Mobile charging robot positioning method for underground parking lot

Abstract

The invention discloses a mobile charging robot positioning method for an underground parking lot, and the method comprises the steps: constructing an underground parking lot map based on obtained point cloud data, carrying out the semantic extraction, obtaining first semantic information, and constructing a database according to the first semantic information; acquiring current pose information, performing coarse positioning, and acquiring a local map by taking a coarse positioning result as a center and combining a preset distance parameter; obtaining first semantic information contained in the local map from a database; performing clustering identification on the point cloud data to obtain a clustering result; performing target detection on the acquired image information to obtain a dynamic target object, and filtering a clustering result to obtain a static target object; fitting the point cloud information of the static target object to obtain a fitting shape, and endowing the fitting shape with second semantic information; the first semantic information and the second semantic information are matched, and the distance between the mobile charging robot and the static target object is obtained; three distances are obtained, coordinate information of the mobile charging robot is calculated through the trilateration principle, and accurate positioning is achieved.

Description

Technical Field

[0001] The present invention relates to the technical field of mobile charging robot positioning, and in particular to a mobile charging robot positioning method, system, equipment and medium used in underground parking lots. Background Art

[0002] With the rapid development of science and technology and the advent of the era of artificial intelligence, mobile charging robots have been widely used in all walks of life. In the smart charging business of charging stations, mobile charging robots need high-precision positioning when working to perform subsequent tasks. Therefore, positioning technology is needed to let the mobile charging robot know its current position in the environment and its position during movement.

[0003] Existing mobile charging robots with autonomous driving functions generally use the adaptive Monte Carlo positioning algorithm to achieve positioning. However, in highly dynamic and highly repeatable scenarios such as underground parking lots, positioning jumps are prone to occur during autonomous navigation, which leads to inaccurate positioning or positioning delays. Summary of the invention

[0004] The technical problem to be solved by the present invention is: in order to solve the technical problem of inaccurate positioning or delayed positioning of mobile charging robots in the prior art, the present invention provides a mobile charging robot positioning method for an underground parking lot, which improves the accuracy of the positioning of the mobile charging robot.

[0005] The technical solution adopted by the present invention to solve the technical problem is: a positioning method for a mobile charging robot used in an underground parking lot, the method comprising the following steps:

[0006] S1, obtaining point cloud data collected by the mobile charging robot, and constructing an underground parking lot map based on the point cloud data;

[0007] S2, performing semantic extraction on the underground parking lot map to obtain first semantic information, and constructing a semantic map database according to the first semantic information;

[0008] S3, obtaining the current posture information collected by the mobile charging robot, performing coarse positioning through an adaptive Monte Carlo positioning algorithm, and obtaining a first positioning result;

[0009] S4, taking the first positioning result as the center and combining a preset distance parameter to obtain a local map from the underground parking lot map;

[0010] S5, based on the semantic map database, obtaining first semantic information included in the local map;

[0011] S6, performing clustering recognition on the point cloud data to obtain a clustering result;

[0012] S7, acquiring image information collected by the mobile charging robot, performing target detection on the image information through a target detection model, and obtaining a dynamic target object;

[0013] S8, filtering the clustering results based on the dynamic target objects to obtain static targets;

[0014] S9, acquiring point cloud information of the static target object in real time and performing fitting processing to obtain a fitting shape, and assigning second semantic information based on the fitting shape;

[0015] S10, matching the first semantic information with the second semantic information to obtain a distance between the mobile charging robot and each static target object in the local map;

[0016] S11, obtaining the distances of three minimum static targets, calculating the coordinate information of the mobile charging robot by the trilateral measurement principle, and realizing the positioning of the mobile charging robot.

[0017] Further, specifically, the first semantic information includes: target object ID, target object name, target object shape and target object location description information;

[0018] The targets include static targets and dynamic targets.

[0019] Further, specifically, the clustering result includes large targets and medium targets;

[0020] The large target is a static target;

[0021] The targets include static targets and dynamic targets.

[0022] Further, specifically, in the step S9, the shape of the target object and the fitting shape are combined, and the second semantic information of the fitting shape is given, and the second semantic information includes the name of the target object and the shape of the target object.

[0023] Further, specifically, in the step S11, the distances of all static targets are sorted from small to large, and the static target with the smallest distance among the three static targets is taken. The distances of the three smallest static targets are used as radii, and the centers of the static targets are used as the centers of the circles to obtain three circles. The intersection of the three circles is calculated by the trilateral measurement principle, and the intersection is the coordinate information of the mobile charging robot.

[0024] Further, specifically, in step S4, the preset distance parameters are that the length of the local map is 5 to 20 meters, and the width is 5 to 20 meters.

[0025] A mobile charging robot positioning system for an underground parking lot, the system comprising:

[0026] A camera collects image information in front of the mobile charging robot;

[0027] LiDAR, which collects point cloud data in front of the mobile charging robot;

[0028] Motion sensor, collecting the current position of the mobile charging robot;

[0029] A central processing unit, wherein the central processing unit adopts the mobile charging robot positioning method for an underground parking lot as described above.

[0030] A computer device comprising:

[0031] processor;

[0032] A memory for storing executable instructions;

[0033] Wherein, the processor is used to read the executable instructions from the memory and execute the executable instructions to implement the mobile charging robot positioning method for an underground parking lot as described above.

[0034] A computer-readable storage medium stores a computer program. When the computer program is executed by a processor, the processor implements the mobile charging robot positioning method for an underground parking lot as described above.

[0035] The beneficial effect of the present invention is that a mobile charging robot positioning method for an underground parking lot of the present invention avoids the problem of inaccurate positioning or delayed positioning of the mobile charging robot, obtains a local map and first semantic information contained in the local map through coarse positioning, and assigns second semantic information by fitting through real-time acquisition of point cloud data, matches the first semantic information with the second semantic information, obtains the distance between the mobile charging robot and the target object in the local map, and realizes the positioning of the mobile charging robot through triangulation, thereby effectively improving the accuracy of the positioning of the mobile charging robot. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] The present invention is further described below in conjunction with the accompanying drawings and embodiments.

[0037] Figure 1 It is a schematic diagram of the method flow of embodiment 1 of the present invention.

[0038] Figure 2 It is a schematic diagram of the system structure of the second embodiment of the present invention.

[0039] Figure 3 It is a schematic diagram of the device structure of embodiment 3 of the present invention.

[0040] In the figure, 20 is a camera; 21 is a lidar; 22 is a motion sensor; 23 is a central processing unit; 10 is a computer device; 1002 is a processor; 1004 is a memory; and 1006 is a transmission device. DETAILED DESCRIPTION

[0041] The present invention will now be described in further detail with reference to the accompanying drawings. These drawings are simplified schematic diagrams, which only illustrate the basic structure of the present invention in a schematic manner, and therefore only show the components related to the present invention.

[0042] In the description of the present invention, it should be understood that the terms "center", "longitudinal", "lateral", "length", "width", "thickness", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", "clockwise", "counterclockwise", "axial", "radial", "circumferential" and the like indicate positions or positional relationships based on the positions or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation on the present invention. In addition, features defined as "first" and "second" may explicitly or implicitly include one or more of the features. In the description of the present invention, unless otherwise specified, "multiple" means two or more.

[0043] In the description of the present invention, it should be noted that, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0044] Example 1

[0045] The embodiment of the present application provides a method for positioning a mobile charging robot for an underground parking lot, the method comprising the following steps:

[0046] S1, obtain the point cloud data collected by the mobile charging robot, and build an underground parking lot map based on the point cloud data.

[0047] S2, extract the semantics of the underground parking map to obtain the first semantic information, and build a semantic map database based on the first semantic information; the first semantic information includes: target ID, target name, target shape and target location description information; wherein the target includes static targets and dynamic targets. For example, a static target can be a column or a wall. The shape of the column can be a rectangle or an ellipse. If it is a rectangle, the target location description information includes the upper left corner coordinates, length and width. If it is an ellipse, the target location description information includes the center point coordinates, the major axis semi-axis length and the minor axis semi-axis length; the shape of the wall can be a straight line segment and a curved line segment. If it is a straight line segment, the target location description information includes the starting point coordinates, the end point coordinates, the slope and the intercept. If it is a curved line segment, the target location description information includes the starting point coordinates and the end point coordinates. For example, a dynamic target can be a vehicle or a pedestrian.

[0048] S3, obtaining the current posture information collected by the mobile charging robot, performing coarse positioning through an adaptive Monte Carlo (AMCL) positioning algorithm, and obtaining a first positioning result.

[0049] S4, taking the first positioning result as the center, and combining with preset distance parameters, obtaining a local map from the underground parking lot map; the preset distance parameters are to set the length of the local map to 5 to 20 meters and the width to 5 to 20 meters.

[0050] S5, based on the semantic map database, obtaining first semantic information included in the local map.

[0051] S6, clustering and identifying the point cloud data to obtain clustering results, which include large targets and medium targets; large targets are static targets; medium targets include static targets and dynamic targets.

[0052] It should be noted that during clustering recognition, small targets are generally considered to be debris through analysis, so the point cloud data of small targets can be directly filtered during clustering.

[0053] S7, acquiring image information collected by the mobile charging robot, performing target detection on the image information through a target detection model, and obtaining a dynamic target object.

[0054] S8, filtering the clustering results based on the dynamic targets to obtain static targets.

[0055] S9, acquiring point cloud information of a static target object in real time and performing fitting processing to obtain a fitting shape, and assigning second semantic information based on the fitting shape; combining the shape of the target object and the fitting shape, and assigning second semantic information to the fitting shape, wherein the second semantic information includes the name of the target object and the shape of the target object.

[0056] S10, matching the first semantic information with the second semantic information to obtain the distance between the mobile charging robot and each static target object in the local map, in other words, obtaining the distance between the mobile charging robot and the pillars and walls.

[0057] S11, obtain the distances of the three smallest static targets, calculate the coordinate information of the mobile charging robot by the trilateral measurement principle, and realize the positioning of the mobile charging robot. Specifically, sort the distances of all static targets from small to large, take the static target with the smallest distance among the three static targets, take the distances of the three smallest static targets as the radius, and take the center of the static target as the center of the circle to obtain three circles, calculate the intersection of the three circles by the trilateral measurement principle, and the intersection is the coordinate information of the mobile charging robot.

[0058] To sum up, the present invention provides a mobile charging robot positioning method for an underground parking lot, which avoids the problem of inaccurate positioning or delayed positioning of the mobile charging robot. A local map and first semantic information contained in the local map are obtained through coarse positioning, and second semantic information is assigned by fitting through real-time acquisition of point cloud data. The first semantic information is matched with the second semantic information, and the distance between the mobile charging robot and the target object in the local map is obtained. The positioning of the mobile charging robot is achieved through triangulation, which effectively improves the accuracy of the positioning of the mobile charging robot.

[0059] Example 2

[0060] The embodiment of the present application also provides a mobile charging robot positioning system for an underground parking lot, the system comprising:

[0061] Camera 20, collecting image information in front of the mobile charging robot;

[0062] Laser radar 21, collecting point cloud data in front of the mobile charging robot;

[0063] A motion sensor 22 for collecting the current position of the mobile charging robot;

[0064] The central processing unit 23 adopts the above positioning method of the mobile charging robot for the underground parking lot.

[0065] The foregoing Figure 1 The various variations and specific examples of the mobile charging robot positioning method for an underground parking lot in Example 1 are also applicable to the mobile charging robot positioning system for an underground parking lot in this embodiment. Through the above detailed description of the mobile charging robot positioning method for an underground parking lot, those skilled in the art can clearly know the implementation method of the mobile charging robot positioning system for an underground parking lot in this embodiment, so for the sake of brevity of the specification, it will not be described in detail here.

[0066] Example 3

[0067] An embodiment of the present application provides a computer device, which includes a processor and a memory, wherein the memory stores at least one instruction or at least one program, and the at least one instruction or the at least one program is loaded and executed by the processor to implement a mobile charging robot positioning method for an underground parking lot as provided in the above method embodiment.

[0068] Figure 3 A schematic diagram of the hardware structure of a device for implementing a method for positioning a mobile charging robot for an underground parking lot provided in an embodiment of the present application is shown. The device may participate in or include the apparatus or system provided in an embodiment of the present application. Figure 3 As shown, the computer device 10 may include one or more processors 1002 (the processor may include but is not limited to a processing device such as a microprocessor MCU or a programmable logic device FPGA), a memory 1004 for storing data, and a transmission device 1006 for communication functions. In addition, it may also include: a display, an input / output interface (I / O interface), a universal serial bus (USB) port (which may be included as one of the ports of the I / O interface), a network interface, a power supply and / or a camera. It can be understood by those skilled in the art that Figure 3 The structure shown is only for illustration and does not limit the structure of the above electronic device. Figure 3 More or fewer components as shown, or with Figure 3 Different configurations are shown.

[0069] It should be noted that the one or more processors and / or other data processing circuits described above may generally be referred to herein as "data processing circuits". The data processing circuits may be embodied in whole or in part as software, hardware, firmware, or any other combination thereof. In addition, the data processing circuit may be a single independent processing module, or may be incorporated in whole or in part into any of the other components in the computer device 10 (or mobile device). As described in the embodiments of the present application, the data processing circuit acts as a processor control (e.g., selection of a variable resistor terminal path connected to an interface).

[0070] The memory 1004 can be used to store software programs and modules of application software, such as a program instruction / data storage device corresponding to a method for positioning a mobile charging robot in an underground parking lot in an embodiment of the present application. The processor executes various functional applications and data processing by running the software programs and modules stored in the memory 1004, that is, implementing the above-mentioned method. The memory 1004 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory 1004 may further include a memory remotely arranged relative to the processor, and these remote memories may be connected to the computer device 10 via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0071] The transmission device 1006 is used to receive or send data via a network. The specific example of the above network may include a wireless network provided by a communication provider of the computer device 10. In one example, the transmission device 1006 includes a network adapter (Network Interface Controller, NIC), which can be connected to other network devices through a base station so as to communicate with the Internet. In one example, the transmission device 1006 can be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0072] The display may be, for example, a touch screen liquid crystal display (LCD) that enables a user to interact with a user interface of the computer device 10 (or mobile device).

[0073] Example 4

[0074] An embodiment of the present application also provides a computer-readable storage medium, which can be set in a server to store at least one instruction or at least one program related to a mobile charging robot positioning method for an underground parking lot in a method embodiment. The at least one instruction or the at least one program is loaded and executed by the processor to implement a mobile charging robot positioning method for an underground parking lot provided in the above method embodiment.

[0075] Optionally, in this embodiment, the storage medium may be located in at least one of the multiple network servers of the computer network. Optionally, in this embodiment, the storage medium may include, but is not limited to, various media that can store program codes, such as a USB flash drive, a read-only memory (ROM), a random access memory (RAM), a mobile hard disk, a magnetic disk, or an optical disk.

[0076] Example 5

[0077] The embodiment of the present invention also provides a computer program product or a computer program, which includes computer instructions stored in a computer-readable storage medium. The processor of the computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device executes a method for positioning a mobile charging robot for an underground parking lot provided in the above various optional embodiments.

[0078] It should be noted that the above-mentioned sequence of the embodiments of the present application is for description only and does not represent the advantages and disadvantages of the embodiments. The above-mentioned specific embodiments of the present application are described. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the embodiments and still achieve the desired results. In addition, the processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0079] Each embodiment in this application is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the device, equipment and storage medium embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0080] A person skilled in the art will understand that all or part of the steps to implement the above embodiments may be accomplished by hardware or by instructing related hardware through a program, and the program may be stored in a computer-readable storage medium, and the above-mentioned storage medium may be a read-only memory, a disk or an optical disk, etc.

[0081] Based on the above ideal embodiments of the present invention, the relevant staff can make various changes and modifications without departing from the technical concept of the present invention through the above description. The technical scope of the present invention is not limited to the contents of the specification, and its technical scope must be determined according to the scope of the claims.

Claims

1. A method for positioning a mobile charging robot in an underground parking lot, characterized in that: The method comprises the following steps: S1, obtaining point cloud data collected by the mobile charging robot, and constructing an underground parking lot map based on the point cloud data; S2, performing semantic extraction on the underground parking lot map to obtain first semantic information, and constructing a semantic map database according to the first semantic information; S3, obtaining the current posture information collected by the mobile charging robot, performing coarse positioning through an adaptive Monte Carlo positioning algorithm, and obtaining a first positioning result; S4, taking the first positioning result as the center and combining a preset distance parameter to obtain a local map from the underground parking lot map; S5, based on the semantic map database, obtaining first semantic information included in the local map; S6, performing clustering recognition on the point cloud data to obtain a clustering result; S7, acquiring image information collected by the mobile charging robot, performing target detection on the image information through a target detection model, and obtaining a dynamic target object; S8, filtering the clustering results based on the dynamic target objects to obtain static targets; S9, acquiring point cloud information of the static target object in real time and performing fitting processing to obtain a fitting shape, and assigning second semantic information based on the fitting shape; S10, matching the first semantic information with the second semantic information to obtain a distance between the mobile charging robot and each static target object in the local map; S11, obtaining the distances of three minimum static targets, calculating the coordinate information of the mobile charging robot by the trilateral measurement principle, and realizing the positioning of the mobile charging robot.

2. The method for positioning a mobile charging robot for an underground parking lot according to claim 1, characterized in that: The first semantic information includes: target object ID, target object name, target object shape and target object location description information; The targets include static targets and dynamic targets.

3. The method for positioning a mobile charging robot for an underground parking lot according to claim 1, characterized in that: The clustering results include large targets and medium targets; The large target is a static target; The intermediate targets include static targets and dynamic targets.

4. The method for positioning a mobile charging robot for an underground parking lot according to claim 1, characterized in that: In the step S9, the shape of the target object and the fitting shape are combined, and the second semantic information is given to the fitting shape, where the second semantic information includes the name of the target object and the shape of the target object.

5. The method for positioning a mobile charging robot for an underground parking lot according to claim 1, characterized in that: In the step S11, the distances of all static targets are sorted from small to large, and the static target with the smallest distance among the three static targets is selected. The distances of the three smallest static targets are used as the radius, and the center of the static target is used as the center of the circle to obtain three circles. The intersection of the three circles is calculated by the trilateral measurement principle, and the intersection is the coordinate information of the mobile charging robot.

6. The method for positioning a mobile charging robot for an underground parking lot according to claim 1, characterized in that: In step S4, the preset distance parameters are that the length of the local map is 5 to 20 meters, and the width is 5 to 20 meters.

7. A mobile charging robot positioning system for an underground parking lot, characterized in that: The system comprises: A camera collects image information in front of the mobile charging robot; LiDAR, which collects point cloud data in front of the mobile charging robot; Motion sensor, collecting the current position of the mobile charging robot; A central processing unit, wherein the central processing unit adopts the mobile charging robot positioning method for an underground parking lot as described in any one of claims 1 to 6.

8. A computer device, characterized in that: include: processor; A memory for storing executable instructions; The processor is used to read the executable instructions from the memory and execute the executable instructions to implement the mobile charging robot positioning method for an underground parking lot as described in any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the processor implements the mobile charging robot positioning method for an underground parking lot according to any one of claims 1 to 6.

Images