Positioning loss detection method, apparatus, self-moving device, and computer program product

Abstract

The application is suitable for the positioning field, and provides a positioning loss detection method, device, self-moving device and computer program product. The positioning loss detection method comprises: dividing a three-dimensional space region where a self-moving device is located into a plurality of point cloud partitions; acquiring a matching score of each point cloud partition, the matching score representing a distance between each point cloud in the point cloud partition and a nearest neighbor point in an electronic map; comparing a number of target partitions with a number threshold, and determining a positioning loss detection result of the self-moving device based on a comparison result, the target partition being a point cloud partition with a matching score greater than a first score threshold, wherein when the number of target partitions is less than the number threshold, the positioning loss detection result is that no positioning loss has occurred. The embodiment of the application can reduce the occurrence of false positioning loss in the actual scene that is greatly changed from the electronic map.

Description

Technical Field

[0001] This application belongs to the field of positioning technology, and in particular relates to a positioning loss detection method, device, self-moving device, and computer program product. Background Technology

[0002] Location loss of a self-moving device refers to the inability of the device to accurately determine its location information during operation, thus preventing it from performing its tasks normally. Related technologies compare the point cloud data collected by the self-moving device with electronic maps to detect location loss. However, in real-world scenarios that differ significantly from electronic maps, false location loss reports are prone to occur, affecting the normal operation of the self-moving device. Summary of the Invention

[0003] This application provides a location loss detection method, device, self-moving device, and computer program product, which can reduce the occurrence of location loss misjudgment problems when the actual scene changes too much from the electronic map.

[0004] The first aspect of this application provides a location loss detection method, comprising: dividing a three-dimensional spatial region where a self-moving device is located into multiple point cloud partitions; obtaining a matching score for each point cloud partition, wherein the matching score represents the distance between each point cloud in the point cloud partition and the nearest neighbor point in an electronic map; comparing the number of target partitions with a number threshold, and determining the location loss detection result of the self-moving device based on the comparison result, wherein the target partitions are point cloud partitions whose matching scores are greater than a first score threshold, wherein when the number of target partitions is less than the number threshold, the location loss detection result is that no location loss has occurred.

[0005] In some embodiments of this application, dividing the three-dimensional spatial region where the self-moving device is located into multiple point cloud partitions includes: dividing the three-dimensional spatial region into multiple comparison partitions along a preset direction, each comparison partition corresponding to a number threshold; dividing each comparison partition into multiple fan-shaped regions along the central axis of the self-moving device in the preset direction, each fan-shaped region being used as a point cloud partition, wherein the number of target partitions in each comparison partition is greater than the corresponding number threshold, and the global matching score of the three-dimensional spatial region is greater than a second score threshold, the positioning loss detection result is that positioning loss has occurred.

[0006] In some embodiments of this application, the plurality of first zones include ground areas and air areas, the ground areas are at a lower height from the ground than the air areas, and the number threshold of the ground areas is less than the number threshold of the air areas.

[0007] In some embodiments of this application, the step of obtaining the matching score of each point cloud partition, comparing the number of target partitions with a number threshold, and determining the location loss detection result of the self-mobile device based on the comparison result includes: obtaining the matching score of each point cloud partition in the ground area and the global matching score; in response to the number of target partitions in the ground area being less than or equal to the number threshold, or the global matching score being less than or equal to a second score threshold, confirming that the location loss detection result is that no location loss has occurred; in response to the number of target partitions in the ground area being greater than the number threshold and the global matching score being greater than the second score threshold, obtaining the matching score of each point cloud partition in the air area; in response to the number of target partitions in the air area being greater than the number threshold, confirming that the location loss detection result is that location loss has occurred; in response to the number of target partitions in the air area being less than or equal to the number threshold, confirming that the location loss detection result is that no location loss has occurred.

[0008] In some embodiments of this application, obtaining the matching score of each point cloud partition includes: determining the nearest neighbor of each point cloud within the point cloud partition in the electronic map; calculating the distance between each point cloud and its nearest neighbor; and determining the matching score of each point cloud partition based on the distance.

[0009] In some embodiments of this application, after determining the matching score of each point cloud partition based on the distance, the method further includes: determining the degree of change of each point cloud partition; determining the correction weight of each point cloud partition based on the degree of change; and adjusting the matching score of each point cloud partition based on the correction weight of each point cloud partition.

[0010] In some embodiments of this application, determining the nearest neighbor of each point cloud within a point cloud partition in the electronic map includes: converting the point cloud collected by the mobile device to the world coordinate system through the current pose; and matching the nearest neighbor in the electronic map based on the coordinates of each point cloud in the world coordinate system to obtain the nearest neighbor of each point cloud.

[0011] A location loss detection device provided in the second aspect of this application includes: a partitioning unit for dividing a three-dimensional spatial region where a self-moving device is located into multiple point cloud partitions; a score acquisition unit for acquiring a matching score for each point cloud partition, wherein the matching score represents the distance between each point cloud in the point cloud partition and the nearest neighbor point in an electronic map; and a location loss detection unit for comparing the number of target partitions with a number threshold, and determining the location loss detection result of the self-moving device based on the comparison result, wherein the target partitions are point cloud partitions whose matching scores are greater than a first score threshold, and wherein when the number of target partitions is less than the number threshold, the location loss detection result is that no location loss has occurred.

[0012] A third aspect of this application provides a self-moving device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the above-described location loss detection method.

[0013] A fourth aspect of this application provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps of the above-described location loss detection method.

[0014] The fifth aspect of this application provides a computer program product that, when the computer program is run, causes the above-described location loss detection method to be executed.

[0015] In the embodiments of this application, the three-dimensional spatial region where the self-moving device is located is divided into multiple point cloud partitions, and the matching score of each point cloud partition is obtained. The number of target partitions is compared with a number threshold, and the positioning loss detection result of the self-moving device is determined based on the comparison result. The target partition is a point cloud partition with a matching score greater than a first score threshold. The matching score represents the distance between each point cloud in the point cloud partition and the nearest neighbor point in the electronic map. When the number of target partitions is less than the number threshold, the positioning loss detection result is that no positioning loss has occurred. Therefore, compared with requiring all point clouds to match the electronic map, allowing differences between the point clouds of some point cloud partitions and the point clouds of the electronic map helps to reduce the occurrence of positioning loss misjudgment problems when the actual scene changes too much from the electronic map. Attached Figure Description

[0016] To more clearly illustrate the technical solutions in the embodiments of this application, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0017] Figure 1 This is a schematic diagram illustrating the implementation process of a location loss detection method provided in an embodiment of this application;

[0018] Figure 2 This is a schematic diagram illustrating the specific implementation process of dividing point cloud into partitions provided in the embodiments of this application;

[0019] Figure 3 This is a schematic diagram of the partitioning of a three-dimensional spatial region provided in an embodiment of this application;

[0020] Figure 4This is a schematic diagram of the structure of a location loss detection device provided in an embodiment of this application;

[0021] Figure 5 This is a schematic diagram of the structure of the self-moving device provided in the embodiments of this application. Detailed Implementation

[0022] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application. All other embodiments obtained by those skilled in the art based on the embodiments of this application without inventive effort are protected by this application.

[0023] Location loss of a self-moving device refers to the inability of the device to accurately determine its location information during operation, thus preventing it from performing its tasks normally. Related technologies compare the point cloud data collected by the self-moving device with electronic maps to detect location loss. However, in real-world scenarios that differ significantly from electronic maps, false location loss reports are prone to occur, affecting the normal operation of the self-moving device.

[0024] In view of this, this application proposes a location loss detection method, which can reduce the occurrence of location loss misjudgment problems when the actual scene changes too much compared to the electronic map.

[0025] To illustrate the technical solution of this application, specific embodiments are described below.

[0026] Figure 1 This illustration shows a schematic flowchart of a location loss detection method provided in an embodiment of this application. This method can be applied to self-moving devices. The aforementioned self-moving device refers to a device with autonomous mobility capabilities, and can be a self-moving device, a smart car, a drone, etc., which are not limited in this application.

[0027] In the embodiments of this application, the aforementioned self-moving device may be equipped with a lidar, which can be used to perform point cloud scanning on the three-dimensional spatial region where the self-moving device is located.

[0028] Specifically, the above-mentioned location loss detection method may include the following steps S101 to S103.

[0029] Step S101: Divide the three-dimensional space region where the self-moving device is located into multiple point cloud partitions.

[0030] The three-dimensional spatial region where the self-moving device is located refers to the physical spatial region where the self-moving device is located, specifically the scanning coverage area of ​​the self-moving device's LiDAR, which is typically a spatial region within a preset distance range centered on the self-moving device. In the embodiments of this application, multiple point cloud partitions can be obtained by dividing the three-dimensional spatial region.

[0031] It should be noted that this application does not impose any restrictions on the way point cloud partitions are divided.

[0032] Step S102: Obtain the matching score for each point cloud partition.

[0033] Among them, the matching score of the point cloud partition can represent the distance between each point cloud in the point cloud partition and the nearest neighbor point in the electronic map.

[0034] Specifically, the electronic map can be obtained through prior environmental scanning or acquired from external sources, and this application does not impose any restrictions on this. The electronic map may record point cloud information at the time of scanning. For each point cloud currently scanned by the mobile device within a point cloud partition, the distance between the point cloud and its nearest neighbor in the electronic map can be calculated to obtain a matching score for the point cloud partition based on the distance.

[0035] Step S103: Compare the number of target partitions with the number threshold, and determine the location loss detection result of the self-moving device based on the comparison result.

[0036] The target partition is a point cloud partition whose matching score is greater than a first score threshold. A matching score greater than the first score threshold indicates that the distance between the point cloud within the point cloud partition and its nearest neighbor in the electronic map is too large.

[0037] It is understandable that when the actual scene differs significantly from the electronic map, the point cloud information recorded in the electronic map may deviate from reality. For example, after scanning to obtain the electronic map, if buildings are modified or construction obstacles are installed in the 3D space, the actual scene changes, while the electronic map still records the point cloud information before the change. In this case, the nearest neighbor points of the point cloud within a point cloud partition on the electronic map may have changed compared to the actual scene. If all point clouds are required to match the electronic map, misjudgments due to positioning loss will occur.

[0038] In the embodiments of this application, point cloud partitions with matching scores greater than a first score threshold can be detected and designated as target partitions. When the number of target partitions is less than a number threshold, the location loss detection result is that no location loss has occurred.

[0039] In other words, even if a small number of point cloud partitions differ from the point cloud on the electronic map, but the majority of point cloud partitions match the electronic map, it can still be confirmed that the mobile device has not lost its location. These target partitions that differ from the point cloud on the electronic map represent areas where the actual scene has changed compared to the electronic map.

[0040] It should be understood that the first score threshold and the number threshold can be set according to the actual situation, and can be either fixed values ​​or dynamically changing values. This application does not impose any restrictions on this.

[0041] In the embodiments of this application, the three-dimensional spatial region where the self-moving device is located is divided into multiple point cloud partitions, and the matching score of each point cloud partition is obtained. The number of target partitions is compared with a number threshold, and the positioning loss detection result of the self-moving device is determined based on the comparison result. The target partition is a point cloud partition with a matching score greater than a first score threshold. The matching score represents the distance between each point cloud in the point cloud partition and the nearest neighbor point in the electronic map. When the number of target partitions is less than the number threshold, the positioning loss detection result is that no positioning loss has occurred. Therefore, compared with requiring all point clouds to match the electronic map, allowing differences between the point clouds of some point cloud partitions and the point clouds of the electronic map helps to reduce the occurrence of positioning loss misjudgment problems when the actual scene changes too much from the electronic map.

[0042] In some embodiments of this application, dividing the three-dimensional spatial region where the self-moving device is located into multiple point cloud partitions may include steps S201 to S202.

[0043] Step S201: Divide the three-dimensional spatial region into multiple comparison partitions along a preset direction.

[0044] Each alignment partition can be used independently to locate missing data.

[0045] Because point clouds have certain distribution characteristics in real-world scenarios, dividing the 3D spatial region into multiple comparison partitions along a preset direction allows for location loss detection within each partition. Furthermore, each comparison partition corresponds to a specific threshold. Thus, comparison partitions with different distribution patterns can use appropriately matched thresholds for location loss detection, helping to reduce false positives for bit loss.

[0046] The preset direction is the direction in which the point cloud has different distributions, such as the vertical direction of the ground or the Z-axis direction of the radar coordinate system.

[0047] In some embodiments of this application, multiple first zones may include ground areas and air areas, with the ground areas having a lower ground clearance than the air areas. Furthermore, the threshold for the number of ground areas is less than the threshold for the number of air areas. The z-coordinate values ​​for specifically dividing the ground and air areas are empirical values.

[0048] Because point clouds near the ground are abundant and feature-rich, most point cloud partitions in the ground region are less affected by changes in the actual scene. Specifically, in the point cloud partitions of the ground region, the number of point clouds that have not undergone scene changes is large, which can maintain the reasonableness of the matching scores of the point cloud partitions in the ground region. Based on this, a smaller threshold number can be set for judgment. However, the number of point clouds and features in the air region are small, and matching scores are prone to abnormalities when the actual scene changes. By setting a larger threshold number for judgment, the occurrence of bit loss misjudgment can be reduced.

[0049] Step S202: Divide each comparison partition into multiple sector regions along the central axis of the self-moving device in a preset direction, and treat each sector region as a point cloud partition.

[0050] In other words, each comparison partition can be divided into multiple sector regions along the central axis. Please refer to [reference needed]. Figure 3 For both ground and air regions, multiple sector regions are divided around the xy coordinate of 0. The center point of the cross-section of each sector region on the xoy plane is located on the z-axis of the self-moving device. The specific number of sector regions can be set according to the actual situation, for example, 12. Each sector region is a point cloud partition.

[0051] At this point, when the number of target partitions in each of the comparison partitions is greater than the corresponding number threshold, and the global matching score of the three-dimensional spatial region is greater than the second score threshold, the location loss detection result is that location loss has occurred.

[0052] The global matching score is obtained based on the distance between all point clouds within the three-dimensional spatial region and the nearest neighbor points in the electronic map.

[0053] by Figure 3 Taking the ground and air regions as examples, if the number of target partitions in both the ground and air regions exceeds the corresponding threshold, and the global matching score is greater than the second score threshold, then location loss can be confirmed. The second score threshold can be set according to the actual situation.

[0054] In some embodiments of this application, obtaining the matching score of each point cloud partition, comparing the number of target partitions with a number threshold, and determining the location loss detection result of the self-moving device based on the comparison result may include: obtaining the matching score of each point cloud partition in the ground area and the global matching score. In response to the number of target partitions in the ground area being less than or equal to the number threshold, or the global matching score being less than or equal to a second score threshold, the location loss detection result is confirmed as no location loss has occurred.

[0055] In response to the number of target partitions in the ground region being greater than the number threshold and the global matching score being greater than the second score threshold, the matching score of each point cloud partition in the air region is obtained; in response to the number of target partitions in the air region being greater than the number threshold, the location loss detection result is confirmed as location loss; in response to the number of target partitions in the air region being less than or equal to the number threshold, the location loss detection result is confirmed as no location loss has occurred.

[0056] In other words, localization loss detection can be performed on the ground area and the entire 3D space. If the number of target partitions in the ground area is less than or equal to a threshold, or the global matching score in the 3D space is less than or equal to a second threshold, the localization loss detection result can be confirmed as no localization loss has occurred. If the number of target partitions in the ground area exceeds the threshold, and the global matching score in the 3D space is greater than the second threshold, then localization loss detection is performed on the aerial area. Since the ground area has a large number of point clouds with rich features, whether localization loss has occurred can usually be reflected by the point cloud data of the ground area. Therefore, prioritizing localization loss detection on the ground area can quickly determine if no localization loss has occurred. Furthermore, combining this with the global matching score can further improve the reliability of localization loss detection.

[0057] In some embodiments of this application, obtaining the matching score of each point cloud partition may include: determining the nearest neighbor of each point cloud within the point cloud partition in an electronic map; calculating the distance between each point cloud and its nearest neighbor; and determining the matching score of each point cloud partition based on the distance.

[0058] Specifically, the nearest neighbor can be determined based on information such as the location and features of the point cloud.

[0059] To facilitate the determination of nearest neighbor points, in some embodiments of this application, determining the nearest neighbor points of each point cloud within a point cloud partition in an electronic map may include: converting the point cloud collected by the mobile device to the world coordinate system through the current pose, and matching the nearest neighbor points in the electronic map based on the coordinates of each point cloud in the world coordinate system to obtain the nearest neighbor points of each point cloud.

[0060] In some embodiments of this application, the matching score for each point cloud partition can be the average of the distances corresponding to all point clouds within the partition.

[0061] To reduce the impact of changing regions in the actual scene on location loss detection, in some other embodiments of this application, after determining the matching score of each point cloud partition based on distance, the method may further include: determining the degree of change of each point cloud partition; determining the correction weight of each point cloud partition based on the degree of change; and adjusting the matching score of each point cloud partition based on the correction weight of each point cloud partition.

[0062] Specifically, the degree of change can be determined based on the point cloud information of each point cloud, such as the difference in quantity or feature within point cloud partitions. The magnitude of the correction weight can be negatively correlated with the degree of change; the greater the degree of change, the smaller the correction weight. Multiplying the correction weight by the matching score can reduce the occurrence of abnormal matching scores in point cloud partitions with large degrees of change. In the case of localization loss, the entire point cloud has deviations, and even if the matching score is multiplied by the correction weight, it will exceed the first score threshold, which is unlikely to affect the reliability of localization loss detection.

[0063] Similarly, the calculation method for the global matching score can refer to the calculation method for the matching score of the point cloud partition, which will not be elaborated in this application.

[0064] As an example, with Figure 3 Taking the ground and air regions as examples, the matching scores of each point cloud partition within the ground region are calculated first. If there are 3 or fewer point cloud partitions (the number threshold for the ground region) with matching scores greater than the first score threshold, then no location loss is considered to have occurred. If there are more than 3 point cloud partitions with matching scores greater than the first score threshold in the ground region, but the global matching score of the ground region is less than or equal to the second score threshold, then no location loss is also considered to have occurred. If there are more than 3 point cloud partitions with matching scores greater than the first score threshold in the ground region, but the global matching score of the ground region is greater than the second score threshold, then the detection of location loss in the air region begins. If there are more than 5 point cloud partitions with matching scores greater than the first score threshold in the air region, then location loss is considered to have occurred; otherwise, no location loss is considered to have occurred.

[0065] It should be noted that, for the sake of simplicity, the aforementioned method embodiments are all described as a series of actions. However, those skilled in the art should understand that this application is not limited to the described order of actions, because according to this application, some steps can be performed in other orders.

[0066] like Figure 4The diagram shown is a schematic diagram of a location loss detection device 400 provided in an embodiment of this application. The location loss detection device 400 is configured on a self-moving device.

[0067] Specifically, the location loss detection device 400 may include:

[0068] The partitioning unit 401 is used to divide the three-dimensional space region where the self-moving device is located into multiple point cloud partitions;

[0069] The score acquisition unit 402 is used to acquire the matching score of each point cloud partition, wherein the matching score represents the distance between each point cloud in the point cloud partition and the nearest neighbor point in the electronic map;

[0070] The location loss detection unit 403 is used to compare the number of target partitions with a number threshold, and determine the location loss detection result of the self-moving device based on the comparison result. The target partition is the point cloud partition with a matching score greater than a first score threshold. When the number of target partitions is less than the number threshold, the location loss detection result is that no location loss has occurred.

[0071] In some embodiments of this application, the partitioning unit 401 can be used to: divide the three-dimensional spatial region into multiple comparison partitions along a preset direction, each comparison partition corresponding to a number threshold; divide each comparison partition into multiple fan-shaped regions along the central axis of the self-moving device in the preset direction, and treat each fan-shaped region as a point cloud partition, wherein the number of target partitions in each comparison partition is greater than the corresponding number threshold, and the global matching score of the three-dimensional spatial region is greater than a second score threshold, the positioning loss detection result is that positioning loss has occurred.

[0072] In some embodiments of this application, multiple first zones include ground areas and air areas, wherein the ground area is at a lower height from the ground than the air area, and the number threshold of the ground area is less than the number threshold of the air area.

[0073] In some embodiments of this application, the score acquisition unit 402 can be used to: acquire the matching score of each point cloud partition of the ground area and the global matching score; the region division unit 401 can be used to: confirm that the positioning loss detection result is that no positioning loss has occurred in response to the number of target partitions in the ground area being less than or equal to a number threshold, or the global matching score being less than or equal to a second score threshold; the score acquisition unit 402 can be used to: acquire the matching score of each point cloud partition of the air area in response to the number of target partitions in the ground area being greater than a number threshold and the global matching score being greater than a second score threshold; the region division unit 401 can be used to: confirm that the positioning loss detection result is that positioning loss has occurred in response to the number of target partitions in the air area being greater than a number threshold; and confirm that the positioning loss detection result is that no positioning loss has occurred in response to the number of target partitions in the air area being less than or equal to a number threshold.

[0074] In some embodiments of this application, the location loss detection device 400 may further include a score calculation unit for: determining the nearest neighbor of each point cloud within a point cloud partition in the electronic map; calculating the distance between each point cloud and its nearest neighbor; and determining the matching score of each point cloud partition based on the distance.

[0075] In some embodiments of this application, the score calculation unit can be used to: determine the degree of change of each point cloud partition; determine the correction weight of each point cloud partition based on the degree of change; and adjust the matching score of each point cloud partition based on the correction weight of each point cloud partition.

[0076] In some embodiments of this application, the score calculation unit can be used to: convert the point cloud collected by the self-mobile device to the world coordinate system through the current pose; and perform nearest neighbor matching in the electronic map based on the coordinates of each point cloud in the world coordinate system to obtain the nearest neighbor of each point cloud.

[0077] It should be noted that, for the sake of convenience and brevity, the specific working process of the aforementioned location loss detection device 400 can be found in the following reference: Figures 1 to 3 The corresponding process of the method will not be described in detail here.

[0078] like Figure 5 The diagram shown is a schematic representation of a self-moving device according to an embodiment of this application. Specifically, the self-moving device 5 may include: a processor 50, a memory 51, and a computer program 52 stored in the memory 51 and executable on the processor 50, such as a location loss detection program. When the processor 50 executes the computer program 52, it implements the steps in the various location loss detection method embodiments described above, for example... Figure 1The steps S101 to S103 are shown. Alternatively, when the processor 50 executes the computer program 52, it implements the functions of each module / unit in the above-described device embodiments, for example... Figure 4 The functions of the division unit 401, the score acquisition unit 402, and the location loss detection unit 403 are shown.

[0079] The computer program can be divided into one or more modules / units, which are stored in the memory 51 and executed by the processor 50 to complete this application. The one or more modules / units can be a series of computer program instruction segments capable of performing a specific function, which describe the execution process of the computer program in the self-moving device.

[0080] For example, the computer program can be divided into: a partitioning unit, a score acquisition unit, and a location loss detection unit. The specific functions of each unit are as follows: the partitioning unit is used to divide the three-dimensional spatial region where the self-moving device is located into multiple point cloud partitions; the score acquisition unit is used to acquire the matching score of each point cloud partition, where the matching score represents the distance between each point cloud within the point cloud partition and its nearest neighbor in the electronic map; the location loss detection unit is used to compare the number of target partitions with a number threshold, and determine the location loss detection result of the self-moving device based on the comparison result, wherein the target partitions are point cloud partitions whose matching scores are greater than a first score threshold, and when the number of target partitions is less than the number threshold, the location loss detection result is that no location loss has occurred.

[0081] The self-moving device may include, but is not limited to, a processor 50 and a memory 51. Those skilled in the art will understand that... Figure 5 This is merely an example of a self-moving device and does not constitute a limitation on the self-moving device. It may include more or fewer components than illustrated, or combine certain components, or different components. For example, the self-moving device may also include input / output devices, network access devices, buses, etc.

[0082] The processor 50 may be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), off-the-shelf programmable gate arrays or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor.

[0083] The memory 51 can be an internal storage unit of the self-moving device, such as a hard drive or memory. The memory 51 can also be an external storage device of the self-moving device, such as a plug-in hard drive, Smart Media Card (SMC), Secure Digital (SD) card, or Flash Card. Furthermore, the memory 51 can include both internal and external storage units of the self-moving device. The memory 51 is used to store the computer program and other programs and data required by the self-moving device. The memory 51 can also be used to temporarily store data that has been output or will be output.

[0084] It should be noted that, for the sake of convenience and brevity, the structure of the self-moving device described above can also be referred to the specific description of the structure in the method embodiment, which will not be repeated here.

[0085] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described division of functional units and modules is merely an example. In practical applications, the above functions can be assigned to different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiments can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit. Furthermore, the specific names of the functional units and modules are only for easy differentiation and are not intended to limit the scope of protection of this application. The specific working process of the units and modules in the above system can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0086] In the above embodiments, the descriptions of each embodiment have different focuses. For parts that are not described in detail or recorded in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0087] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for various specific applications, but such implementations should not be considered beyond the scope of this application.

[0088] In the embodiments provided in this application, it should be understood that the disclosed devices / self-moving devices and methods can be implemented in other ways. For example, the device / self-moving device embodiments described above are merely illustrative. For instance, the division of modules or units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the displayed or discussed mutual couplings or direct couplings or communication connections may be through some interfaces; indirect couplings or communication connections between devices or units may be electrical, mechanical, or other forms.

[0089] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0090] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0091] If the integrated module / unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the methods of the above embodiments can also be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include: any entity or device capable of carrying the computer program code, recording media, USB flash drives, portable hard drives, magnetic disks, optical disks, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signals, telecommunication signals, and software distribution media, etc. It should be noted that the content included in the computer-readable medium can be appropriately added or removed according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer-readable media do not include electrical carrier signals and telecommunication signals.

[0092] The above-described embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application, and should all be included within the protection scope of this application.

Claims

1. A method for detecting location loss, characterized in that, include: The three-dimensional space region where the self-moving device is located is divided into multiple point cloud partitions; Obtain the matching score for each point cloud partition, where the matching score represents the distance between each point cloud within the point cloud partition and the nearest neighbor point in the electronic map; The number of target partitions is compared with a number threshold, and the location loss detection result of the self-mobile device is determined based on the comparison result. The target partition is the point cloud partition with a matching score greater than a first score threshold. When the number of target partitions is less than the number threshold, the location loss detection result is that no location loss has occurred.

2. The location loss detection method as described in claim 1, characterized in that, The process of dividing the three-dimensional spatial region where the self-moving device is located into multiple point cloud partitions includes: The three-dimensional spatial region is divided into multiple comparison partitions along a preset direction, and each comparison partition corresponds to a number threshold. Each comparison partition is divided into multiple sector regions along the central axis of the self-moving device in the preset direction. Each sector region is treated as a point cloud partition. When the number of target partitions in each comparison partition is greater than the corresponding number threshold, and the global matching score of the three-dimensional spatial region is greater than the second score threshold, the positioning loss detection result is that positioning loss has occurred.

3. The location loss detection method as described in claim 2, characterized in that, The plurality of first zones include ground areas and air areas, wherein the ground area is at a lower height from the ground than the air area, and the threshold number of ground areas is lower than the threshold number of air areas.

4. The location loss detection method as described in claim 3, characterized in that, The step of obtaining the matching score of each point cloud partition, comparing the number of target partitions with a threshold number, and determining the location loss detection result of the self-moving device based on the comparison result includes: Obtain the matching score for each point cloud partition of the ground area and the global matching score; In response to the number of target partitions in the ground area being less than or equal to a number threshold, or the global matching score being less than or equal to a second score threshold, the location loss detection result is confirmed as no location loss has occurred. In response to the fact that the number of target partitions in the ground area is greater than a number threshold and the global matching score is greater than a second score threshold, the matching score of each point cloud partition in the air area is obtained; In response to the number of target partitions in the air region being greater than a threshold, the location loss detection result is confirmed as location loss. In response to the number of target partitions in the air region being less than or equal to a number threshold, the location loss detection result is confirmed as no location loss has occurred.

5. The location loss detection method according to any one of claims 1-4, characterized in that, The process of obtaining the matching score for each point cloud partition includes: In the electronic map, the nearest neighbor points of each point cloud within a point cloud partition are determined; Calculate the distance between each point cloud and its nearest neighbor; Based on the distance, the matching score for each point cloud partition is determined.

6. The location loss detection method as described in claim 5, characterized in that, After determining the matching score for each point cloud partition based on the distance, the method further includes: Determine the degree of change in each point cloud partition; The correction weights for each point cloud partition are determined based on the degree of change. The matching score of each point cloud partition is adjusted based on the corrected weight of each point cloud partition.

7. The location loss detection method as described in claim 5, characterized in that, The step of determining the nearest neighbor points of each point cloud within a point cloud partition in the electronic map includes: The point cloud acquired by the mobile device is transformed into the world coordinate system based on the current pose; Based on the coordinates of each point cloud in the world coordinate system, the nearest neighbor is matched in the electronic map to obtain the nearest neighbor of each point cloud.

8. A location loss detection device, characterized in that, include: The partitioning unit is used to divide the three-dimensional spatial region where the self-moving device is located into multiple point cloud partitions; The score acquisition unit is used to acquire the matching score of each point cloud partition, wherein the matching score represents the distance between each point cloud in the point cloud partition and the nearest neighbor point in the electronic map; The location loss detection unit is used to compare the number of target partitions with a number threshold, and determine the location loss detection result of the self-moving device based on the comparison result. The target partition is the point cloud partition with a matching score greater than a first score threshold. When the number of target partitions is less than the number threshold, the location loss detection result is that no location loss has occurred.

9. A self-moving device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the location loss detection method as described in any one of claims 1 to 7.

10. A computer program product, characterized in that, Includes a computer program, which, when run, causes the location loss detection method as described in any one of claims 1 to 7 to be performed.

Images