Automatic updating method and device of robot map, electronic equipment and storage medium

Abstract

The invention provides an automatic updating method and device for a robot map, electronic equipment and a storage medium. The automatic updating method comprises the steps that a global map and a historical information matching table of a robot in a working area are acquired; wherein the historical information matching table is determined according to environment information collected when the robot moves in the working area in a non-initial mode and a global map; detecting whether the similarity between the current feature of the current environment information of the robot at any position of the working area and the global map is smaller than a preset threshold value or not; if not, not updating the global map, and dynamically updating the historical information matching table; and if yes, determining whether to update the current feature to the global map based on a historical information matching table and the current feature. According to the method, the robot map can be accurately updated through the historical information matching table when the environment change is large and is not matched with most of the map.

Description

Technical Field

[0001] The present application relates to the technical field of intelligent control, and in particular, to a method, device, electronic device, and storage medium for automatically updating a robot map. Background Art

[0002] Mobile robots have served various industries in today's social development, such as factories, hospitals, families, hotels, exhibition halls, restaurants, etc., and mainly perform tasks such as logistics, handling, distribution, and guiding. Mobile robots navigate autonomously in these scenarios. The adaptability and safety of their dynamic and complex environment are important manifestations of their intelligence, and accurate global positioning is the most basic requirement for their autonomous navigation. Only with accurate global positioning can safe path planning be carried out and accurate multi-point reciprocating movement be achieved. Considering the dynamics and complexity of the working scenario, temporary obstacles often appear within the sensor's field of view of the mobile robot, and even the working scenario undergoes local changes and does not match the already constructed global map. Therefore, for the global positioning algorithm to be accurate and reliable, it must have strong environmental adaptability and robustness. Therefore, how to automatically update the robot map has become a technical problem that cannot be underestimated. Summary of the Invention

[0003] In view of this, the purpose of the present application is to provide a method, device, electronic device, and storage medium for automatically updating a robot map. When the similarity between the current environmental information at a certain position and the global map is lower than a threshold, the current environmental information is matched with the historical information matching table. If the match is successful, the robot map is updated, realizing accurate updating of the robot map through the historical information matching table even when the environment changes greatly and most of the map does not match.

[0004] The embodiment of the present application provides a method for automatically updating a robot map. The automatic updating method includes:

[0005] Obtain the global map of the robot in the working area and the historical information matching table; wherein, the historical information matching table is determined according to the environmental information collected when the robot moves in the working area for non-initial times and the global map;

[0006] Detect whether the similarity between the current feature of the current environmental information at any position of the robot in the working area and the global map is less than a preset threshold;

[0007] If not, do not update the global map, and dynamically update the historical information matching table;

[0008] If so, it is determined whether to update the current feature into the global map based on the historical information matching table and the current feature.

[0009] In a possible implementation manner, the global map is determined through the following steps:

[0010] When the robot first moves in the working area, an environmental map is constructed according to the first environmental image collected by the robot and the distance information in the working area;

[0011] The environmental map is rasterized to determine the global map;

[0012] When the robot is not used for the first time, the updated global map stored is used as the obtained global map.

[0013] In a possible implementation manner, the historical information matching table is determined through the following steps:

[0014] When controlling the robot to move non-first time in the working area, the second environmental information of the working area is collected in real time; wherein, the second environmental information includes obstacle information and dynamic object information;

[0015] Based on a deep learning algorithm, feature extraction is performed on the second environmental information to determine environmental features;

[0016] Based on the Euclidean distance calculation formula, the environmental features and the global map are matched to determine the first similarity between the environmental features and the global map;

[0017] The environmental features corresponding to the first similarity greater than the threshold and the corresponding similarity are mapped and stored to generate the historical information matching table.

[0018] In a possible implementation manner, the determining whether to update the current feature into the global map based on the historical information matching table and the current feature includes:

[0019] Multiple environmental features corresponding to the current feature are obtained in the historical information matching table;

[0020] Based on the Euclidean distance calculation formula, the environmental features and the current feature are calculated to determine the second similarity between each environmental feature and the current feature;

[0021] If the number of second similarities exceeding the threshold is greater than the preset number, the environmental feature and the current feature are successfully matched, and the current feature is updated into the global map.

[0022] In a possible implementation manner, updating the current feature to the global map includes:

[0023] Adding the current feature to the global map, and sequentially performing smoothing processing, fusion processing, and redundant information removal processing on the current feature and the old features in the global map to determine an initial global map;

[0024] Optimizing the map position corresponding to the current feature added in the initial global map based on a Kalman filter to determine the optimized global map.

[0025] In a possible implementation manner, dynamically updating the historical information matching table includes:

[0026] Storing the similarity between the current feature and the global map into the historical information matching table;

[0027] Detecting whether there are environmental features in the historical information matching table that have not been successfully matched for a long time;

[0028] If so, removing this environmental feature.

[0029] The embodiment of the present application further provides an automatic update device for a robot map. The automatic update device includes:

[0030] An acquisition module, configured to acquire a global map and a historical information matching table of the robot in the working area; wherein, the historical information matching table is determined according to the environmental information collected when the robot moves in the working area non-initially and the global map;

[0031] A matching module, configured to detect whether the similarity between the current feature of the current environmental information of the robot at any position in the working area and the global map is less than a preset threshold;

[0032] A map update module, configured to, if not, not update the global map and dynamically update the historical information matching table; if so, determine whether to update the current feature to the global map based on the historical information matching table and the current feature.

[0033] In a possible implementation manner, the automatic update device further includes a map construction module. The map construction module determines the global map through the following steps:

[0034] When the robot initially moves in the working area, construct an environmental map according to the first environmental image collected by the robot and the distance information in the working area;

[0035] Perform rasterization processing on the environmental map to determine a global map;

[0036] When the robot is not used for the first time, use the stored updated global map as the obtained global map.

[0037] An embodiment of the present application also provides an electronic device, including: a processor, a memory, and a bus. The memory stores machine-readable instructions executable by the processor. When the electronic device runs, the processor communicates with the memory through the bus. When the machine-readable instructions are executed by the processor, the steps of the automatic update method of the robot map as described above are executed.

[0038] An embodiment of the present application also provides a computer-readable storage medium. A computer program is stored on the computer-readable storage medium. When the computer program is run by a processor, the steps of the automatic update method of the robot map as described above are executed.

[0039] An automatic update method, device, electronic device, and storage medium for a robot map provided by an embodiment of the present application. The automatic update method includes: obtaining a global map of a working area of a robot and a historical information matching table; wherein, the historical information matching table is determined according to environmental information collected when the robot moves in the working area for non-initial time and the global map; detecting whether the similarity between the current feature of the current environmental information of the robot at any position in the working area and the global map is less than a preset threshold; if not, do not update the global map and perform dynamic update on the historical information matching table; if so, determine whether to update the current feature to the global map based on the historical information matching table and the current feature. By matching the current environmental information with the historical information matching table when the similarity between the current environmental information at a certain position and the global map is lower than the threshold, and if the match is successful, the robot map is updated, it is realized that even when the environmental change is large and most of the map does not match, the robot map can be accurately updated through the historical information matching table.

[0040] To make the above objects, features, and advantages of the present application more obvious and understandable, the following specifically enumerates preferred embodiments and, in conjunction with the accompanying drawings, makes the following detailed description. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] To more clearly illustrate the technical solutions of the embodiments of the present application, the following will briefly introduce the accompanying drawings required in the embodiments. It should be understood that the following drawings only show some embodiments of the present application, and therefore should not be regarded as limiting the scope. For those of ordinary skill in the art, without creative efforts, other related drawings can also be obtained based on these drawings.

[0042] Figure 1 It is a flowchart of an automatic update method for a robot map provided by an embodiment of the present application;

[0043] Figure 2 It is one of the structural schematic diagrams of an automatic update device for a robot map provided by an embodiment of the present application;

[0044] Figure 3 It is another structural schematic diagram of an automatic update device for a robot map provided by an embodiment of the present application;

[0045] Figure 4 It is a structural schematic diagram of an electronic device provided by an embodiment of the present application. Specific embodiments

[0046] To make the objectives, technical solutions, and advantages of the embodiments of the present application clearer, the following will clearly and completely describe the technical solutions in the embodiments of the present application in conjunction with the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only some of the embodiments of the present application, rather than all of them. Usually, the components of the embodiments of the present application described and shown in the accompanying drawings here can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present application provided in the accompanying drawings is not intended to limit the scope of the present application to be protected, but only represents the selected embodiments of the present application. Based on the embodiments of the present application, every other embodiment obtained by those of ordinary skill in the art without creative efforts belongs to the scope of protection of the present application.

[0047] In addition, the described embodiments are only some of the embodiments of the present application, rather than all of them. Usually, the components of the embodiments of the present application described and shown in the accompanying drawings here can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present application provided in the accompanying drawings is not intended to limit the scope of the present application to be protected, but only represents the selected embodiments of the present application. Based on the embodiments of the present application, all other embodiments obtained by those of ordinary skill in the art without creative efforts belong to the scope of protection of the present application.

[0048] To enable those skilled in the art to use the content of this application, in combination with a specific application scenario of "updating a robot map", the following embodiments are given. For those skilled in the art, without departing from the spirit and scope of this application, the general principles defined here can be applied to other embodiments and application scenarios.

[0049] The following methods, devices, electronic devices, or computer-readable storage media in the embodiments of this application can be applied to any scenario that requires updating a robot map. The embodiments of this application do not limit the specific application scenario. Any solution that uses the automatic update method, device, electronic device, and storage medium of a robot map provided by the embodiments of this application is within the protection scope of this application.

[0050] First, an application scenario applicable to this application is introduced. This application can be applied to the field of intelligent control technology.

[0051] Through research, it is found that mobile robots have served various industries in today's social development, such as factories, hospitals, families, hotels, exhibition halls, restaurants, etc., mainly performing tasks such as logistics, handling, distribution, and guidance. Mobile robots navigate autonomously in these scenarios. The adaptability and safety of their dynamic complex environment are important manifestations of their intelligence, and accurate global positioning is the most basic requirement for their autonomous navigation. Only with accurate global positioning can safe path planning be carried out and accurate multi-point reciprocating movement be achieved. Considering the dynamic and complex nature of the working scenario, temporary obstacles often appear within the sensor's field of view of the mobile robot, and even the working scenario undergoes local changes and does not match the already constructed global map. Therefore, for the global positioning algorithm to be accurate and reliable, it must have strong environmental adaptability and robustness. Therefore, how to automatically update the robot map has become a technical problem that cannot be underestimated.

[0052] Based on this, the embodiments of this application provide an automatic update method for a robot map. When the similarity between the current environmental information at a certain position and the global map is lower than a threshold, the current environmental information is matched with the historical information matching table. If the match is successful, the robot map is updated, realizing that even when the environment changes greatly and most of the map does not match, the robot map can be accurately updated through the historical information matching table.

[0053] Please refer to Figure 1 , Figure 1 which is a flowchart of an automatic update method for a robot map provided by the embodiments of this application. As Figure 1 shown in it, the automatic update method provided by the embodiments of this application includes:

[0054] S101: Obtain the global map of the robot in the working area and the historical information matching table; wherein, the historical information matching table is determined according to the environmental information collected when the robot moves in the working area non-initially and the global map.

[0055] In this step, obtain the global map of the robot in the working area and the historical information matching table.

[0056] Among them, the historical information matching table is determined according to the environmental information collected when the robot moves in the working area non-initially and the global map.

[0057] In a possible implementation manner, the global map is determined through the following steps:

[0058] A: When the robot moves in the working area for the first time, construct an environmental map according to the first environmental image collected by the robot and the distance information in the working area.

[0059] Here, when the robot moves in the working area for the first time, construct an environmental map according to the first environmental image collected by the robot and the distance information in the working area.

[0060] Among them, during the process of the robot executing tasks, it collects environmental information in real time through the mounted lidar and camera. This includes detecting obstacles, surface features, and dynamic objects in the environment, using deep learning algorithms to process camera images to extract rich visual features, and obtaining accurate distance information through the lidar. Feature matching is performed on the extracted visual features, the successfully matched feature points and their descriptors are mapped onto the map, and combined with the distance information of the lidar and other sensor data, the geometric structure of the map is further improved to obtain the environmental map.

[0061] B: Perform rasterization processing on the environmental map to determine the global map.

[0062] Here, perform rasterization processing on the environmental map to obtain a global raster map, and this global raster map is a two-dimensional global raster map corresponding to the working environment, so that the mobile robot can perform autonomous navigation in a dynamic and complex scene.

[0063] C: When the robot is not used for the first time, use the stored updated global map as the obtained global map.

[0064] Here, when the robot is not initially used, use the updated global map as the obtained global map, and use the updated global map to navigate the robot.

[0065] In a possible implementation, the historical information matching table is determined through the following steps:

[0066] (1): When controlling the robot to move non-initially in the working area, the second environmental information of the working area is collected in real time; wherein, the second environmental information includes obstacle information and dynamic object information.

[0067] Here, when controlling the robot to move non-initially in the working area, the second environmental information of the working area is collected in real time.

[0068] (2): Based on the deep learning algorithm, feature extraction is performed on the second environmental information to determine environmental features.

[0069] Here, based on the deep learning algorithm, feature extraction is performed on the second environmental information to determine environmental features.

[0070] Among them, an efficient feature extraction algorithm is used to process the captured image to generate feature points and their descriptors. These feature descriptors are used for subsequent matching processes to identify the same position at different time points.

[0071] (3): Based on the Euclidean distance calculation formula, the environmental features and the global map are matched to determine the first similarity between the environmental features and the global map.

[0072] Here, based on the Euclidean distance calculation formula, the environmental features and the global map are matched to determine the first similarity between the environmental features and the global map.

[0073] (4): The environmental features corresponding to the first similarity greater than the threshold and the corresponding similarity are mapped and stored to generate the historical information matching table.

[0074] Here, the environmental features corresponding to the first similarity greater than the threshold and the corresponding similarity are mapped and stored to generate the historical information matching table.

[0075] Among them, after each collection of environmental information, the robot calculates the matching degree between the current features and the pre-stored global map. This matching degree can be obtained by calculating the similarity between feature descriptors (such as Hamming distance or Euclidean distance) and the result is stored in the database to form the historical information matching table.

[0076] S102: Detect whether the similarity between the current features of the current environmental information of the robot at any position in the working area and the global map is less than a preset threshold.

[0077] In this step, it is detected whether the similarity between the current feature of the current environmental information at any position in the working area of the robot and the global map is less than a preset threshold.

[0078] Among them, the system sets a suitable matching threshold according to the dynamic changes of the environment, and this threshold can be dynamically adjusted through historical data analysis to adapt to the characteristics of different environments.

[0079] S103: If not, the global map is not updated, and the historical information matching table is dynamically updated.

[0080] Here, if not, when updating the global map, it is necessary to dynamically update the historical information matching table according to the current environmental information.

[0081] In a possible implementation manner, the dynamically updating the historical information matching table includes:

[0082] a: Storing the current feature and the similarity between it and the global map into the historical information matching table.

[0083] Here, the current feature and the similarity between it and the global map are stored into the historical information matching table.

[0084] b: Detecting whether there are environmental features in the historical information matching table that have not been successfully matched for a long time; if so, removing this environmental feature.

[0085] Here, it is detected whether there are environmental features in the historical information matching table that have not been successfully matched for a long time; if so, this environmental feature is removed to realize the dynamic update of the historical information matching table.

[0086] S104: If so, it is determined whether to update the current feature to the global map based on the historical information matching table and the current feature.

[0087] In this step, if so, it is determined whether to update the current feature to the global map according to the historical information matching table and the current feature.

[0088] In a possible implementation manner, the determining whether to update the current feature to the global map based on the historical information matching table and the current feature includes:

[0089] I: Obtaining multiple environmental features corresponding to the current feature in the historical information matching table.

[0090] Here, multiple environmental features most similar to the current feature are obtained in the historical information matching table according to the current feature.

[0091] II: Calculate the environmental features and the current features based on the Euclidean distance calculation formula to determine the second similarity between each environmental feature and the current feature.

[0092] Here, calculate the environmental features and the current features according to the Euclidean distance calculation formula to determine the second similarity between each environmental feature and the current feature.

[0093] III: If the number of second similarities exceeding the threshold is greater than the preset number, the environmental feature and the current feature are successfully matched, and the current feature is updated to the global map.

[0094] Here, if the number of second similarities exceeding the threshold is greater than the preset number, the environmental feature and the current feature are successfully matched, and the current feature is updated to the global map.

[0095] Once the detected matching value is lower than the threshold, the system will automatically retrieve relevant environmental features from the historical information matching table. By analyzing the environmental features, identify the environmental features similar to the current feature for secondary matching. This process uses an efficient matching algorithm to improve speed and accuracy.

[0096] In a possible implementation, updating the current feature to the global map includes:

[0097] i: Add the current feature to the global map, and perform smoothing processing, fusion processing, and redundant information removal processing on the current feature and the old features in the global map in sequence to determine the initial global map.

[0098] Here, add the current feature to the global map, and perform smoothing processing, fusion processing, and redundant information removal processing on the current feature and the old features in the global map in sequence to determine the initial global map.

[0099] ii: Optimize the map position corresponding to the added current feature in the initial global map based on the Kalman filter to determine the optimized global map.

[0100] Here, optimize the map position corresponding to the added current feature in the initial global map according to the Kalman filter to determine the optimized global map.

[0101] Among specific embodiments, environmental information collection: The robot collects environmental information in real time through the mounted lidar and camera. The lidar is used to obtain accurate distance information, and the camera is used to capture visual features in the environment. Feature extraction: Process the collected images to extract feature points and their descriptors. Matching degree calculation: The robot calculates the matching degree between the current feature and the pre-stored visual map. It can be obtained by calculating the similarity between feature descriptors (such as Hamming distance or Euclidean distance). Storing historical information: Store the matching results in the database to form a historical information matching table. Threshold setting and monitoring: Set an appropriate matching threshold according to the dynamic changes of the environment, and dynamically adjust it through historical data analysis. The system monitors the matching value between the current environmental information and the map in real time. When the matching value is lower than the threshold, the map update mechanism is triggered. Historical information comparison: The system automatically retrieves relevant historical information. By analyzing the historical matching data, identify historical features similar to the current feature and perform secondary matching. Map update mechanism: Incorporate the new environmental information into the existing map, use algorithms to smooth and fuse the new and old information, and eliminate redundant information. Adjust the positions of relevant features in the map through optimized algorithms to ensure the overall consistency and accuracy of the map.

[0102] An automatic update method for a robot map provided by an embodiment of the present application, the automatic update method includes: obtaining a global map of the robot in the working area and a historical information matching table; wherein, the historical information matching table is determined according to the environmental information collected when the robot moves in the working area non-initially and the global map; detecting whether the similarity between the current feature of the current environmental information of the robot at any position in the working area and the global map is less than a preset threshold; if not, then do not update the global map and dynamically update the historical information matching table; if so, determine whether to update the current feature to the global map based on the historical information matching table and the current feature. By when the similarity between the current environmental information at a certain position and the global map is lower than the threshold, the current environmental information will be matched with the historical information matching table. If the match is successful, the robot map is updated, which realizes accurately updating the robot map through the historical information matching table when the environmental change is large and most of the map does not match.

[0103] Please refer to Figure 2 、 Figure 3 , Figure 2 which is one of the structural schematic diagrams of an automatic update device for a robot map provided by an embodiment of the present application; Figure 3 which is the second structural schematic diagram of an automatic update device for a robot map provided by an embodiment of the present application. As Figure 2As shown in the figure, the automatic update device 200 of the robot map includes:

[0104] An acquisition module 210, configured to acquire a global map of the robot in the working area and a historical information matching table; wherein, the historical information matching table is determined according to the environmental information collected when the robot moves in the working area for non-initial times and the global map;

[0105] A matching module 220, configured to detect whether the similarity between the current feature of the current environmental information of the robot at any position in the working area and the global map is less than a preset threshold;

[0106] A map update module 230, configured to, if not, not update the global map and dynamically update the historical information matching table; if so, determine whether to update the current feature to the global map based on the historical information matching table and the current feature.

[0107] Further, as Figure 3 shown, the automatic update device 200 of the robot map further includes a map construction module 240, and the map construction module 240 determines the global map through the following steps:

[0108] When the robot moves in the working area for the first time, construct an environmental map according to the first environmental image collected by the robot and the distance information in the working area;

[0109] Perform rasterization processing on the environmental map to determine the global map;

[0110] When the robot is not used for the first time, use the stored updated global map as the acquired global map.

[0111] Further, as Figure 3 shown, the automatic update device 200 of the robot map further includes a matching degree recording module 250, and the matching degree recording module 250 determines the historical information matching table through the following steps:

[0112] Control the robot to collect the second environmental information of the working area in real time when it moves in the working area for non-initial times; wherein, the second environmental information includes obstacle information and dynamic object information;

[0113] Extract features from the second environmental information based on a deep learning algorithm to determine environmental features;

[0114] Match the environmental features and the global map based on the Euclidean distance calculation formula to determine the first similarity between the environmental features and the global map;

[0115] The environmental features corresponding to the first similarity greater than a threshold and the corresponding similarity are mapped and stored to generate the historical information matching table.

[0116] Furthermore, the map updating module 230 is used to determine whether to update the current feature into the global map based on the historical information matching table and the current feature. The map updating module 230 is specifically used to:

[0117] Acquire multiple environmental features corresponding to the current feature in the historical information matching table;

[0118] Calculate the environmental features and the current features based on a Euclidean distance calculation formula to determine a second similarity between each of the environmental features and the current feature;

[0119] If the number of second similarities exceeding the threshold is greater than a preset number, the environmental feature is successfully matched with the current feature, and the current feature is updated to the global map.

[0120] Furthermore, the map updating module 230 is used to update the current feature to the global map. The map updating module 230 is specifically used to:

[0121] Adding the current feature to the global map, performing smoothing, fusion and redundant information elimination on the current feature and old features in the global map in sequence, and determining an initial global map;

[0122] The map position corresponding to the added current feature in the initial global map is optimized based on the Kalman filter to determine the optimized global map.

[0123] Furthermore, when the map updating module 230 is used to dynamically update the historical information matching table, the map updating module 230 is specifically used to:

[0124] Storing the current feature and the similarity with the global map in the historical information matching table;

[0125] Detecting whether there are environmental features in the historical information matching table that have not been successfully matched for a long time;

[0126] If so, the environmental feature is eliminated.

[0127] An automatic update device for a robot map provided by an embodiment of the present application, the automatic update device includes: an acquisition module, configured to acquire a global map of a working area of the robot and a historical information matching table; wherein, the historical information matching table is determined according to environmental information collected when the robot moves in the working area non-initially and the global map; a matching module, configured to detect whether the similarity between the current feature of the current environmental information of the robot at any position in the working area and the global map is less than a preset threshold; a map update module, configured to, if not, not update the global map and dynamically update the historical information matching table; if so, determine whether to update the current feature to the global map based on the historical information matching table and the current feature. By matching the current environmental information with the historical information matching table when the similarity between the current environmental information at a certain position and the global map is lower than the threshold, and if the matching is successful, the robot map is updated, it is realized that even when the environmental change is large and most of the map does not match, the robot map can be accurately updated through the historical information matching table.

[0128] Please refer to Figure 4 , Figure 4 which is a schematic structural diagram of an electronic device provided by an embodiment of the present application. As Figure 4 shown in

[0129] the electronic device 400 includes a processor 410, a memory 420, and a bus 430. Figure 1 The memory 420 stores machine-readable instructions executable by the processor 410. When the electronic device 400 runs, the processor 410 communicates with the memory 420 through the bus 430. When the machine-readable instructions are executed by the processor 410, the steps of the automatic update method of the robot map in the method embodiment as shown above

[0130] can be executed. For the specific implementation manner, reference can be made to the method embodiment, which will not be elaborated here. Figure 1 The present application embodiment also provides a computer-readable storage medium. A computer program is stored on the computer-readable storage medium. When the computer program is run by a processor, the steps of the automatic update method of the robot map in the method embodiment as shown above

[0131] can be executed. For the specific implementation manner, reference can be made to the method embodiment, which will not be elaborated here.

[0132] In several embodiments provided by the present application, it should be understood that the disclosed systems, devices, and methods can be implemented in other ways. The device embodiments described above are merely illustrative. For example, the division of the units is only a logical function division. In actual implementation, there may be other division methods. For another example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed couplings or direct couplings or communication connections to each other can be through some communication interfaces. The indirect couplings or communication connections of the devices or units can be in electrical, mechanical, or other forms.

[0133] The units described as separate components may or may not be physically separated. The components displayed as units may or may not be physical units, that is, they can be located in one place or distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0134] In addition, in each embodiment of the present application, the functional units can be integrated in a processing unit, or each unit can exist physically alone, or two or more units can be integrated in one unit.

[0135] If the function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a non-volatile computer-readable storage medium executable by a processor. Based on such an understanding, the technical solution of the present application, in essence, or the part that contributes to the prior art, or a part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in each embodiment of the present application. The aforementioned storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical discs that can store program codes.

[0136] Finally, it should be noted that the above-described embodiments are only specific implementation manners of the present application, used to illustrate the technical solutions of the present application, rather than limiting it. The protection scope of the present application is not limited thereto. Although the present application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that any person skilled in the technical field of the present application can still modify the technical solutions described in the foregoing embodiments, or can easily think of changes, or perform equivalent replacements on some of the technical features; and these modifications, changes or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application, and should all be covered within the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.

Claims

1. A method for automatically updating a robot map, characterized in that: The automatic updating method comprises: Obtaining a global map of the robot in the working area and a historical information matching table; wherein the historical information matching table is determined based on environmental information collected when the robot is not initially moving in the working area and the global map; Detecting whether the similarity between the current features of the current environmental information of the robot at any position in the working area and the global map is less than a preset threshold; If not, the global map is not updated, and the historical information matching table is dynamically updated; If so, it is determined whether to update the current feature into the global map based on the historical information matching table and the current feature.

2. The automatic updating method according to claim 1, characterized in that: The global map is determined by the following steps: When the robot moves in the working area for the first time, constructing an environment map according to a first environment image collected by the robot and distance information in the working area; rasterizing the environment map to determine a global map; When the robot is not used for the first time, the stored updated global map is used as the acquired global map.

3. The automatic updating method according to claim 1, characterized in that: The historical information matching table is determined by the following steps: Controlling the robot to collect second environmental information of the working area in real time when the robot moves in the working area other than for the first time; wherein the second environmental information includes obstacle information and dynamic object information; Extracting features of the second environmental information based on a deep learning algorithm to determine environmental features; Matching the environmental features and the global map based on a Euclidean distance calculation formula to determine a first similarity between the environmental features and the global map; The environmental features corresponding to the first similarity greater than a threshold and the corresponding similarity are mapped and stored to generate the historical information matching table.

4. The automatic updating method according to claim 1, characterized in that: The determining whether to update the current feature into the global map based on the historical information matching table and the current feature includes: Acquire multiple environmental features corresponding to the current feature in the historical information matching table; Calculate the environmental features and the current features based on a Euclidean distance calculation formula to determine a second similarity between each of the environmental features and the current feature; If the number of second similarities exceeding the threshold is greater than a preset number, the environmental feature is successfully matched with the current feature, and the current feature is updated to the global map.

5. The automatic updating method according to claim 4, characterized in that: The updating of the current feature into the global map comprises: Adding the current feature to the global map, performing smoothing, fusion and redundant information elimination on the current feature and old features in the global map in sequence, and determining an initial global map; The map position corresponding to the added current feature in the initial global map is optimized based on the Kalman filter to determine the optimized global map.

6. The automatic updating method according to claim 1, characterized in that: The dynamically updating the historical information matching table includes: Storing the current feature and the similarity with the global map in the historical information matching table; Detecting whether there are environmental features in the historical information matching table that have not been successfully matched for a long time; If so, the environmental feature is eliminated.

7. A robot map automatic updating device, characterized in that: The automatic updating device comprises: An acquisition module, used to acquire a global map of the robot in the working area and a historical information matching table; wherein the historical information matching table is determined based on environmental information collected when the robot is not initially moving in the working area and the global map; A matching module, used to detect whether the similarity between the current features of the current environmental information of the robot at any position in the working area and the global map is less than a preset threshold; The map update module is used for not updating the global map and dynamically updating the historical information matching table if no; and for determining whether to update the current feature to the global map based on the historical information matching table and the current feature if yes.

8. The automatic updating device according to claim 7, characterized in that: The automatic updating device further includes a map construction module, which determines the global map by the following steps: When the robot moves in the working area for the first time, constructing an environment map according to a first environment image collected by the robot and distance information in the working area; rasterizing the environment map to determine a global map; When the robot is not used for the first time, the stored updated global map is used as the acquired global map.

9. An electronic device, characterized in that: include: A processor, a memory and a bus, wherein the memory stores machine-readable instructions executable by the processor, and when the electronic device is running, the processor and the memory communicate through the bus, and the machine-readable instructions are executed by the processor to perform the steps of the automatic update method of the robot map as described in any one of claims 1 to 6.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the method for automatically updating a robot map according to any one of claims 1 to 6 are executed.

Images