodiments of a shelf posture recognition device based on laser radar according to the present disclosure;

[0014] Figure 5 is a schematic structural diagram of an electronic device suitable for implementing some embodiments of the present disclosure. DETAILED DESCRIPTION

[0015] Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although certain embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be construed as being limited to the embodiments described herein. On the contrary, these embodiments are provided to provide a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are for illustrative purposes only and are not intended to limit the scope of protection of the present disclosure.

[0016] It should also be noted that, for ease of description, only the parts related to the invention are shown in the drawings. In the absence of conflict, the embodiments and features in the embodiments of the present disclosure may be combined with each other.

[0017] It should be noted that the concepts of "first" and "second" mentioned in this disclosure are only used to distinguish different devices, modules or units, and are not used to limit the order or interdependence of the functions performed by these devices, modules or units.

[0018] It should be noted that the modifications of "one" and "multiple" mentioned in the present disclosure are illustrative rather than restrictive, and those skilled in the art should understand that unless otherwise clearly indicated in the context, they should be understood as "one or more".

[0019] The names of the messages or information exchanged between multiple devices in the embodiments of the present disclosure are only used for illustrative purposes and are not used to limit the scope of these messages or information.

[0020] The present disclosure will be described in detail below with reference to the accompanying drawings and in conjunction with embodiments.

[0021] Figure 1 This is a schematic diagram of an application scenario of a shelf posture recognition method based on lidar according to some embodiments of the present disclosure.

[0022] exist Figure 1 In the application scenario, first, the computing device 101 can obtain the coordinates 103 of each laser point in the first annular area formed by a circle with the center of the chassis as the first center 102 and a first radius and a second radius in the target laser area at the bottom of the shelf, and obtain a coordinate set 104. Then, based on the above coordinate set 104, the computing device 101 can group the laser points in the above first annular area to obtain at least one point set group 105. Thereafter, based on the above coordinate set 104, the computing device 101 can select a target laser point 106 for each point set group 105 in the above at least one point set group. Finally, based on the coordinates of the above target laser points, the computing device 101 can determine the position 107 of the above shelf.

[0023] It should be noted that the computing device 101 described above can be either hardware or software. When the computing device 101 is hardware, it can be implemented as a distributed cluster consisting of multiple servers or terminal devices, or as a single server or a single terminal device. When the computing device 101 is software, it can be installed in the hardware devices listed above. It can be implemented as multiple software programs or software modules, for example, to provide distributed services, or as a single software program or software module. No specific limitations are imposed herein.

[0024] It should be understood that Figure 1 The number of computing devices in the embodiment is merely illustrative. Any number of computing devices may be provided according to implementation requirements.

[0025] Figure 2 Flowchart of some embodiments of the laser radar-based shelf posture recognition method according to the present disclosure. Figure 2 The shelf pose recognition method based on LiDAR can be Figure 1 The computing device 101 executes. Figure 2 As shown, the laser radar-based shelf posture recognition method includes:

[0026] Step 201 , obtaining the coordinates of each laser point in a first annular area formed by a circle with a first radius and a second radius and a first center in a target laser area at the bottom of the shelf, to obtain a coordinate set.

[0027] In some embodiments, the execution body of the laser radar-based shelf posture recognition method (such as Figure 1 The computing device 101 shown in the figure can obtain the coordinates of each laser point in the first annular area formed by a circle with the center of the chassis as the first center, the first radius and the second radius in the target laser area at the bottom of the shelf, and obtain a coordinate set. As an example, Figure 3 As shown, for a shelf supported by pillars, the present disclosure sets a drooping object 301 as a feature object at the bottom of the shelf at a central longitudinal axis facing the direction of the laser radar. The above-mentioned drooping object 301 can be set as a foldable thin rod-shaped feature object. An identification object 302 can be installed along the central longitudinal axis of the shelf on two pillars symmetrical about the central longitudinal axis at the rear of the shelf relative to the direction of the drooping object 301. The above-mentioned identification object 302 can be a 10 cm long angle steel, so that the two identification objects 302 at the rear of the shelf and the drooping object 301 in front form an isosceles triangle. The area formed by the above-mentioned isosceles triangle is the above-mentioned target laser area.

[0028] Step 202: based on the coordinate set, group the laser points within the first annular area to obtain at least one point set group.

[0029] In some embodiments, based on the coordinate set, the execution entity may group the laser points within the first annular area through the following steps to obtain at least one point set group:

[0030] In the first step, based on the coordinate set, the execution entity calculates the distances between adjacent laser points to obtain a distance set. Specifically, based on the coordinate set, the execution entity calculates the distances between each laser point in the first annular area and all adjacent laser points to obtain a distance set.

[0031] In the second step, based on the above-mentioned spacing set, the above-mentioned execution entity divides the laser points whose spacing between adjacent laser points is greater than the first preset spacing into a group to obtain a first point group set.

[0032] In a third step, the execution entity determines whether there is a point set in the first set of point sets in which the distance between two laser points is greater than a second preset distance. As an example, the first preset distance and the second preset distance are preset based on actual conditions, and the first preset distance is smaller than the second preset distance.

[0033] In step 4, in response to determining that a point set exists, the execution entity filters the first set of point sets to obtain a second set of point sets. Specifically, in response to determining that a point set exists in the first set of point sets in which the distance between two laser points is greater than a second preset distance, the execution entity deletes the point set in which the distance between two laser points is greater than the second preset distance from the first set of point sets, and the remaining point sets form the second set of point sets.

[0034] In step 5, the execution entity calculates the first arithmetic average center point corresponding to the laser points of the second point set group. Specifically, the execution entity obtains the coordinates of the laser points of all second point sets in the second point set group, and based on the coordinates of the laser points of all second point sets, calculates the arithmetic average of all horizontal coordinates and the arithmetic average of all vertical coordinates. The obtained coordinates are the coordinates of the arithmetic average center point of all laser points of the second point set group in the second point set group, which serves as the first arithmetic average center point.

[0035] In step 6, the execution entity constructs a second annular region with the first arithmetic mean center point as the second center and a third and fourth radius. The execution entity then defines a third point group by grouping at least two adjacent laser points whose spacing is less than the second preset spacing, thereby obtaining a third point group set. For example, the first, second, third, and fourth radii are preset based on actual conditions.

[0036] Step 203 : Based on the coordinate set, for each point set group in the at least one point set group, a target laser point is selected.

[0037] In some embodiments, based on the coordinate set, the execution entity may select a target laser point for each point set in the at least one point set group by performing the following steps:

[0038] In the first step, for each third point set in the third point set set, the execution entity calculates the distance between each laser point in the third point set and the first arithmetic mean center point to obtain a distance set corresponding to the third point set.

[0039] In the second step, based on the distance set, the execution entity selects the laser point with the smallest distance as the target laser point corresponding to the third point set to form a target laser point set.

[0040] In some embodiments, the laser radar-based shelf posture recognition method further includes: a first step of forming at least one triangular region based on the first arithmetic mean center point and the target laser point set; and a second step of filtering the third point set based on the at least one triangular region to obtain a fourth point set. Specifically, the fourth point set includes two fourth point sets.

[0041] Step 204: Determine the position of the shelf based on the coordinates of the target laser point.

[0042] In some embodiments, based on the coordinates of the target laser point, the execution entity may determine the position of the shelf by the following steps:

[0043] In the first step, based on the target laser points corresponding to each fourth point set in the fourth point set, the execution entity may calculate the coordinates of the second arithmetic mean center point corresponding to the target laser points. Specifically, the execution entity calculates the distance between each laser point in each fourth point set in the fourth point set and the first arithmetic mean center point to obtain a distance set corresponding to the fourth point set. Based on the distance set, the execution entity selects the laser point with the smallest distance as the target laser point corresponding to the fourth point set. The execution entity may then calculate the coordinates of the second arithmetic mean center point corresponding to the target laser points corresponding to the fourth point set.

[0044] In the second step, the angle of the line connecting the above coordinates and the above first arithmetic mean center point in the target laser coordinate system is determined as the angle of the above shelf longitudinal axis in the above target laser coordinate system, and the horizontal coordinate of the first arithmetic mean center point is determined as the coordinate of the hanging object 301 at the bottom of the above shelf in the above target laser coordinate system.

[0045] In the third step, based on the above angles and coordinates, the execution entity determines the position of the shelf

[0046] In some embodiments, the aforementioned laser radar-based shelf posture recognition method further includes: a first step of presetting a shelf posture category, where the shelf posture status categories include robot-accessible and robot-restricted; and a second step of, in response to the shelf posture being in the robot-accessible state, the robot performing an operation on the shelf. For example, the operation may be based on the robot's task information, including but not limited to moving the shelf, raising the shelf, and the like.

[0047] As an example, after receiving a task, the robot moves to the front of a shelf, where a laser radar mounted on the robot body detects the shelf's position. With the chassis center A within the target laser area at the bottom of the shelf as the first center, the robot scans laser points within a first annular area defined by a circle with a first radius R1 and a second radius R2. The coordinates of each laser point are obtained to form a coordinate set. The distances between each laser point and all adjacent laser points are then determined. Laser points with distances greater than a first preset distance D1 are grouped together to form a first set of point groups α. The α groups include α1, α2, ..., αn, where n ≥ 2. For each point group in the α group, a determination is made as to whether any point group exists where the distance between any two laser points exceeds a second preset distance D2. Point groups where the distance between any two laser points exceeds the second preset distance are removed from the first set of point groups. The remaining point groups form a second set of point groups β. The β groups include β1, β2, ..., βm, where 2 ≤ m ≤ n. The arithmetic mean center point of all laser points in the β group set is calculated as the first arithmetic mean center point H. A second annular region is formed by a circle with a third radius R3 and a fourth radius R4, with point H as the second center. The laser points within the second annular region are scanned, and at least two adjacent laser points with a spacing less than the second predetermined spacing D2 are identified as a third point group set, resulting in a third point group set γ group set. The γ group set includes γ1, γ2, ..., γi, where 2 ≤ i ≤ m. For each point group in the γ group set, the distance from each laser point in the group to point H is calculated. The laser point with the smallest distance within each group is used as the target laser point corresponding to each point group. A triangular region is formed between the target laser points corresponding to the two adjacent γ groups and point H. All γ groups with laser points falling within the triangular region are excluded. The remaining two point groups form the fourth point group set δ group set. The δ group set includes δ1 and δ2. The arithmetic mean center point of the target laser points corresponding to the δ1 and δ2 groups is calculated as the second arithmetic mean center point M. The angle of the line connecting point M and point H relative to the X-axis of the laser coordinate system is determined as the angle of the longitudinal axis of the shelf in the target laser coordinate system, and the horizontal coordinate of point H is determined as the coordinate of the hanging object 301 at the bottom of the shelf in the target laser coordinate system, thereby determining the position and posture of the shelf. Determine whether the position and posture of the shelf belongs to the robot access state or the robot prohibited state. When the position and posture of the shelf belongs to the robot access state, the robot operates the shelf based on the task information; when the position and posture of the shelf belongs to the robot prohibited state, the robot feeds back information to the execution entity, and the feedback information includes the current position and posture information of the shelf and the information that the shelf cannot be operated. The above is only for illustration and is not limited to one by one.

[0048] Compared with the prior art, the beneficial effects of the embodiments of the present disclosure are as follows: first, the coordinates of each laser point in the first annular area formed by a circle with the center of the chassis as the first center, the first radius and the second radius in the target laser area at the bottom of the shelf are obtained to obtain a coordinate set; then, based on the above coordinate set, the laser points in the above first annular area are grouped to obtain at least one point set group; thereafter, based on the above coordinate set, for each point set group in the above at least one point set group, a target laser point is selected; finally, based on the coordinates of the above target laser point, the posture of the above shelf is determined. The method provided by the present disclosure is based on a laser radar, and utilizes the depth space at the bottom of the shelf to set two identification objects parallel to the central longitudinal axis of the shelf. The shelf angle and horizontal coordinates are calculated in combination with the drooping objects in the direction of the central longitudinal axis, which can effectively reduce the influence of the laser point coordinate stability on the characteristic object angle calculation. At the same time, the light intensity feature is not used, which avoids the problem of misidentification, and does not require additional changes to the shelf structure, thereby reducing costs.

[0049] All of the above optional technical solutions can be combined in any way to form optional embodiments of the present application, and will not be described in detail here.

[0050] The following are embodiments of the apparatus disclosed herein, which can be used to implement the method embodiments disclosed herein. For details not disclosed in the apparatus embodiments disclosed herein, please refer to the method embodiments disclosed herein.

[0051] Figure 4 Schematic diagram of the structure of some embodiments of the shelf posture recognition device based on laser radar according to the present disclosure. Figure 4 As shown, the laser radar-based shelf posture recognition device includes: an acquisition unit 401, a grouping unit 402, a selection unit 403, and a determination unit 404. The acquisition unit 401 is configured to acquire the coordinates of each laser point in a first annular area formed by a circle with the center of the chassis as the first center and a first radius and a second radius within the target laser area at the bottom of the shelf, to obtain a coordinate set; the grouping unit 402 is configured to group the laser points in the first annular area based on the coordinate set to obtain at least one point set group; the selection unit 403 is configured to select a target laser point for each point set in the at least one point set group based on the coordinate set; and the determination unit 404 is configured to determine the posture of the shelf based on the coordinates of the target laser point.

[0052] In some optional implementations of some embodiments, the grouping unit 402 of the laser radar-based shelf posture recognition device is further configured to: calculate the distance between adjacent laser points based on the above-mentioned coordinate set to obtain a distance set; based on the above-mentioned distance set, divide the laser points whose distance between adjacent laser points is greater than the first preset distance into a group to obtain a first point group set; determine whether there is a point group in the above-mentioned first point group set in which the distance between two laser points is greater than the second preset distance; in response to the determination of existence, filter the above-mentioned first point group set to obtain a second point group set; calculate the first arithmetic mean center point corresponding to the laser points of the above-mentioned second point group set; use the above-mentioned first arithmetic mean center point as the second center point, the third radius and the fourth radius to draw a circle to form a second annular area, determine at least two adjacent laser points whose adjacent distance is less than the above-mentioned second preset distance as a third point group, and obtain a third point group set.

[0053] In some optional implementations of some embodiments, the selection unit 403 of the laser radar-based shelf posture recognition device is further configured to: for each third point group in the above-mentioned third point group set, calculate the distance between each laser point in the above-mentioned third point group and the first arithmetic mean center point, and obtain the distance set corresponding to the above-mentioned third point group; based on the above-mentioned distance set, select the laser point with the smallest distance as the target laser point corresponding to the above-mentioned third point group to form a target laser point set.

[0054] In some optional implementations of some embodiments, the laser radar-based shelf posture recognition device also includes: an area construction unit, configured to construct at least one triangular area based on the above-mentioned first arithmetic mean center point and the above-mentioned target laser point set; a screening unit, configured to screen the above-mentioned third point set group based on the above-mentioned at least one triangular area to obtain a fourth point set group set.

[0055] In some optional implementations of some embodiments, the determination unit 404 of the laser radar-based shelf posture recognition device is further configured to: calculate the coordinates of the second arithmetic mean center point corresponding to the above-mentioned target laser points based on the target laser points corresponding to each fourth point set in the above-mentioned fourth point set set; determine the angle of the line connecting the above-mentioned coordinates and the above-mentioned first arithmetic mean center point in the target laser coordinate system as the angle of the above-mentioned shelf longitudinal axis in the above-mentioned target laser coordinate system, and determine the horizontal coordinate of the first arithmetic mean center point as the coordinate of the hanging object at the bottom of the above-mentioned shelf in the above-mentioned target laser coordinate system; determine the posture of the above-mentioned shelf based on the above-mentioned angle and the above-mentioned coordinates.

[0056] In some optional implementations of some embodiments, the laser radar-based shelf posture recognition device also includes: a preset category unit, configured to preset the category of the shelf's posture, the posture state category of the above-mentioned shelf including a robot access state and a robot no-entry state; an operation unit, configured to respond to the posture of the above-mentioned shelf belonging to the robot access state, and the above-mentioned robot performs an operation on the above-mentioned shelf.

[0057] It should be understood that the size of the serial numbers of the steps in the above embodiments does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present disclosure.

[0058] Reference below Figure 5 , which shows an electronic device (eg, Figure 1 Schematic diagram of the structure of the computing device 101)500. Figure 5 The server 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.

[0059] like Figure 5 As shown, the electronic device 500 may include a processing device (e.g., a central processing unit, a graphics processing unit, etc.) 501, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 502 or a program loaded from a storage device 508 into a random access memory (RAM) 503. Various programs and data required for the operation of the electronic device 500 are also stored in the RAM 503. The processing device 501, the ROM 502, and the RAM 503 are connected to each other via a bus 504. An input / output (I / O) interface 505 is also connected to the bus 504.

[0060] Typically, the following devices may be connected to the I / O interface 505: an input device 506 including, for example, a touch screen, a touchpad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; an output device 507 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; a storage device 508 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 509. The communication device 509 may allow the electronic device 500 to communicate with other devices wirelessly or by wire to exchange data. Although Figure 5 The electronic device 500 is shown with various devices, but it should be understood that it is not required to implement or possess all of the devices shown. More or fewer devices may be implemented or possessed instead. Figure 5 Each block shown in the figure may represent one device, or may represent multiple devices as needed.

[0061] In particular, according to some embodiments of the present disclosure, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, some embodiments of the present disclosure include a computer program product comprising a computer program carried on a computer-readable medium, the computer program comprising program code for executing the method shown in the flowchart. In some such embodiments, the computer program can be downloaded and installed from a network via the communication device 509, or installed from the storage device 508, or installed from the ROM 502. When the computer program is executed by the processing device 501, the above-mentioned functions defined in the method of some embodiments of the present disclosure are performed.

[0062] It should be noted that in some embodiments of the present disclosure, the computer-readable medium mentioned above may be a computer-readable signal medium or a computer-readable storage medium, or any combination of the 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 some embodiments of the present disclosure, the computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, device, or device. In some embodiments of the present disclosure, the computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, which carries computer-readable program code. Such a propagated data signal may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium that can transmit, propagate, or transport 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 suitable medium, including but not limited to wires, optical cables, RF (radio frequency), etc., or any suitable combination thereof.

[0063] In some embodiments, the client and server can communicate using any currently known or future developed network protocol, such as HTTP (HyperText Transfer Protocol), and can be interconnected with any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network ("LAN"), a wide area network ("WAN"), an internet (e.g., the Internet), and a peer-to-peer network (e.g., an ad hoc peer-to-peer network), as well as any currently known or future developed network.

[0064] The computer-readable medium may be included in the apparatus, or may exist independently and not incorporated into the electronic device. The computer-readable medium carries one or more programs that, when executed by the electronic device, cause the electronic device to: obtain the coordinates of each laser point within a first annular region defined by a circle with the center of the chassis as the first center and a first radius and a second radius within a target laser region at the bottom of the shelf, thereby obtaining a coordinate set; group the laser points within the first annular region based on the coordinate set to obtain at least one point set group; select a target laser point for each point set within the at least one point set group based on the coordinate set; and determine the position of the shelf based on the coordinates of the target laser point.

[0065] Computer program code for performing the operations of some embodiments 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 stand-alone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer through 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., through the Internet using an Internet service provider).

[0066] The flowcharts and block diagrams in the accompanying drawings illustrate the possible implementation architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each box in the flowchart or block diagram can represent a module, program segment, or a part of code, and the module, program segment, or a part of code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order than that marked in the accompanying drawings. For example, two 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 box in the block diagram and / or flowchart, and the combination of the boxes in the block diagram and / or flowchart, can be implemented with a dedicated hardware-based system that performs the specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0067] The units described in some embodiments of the present disclosure may be implemented by software or by hardware. The described units may also be provided in a processor, for example, they may be described as: a processor comprising an acquisition unit, a grouping unit, a selection unit, and a determination unit. The names of these units do not, in some cases, constitute a limitation on the units themselves. For example, the acquisition unit may also be described as "a unit for acquiring the coordinates of each laser point in the first annular area formed by a circle with the center of the chassis as the first center, the first radius, and the second radius in the target laser area at the bottom of the shelf, and obtaining a coordinate set."

[0068] The functions described above herein may be performed, at least in part, by one or more hardware logic components. For example, and 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 chip (SOCs), complex programmable logic devices (CPLDs), and the like.

[0069] The above description is only an illustration of some preferred embodiments of the present disclosure and the technical principles used. Those skilled in the art should understand that the scope of the invention involved in the embodiments of the present disclosure is not limited to the technical solutions formed by the specific combination of the above-mentioned technical features, but should also cover other technical solutions formed by any combination of the above-mentioned technical features or their equivalent features without departing from the above-mentioned inventive concept. For example, the above-mentioned features are replaced with (but not limited to) technical features with similar functions disclosed in the embodiments of the present disclosure.

Claims

1. A method for shelf posture recognition based on laser radar, characterized in that: include: Obtain the coordinates of each laser point in a first annular area formed by a circle with the center of the chassis as the first center and a first radius and a second radius in the target laser area at the bottom of the shelf to obtain a coordinate set; grouping the laser points within the first annular area based on the coordinate set to obtain at least one point set group; Based on the coordinate set, for each point set group in the at least one point set group, selecting a target laser point; Determining the position of the shelf based on the coordinates of the target laser point; The step of grouping the laser points within the first annular area based on the coordinate set to obtain at least one point set group includes: Based on the coordinate set, calculating the distances between adjacent laser points to obtain a distance set; Based on the spacing set, the laser points whose spacing between adjacent laser points is greater than a first preset spacing are divided into a group to obtain a first point group set; Determining whether there is a point set group in the first point set group set in which the distance between two laser points is greater than a second preset distance; In response to determining that the point set exists, removing point set groups in which the distance between two laser points is greater than a second preset distance from the first point set group to obtain a second point set group; Calculating a first arithmetic mean center point corresponding to the laser points of the second point set group; A second annular area is formed by drawing a circle with the first arithmetic mean center point as the second center and a third radius and a fourth radius, and at least two adjacent laser points with an adjacent spacing less than the second preset spacing are determined as a third point set group to obtain a third point set group set.

2. The method for shelf posture recognition based on laser radar according to claim 1, characterized in that: The step of selecting a target laser point for each point set group in the at least one point set group based on the coordinate set includes: For each third point set in the third point set set, calculating the distance between each laser point in the third point set and the first arithmetic mean center point, to obtain a distance set corresponding to the third point set; Based on the distance set, the laser point with the smallest distance is selected as the target laser point corresponding to the third point set group to form a target laser point set.

3. The method for shelf posture recognition based on laser radar according to claim 2, characterized in that: The method further comprises: Based on the first arithmetic mean center point and the target laser point set, at least one triangular area is formed; Based on the at least one triangular area, the third point set group set is filtered for each third point set group in the third point set group set to obtain a fourth point set group set.

4. The method for shelf posture recognition based on laser radar according to claim 3, characterized in that: The determining the position of the shelf based on the coordinates of the target laser point includes: Calculating the coordinates of a second arithmetic mean center point corresponding to each target laser point in each fourth point set in the fourth point set group set; Determine the angle of the line connecting the coordinates and the first arithmetic mean center point in the target laser coordinate system as the angle of the longitudinal axis of the shelf in the target laser coordinate system, and determine the horizontal coordinate of the first arithmetic mean center point as the coordinate of the hanging object at the bottom of the shelf in the target laser coordinate system; Based on the angle and the coordinates, the position of the shelf is determined.

5. The method for shelf posture recognition based on laser radar according to claim 3, characterized in that: The method further comprises: Preset the category of the shelf's posture, where the shelf's posture status category includes a robot entry state and a robot entry prohibition state; In response to the posture of the shelf belonging to the robot admission state, the robot performs an operation on the shelf.

6. A shelf posture recognition device based on laser radar, characterized in that: include: An acquisition unit is configured to acquire the coordinates of each laser point in a first annular area formed by a circle with a first radius and a second radius and a center of the chassis as a first center in a target laser area at the bottom of the shelf, to obtain a coordinate set; a grouping unit configured to group the laser points within the first annular area based on the coordinate set to obtain at least one point set group; A selection unit is configured to select a target laser point for each point set group in the at least one point set group based on the coordinate set; a determination unit configured to determine the position and posture of the shelf based on the coordinates of the target laser point; The step of grouping the laser points within the first annular area based on the coordinate set to obtain at least one point set group includes: Based on the coordinate set, calculating the distances between adjacent laser points to obtain a distance set; Based on the spacing set, the laser points whose spacing between adjacent laser points is greater than a first preset spacing are divided into a group to obtain a first point group set; Determining whether there is a point set group in the first point set group set in which the distance between two laser points is greater than a second preset distance; In response to determining that the point set exists, removing point set groups in which the distance between two laser points is greater than a second preset distance from the first point set group to obtain a second point set group; Calculating a first arithmetic mean center point corresponding to the laser points of the second point set group; A second annular area is formed by drawing a circle with the first arithmetic mean center point as the second center and a third radius and a fourth radius, and at least two adjacent laser points with an adjacent spacing less than the second preset spacing are determined as a third point set group to obtain a third point set group set.

7. The laser radar-based shelf position recognition device according to claim 6, characterized in that: The device further comprises: A preset unit is configured to preset a category of a shelf's posture, wherein the category of the shelf's posture state includes a robot entry state and a robot entry prohibition state; The execution unit is configured to, in response to the posture of the shelf belonging to the robot admission state, enable the robot to perform an operation on the shelf.

8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 5 are implemented.

9. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 5 are implemented.

Images