Map merging method and device, nonvolatile storage medium and electronic equipment

Abstract

The invention discloses a map merging method and device, a nonvolatile storage medium and electronic equipment. The method comprises the following steps: determining a plurality of coincidence devices, the plurality of coincidence devices being unmanned devices with coincidence parts in corresponding local maps; the position relation between the overlapping part and positioning areas corresponding to the multiple overlapping devices is determined, and the positioning areas are determined based on the motion trails of the corresponding overlapping devices in the mapping scanning process; performing duplicate removal processing on the overlapped part according to the position relation; and merging the local maps corresponding to the multiple pieces of coincident equipment after de-duplication to obtain a global map. The technical problem that the completeness of the combined map is not ideal is solved.

Description

Technical Field

[0001] The present application relates to the field of map merging algorithms, and in particular, to a map merging method, device, non-volatile storage medium and electronic device. Background Art

[0002] With the continuous development of unmanned technology, unmanned equipment has been widely used in all walks of life. In order to improve work efficiency and perform more complex tasks more intelligently, multi-device collaborative control must become a prerequisite. In order to achieve multi-device collaborative work, the first thing to solve is the problem of collaborative construction of maps by multiple unmanned equipment and merging of local maps. For the problem of building a merged map based on the local map of unmanned equipment, the relevant technology mainly uses deep learning methods to perform feature analysis on the local map, and then merges the local maps by extracting the same feature points. However, this method is aimed at scenes with relatively few feature differences, such as outdoor open areas or single-line laser radar scanning. The missing feature points will make the deduplication effect of the overlapping areas between the local maps unsatisfactory during the merging process, which will lead to the inconsistency between the size of the merged global map and the actual scene map caused by excessive merging, and there is a problem of unsatisfactory integrity of the merged map.

[0003] To address the above-mentioned problems, no effective solution has been proposed yet. Summary of the invention

[0004] The embodiments of the present application provide a map merging method, device, non-volatile storage medium and electronic device to at least solve the technical problem of unsatisfactory integrity of the merged map.

[0005] According to one aspect of an embodiment of the present application, a map merging method is provided, including: determining a plurality of overlapping devices, wherein the plurality of overlapping devices are unmanned devices having overlapping portions in corresponding local maps; determining a positional relationship between the overlapping portions and positioning areas respectively corresponding to the plurality of overlapping devices, wherein the positioning areas are determined based on motion trajectories of the corresponding overlapping devices during a mapping scanning process; deduplicating the overlapping portions according to the positional relationship; and merging the local maps respectively corresponding to the plurality of overlapping devices after deduplication to obtain a global map.

[0006] Optionally, the method further includes: determining scanning ranges respectively corresponding to the multiple overlapping devices; and determining positioning areas of the multiple overlapping devices based on the motion trajectories and scanning ranges respectively corresponding to the multiple overlapping devices.

[0007] Optionally, deduplication processing is performed on the overlapping parts according to the position relationship, including: when the position relationship indicates that the overlapping part does not belong to any area among the positioning areas respectively corresponding to the multiple overlapping devices, determining the area type to which the overlapping part belongs by the multiple overlapping devices respectively; among the area types respectively determined by the multiple overlapping devices, determining a first target type with the same judgment and the largest judgment count, wherein the judgment count is the number of devices that make the same judgment among the multiple overlapping devices; determining the area type of the overlapping part to be the first target type as deduplication processing for the overlapping part.

[0008] Optionally, the method also includes: when the first target type does not exist in the area types respectively determined by multiple overlapping devices, determining the connection status between the overlapping part and the known area, wherein the known area is a partial area in the positioning areas respectively corresponding to the multiple overlapping devices; when the connection status is that the boundary length between the overlapping part and the known area is greater than or equal to a predetermined length threshold, using the area type of the known area as the area type of the overlapping part; when the connection status is that the boundary length between the overlapping part and the known area is less than a predetermined length threshold, determining the proportion of obstacles in the predetermined range where the overlapping part is located; based on the obstacle proportion, determining the area type of the overlapping part.

[0009] Optionally, multiple overlapping devices are part of multiple unmanned devices, and the multiple unmanned devices are used to collaboratively complete mapping scanning. The method also includes: determining the global map size based on the boundary coordinates reached by the multiple unmanned devices during the scanning process, and the scanning ranges corresponding to the multiple unmanned devices; determining the average size of obstacles in a known area; and determining a predetermined range according to the global map size and the average size.

[0010] Optionally, deduplication processing is performed on the overlapping parts according to the positional relationship, including: when the positional relationship indicates that the overlapping part belongs to at least one of the positioning areas respectively corresponding to the multiple overlapping devices, determining a target area including the overlapping part in the positioning areas respectively corresponding to the multiple overlapping devices; determining the type of area to which the overlapping part belongs determined by the overlapping device corresponding to the target area as a second target type; and determining the area type of the overlapping part as the second target type as deduplication processing for the overlapping part.

[0011] Optionally, multiple overlapping devices belong to a part of multiple unmanned devices, and the multiple unmanned devices are used to collaboratively complete mapping scanning. The local map belongs to the device coordinate system of the corresponding unmanned device. Before deduplication processing is performed on the overlapping parts, the method also includes: determining the starting point coordinates of the multiple unmanned devices to start mapping scanning, wherein the starting point coordinates are in the device coordinate system of the corresponding unmanned device; based on the positioning information and starting point coordinates corresponding to the multiple unmanned devices, respectively, determining the coordinate conversion matrices corresponding to the multiple unmanned devices, wherein the coordinate conversion matrix is ​​used to convert the device coordinate system to the world coordinate system; respectively converting through the coordinate conversion matrix, adding the local maps corresponding to the multiple unmanned devices to the global grid, wherein the global grid is a grid structure generated based on the size of the global map.

[0012] According to another aspect of an embodiment of the present application, a map merging device is provided, including: an overlapping device determination module, used to determine multiple overlapping devices, wherein the multiple overlapping devices are unmanned devices having overlapping parts in corresponding local maps; a position relationship determination module, used to determine the position relationship between the overlapping parts and the positioning areas respectively corresponding to the multiple overlapping devices, wherein the positioning areas are determined based on the motion trajectories of the corresponding overlapping devices during the mapping scanning process; a deduplication processing module, used to perform deduplication processing on the overlapping parts according to the position relationship; and a merging module, used to merge the local maps respectively corresponding to the multiple overlapping devices after deduplication to obtain a global map.

[0013] According to another aspect of an embodiment of the present application, a non-volatile storage medium is provided, wherein the non-volatile storage medium stores a plurality of instructions, and the instructions are suitable for being loaded by a processor and executing any one of the map merging methods.

[0014] According to another aspect of an embodiment of the present application, an electronic device is provided, comprising: one or more processors and a memory, the memory being used to store one or more programs, wherein when the one or more programs are executed by one or more processors, the one or more processors implement any one of the map merging methods.

[0015] In the embodiment of the present application, multiple overlapping devices are determined, wherein the multiple overlapping devices are unmanned devices with overlapping parts in the corresponding local maps; the positional relationship between the overlapping parts and the positioning areas corresponding to the multiple overlapping devices is determined, wherein the positioning areas are determined based on the motion trajectories of the corresponding overlapping devices during the mapping scanning process; the overlapping parts are deduplicated according to the positional relationship; and the local maps corresponding to the multiple overlapping devices after deduplication are merged to obtain a global map. The purpose of deduplicating the overlapping parts according to the positional relationship of the overlapping areas between the local maps is achieved, and the technical effect of improving the integrity of the merged map is achieved, thereby solving the technical problem of unsatisfactory integrity of the merged map. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0017] Figure 1 is a flowchart of an optional map merging method provided according to an embodiment of the present application;

[0018] Figure 2 It is a schematic diagram of an optional map merging device provided according to an embodiment of the present application. DETAILED DESCRIPTION

[0019] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present application.

[0020] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0021] For the convenience of description, some nouns or terms involved in the embodiments of the present application are explained below:

[0022] UWB (Ultra Wide Band) is a carrier-free communication technology that uses non-sinusoidal narrow pulses from nanoseconds to picoseconds to transmit data. It has the characteristics of high-speed data transmission, precise positioning, low power consumption and strong anti-interference ability.

[0023] GPS (Global Positioning System) can provide real-time three-dimensional position, three-dimensional speed and precise time information.

[0024] According to an embodiment of the present application, a method embodiment of a map merging method is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0025] Figure 1 is a flowchart of an optional map merging method provided according to an embodiment of the present application, such as Figure 1 As shown, the method comprises the following steps:

[0026] Step S102, determining a plurality of overlapping devices, wherein the plurality of overlapping devices are unmanned devices having overlapping portions in corresponding local maps;

[0027] It is understandable that when using multiple unmanned devices to build local maps, there will be overlaps between some local maps. In order to perform subsequent deduplication processing, it is first necessary to determine multiple overlapping devices based on the local maps with overlapping parts, that is, to determine the unmanned devices corresponding to the local maps with overlapping parts. By accurately identifying and processing overlapping areas, possible information conflicts and losses during the merging process are avoided, ensuring the integrity and accuracy of the final global map (i.e., the merged map).

[0028] Optionally, the unmanned equipment mentioned above may be a drone, an unmanned vehicle, etc.

[0029] In an optional embodiment, multiple overlapping devices belong to a part of multiple unmanned devices, and the multiple unmanned devices are used to collaboratively complete mapping scanning. The local map belongs to the device coordinate system of the corresponding unmanned device. Before deduplication processing is performed on the overlapping parts, the method also includes: determining the starting point coordinates of the multiple unmanned devices to start mapping scanning, wherein the starting point coordinates are in the device coordinate system of the corresponding unmanned device; based on the positioning information and starting point coordinates corresponding to the multiple unmanned devices, respectively, determining the coordinate conversion matrices corresponding to the multiple unmanned devices, wherein the coordinate conversion matrix is ​​used to convert the device coordinate system to the world coordinate system; respectively converting through the coordinate conversion matrix, adding the local maps corresponding to the multiple unmanned devices to the global grid, wherein the global grid is a grid structure generated based on the size of the global map.

[0030] It can be understood that when constructing a global map, it is necessary to merge the local maps scanned by multiple unmanned devices to obtain a global map, wherein the coordinate system of each local map is the same as the device coordinate system of the corresponding unmanned device, and the coordinate system of the global map is the world coordinate system. Since there will be overlapping parts between multiple local maps, it is necessary to determine multiple overlapping devices based on the local maps with overlapping parts, that is, to determine the unmanned devices corresponding to the local maps with overlapping parts, wherein the multiple overlapping devices are part of the multiple unmanned devices. Before deduplication of the overlapping parts between the local maps, it is necessary to convert the local maps constructed by the multiple unmanned devices from their corresponding device coordinate systems to the world coordinate system. First, determine the starting point coordinates of the multiple unmanned devices at the beginning of the map construction scan, and the coordinate system of the above starting point is the device coordinate system of the corresponding unmanned device. According to the starting point coordinates of each unmanned device recorded by the positioning device, and the positioning information corresponding to the starting point coordinates, determine the coordinate conversion matrix corresponding to each unmanned device, wherein the coordinate conversion matrix is ​​used to convert the device coordinate system into the world coordinate system. After determining the coordinate transformation matrix corresponding to each unmanned device, the coordinate transformation matrix is ​​used to transform the device coordinate systems corresponding to multiple local maps into the world coordinate system, and the converted local maps are added to the global grid of the global map. Among them, the global grid is a grid structure constructed according to the size of the global map, and the content of the grid structure needs to be determined based on the local map. Through precise coordinate transformation, it is ensured that the local map can be accurately superimposed on the global grid, avoiding map information deviation caused by coordinate errors, improving the construction quality of the global map, and ensuring that the unmanned equipment can maintain consistent and accurate environmental information in collaborative operations.

[0031] Optionally, multiple positioning modules can be arranged in a specified environment to record the changes in the location information of each unmanned device during the construction of a local map. For indoor environments, UWB can be used to locate unmanned devices; for outdoor environments, satellite navigation systems, such as Beidou, or GPS and other positioning facilities can be combined to obtain location information. The maximum and minimum coordinates are obtained by integrating the positioning information of all unmanned devices, and the global map size is determined by combining the maximum value of the radar scanning range, and then the global map grid (i.e., global grid) is constructed based on the resolution.

[0032] Optionally, after obtaining the global map grid, the resolution of the local map needs to be unified with the global map resolution, and then the local map resolution is obtained by parsing. Figure 1The local map information file generated by the unmanned device is used to obtain the coordinate position of the starting point of the unmanned device when constructing the local map relative to the current local coordinate system (i.e., the device coordinate system), and then the coordinate conversion matrix is ​​obtained in combination with the recorded positioning information. Then, by reading the image of the local map, the valid information coordinates are transferred to the world coordinate system of the global map grid through the coordinate conversion matrix. The above valid information indicates that during the map construction process, a grid filled with unknown areas will be constructed according to a predetermined size, and then the unmanned device will continuously move the radar to scan the environmental information on the way to obtain the obstacle area and the safety area. Therefore, there will only be three types of information in the map file: unknown area, obstacle area, and safety area. The valid information refers to the obstacle area and the safety area, and the area type can be an obstacle area or a safety area.

[0033] Step S104, determining a positional relationship between the overlapping portion and positioning areas respectively corresponding to the plurality of overlapping devices, wherein the positioning areas are determined based on movement trajectories of the corresponding overlapping devices during the mapping scanning process;

[0034] It can be understood that in the process of map construction, each unmanned device can determine its corresponding positioning area according to its motion trajectory and scanning range. According to the positioning areas corresponding to multiple overlapping devices, the positional relationship between the overlapping part and the positioning areas corresponding to the multiple overlapping devices is determined, for example, the overlapping part is inside the positioning area, or the overlapping part is at the boundary of the positioning area. Based on the positioning area and motion trajectory of the unmanned device, the positional relationship between the overlapping part and the positioning area can be effectively judged, and then deduplication processing can be performed according to the positional relationship, thereby improving the construction accuracy of the global map, reducing the uncertainty in the merging process, and enhancing the stability of the local map merging.

[0035] In an optional embodiment, the method further includes: determining scanning ranges corresponding to the multiple overlapping devices respectively; and determining positioning areas of the multiple overlapping devices based on the motion trajectories and scanning ranges corresponding to the multiple overlapping devices respectively.

[0036] It can be understood that the motion trajectories and scanning ranges corresponding to the multiple overlapping devices are determined, and the positioning areas corresponding to the multiple overlapping devices are determined according to the motion trajectories and scanning ranges corresponding to the multiple overlapping devices. By determining the positioning area of ​​each unmanned device, the overlapping parts between the local maps can be more accurately identified and processed, avoiding the information redundancy or omission that may occur during the merging process, and ensuring the high accuracy and integrity of the global map.

[0037] Optionally, the scanning range of the unmanned device can be determined based on the maximum scanning distance and angle range of the sensor (such as a lidar) carried on the device. The scanning range of each unmanned device is a circle with its current position as the center and the maximum scanning distance as the radius, or other shapes determined according to the characteristics of the sensor. Based on the motion trajectory and scanning range of the unmanned device, the area actually covered by each unmanned device during the mission can be determined, that is, its positioning area. The size of the positioning area reflects the size of the range actually scanned by the unmanned device in the environment.

[0038] Step S106, performing deduplication processing on the overlapping parts according to the position relationship;

[0039] It can be understood that the overlapping parts are deduplicated according to the positional relationship between the overlapping parts and the positioning areas corresponding to the multiple overlapping devices. Deduplication effectively solves the information conflict problem when merging local maps, ensures the accuracy of the global map, reduces misjudgments caused by redundant or missing information, and improves the safety of unmanned equipment operations.

[0040] Optionally, after all local maps have completed the coordinate conversion, there will inevitably be some areas in the global map with scanning overlap. In order to ensure the accuracy of the final global map, the preliminary global map needs to be deduplicated. The positioning area of ​​a single unmanned device is constructed by combining the positioning trajectory in the process of local map construction. The positioning area is used to determine whether the overlapping part is in the boundary area of ​​the local map, that is, to determine the positional relationship between the overlapping part and the positioning areas corresponding to multiple overlapping devices.

[0041] In an optional embodiment, deduplication processing is performed on the overlapping parts according to the position relationship, including: when the position relationship indicates that the overlapping part does not belong to any area among the positioning areas respectively corresponding to the multiple overlapping devices, determining the area type to which the overlapping part belongs by the multiple overlapping devices respectively; among the area types respectively determined by the multiple overlapping devices, determining the first target type with the same judgment and the largest judgment count, wherein the judgment count is the number of devices that make the same judgment among the multiple overlapping devices; determining the area type of the overlapping part to be the first target type as deduplication processing for the overlapping part.

[0042] It can be understood that if the positional relationship between the overlapping part and the positioning areas corresponding to the multiple overlapping devices is indicated as that the overlapping part does not belong to any of the positioning areas corresponding to the multiple overlapping devices, that is, the overlapping part belongs to the boundary of the positioning areas corresponding to the multiple overlapping devices, the area type determined by the overlapping part in the positioning areas corresponding to the above-mentioned multiple overlapping devices is determined, and the area type with a larger count among the area types determined by the overlapping part is determined as the first target type. The area type of the overlapping part is determined as the above-mentioned first target type as the result of the deduplication processing of the overlapping part. By counting the determination types of multiple devices and selecting the type with the largest determination count, the reliability of the global map information can be increased. Even if there is an error in the determination of a device, the correct determination of most devices can ensure the accuracy of the final information.

[0043] In an optional embodiment, the method also includes: when the first target type does not exist in the area types respectively determined by multiple overlapping devices, determining the connection status between the overlapping part and the known area, wherein the known area is a partial area in the positioning areas respectively corresponding to the multiple overlapping devices; when the connection status is that the boundary length between the overlapping part and the known area is greater than or equal to a predetermined length threshold, using the area type of the known area as the area type of the overlapping part; when the connection status is that the boundary length between the overlapping part and the known area is less than a predetermined length threshold, determining the proportion of obstacles in the predetermined range where the overlapping part is located; based on the obstacle proportion, determining the area type of the overlapping part.

[0044] It can be understood that, in the case where the overlapping part belongs to the boundary of the positioning area corresponding to multiple overlapping devices, if the first target type does not exist in the area types determined by the multiple overlapping devices, that is, the counts of several area types corresponding to the overlapping part are the same, the connection status of the overlapping area and the known area is determined. Among them, the known area belongs to a part of the positioning area corresponding to multiple overlapping devices, and the area type of the area has been determined. In the case where the connection status is displayed as the boundary length between the overlapping area and the known area is greater than or equal to the predetermined length threshold, the area type of the known area is used as the area type of the overlapping part. In the case where the connection status is displayed as the boundary length between the overlapping area and the known area is less than the predetermined length threshold, the proportion of obstacles in the predetermined range where the overlapping part is located is further determined. Based on the proportion of obstacles, the area type of the overlapping part is determined. If the obstacle proportion exceeds the predetermined threshold, for example, 90%, the obstacle type is used as the area type of the overlapping part; if the obstacle proportion is less than or equal to the predetermined threshold, the safe area type is used as the area type of the overlapping part. The decision-making method based on the intersection length is adopted to reduce redundant processing when information overlaps, while avoiding global map information conflicts caused by differences in device judgment, optimizing the entire map construction process, and improving the accuracy and environmental adaptability of global map construction.

[0045] In an optional embodiment, multiple overlapping devices are part of multiple unmanned devices, and the multiple unmanned devices are used to collaboratively complete mapping scanning. The method also includes: determining the global map size based on the boundary coordinates reached by the multiple unmanned devices during the scanning process, and the scanning ranges corresponding to the multiple unmanned devices; determining the average size of obstacles in a known area; and determining a predetermined range according to the global map size and the average size.

[0046] It can be understood that when constructing a global map, it is necessary to merge the local maps scanned by multiple unmanned devices to obtain a global map. Determine the entire range covered by multiple unmanned devices based on the boundary coordinates and scanning range of multiple unmanned devices during the scanning process, and determine the size of the global map based on the entire range covered by multiple unmanned devices. Determine the average size of obstacles in the known area of ​​the global map, and determine the predetermined range based on the global map size and the average size of the obstacles, with the overlapping part as the center. The predetermined range determined based on the average size of the obstacles and the global map size ensures the rationality of the predetermined range division, optimizes the overlapping part processing strategy in the local map merging, improves the accuracy and efficiency of global map construction, and enhances the collaborative operation capability and adaptability of the unmanned equipment system in complex environments.

[0047] Optionally, for overlapping points in the boundary area, that is, the overlapping part does not belong to any of the positioning areas corresponding to the multiple overlapping devices, if the cumulative overlap is greater than two (that is, the number of local maps with overlapping parts is greater than two), the type of area with a larger count (that is, the first target type) shall prevail. For the cumulative overlap of only two (that is, the number of local maps with overlapping parts is equal to two), it is necessary to process by comprehensively analyzing the values ​​within a certain range around. Specifically, the radius is comprehensively defined based on the current global environment size and the average size of obstacles in the environment with the current point as the center point to determine the predetermined range. If the overlapping part is connected to other complete obstacle areas within the predetermined range, and the length of the connection (that is, the junction length) is greater than or equal to the predetermined length threshold, the current point is judged as an obstacle type; if the length of the connection (that is, the junction length) is less than the predetermined length threshold, but more than 90% of the current range is an obstacle type, then the point is also judged as an obstacle type, otherwise the point is judged as a safe area type.

[0048] In an optional embodiment, deduplication processing is performed on the overlapping parts according to the positional relationship, including: when the positional relationship indicates that the overlapping part belongs to at least one of the positioning areas respectively corresponding to the multiple overlapping devices, determining a target area including the overlapping part in the positioning areas respectively corresponding to the multiple overlapping devices; determining the type of area to which the overlapping part belongs determined by the overlapping device corresponding to the target area as the second target type; and determining the area type of the overlapping part as the second target type as deduplication processing for the overlapping part.

[0049] It can be understood that if the positional relationship between the overlapping part and the positioning areas corresponding to the multiple overlapping devices is indicated as that the overlapping part belongs to at least one of the positioning areas corresponding to the multiple overlapping devices, that is, the overlapping part belongs to at least the inside of the positioning area corresponding to one of the overlapping devices, the target area containing the overlapping part in the positioning areas corresponding to the multiple overlapping devices is determined. The area type of the overlapping part determined by the overlapping device corresponding to the target area is taken as the second target type. The second target type is determined as the area type corresponding to the overlapping part as the result of the deduplication processing of the overlapping part. By identifying the target area and analyzing its area type determination information, the problem of processing the overlapping part located at the boundary of the unmanned equipment positioning area during the local map merging process is effectively solved, the accuracy and efficiency of global map construction are improved, and the integrity of the map is ensured.

[0050] Optionally, for overlapping points (i.e., overlapping parts) in non-boundary areas, that is, the overlapping parts belong to at least one of the positioning areas corresponding to multiple overlapping devices, the area type value (i.e., the second target type) of the point in the positioning area to which the point belongs shall prevail (the reason for this phenomenon is that during the movement of the unmanned equipment, the radar will scan with the farthest scanning range as the radius, and at the current position, the radar cannot scan the area beyond the farthest scanning range, so the value of the farthest point defaults to the obstacle type. In this case, if this area overlaps with the area scanned by another device, the above phenomenon will occur during the merging process).

[0051] Step S108, merging the local maps corresponding to the multiple overlapping devices after deduplication to obtain a global map.

[0052] It can be understood that the global map is obtained by merging the local maps after deduplication processing. By performing detailed deduplication processing on the overlapping parts, the global map error caused by inconsistent positioning information or conflicting local map information is avoided, ensuring the accuracy of the global map.

[0053] Through the above step S102, multiple overlapping devices are determined, wherein the multiple overlapping devices are unmanned devices with overlapping parts in the corresponding local maps; step S104, determine the positional relationship between the overlapping parts and the positioning areas corresponding to the multiple overlapping devices, wherein the positioning areas are determined based on the motion trajectories of the corresponding overlapping devices during the mapping and scanning process; step S106, perform deduplication processing on the overlapping parts according to the positional relationship; step S108, merge the local maps corresponding to the multiple overlapping devices after deduplication to obtain a global map. The purpose of deduplication processing on the overlapping parts according to the positional relationship of the overlapping areas between the local maps can be achieved, and the technical effect of improving the integrity of the merged map is achieved, thereby solving the technical problem of unsatisfactory integrity of the merged map.

[0054] Based on the above embodiments and optional embodiments, the present application proposes an optional implementation method that can be used to merge and deduplicate local maps constructed by unmanned equipment to obtain an accurate and complete global map.

[0055] By arranging multiple positioning modules in a specified environment, the location information changes of each unmanned device during the local map construction process are recorded. For indoor environments, UWB can be used to locate unmanned devices; for outdoor environments, satellite navigation systems, such as Beidou, or GPS and other positioning facilities can be combined to obtain location information. The maximum and minimum coordinates are obtained by integrating the positioning information of all unmanned devices, and the global map size is determined by combining the maximum value of the radar scanning range, and then the global map grid (i.e., global grid) is constructed based on the resolution.

[0056] After obtaining the global map grid, the resolution of the local map must first be unified with the global map resolution, and then the local map resolution must be Figure 1 The local map information file generated by the unmanned device obtains the coordinate position of the starting point of the unmanned device when constructing the local map relative to the current local coordinate system (i.e., the device coordinate system), and then combines the recorded positioning information to obtain the coordinate conversion matrix. Then, by reading the image of the local map, the valid information coordinates are transferred to the world coordinate system of the global map grid through the coordinate conversion matrix. The above valid information indicates that during the map construction process, a grid filled with unknown areas will be constructed according to a predetermined size, and then the unmanned device will continuously move the radar to scan the environmental information on the way to obtain the obstacle area and the safe area. Therefore, there will only be three types of information in the map file: unknown area, obstacle area, and safe area. The valid information refers to the obstacle area and the safe area.

[0057] After all local maps have completed the coordinate conversion, there will inevitably be some areas in the global map where scanning overlaps. In order to ensure the accuracy of the final global map, the preliminary global map needs to be deduplicated. The positioning area of ​​a single unmanned device is constructed by combining the positioning trajectory in the local map construction process. The positioning area is used to determine whether the overlapping part is in the boundary area of ​​the local map, that is, to determine the positional relationship between the overlapping part and the positioning areas corresponding to multiple overlapping devices.

[0058] For overlapping points in non-boundary areas (i.e., overlapping parts), that is, the overlapping parts belong to at least one of the positioning areas corresponding to multiple overlapping devices, the area type value of the point in the positioning area to which the point belongs (i.e., the second target type) shall prevail (the reason for this phenomenon is that during the movement of the unmanned equipment, the radar will scan with the farthest scanning range as the radius, and at the current position, the radar cannot scan the area beyond the farthest scanning range, so the value of the farthest point defaults to the obstacle type. In this case, if this area overlaps with the area scanned by another device, it will cause the above phenomenon during the merging process).

[0059] For overlapping points in the boundary area, that is, the overlapping part does not belong to any of the positioning areas corresponding to multiple overlapping devices, if the cumulative overlap is greater than two (that is, the number of local maps with overlapping parts is greater than two), the area type with a larger count (that is, the first target type) shall prevail. For the cumulative overlap of only two (that is, the number of local maps with overlapping parts is equal to two), it is necessary to process it by comprehensively analyzing the values ​​within a certain range around it. Specifically, the radius is comprehensively defined based on the current global environment size and the average size of obstacles in the environment with the current point as the center point to determine the predetermined range. If the overlapping part is connected to other complete obstacle areas within the predetermined range, and the length of the connection (that is, the junction length) is greater than or equal to the predetermined length threshold, the current point is judged as an obstacle type; if the length of the connection (that is, the junction length) is less than the predetermined length threshold, but more than 90% of the current range is an obstacle type, then the point is also judged as an obstacle type, otherwise the point is judged as a safe area type.

[0060] The above global map merging method can ensure the integrity of each local map while merging the maps when the local map feature information is relatively small. For the deduplication of the overlapping parts during the merging process, corresponding processing solutions are made for several foreseeable overlapping situations, including targeted processing of the problems of mis-scanning and missing scanning of obstacles in non-boundary areas and boundary areas, so as to ensure the integrity of the global map that is finally merged.

[0061] The above optional implementation achieves at least the following effects: by combining the positioning information to complete the merging of local maps, the merging can be completed without modifying the size of the local maps, ensuring that the final merged global map is highly consistent with the actual scene; by classifying the overlapping parts and performing deduplication processing in a corresponding manner, global map errors caused by inconsistent positioning information or conflicts in local map information are avoided, thereby ensuring the accuracy of the global map.

[0062] It should be noted that the steps shown in the flowcharts of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and that, although a logical order is shown in the flowcharts, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0063] In this embodiment, a map merging device is also provided, which is used to implement the above-mentioned embodiments and preferred implementation modes, and will not be repeated hereafter. As used below, the terms "module" and "device" can implement a combination of software and / or hardware for a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceivable.

[0064] According to an embodiment of the present application, a device embodiment for implementing the map merging method is also provided. Figure 2 is a schematic diagram of a map merging device according to an embodiment of the present application, such as Figure 2 As shown, the map merging device includes an overlapping device determination module 202, a position relationship determination module 204, a deduplication processing module 206, and a merging module 208. The device is described below.

[0065] An overlapping device determination module 202 is used to determine a plurality of overlapping devices, wherein the plurality of overlapping devices are unmanned devices having overlapping portions in corresponding local maps;

[0066] The position relationship determination module 204 is connected to the overlap device determination module 202, and is used to determine the position relationship between the overlapped portion and the positioning areas respectively corresponding to the plurality of overlapped devices, wherein the positioning areas are determined based on the motion trajectories of the corresponding overlapped devices during the mapping scanning process;

[0067] A deduplication processing module 206, connected to the position relationship determination module 204, is used to perform deduplication processing on the overlapping parts according to the position relationship;

[0068] The merging module 208 is connected to the deduplication processing module 206 and is used to merge the local maps corresponding to the multiple overlapping devices after deduplication to obtain a global map.

[0069] In a map merging device provided by an embodiment of the present application, an overlapping device determination module 202 is set to determine multiple overlapping devices, wherein the multiple overlapping devices are unmanned devices with overlapping parts in the corresponding local maps; a position relationship determination module 204 is connected to the overlapping device determination module 202, and is used to determine the position relationship between the overlapping part and the positioning areas corresponding to the multiple overlapping devices, wherein the positioning areas are determined based on the movement trajectory of the corresponding overlapping devices during the map building and scanning process; a deduplication processing module 206 is connected to the position relationship determination module 204, and is used to perform deduplication processing on the overlapping part according to the position relationship; a merging module 208 is connected to the deduplication processing module 206, and is used to merge the local maps corresponding to the multiple overlapping devices after deduplication to obtain a global map. The purpose of deduplication processing on the overlapping part according to the position relationship of the overlapping areas between the local maps is achieved, and the technical effect of improving the integrity of the merged map is achieved, thereby solving the technical problem of unsatisfactory integrity of the merged map.

[0070] It should be noted that the above modules can be implemented by software or hardware. For example, for the latter, it can be implemented in the following ways: the above modules can be located in the same processor; or the above modules can be located in different processors in any combination.

[0071] It should be noted that the above-mentioned overlapping device determination module 202, position relationship determination module 204, deduplication processing module 206, and merging module 208 correspond to steps S102 to S108 in the embodiment, and the examples and application scenarios implemented by the above-mentioned modules and corresponding steps are the same, but are not limited to the contents disclosed in the above-mentioned embodiment. It should be noted that the above-mentioned modules can be run in a computer terminal as part of the device.

[0072] It should be noted that the optional or preferred implementation of this embodiment can refer to the relevant description in the embodiment, which will not be repeated here.

[0073] The above-mentioned map merging device may also include a processor and a memory. The overlapping device determination module 202, the position relationship determination module 204, the deduplication processing module 206, the merging module 208, etc. are all stored in the memory as program units, and the processor executes the above-mentioned program units stored in the memory to realize the corresponding functions.

[0074] The processor includes a kernel, which retrieves the corresponding program unit from the memory. There can be one or more kernels. The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM, and the memory includes at least one storage chip.

[0075] An embodiment of the present application provides a non-volatile storage medium on which a program is stored, and when the program is executed by a processor, a map merging method is implemented.

[0076] The embodiment of the present application provides an electronic device, which includes a processor, a memory, and a program stored in the memory and can be run on the processor. When the processor executes the program, the following steps are implemented: determining multiple overlapping devices, wherein the multiple overlapping devices are unmanned devices with overlapping parts in the corresponding local maps; determining the positional relationship between the overlapping parts and the positioning areas corresponding to the multiple overlapping devices, wherein the positioning areas are determined based on the motion trajectories of the corresponding overlapping devices during the mapping scanning process; deduplicating the overlapping parts according to the positional relationship; merging the local maps corresponding to the multiple overlapping devices after deduplication to obtain a global map. The device in this article can be a server, a PC, etc.

[0077] The present application also provides a computer program product, which, when executed on a data processing device, is suitable for executing a program that initializes the following method steps: determining multiple overlapping devices, wherein the multiple overlapping devices are unmanned devices with overlapping parts in corresponding local maps; determining a positional relationship between the overlapping parts and positioning areas respectively corresponding to the multiple overlapping devices, wherein the positioning areas are determined based on the motion trajectories of the corresponding overlapping devices during the mapping and scanning process; deduplicating the overlapping parts according to the positional relationship; and merging the local maps respectively corresponding to the multiple overlapping devices after deduplication to obtain a global map.

[0078] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.

[0079] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0080] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0081] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0082] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0083] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0084] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0085] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0086] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems or computer program products. Therefore, the present application may take the form of a complete hardware embodiment, a complete software embodiment or an embodiment combining software and hardware. Moreover, the present application may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.

[0087] The above are only embodiments of the present application and are not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included within the scope of the claims of the present application.

Claims

1. A map merging method, characterized in that: include: Determine a plurality of overlapping devices, wherein the plurality of overlapping devices are unmanned devices having overlapping portions in corresponding local maps; Determine a positional relationship between the overlapped portion and positioning areas respectively corresponding to the plurality of overlapped devices, wherein the positioning areas are determined based on motion trajectories of the corresponding overlapped devices during a mapping and scanning process; According to the positional relationship, deduplication processing is performed on the overlapping parts; The local maps corresponding to the multiple overlapping devices after deduplication are merged to obtain a global map.

2. The method according to claim 1, characterized in that The method further comprises: Determine the scanning ranges respectively corresponding to the multiple overlapping devices; Based on the motion trajectories and scanning ranges respectively corresponding to the multiple overlapping devices, the positioning areas of the multiple overlapping devices are determined.

3. The method according to claim 1, characterized in that The deduplication processing of the overlapping parts according to the position relationship includes: In a case where the position relationship indicates that the overlapped portion does not belong to any area of ​​the positioning areas respectively corresponding to the plurality of overlapped devices, determining the type of area to which the overlapped portion belongs as determined by the plurality of overlapped devices respectively; Determine, among the area types respectively determined by the plurality of overlapping devices, a first target type having the same determination and the largest determination count, wherein the determination count is the number of devices that make the same determination among the plurality of overlapping devices; The region type of the overlapping portion is determined to be the first target type, as deduplication processing for the overlapping portion.

4. The method according to claim 3, characterized in that The method further comprises: In the case that the first target type does not exist in the area types respectively determined by the multiple overlapping devices, determining the connection status between the overlapping part and the known area, wherein the known area is a partial area belonging to the positioning areas respectively corresponding to the multiple overlapping devices; When the connection condition is that the boundary length between the overlapped portion and the known region is greater than or equal to a predetermined length threshold, the region type of the known region is used as the region type of the overlapped portion; When the connection condition is that the boundary length between the overlapping portion and the known area is less than a predetermined length threshold, determine the obstacle ratio in the predetermined range where the overlapping portion is located; and determine the area type of the overlapping portion based on the obstacle ratio.

5. The method according to claim 4, characterized in that The multiple overlapping devices are part of a plurality of unmanned devices, and the multiple unmanned devices are used to collaboratively complete mapping scanning. The method further includes: Determine the size of the global map based on the boundary coordinates reached by the multiple unmanned devices during the scanning process and the scanning ranges respectively corresponding to the multiple unmanned devices; determining an average size of obstacles in the known area; The predetermined range is determined according to the global map size and the average size.

6. The method according to claim 1, characterized in that The deduplication processing of the overlapping parts according to the position relationship includes: In the case where the positional relationship indicates that the overlapped portion belongs to at least one of the positioning areas respectively corresponding to the plurality of overlapping devices, determining a target area including the overlapped portion in the positioning areas respectively corresponding to the plurality of overlapping devices; Determine the overlap device corresponding to the target area and determine the area type to which the overlapped part belongs as the second target type; The area type of the overlapping portion is determined to be the second target type, as deduplication processing for the overlapping portion.

7. The method according to any one of claims 1 to 6, characterized in that: The multiple overlapping devices belong to a part of multiple unmanned devices, the multiple unmanned devices are used to collaboratively complete map building and scanning, the local map belongs to the device coordinate system of the corresponding unmanned device, and before performing deduplication processing on the overlapping parts, the method further includes: Determine the starting point coordinates of the multiple unmanned devices for starting mapping scanning, wherein the starting point coordinates are in the device coordinate system of the corresponding unmanned device; Based on the positioning information and starting point coordinates respectively corresponding to the multiple unmanned devices, determining the coordinate conversion matrices respectively corresponding to the multiple unmanned devices, wherein the coordinate conversion matrix is ​​used to convert the device coordinate system to the world coordinate system; The local maps corresponding to the multiple unmanned devices are respectively converted through the coordinate conversion matrix to add them to the global grid, wherein the global grid is a grid structure generated based on the size of the global map.

8. A map merging device, characterized in that: include: An overlapping device determination module, used to determine a plurality of overlapping devices, wherein the plurality of overlapping devices are unmanned devices having overlapping parts in corresponding local maps; A position relationship determination module, used to determine the position relationship between the overlapped portion and the positioning areas respectively corresponding to the plurality of overlapped devices, wherein the positioning areas are determined based on the motion trajectories of the corresponding overlapped devices during the mapping scanning process; A deduplication processing module, used for performing deduplication processing on the overlapping parts according to the position relationship; The merging module is used to merge the local maps corresponding to the multiple overlapping devices after deduplication to obtain a global map.

9. A non-volatile storage medium, characterized in that: The non-volatile storage medium stores a plurality of instructions, and the instructions are suitable for being loaded by a processor and executing the map merging method described in any one of claims 1 to 7.

10. An electronic device, characterized in that: include: One or more processors and a memory, wherein the memory is used to store one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors implement the map merging method described in any one of claims 1 to 7.

Images