Mobile robot repositioning method, apparatus, and mobile robot

Abstract

The application relates to the technical field of robots, and discloses a mobile robot repositioning method and device and a mobile robot. The method comprises the following steps: when it is detected that positioning information is lost, the mobile robot enters a local map exploration mode; in the local map exploration mode, local path planning and navigation are performed, and it is identified whether there is an indication mark; when the indication mark is identified, relative navigation is performed according to the pose information of the indication mark until text information in the indication mark is identified through a text recognition technology; and the mobile robot is repositioned by using the pose information and the text information of the indication mark and combining a global map. The method can realize repositioning of the mobile robot in a scene with few structural features, and can effectively solve the repositioning problem of low-cost robots in the case that the performance or hardware of the robots is limited.

Description

Technical Field

[0001] This application relates to the field of robotics technology, and in particular to a method, apparatus and mobile robot relocation method for mobile robots. Background Technology

[0002] With the development of intelligent robots, mobile robots are increasingly used in places like hospitals and office buildings to automatically deliver items of various sizes, providing great convenience. However, in scenarios with repetitive layouts and a lack of unique features—for example, finding a specific room or office in a corridor with similar room layouts—low-cost mobile robots, which rely solely on single-line LiDAR, odometry, and global grid maps for global positioning, are prone to losing their own location information. In practical applications, once positioning is lost, repositioning is often difficult, leading to task interruption and inability to continue. Summary of the Invention

[0003] In view of this, embodiments of this application provide a mobile robot relocation method, apparatus, and mobile robot, which can solve the problem of robot positioning loss and difficulty in relocation during movement.

[0004] In a first aspect, embodiments of this application provide a mobile robot relocation method, including:

[0005] When the loss of location information is detected, the mobile robot enters a local map exploration mode;

[0006] In the local map exploration mode, local path planning and navigation are performed, and local path images are acquired in real time to identify whether there are any indicator signs in the local path images;

[0007] When the indicator is detected, relative navigation is performed using the pose information of the indicator, so that the mobile robot gradually approaches the indicator until the text information in the indicator is recognized by the text recognition technology, and the relative navigation stops.

[0008] The positional information of the indicated marker, the text information, and the global map are used to determine the current position of the mobile robot in the global map.

[0009] In some embodiments, the local path planning and navigation includes:

[0010] The point cloud data at the current moment is collected in real time by the lidar device installed on the mobile robot in order to construct a local map in the robot coordinate system.

[0011] The local map is analyzed for grid vacancy or occupancy status to identify all vacant areas. Navigation target points are selected from vacant areas that meet the conditions, local path planning is performed, and then movement and exploration are carried out according to the generated local path.

[0012] In some embodiments, selecting a navigation target point from an idle state area that meets certain conditions includes:

[0013] The largest idle area or the idle area exceeding a preset threshold is selected as the target idle area, and the center of the target idle area is selected as the navigation target point for the next moment.

[0014] In some embodiments, selecting a navigation target point from an idle state area that meets certain conditions includes:

[0015] Based on the diameter of the mobile robot, an expansion radius is determined, and a circle is formed by combining the expansion radius with the center of the mobile robot as the center.

[0016] The circle is evenly divided into sectors of a preset size, and the local map is searched using the circle to find the position where the sector is occupied by the most idle areas. This position is then used as the navigation target point for the next moment.

[0017] In some embodiments, the step of performing relative navigation based on the pose information of the indicator when the indicator is identified includes:

[0018] When the indicator is identified, the indicator pixel region in the local path image is semantically segmented, and the centroid and depth information of the indicator pixel region are extracted, and the normal vector of the indicator is calculated.

[0019] Using the angle between the centroid and the normal vector, the pose information of the indicator in the camera coordinate system of the mobile robot is obtained, and the pose information in the camera coordinate system is mapped to the robot coordinate system to obtain the pose information of the indicator in the robot coordinate system.

[0020] Set the pose information in the robot coordinate system as the relative target point and begin relative navigation.

[0021] In some embodiments, determining the current position of the mobile robot in the global map by utilizing the pose information of the indicator, the text information, and combining them with the global map includes:

[0022] Based on the text information of the indicator, the global position of the indicator in the pre-built global map is queried, and coordinate mapping is performed by combining the pose information of the indicator in the robot coordinate system to obtain the current position of the mobile robot in the global map.

[0023] In some embodiments, the mobile robot relocation method further includes:

[0024] After re-acquiring its position on the global map, the system switches from the local map exploration mode to the global map navigation mode to continue executing the current task.

[0025] Secondly, embodiments of this application provide a mobile robot repositioning device, comprising:

[0026] The mode switching module is used to enable the mobile robot to enter a local map exploration mode when the loss of positioning information is detected.

[0027] The local exploration module is used to perform local path planning and navigation in the local map exploration mode, and to collect local path images in real time to identify whether there are indicator marks in the local path images.

[0028] The relative navigation module is used to perform relative navigation based on the pose information of the indicator when the indicator is detected, so that the mobile robot gradually approaches the indicator until the text information in the indicator is recognized by the text recognition technology, and the relative navigation stops.

[0029] The global positioning module is used to obtain the current position of the mobile robot in the global map by using the pose information of the indicator, the text information and combining them with the global map.

[0030] Thirdly, embodiments of this application provide a mobile robot, which includes a processor and a memory. The memory stores a computer program, and the processor executes the computer program to implement the above-described mobile robot relocation method.

[0031] Fourthly, embodiments of this application provide a readable storage medium storing a computer program, which, when executed on a processor, implements the aforementioned mobile robot relocation method.

[0032] The embodiments of this application have the following beneficial effects:

[0033] The mobile robot relocalization method of this application enters a local map exploration mode when local map information loss is detected. In this mode, local path planning and navigation are performed, and the presence of markers is identified. Upon identification of a marker, relative navigation is performed based on its pose information until the text information within the marker is recognized using text recognition technology. Finally, global relocalization is performed using the marker's pose information, text information, and the global map. This method, by utilizing free exploration of the local map and combining it with image recognition technology for marker identification, and then performing relative navigation to identify the marker's text, can achieve robot relocalization in scenarios with limited structural features. It is particularly effective for low-cost robots facing performance or hardware limitations in their relocalization challenges. Attached Figure Description

[0034] To more clearly illustrate the technical solutions of the embodiments of this application, the accompanying drawings used in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of this application and should not be regarded as a limitation of the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0035] Figure 1 A flowchart of a mobile robot relocation method according to an embodiment of this application is shown;

[0036] Figure 2 A flowchart of the local path exploration in the mobile robot relocalization method according to an embodiment of this application is shown;

[0037] Figure 3 This illustration shows a first schematic diagram of the target free area selection method of the mobile robot relocation method according to an embodiment of this application;

[0038] Figure 4 This illustration shows a second schematic diagram of the target free area selection method for the mobile robot relocation method according to an embodiment of this application;

[0039] Figure 5 A flowchart of the relative navigation method for mobile robot relocalization according to an embodiment of this application is shown;

[0040] Figure 6 This paper shows a schematic diagram of a mobile robot repositioning device according to an embodiment of the present application;

[0041] Figure 7 A schematic diagram of a mobile robot according to an embodiment of this application is shown. Detailed Implementation

[0042] The technical solutions in the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments.

[0043] The components of the embodiments of this application described and illustrated in the accompanying drawings can be arranged and designed in a variety of different configurations. Therefore, the following detailed description of the embodiments of this application provided in the drawings is not intended to limit the scope of the claimed application, but merely to illustrate selected embodiments of the application. All other embodiments obtained by those skilled in the art based on the embodiments of this application without inventive effort are within the scope of protection of this application.

[0044] In the following text, the terms "comprising," "having," and their cognates, which may be used in various embodiments of this application, are intended only to indicate a particular feature, number, step, operation, element, component, or combination thereof, and should not be construed as primarily excluding the presence of one or more other features, numbers, steps, operations, elements, components, or combinations thereof, or adding the possibility of one or more combinations thereof. Furthermore, the terms "first," "second," "third," etc., are used only for distinguishing descriptions and should not be construed as indicating or implying relative importance.

[0045] Unless otherwise specified, all terms used herein (including technical and scientific terms) shall have the same meaning as commonly understood by one of ordinary skill in the art to which the various embodiments of this application pertain. Terms (such as those defined in commonly used dictionaries) shall be interpreted as having the same meaning as in their contextual meaning in the relevant technical field and shall not be construed as having an idealized or overly formal meaning, unless clearly defined in the various embodiments of this application.

[0046] The following detailed description of some embodiments of this application is provided in conjunction with the accompanying drawings. Unless otherwise specified, the following embodiments and features can be combined with each other.

[0047] In scenarios with repetitive structures and a lack of distinctive features, some low-cost mobile robots are prone to losing localization information and becoming unable to relocate. This loss of localization information refers to the mobile robot's inability to determine its position on the global map. This could be due to lost odometry data or the presence of too many similar structural features in the environment, leading to feature extraction failures or recognition errors. Once localization information is lost, the robot cannot use the global map for localization and navigation, thus halting its mission.

[0048] To avoid interrupting robot task execution, a novel relocalization method is proposed. Based on the existing hardware structure of the mobile robot, such as a single-line LiDAR, odometry, and camera, it combines local map exploration, semantic recognition, and text recognition technologies to establish a connection between effective textual information and the global map, thereby completing the relocalization. The following specific embodiments illustrate this mobile robot relocalization method.

[0049] Figure 1 A flowchart of a mobile robot relocalization method according to an embodiment of this application is shown. Exemplarily, the mobile robot relocalization method includes the following steps:

[0050] S110: When the loss of positioning information is detected, the mobile robot enters a local map exploration mode.

[0051] The local map exploration mode is a navigation mode implemented in this mobile robot. In this mode, a local path is planned based on the robot's real-time constructed local map information, starting from the robot's current position. This local path is generally short, for example, moving 1-2 meters at a time, but it can be shorter or longer depending on the specific situation. Essentially, during local path navigation, the mobile robot moves while simultaneously exploring its next destination. In contrast, the global map navigation mode allows the mobile robot to continuously acquire its position on the global map while performing tasks, and then moves towards the target location on the global map. The global map is represented in a world coordinate system.

[0052] As an example, the mobile robot defaults to global map navigation mode for global path planning and navigation. During movement, it can collect point cloud data in real time using LiDAR to construct a local map and use odometry to calculate the robot's travel distance. Combined with the global map, this determines the robot's position information within the global map. However, if the robot loses its positioning information for some reason, it will automatically switch from global map navigation mode to local map exploration mode and begin obstacle avoidance and local path planning based on the local map.

[0053] S120 performs local path planning and navigation in local map exploration mode, and collects local path images in real time to identify whether there are any indicator signs in the local path images.

[0054] As an example, in the local map exploration mode, the mobile robot will use the local map for exploration and navigation. By analyzing the idle areas in the local map and selecting navigation target points from them, local path planning can be performed, which can ensure that the generated local path can avoid obstacles along the way.

[0055] In one implementation, such as Figure 2 As shown, the local path planning and navigation in step S120 above may include the following sub-steps:

[0056] S121 uses a lidar device mounted on the mobile robot to collect point cloud data in real time to construct a local map in the robot's coordinate system.

[0057] It is understandable that, since the LiDAR device is mounted on the robot, the local map constructed based on real-time point cloud data is represented in the robot's coordinate system. Furthermore, the environmental information contained in the local map is limited, as it is related to the detection angle of the LiDAR device.

[0058] S122, perform a raster idle or occupied state analysis on the local map to determine all idle areas in the local map.

[0059] In this implementation, a grid map is used to divide the environment into several uniformly sized grids. Each grid is either occupied (indicating the presence of an obstacle) or idle (indicating the absence of an obstacle). In this embodiment, by rasterizing the local map and then determining the state of each grid, all idle areas within the local map are identified. Subsequently, local path planning is performed from these idle areas to ensure that the planned local path avoids obstacles.

[0060] S123, Select a navigation target point from the available area that meets the conditions, perform local path planning, and then move and explore according to the generated local path.

[0061] When performing local path planning, it is necessary to first select the navigation target point. Considering that not all idle areas are necessarily connected, there are usually multiple idle areas, or they can be divided into multiple areas according to a relatively regular shape, in one implementation, the largest idle area among all idle areas (e.g., Figure 3The area S0 shown is designated as the target free area, and the center of this target free area is used as the navigation target point for the next moment. The center can be the exact center of the target free area, or a location within a central area containing the exact center, etc., depending on the requirements; no limitation is made here. Optionally, one of the free areas whose area exceeds a preset threshold can also be designated as the target free area, etc., again without limitation. It can be understood that a free area with the largest area or exceeding the preset threshold indicates that there are few obstacles in that area, allowing the robot to pass smoothly.

[0062] As an alternative solution, considering the robot's width, to avoid collisions with obstacles, for example, in another implementation, when selecting a navigation target point from an idle area, such as... Figure 4 As shown, an expansion radius can be determined based on the diameter of the mobile robot, and a circle can be formed by combining the expansion radius with the center of the mobile robot. Then, the circle is evenly divided according to the preset sector size, and the circle is used to search the local map to find the position where the sector is occupied by the most idle state areas, that is, the sector area overlaps with the idle state area to the maximum extent. Then, the position is used as the navigation target point for the next moment.

[0063] Furthermore, a navigation target point is selected from the target's idle state area, and an optimal local path is generated using a local planner. The planning of the local path is not described in detail here; it can be achieved using some publicly available planning methods, and no specific limitations are imposed.

[0064] In this embodiment, during local map exploration, image recognition will be activated to search for directional markers within the current local path. These directional markers refer to objects that provide location or direction indication during navigation, such as, but not limited to, signs displaying house numbers or indicator lights displaying directions. It is understood that in most scenarios, directional markers are provided to help users find specific rooms or locations. These directional markers are typically pre-recorded in the global map.

[0065] In order to reacquire the robot's position information in the global map, this embodiment will use image recognition technology to search for existing signs, such as signs, on the local path. For example, the mobile robot can use the installed camera device to acquire local path images, and then identify signs in the local path images. For example, the pixel areas in the image that may be signs can be semantically segmented and pixel-level classification can be performed to determine whether the pixel area is a sign.

[0066] If a valid indicator is identified, the segmented pixel region containing the indicator can be further processed to obtain its pose information, thereby initiating a relative navigation task. Conversely, if no valid indicator is identified in the current local map, the search can continue in the next local map until a valid indicator is identified. This semantic segmentation technique can be implemented using existing related networks, which will not be described in detail here.

[0067] S130, when an indicator is detected, uses the positional information of the indicator for relative navigation, so that the mobile robot gradually approaches the indicator until the text information in the indicator is recognized by the text recognition technology, and then stops the relative navigation.

[0068] This relative navigation refers to moving towards a target point, gradually approaching the identified marker. It's understandable that, because the text on the markers is usually small and the robot's height is limited, it needs to get close enough to read the text.

[0069] In one implementation, such as Figure 5 As shown, in step S130 above, relative navigation is performed using the pose information of the indicator, including:

[0070] S131, when an indicator is identified, the indicator pixel region in the local path image is segmented semantically, and the centroid and depth information of the indicator pixel region are extracted, and the normal vector of the indicator is calculated.

[0071] Exemplarily, when using a depth camera for image acquisition, the depth information of the indicator pixel region can be extracted. The centroid of this indicator pixel region can be calculated, for example, using image moments. In one implementation, the indicator pixel region image can be converted into a binary image. The number of pixels with a value greater than zero in the binary image is taken as the area of ​​the binary image. Then, the corresponding coordinates are multiplied by the value of each pixel, and the sum is calculated. The ratio of this sum to the sum of all pixel values ​​is the location of the centroid. Of course, the location of the centroid can also be obtained in other ways; this is just one example.

[0072] Furthermore, based on the depth information of each pixel in the indicator pixel area, a group of these pixels can be selected to form a plane as the plane of the indicator. When selecting, it is necessary to ensure that the distance from this group of pixels to the plane is minimized.

[0073] S132, using the angle between the centroid and the normal vector, obtain the pose information of the indicator in the camera coordinate system of the mobile robot, and map the pose information in the camera coordinate system to the robot coordinate system to obtain the pose information of the indicator in the robot coordinate system.

[0074] The pose includes the position and orientation information of the mobile robot. Specifically, the position of the mobile robot can be determined by the centroid of the indicator pixel region, and the orientation can be obtained using the angle between the centroid and the normal vector. It can be understood that the above solution yields the pose of the indicator in the camera coordinate system. Then, through coordinate system transformation, i.e., using the transformation matrix between the camera coordinate system and the robot coordinate system, the pose information in the camera coordinate system can be mapped to the robot coordinate system.

[0075] If described by an expression, then: in, This indicates the pose of the indicator in the robot coordinate system r. This indicates the pose of the indicator in camera coordinate system c. This is the transformation matrix between the camera coordinate system and the robot coordinate system.

[0076] S133 sets the robot's pose information in the robot's coordinate system as a relative target point for relative navigation.

[0077] It is understandable that by unifying the indications and markings to the robot coordinate system, and since the local map is also represented in the robot coordinate system, relative navigation becomes easier.

[0078] As an example, a path to the sign can be planned again using the local planner. During the relative navigation process, the mobile robot will gradually approach the sign and activate text recognition functions, such as OCR (Optical Character Recognition). In this way, the mobile robot can continuously recognize the text information on the sign, such as a house number, until the specific text is recognized, at which point the current relative navigation task can be stopped.

[0079] S140: Using the pose information and text information of the indicator and combining them with the global map, the current position of the mobile robot in the global map is obtained.

[0080] As an example, the global position of the indicator in a pre-built global map can be queried based on the text information on the indicator. This position is then combined with the indicator's pose information in the robot's coordinate system to perform coordinate mapping, thus obtaining the current position of the mobile robot in the global map and completing the relocalization. It can be understood that this coordinate mapping mainly involves the transformation between the robot's coordinate system and the world coordinate system.

[0081] As an optional solution, this mobile robot relocalization method also includes:

[0082] After regaining its position on the global map, it switches from local map exploration mode to global map navigation mode to continue executing the current task.

[0083] It is understandable that if the robot's position information in the global map is regained, it can switch to global localization, which can reduce the time spent exploring local paths and thus improve the efficiency of task execution.

[0084] The mobile robot relocalization method of this application enters a local map exploration mode when location information loss is detected. In this mode, a local map is explored, and existing markers are identified during the exploration process for relative navigation to these markers, until the text information in the markers is recognized using technologies such as OCR. Finally, global relocalization is performed using the pose information and text information of the markers in conjunction with the global map. Since relocalization does not rely excessively on structural features, it can achieve robot relocalization in scenarios with limited structural features. This is particularly beneficial for low-cost robots, effectively solving relocalization problems under performance or hardware constraints.

[0085] Figure 6 A schematic diagram of a mobile robot relocation device according to an embodiment of this application is shown. Exemplarily, the mobile robot relocation device includes:

[0086] The mode switching module 110 is used to enable the mobile robot to enter a local map exploration mode when the loss of positioning information is detected.

[0087] The local exploration module 120 is used to perform local path planning and navigation in local map exploration mode, and to collect local path images in real time to identify whether there are indicator signs in the local path images.

[0088] The relative navigation module 130 is used to perform relative navigation based on the pose information of the indicator when the indicator is detected, so that the mobile robot gradually approaches the indicator until the text information in the indicator is recognized by the text recognition technology and the relative navigation stops.

[0089] The global positioning module 140 is used to determine the current position of the mobile robot in the global map by using the pose information and text information of the indicator and combining them with the global map.

[0090] It is understood that the device in this embodiment corresponds to the mobile robot relocation method in the above embodiments, and the options in the above embodiments are also applicable to this embodiment, so they will not be described again here.

[0091] This application also provides a mobile robot, which may be a wheeled robot or a legged robot, and its form is not limited. It can be applied to various scenarios, especially in some situations where the structure is repetitive and there are no unique features, such as office buildings and hospitals with similar decoration styles.

[0092] Exemplary, such as Figure 7 As shown, the mobile robot includes a processor 11, a memory 12, and a sensing unit 13. For example, the sensing unit 13 may include, but is not limited to, basic hardware such as a camera, a lidar device, and an odometer. In this application, the camera can be used to collect environmental image information during the robot's movement for image recognition, etc.; the lidar device can be used to collect spatial point cloud information during movement for map building, point cloud imaging, etc.; the odometer can be used to measure the distance the robot has traveled, etc. Of course, in other scenarios, these sensing units 13 may also have other functions, which are not limited here. The memory 12 stores a computer program, and the processor 11 runs the computer program to enable the mobile robot to perform the functions of the various modules in the aforementioned mobile robot relocation method or mobile robot relocation device.

[0093] The processor 11 can be an integrated circuit chip with signal processing capabilities. The processor can be a general-purpose processor, including at least one of a Central Processing Unit (CPU), Graphics Processing Unit (GPU), Network Processor (NP), Digital Signal Processor (DSP), Application-Specific Integrated Circuit (ASIC), Field-Programmable Gate Array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. The general-purpose processor can be a microprocessor or any conventional processor, capable of implementing or executing the methods, steps, and logic block diagrams disclosed in the embodiments of this application.

[0094] The memory 12 may be, but is not limited to, Random Access Memory (RAM), Read Only Memory (ROM), Programmable Read-Only Memory (PROM), Erasable Programmable Read-Only Memory (EPROM), Electrically Erasable Programmable Read-Only Memory (EEPROM), etc. The memory stores computer programs, and the processor can execute these programs upon receiving execution instructions.

[0095] This application also provides a readable storage medium for storing the computer program used in the mobile robot described above. When the computer program is executed on a processor, it implements the mobile robot relocalization method of the above embodiments. The method includes: when the loss of positioning information is detected, the mobile robot enters a local map exploration mode; in the local map exploration mode, it performs local path planning and navigation, and collects local path images in real time to identify whether there are any indicator marks in the local path images; when an indicator mark is identified, it performs relative navigation based on the pose information of the indicator mark, so that the mobile robot gradually approaches the indicator mark until the text information in the indicator mark is recognized by text recognition technology, and then stops the relative navigation; using the pose information and text information of the indicator mark and combining them with the global map, it determines the current position of the mobile robot in the global map.

[0096] It is understood that the optional methods for mobile robot relocation described in the above embodiments are also applicable to this embodiment, and therefore will not be described again here.

[0097] In the several embodiments provided in this application, it should be understood that the disclosed apparatus and methods can also be implemented in other ways. The apparatus embodiments described above are merely illustrative. For example, the flowcharts and block diagrams in the accompanying drawings show the architecture, functionality, and operation of possible implementations of apparatus, methods, and computer program products according to various embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that, in alternative implementations, the functions marked in the blocks may occur in a different order than those marked in the drawings. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagram and / or flowchart, and combinations of blocks in the block diagram and / or flowchart, can be implemented using a dedicated hardware-based system that performs the specified function or action, or using a combination of dedicated hardware and computer instructions.

[0098] In addition, the functional modules or units in the various embodiments of this application can be integrated together to form an independent part, or each module can exist independently, or two or more modules can be integrated to form an independent part.

[0099] If the aforementioned functions are implemented as software functional modules and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium, including several instructions to cause a computer device (which may be a smartphone, personal computer, server, or network device, etc.) to execute all or part of the methods described in the various embodiments of this application. Various media capable of storing program code, such as magnetic disks or optical disks, can also be used.

[0100] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any changes or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application.

Claims

1. A mobile robot relocalization method, characterized in that, include: When the loss of location information is detected, the mobile robot enters a local map exploration mode; In the local map exploration mode, local path planning and navigation are performed, and local path images are acquired in real time to identify whether there are any indicator signs in the local path images; When the indicator is detected, relative navigation is performed using the pose information of the indicator, so that the mobile robot gradually approaches the indicator until the text information in the indicator is recognized by the text recognition technology, and the relative navigation stops. The positional information and text information of the indicated markers are used in conjunction with the global map to determine the current position of the mobile robot in the global map; Wherein, the step of performing relative navigation based on the pose information of the indicator when the indicator is identified includes: Upon identification of the indicator, the pixel region of the indicator in the local path image is semantically segmented, and the centroid and depth information of the pixel region of the indicator are extracted, as well as the normal vector of the indicator is calculated. Using the angle between the centroid and the normal vector, the pose information of the indicator in the camera coordinate system of the mobile robot is obtained, and the pose information in the camera coordinate system is mapped to the robot coordinate system to obtain the pose information of the indicator in the robot coordinate system. The pose information in the robot coordinate system is set as the relative target point, and relative navigation begins.

2. The mobile robot relocation method according to claim 1, characterized in that, The local path planning and navigation includes: The point cloud data at the current moment is collected in real time by the lidar device installed on the mobile robot in order to construct a local map in the robot coordinate system. The local map is analyzed for grid vacancy or occupancy status to identify all vacant areas. Navigation target points are selected from vacant areas that meet the conditions, local path planning is performed, and then movement and exploration are carried out according to the generated local path.

3. The mobile robot relocation method according to claim 2, characterized in that, The step of selecting a navigation target point from an idle area that meets certain conditions includes: The largest idle area or the idle area exceeding a preset threshold is selected as the target idle area, and the center of the target idle area is selected as the navigation target point for the next moment.

4. The mobile robot relocation method according to claim 2, characterized in that, The step of selecting a navigation target point from an idle area that meets certain conditions includes: Based on the diameter of the mobile robot, an expansion radius is determined, and a circle is formed by combining the expansion radius with the center of the mobile robot as the center. The circle is evenly divided into sectors of a preset size, and the local map is searched using the circle to find the position where the sector is occupied by the most idle areas. This position is then used as the navigation target point for the next moment.

5. The mobile robot relocation method according to claim 1, characterized in that, The step of determining the current position of the mobile robot in the global map by using the pose information of the indicator, the text information, and combining them with the global map includes: Based on the text information of the indicator, the global position of the indicator in the pre-built global map is queried, and coordinate mapping is performed by combining the pose information of the indicator in the robot coordinate system to obtain the current position of the mobile robot in the global map.

6. The mobile robot relocation method according to any one of claims 1 to 5, characterized in that, Also includes: After re-acquiring its position on the global map, the system switches from the local map exploration mode to the global map navigation mode to continue executing the current task.

7. A mobile robot repositioning device, characterized in that, include: The mode switching module is used to enable the mobile robot to enter a local map exploration mode when the loss of positioning information is detected. The local exploration module is used to perform local path planning and navigation in the local map exploration mode, and to collect local path images in real time to identify whether there are indicator marks in the local path images. The relative navigation module is used to perform relative navigation based on the pose information of the indicator when the indicator is detected, so that the mobile robot gradually approaches the indicator until the text information in the indicator is recognized by the text recognition technology, and the relative navigation stops. A global positioning module is used to obtain the current position of the mobile robot in the global map by using the pose information of the indicator, the text information and combining them with the global map; The relative navigation module is configured to perform relative navigation based on the pose information of the indicator when the indicator is detected, including: Upon identification of the indicator, the pixel region of the indicator in the local path image is semantically segmented, and the centroid and depth information of the pixel region of the indicator are extracted, as well as the normal vector of the indicator is calculated. Using the angle between the centroid and the normal vector, the pose information of the indicator in the camera coordinate system of the mobile robot is obtained, and the pose information in the camera coordinate system is mapped to the robot coordinate system to obtain the pose information of the indicator in the robot coordinate system. The pose information in the robot coordinate system is set as the relative target point, and relative navigation begins.

8. A mobile robot, characterized in that, The mobile robot includes a processor and a memory, the memory storing a computer program, and the processor executing the computer program to implement the mobile robot relocation method according to any one of claims 1-6.

9. A readable storage medium, characterized in that, It stores a computer program that, when executed on a processor, implements the mobile robot relocation method according to any one of claims 1-6.

Images