Navigation method and device, electronic equipment and storage medium

Abstract

Embodiments of the present application relate to a navigation method and device, electronic equipment and storage medium, the method comprising: obtaining a grid map of a target area, the grid map being obtained by rasterizing a plan view of the target area; determining a target node of a target object in the grid map, and determining a starting node of the target object in the grid map; determining a target path of the target object from the starting node to the target node; and navigating the target object according to a preset navigation mode based on the target path. Thus, the target path of the target object from the current starting node to the target node can be determined based on the grid map of the target area, and the target object can be navigated according to the preset navigation mode. The user can be guided from the starting position to the specified location in the target area, and the target object can be prevented from finding the wrong position and wasting a lot of time and effort.

Description

Technical Field

[0001] The present invention relates to the field of computer technology, and in particular to a navigation method, device, electronic device and storage medium. Background Technology

[0002] With the continuous development of sensor and information technologies, all aspects of life are becoming more intelligent. People are no longer satisfied with traditional information transmission methods and are pursuing wireless, high-speed, secure, and convenient information transmission methods, giving rise to the Internet of Things (IoT). The most significant impact is on navigation, which, as one of the core issues in robotics, has strong application demands in scenarios such as aircraft control, autonomous driving, and home service robots.

[0003] In real life, as buildings become larger and filled with more obstacles, it becomes more difficult for users to find the place or room they want to go to. For example, when a user is visiting a host's home, they often find it difficult to locate the toilet or guest room.

[0004] Therefore, there is an urgent need for a technical solution that can guide users from their starting point in a building to a designated location, enabling users to accurately reach their destination. Summary of the Invention

[0005] In view of this, to address the technical problem that as buildings become larger and filled with more obstacles, it becomes more difficult for users to find the desired location or room within a building, embodiments of the present invention provide a navigation method, apparatus, electronic device, and storage medium.

[0006] In a first aspect, embodiments of the present invention provide a navigation method, the method comprising:

[0007] Obtain a raster map of the target area, wherein the raster map is obtained by rasterizing a plan view of the target area;

[0008] Determine the target node of the target object in the grid map, and determine the starting node of the target object in the grid map;

[0009] Determine the target path of the target object from the starting node to the target node;

[0010] Based on the target path, the target object is navigated according to a preset navigation method.

[0011] In an optional implementation, acquiring the raster map of the target area includes:

[0012] Obtain a plan view and area information of the target region;

[0013] The grid size of the plan is determined based on the area information of the region;

[0014] Based on the grid size and pre-set grid division information, the plan view of the target area is rasterized to obtain a raster map of the target area.

[0015] In an optional implementation, when the target area comprises multiple sub-regions, obtaining a raster map of the target area includes:

[0016] Obtain sub-planar maps and corresponding regional feature information for each sub-region in the target region. The regional feature information includes at least: area information and / or height information for each sub-region.

[0017] For each sub-region within the target region, the grid size of the sub-planar map is determined based on the area information of the sub-region;

[0018] Obtain the grid division information set for the sub-planar diagram;

[0019] The sub-planar map is rasterized according to the grid size and the set grid division information to obtain a sub-raster map of the sub-region, and the sub-raster map carries the height information of the sub-region;

[0020] The sub-raster map of the multi-layered sub-region is determined as the raster map of the target region.

[0021] In an optional implementation, acquiring the raster map of the target area further includes:

[0022] The plan view of the target area is identified to determine the obstacles and passable areas contained in the plan view;

[0023] Determine the obstacle grid area and the passable grid area in the grid map of the target area that correspond to the obstacles and passable areas contained in the plan view;

[0024] The obstacle grid area and the passable grid area in the grid map are marked according to the preset attribute information to obtain the marked grid map.

[0025] In an optional implementation, determining the target node of the target object in the grid map includes:

[0026] Obtain object information of the target object, wherein the object information is collected by a preset information acquisition module;

[0027] Search a preset database to determine the target grid in the grid map of the target area that matches the object information. The database includes the correspondence between the object information and the grid in the grid map.

[0028] The node of the target grid in the grid map is determined as the target node.

[0029] In an optional implementation, the object information includes the facial information of the target object; the step of searching a preset database to determine the target raster that matches the object information includes:

[0030] Feature extraction is performed on the facial information of the target object to obtain facial feature information;

[0031] Search a preset database to determine the target grid in the grid map of the target area that matches the facial feature information.

[0032] In an optional implementation, determining the target path from the starting node to the target node includes:

[0033] The labeled raster map is subjected to attribute recognition to determine the passable raster area in the raster map, and the passable node corresponding to the passable raster area in the raster map is determined. The passable node includes the target node of the target object in the raster map.

[0034] Based on a preset movement cost algorithm, calculations are performed on the passable nodes and the initial node of the target object to determine the target path from the starting node to the target node.

[0035] In an optional implementation, the step of calculating the target path from the starting node to the target node based on a preset movement cost algorithm for the passable nodes and the initial node of the target object includes:

[0036] Store the starting node of the target object in the grid map into a preset open list;

[0037] Determine the path nodes adjacent to the initial node from the passable nodes, and store the adjacent path nodes in the open list;

[0038] By using a preset movement cost algorithm, the cost from the initial node to each path node in the open list is calculated.

[0039] Select the target path node with the minimum cost value from the cost values ​​as the next node, and store the target path node in a preset closed list;

[0040] For the target path node, perform the step of determining the path node adjacent to the target path node from the passable nodes;

[0041] If the target path node corresponding to the minimum cost value is selected from the cost values, and it is the target node of the target object in the grid map, the target node is stored in the closed list.

[0042] Obtain the target path node saved in the closed list, and determine that the path corresponding to the target path node is the target path of the target object from the starting node to the target node.

[0043] In a second aspect, embodiments of the present invention provide a navigation device, the device comprising:

[0044] The map acquisition module is used to acquire a raster map of the target area, wherein the raster map is obtained by rasterizing a plan view of the target area.

[0045] The node determination module is used to determine the target node of the target object in the floor grid diagram, and to determine the starting node of the target object in the floor grid diagram.

[0046] A path determination module is used to determine the target path of the target object from the starting node to the target node;

[0047] The navigation module is used to navigate the target object according to a preset navigation method based on the target path.

[0048] Thirdly, embodiments of the present invention provide an electronic device, including: a processor and a memory, wherein the processor is configured to execute a navigation program stored in the memory to implement the navigation method described in any one of the first aspects.

[0049] Fourthly, embodiments of the present invention provide a storage medium storing one or more programs, which can be executed by one or more processors to implement the navigation method described in any one aspect.

[0050] The technical solution provided by this invention involves acquiring a raster map of the target area, which is obtained by rasterizing a plan view of the target area. The target node of the target object in the raster map is determined, as well as the current starting node of the target object in the raster map. The target path from the starting node to the target node is determined, and based on the target path, the target object is navigated according to a preset navigation method. In this way, the plan view of the target area can be rasterized, and based on the processed raster map of the target area, the target path from the current starting node to the target node can be determined. The target object is then navigated according to a preset navigation method. This guides the user from the starting point to the designated location within the target area, preventing the target object from finding the wrong location and wasting a lot of time and effort. Attached Figure Description

[0051] Figure 1 A flowchart illustrating an embodiment of a navigation method provided by the present invention;

[0052] Figure 2 A flowchart illustrating another embodiment of the navigation method provided by this invention;

[0053] Figure 3 A flowchart illustrating another embodiment of the navigation method provided by the present invention;

[0054] Figure 4 This is a schematic diagram illustrating the various nodes in an embodiment of the present invention;

[0055] Figure 5 A block diagram illustrating an embodiment of a navigation device provided by the present invention;

[0056] Figure 6 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention. Detailed Implementation

[0057] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0058] The navigation method provided by the present invention will be further explained and described below with reference to the accompanying drawings and specific embodiments. The embodiments do not constitute a limitation on the embodiments of the present invention.

[0059] See Figure 1 This is a flowchart illustrating an embodiment of a navigation method provided by the present invention. Figure 1 As shown, the process may include the following steps:

[0060] Step 101: Obtain a raster map of the target area. The raster map is obtained by rasterizing the planar map of the target area.

[0061] The aforementioned raster map represents a raster image obtained by rasterizing a map (e.g., a 2D map, a 3D map, etc.) of the target area. A raster map is essentially an image that has been discretized in both space and brightness. In practice, a raster image can be considered as a matrix, where each element corresponds to a point in the image.

[0062] In one embodiment, an image rasterization application can be invoked in advance to rasterize the plan view of the target area, thereby obtaining a raster map of the target area.

[0063] In another embodiment, a raster map of the target area can be directly obtained and input into a pre-processing system through a visual interface to perform further operations on the raster map. For details, please refer to the relevant description of the process below, which will not be elaborated here.

[0064] In another embodiment, a processing program capable of image rasterization can be pre-written using encoding software. By inputting a planar image of the target area into the program, the planar image of the target area is rasterized according to the set rasterization rules to obtain a raster map of the target area. Thus, a raster map of the target area that meets the user's specified requirements can be obtained.

[0065] It should be noted that the above are only a few examples of methods for obtaining a raster map of a target area. In practice, other methods can also be used to obtain a raster map, and the embodiments of the present invention do not limit this.

[0066] Step 102: Determine the target node of the target object in the grid map, and determine the starting node of the target object in the grid map.

[0067] In this context, the target node refers to the target location that the target object needs to reach within the target area. The grid cell occupied by this target location in the grid map of the target area is called the target grid cell. Correspondingly, the node displayed by this target grid cell in the grid map is called the target node.

[0068] Similarly, the aforementioned starting node represents the current position of the target object within the target area. The grid cell occupied by this current position in the grid map of the target area is called the starting grid cell. Correspondingly, the node displayed by this starting grid cell in the grid map is called the starting node.

[0069] In one embodiment, the correspondence between the raster map of the target area and the target area can be predetermined (e.g., a ratio of 1:10). To enable navigation of the target object using the raster map of the target area, it is necessary to determine the target object's current position within the target area and its target position. Furthermore, based on the aforementioned correspondence between the raster map of the target area and the target area, the target object's current position and target position, as well as the corresponding starting and target nodes in the raster map of the target area, can be determined. Thus, the destination of the target object is known and displayed on the raster map, preventing the target object from wasting time searching for the target location or going to the wrong place.

[0070] Step 103: Determine the target path from the starting node to the target node.

[0071] In one embodiment, the aforementioned grid map is a gridded representation of the target area. It includes at least the movable routes within the target area. Therefore, after determining the starting node and target node of the target object in the grid map, the target path from the starting node to the target node can be determined based on the grid map.

[0072] The aforementioned target path can be the optimal path for a target object within a target region from the starting node to the target node. This optimal path signifies minimizing the cost incurred by the target object in traveling from the starting node to the target node. This cost may include at least time, and / or money, and / or physical effort, etc., but this embodiment of the invention does not impose specific limitations on this.

[0073] For example, taking the cost mentioned above as time, the corresponding target path is the shortest path. Assume there are three paths from the starting node to the target node, and the time distribution for each path is as follows: Path 1 takes 5 minutes; Path 2 takes 6 minutes; Path 3 takes 10 minutes. Therefore, the target path from the starting node to the target node is Path 1.

[0074] Optionally, a pre-set movement cost algorithm can be obtained to calculate the cost from the starting node to the target node. Based on this cost, the target path is determined. For details on how to determine the target path from the starting node to the target node, please refer to the following... Figure 2 The process described in the diagram will not be detailed here.

[0075] Step 104: Based on the target path, navigate to the target object according to the preset navigation method.

[0076] The aforementioned preset navigation methods may include, but are not limited to, voice navigation, image navigation, and 3D model-guided navigation. This embodiment of the invention does not impose specific limitations on these methods.

[0077] In this embodiment of the invention, after determining the target path from the starting node to the target node, the target object can be navigated according to a preset navigation method based on the target path.

[0078] For example, assuming the preset navigation method is voice navigation, and the target path is to walk 50 meters forward from the starting node, then turn right and walk 100 meters to the target node, then, according to the above description, the target object can be given voice navigation: "Start from the current starting node, walk 50 meters forward, then turn right and walk 100 meters to the target node."

[0079] Understandably, to ensure the real-time effectiveness of navigation, the nodes of the target object in the grid map of the target area can be monitored in real time. This prevents the target object from going astray and allows for timely reminders to correct the walking route, ensuring that the target object can accurately reach the target node.

[0080] This concludes the process. Figure 1 The process described is as follows.

[0081] pass Figure 1 As shown in the flowchart, in the technical solution of this invention, a raster map of the target area is obtained, which is obtained by rasterizing a plan view of the target area. The target node of the target object in the raster map and the current starting node of the target object in the raster map are determined. The target path from the starting node to the target node is determined, and based on the target path, the target object is navigated according to a preset navigation method. In this way, the plan view of the target area can be rasterized, and based on the processed raster map of the target area, the target path from the current starting node to the target node can be determined. The target object is then navigated according to a preset navigation method. This guides the user from the starting point to the designated location in the target area, avoiding the user going to the wrong location and wasting a lot of time and effort, thus improving the user experience.

[0082] See Figure 2 This is a flowchart illustrating another embodiment of the navigation method provided by the present invention. Figure 2 The process shown is in Figure 1 Based on the illustrated process, this section describes in detail how to obtain the raster map of the target area, and the specific target path suitable for determining the target object from the starting node to the target node. For example... Figure 2 As shown, the process may include the following steps:

[0083] Step 201: Obtain a raster map of the target area. The raster map is obtained by rasterizing the planar map of the target area.

[0084] In one embodiment, taking the target area as an example, it can be a single planar area (e.g., a floor, a home, an office, etc.), meaning the target area does not contain multiple sub-areas. The specific implementation of obtaining the raster map of the target area may include: obtaining a plan view and area information of the target area; determining the raster size of the plan view based on the area information; and rasterizing the plan view of the target area based on the raster size and pre-set raster division information to obtain a raster map of the target area.

[0085] The aforementioned raster division information refers to the division information of the target area's planar map after rasterization, and it includes at least the number of raster rows and columns. Therefore, the specific number of raster cells in the target area's map can be determined.

[0086] The grid size mentioned above refers to the size of the raster map obtained after rasterizing the plan view of the target area.

[0087] Optionally, the specific implementation of determining the grid size of the plan view based on the area information may include: obtaining a pre-set correspondence between area information and grid size, and determining the grid size corresponding to the area information based on this correspondence. For example, the correspondence between the area information and grid size is 10:1. If the area is 100, then the corresponding grid size is 10.

[0088] The aforementioned correspondence can be a proportional relationship between area information and grid size, or it can be a table or database showing the relationship between area information and grid size, etc., without any specific limitations.

[0089] In another embodiment, when the target area includes multiple sub-regions, the specific implementation of obtaining the raster map of the target area may include: obtaining a sub-planar map of each sub-region in the target area and corresponding regional feature information, wherein the regional feature information includes at least: area information and / or height information of each sub-region; determining the raster size of the sub-planar map for each sub-region in the target area based on the area information of the sub-region; obtaining the raster division information set for the sub-planar map; performing rasterization processing on the sub-planar map based on the raster size of the sub-planar map and the set raster division information to obtain a sub-raster map of the sub-region, wherein the sub-raster map carries the height information of the sub-region; and determining the sub-raster map of the multiple sub-regions as the raster map of the target area.

[0090] The target area mentioned above can be a building with multiple floors (such as an office building, apartment building, etc.), or a part of a building; it can also be a user's home, and correspondingly, the sub-area mentioned above can be each room in the user's home. There are no specific restrictions on this.

[0091] The height information of the aforementioned sub-region can be its height relative to the ground (e.g., 3 meters, 10 meters, etc.), or it can be the height information of the sub-region within the target area. For example, if the target area is a 10-story apartment building, then the height information of the sub-region can be its height within the target area, such as the 1st floor, 2nd floor, 3rd floor, etc. This embodiment of the invention does not impose specific limitations on this. Therefore, after determining the target path, this embodiment of the invention can navigate the object according to the target path using a preset navigation method based on the aforementioned height information.

[0092] In this embodiment of the invention, when the target area comprises multiple sub-regions, the sub-planar map of each sub-region can be rasterized to obtain a sub-raster map of each sub-region. Optionally, the sub-raster map of each sub-region may include the height information of that sub-region.

[0093] Optionally, the sub-raster maps of multiple sub-regions can be integrated to obtain a raster map of the target region. The integrated sub-raster maps of multiple sub-regions can be sub-raster maps of all sub-regions included in the target region, or they can be sub-raster maps of only some sub-regions included in the target region; this embodiment of the invention does not impose specific limitations on this.

[0094] In another embodiment, to facilitate subsequent identification and navigation operations based on the grid map of the target area, and to accurately navigate the target object to its target location, the specific implementation of obtaining the grid map of the target area may include: identifying the plan view of the target area to determine the obstacles and passable areas contained in the plan view; determining the obstacle grid areas and passable grid areas in the grid map of the target area that correspond to the obstacles and passable areas contained in the plan view; and annotating the obstacle grid areas and passable grid areas in the grid map according to preset attribute information to obtain the annotated grid map. The aforementioned attribute information may be the attribute information of various elements (at least including obstacles, floors, etc.) contained in the plan view or grid map of the target area, specifically including color, name, identification code, mass, volume, etc., which are not limited in this embodiment of the present invention.

[0095] Optionally, taking the aforementioned attribute information as an example, to facilitate subsequent determination of the target path from the starting node to the target node based on the grid map, the colors used to mark the obstacle grid area and the passable grid area are different. For example, black is used to mark the obstacle grid area, and white is used to mark the passable grid area. This embodiment of the invention does not impose specific limitations on the types of colors used to mark the obstacle grid area and the passable grid area in the grid map.

[0096] Furthermore, to facilitate accurate determination of the target node and starting node of the target object in the raster map, the target position and starting position of the target object in the plan view of the target area can be determined. Further, based on the correspondence between the plan view of the target area and the raster map, the target position and starting position of the target object in the plan view can be determined. Correspondingly, the target raster area and the starting raster area are marked in the raster map according to preset colors. Thus, the marked raster map contains target raster areas and starting raster areas marked with different colors.

[0097] As described above, the colors used to label the target grid area and the starting grid area are also different. For example, red is used to label the target grid area, and yellow is used to label the starting grid area. This embodiment of the invention does not impose specific limitations on the types of colors used to label the target grid area and the starting grid area in the grid map. Furthermore, this embodiment of the invention does not limit the categories of the aforementioned attribute information.

[0098] Step 202: Obtain the object information of the target object. The object information is obtained through a preset information collection module.

[0099] Step 203: Search the preset database to determine the target grid in the grid map of the target area that matches the object information. The database includes the correspondence between the object information and the grid in the grid map.

[0100] Step 204: Determine the node of the target raster in the raster map as the target node.

[0101] The following provides a unified description of steps 202 to 204:

[0102] The aforementioned object information can be information that characterizes the features of the target object, such as the target object's name, contact information, facial information, fingerprint information, iris information, etc., or feature information of the identifier carried by the target object (such as card number, etc.), without specific limitations.

[0103] Taking hotels as an example, in real life, some hotels record the facial information and room information of their guests by taking photos of them. Therefore, by collecting the facial information of a target, the hotel's database can be used to find rooms that match that target's facial information.

[0104] In one embodiment, the object information includes the facial information of the target object; the specific implementation of searching a preset database to determine the target grid in the grid map of the target area that matches the object information may include: extracting features from the facial information of the target object to obtain facial feature information; and searching a preset database to determine the target grid in the grid map of the target area that matches the facial feature information.

[0105] The aforementioned facial information can be a facial image of the target object. The aforementioned database includes at least the correspondence between facial feature information and grids in a raster map of the target area, or the correspondence between facial feature information and sub-regions (e.g., rooms) within the target area.

[0106] Optionally, taking the aforementioned database, which includes the correspondence between facial feature information and sub-regions within the target area, as an example, the above-mentioned search of the preset database determines the target raster in the raster map of the target area that matches the facial feature information. Specifically, this can be achieved by searching the preset database to determine the sub-region in the target area that corresponds to the facial feature information of the target object. Furthermore, the raster corresponding to this sub-region in the raster map of the target area is determined, and this corresponding raster is identified as the target raster in the raster map that matches the facial feature information.

[0107] For example, assuming the aforementioned sub-region is a room, and the database includes the correspondence between facial feature information and sub-regions within the target area, then, as described above, by searching the preset database, the sub-region corresponding to the facial feature information of the target object is determined to be room 110, and the grid corresponding to room 110 in the grid map of the target area is determined to be the first grid. Thus, the target grid in the grid map that matches the facial feature information can be identified as the first grid.

[0108] Furthermore, as described in step 201 above, in this embodiment of the invention, when the target area includes multiple sub-regions, the sub-grid map of the multiple sub-regions can be determined as the grid map of the target area. The aforementioned sub-grid map carries the height information of each sub-region.

[0109] In one embodiment, height information matching the object information of the target object can also be obtained, thereby determining a sub-region within the target area that matches the height information. Further, the target grid of the target object can be determined in the sub-grid map to which the sub-region belongs. Thus, detailed navigation of the target object can be subsequently performed based on the height information.

[0110] In another embodiment, the object information includes the object fingerprint information of the target object; the specific implementation of searching a preset database to determine the target raster in the raster map of the target area that matches the object information may include: searching a preset database to determine the target raster in the raster map of the target area that matches the object fingerprint information.

[0111] In another embodiment, the object information includes the object iris information of the target object; the specific implementation of searching a preset database to determine the target raster in the raster map of the target area that matches the object information may include: searching a preset database to determine the target raster in the raster map of the target area that matches the object iris information.

[0112] It should be noted that the above is merely an exemplary description of the form of object information and the method of determining the target raster that matches the object information. In practice, the above object information can be other forms of data, and other methods can be used to determine the target raster that matches the object information. This embodiment of the invention does not impose specific limitations on this.

[0113] In another embodiment, taking the object information including the object's facial information as an example, the specific implementation of searching a preset database and determining the target grid that matches the object information may include: by calling a pre-set image acquisition device, obtaining the historical acquisition data of the image acquisition device, determining the location information that matches the object's facial information from the historical acquisition data, and determining the target grid that matches the location information in the target area's grid map.

[0114] The image acquisition device mentioned above can be any electronic device such as a camera or video recorder installed within the target area, without specific limitations. The historical acquisition data mentioned above can at least include the correspondence between object information and location information. Based on this, location information matching the aforementioned object's facial information can be determined from the historical acquisition data.

[0115] Step 205: Determine the starting node of the target object in the raster map.

[0116] In one embodiment, when the target area comprises multiple sub-regions, the current height information of the target object within the target area can be obtained, and the sub-region matching the aforementioned height information within each sub-region of the target area can be determined. Further, the current position of the target area within that sub-region can be obtained, and the corresponding grid cell in the sub-grid map of the sub-region can be determined. The starting node of the corresponding grid cell in the current grid map can be determined. Here, the grid map can be a sub-grid sub-map of the aforementioned sub-region, or a grid map containing sub-grid maps of sub-regions, such as a grid map of the target area; no specific limitation is imposed.

[0117] For a detailed description of step 205, please refer to the detailed explanation of step 102 above, which will not be repeated here.

[0118] Step 206: Determine the target path from the starting node to the target node of the target object.

[0119] As can be seen from the description of step 201 above, in the process of obtaining the grid map of the target area in this embodiment of the invention, the obstacle grid area and the passable grid area in the grid map can also be marked according to the preset attribute information to obtain the marked grid map.

[0120] In one embodiment, the specific implementation of determining the target path from the starting node to the target node may include: performing attribute recognition on the labeled raster map, determining the passable raster areas in the raster map, and determining the passable nodes corresponding to the passable raster areas in the raster map, whereby the passable nodes include the target node of the target object in the raster map. Based on a preset movement cost algorithm, calculations are performed on the passable nodes and the initial node of the target object to determine the target path from the starting node to the target node.

[0121] The aforementioned passable nodes are the nodes corresponding to passable graticets in the raster map. A passable graticet is a series of consecutive graticets within a passable graticet region in the raster map.

[0122] Specifically, taking the aforementioned attribute information as color, and using black to mark obstacle grid areas and white to mark passable grid areas as an example, color recognition can be performed on the marked grid map to determine that the white-marked areas in the grid map are passable grid areas. Furthermore, based on the white-marked areas in the grid map, areas with continuous color are identified as the corresponding passable grids in the grid map. Further, passable nodes can be determined based on these passable grids.

[0123] Optionally, the specific implementation of the above-mentioned calculation of the passable nodes and the initial node of the target object based on the preset movement cost algorithm to determine the target path from the starting node to the target node may include: storing the starting node of the target object in the grid map into a preset open list, determining the path nodes adjacent to the initial node from the passable nodes, and storing the adjacent path nodes into the open list.

[0124] Furthermore, a preset movement cost algorithm can be used to calculate the cost from the initial node to each path node in the open list. The target path node with the lowest cost is selected as the next node, and this target path node is stored in a preset closed list. For each target path node, the step of determining the adjacent path nodes from the passable nodes is performed. If the target path node with the lowest cost is indeed the target node of the target object in the raster map, this target node is stored in the closed list.

[0125] Furthermore, it is possible to obtain the target path nodes saved in the closed list and determine that the path corresponding to the target path node is the target path of the target object from the starting node to the target node.

[0126] The open list includes walkable nodes contained in the raster map. The closed list includes target path nodes filtered from the walkable nodes contained in the raster map; that is, walkable nodes that the target object needs to traverse from the starting node to the target node.

[0127] It should be noted that the above method uses a preset movement cost algorithm to calculate the cost from the initial node to each path node in the open list. A higher cost indicates a higher cost incurred by the target object, meaning a worse path. Conversely, a lower cost indicates a lower cost incurred by the target object, meaning a better path.

[0128] Specifically, the above-mentioned movement cost algorithm is used to calculate the cost from the initial node to each path node in the open list, and the cost of moving from the initial node to each path node is obtained. The movement cost algorithm is shown in Equation (I) below:

[0129] f(n) = g(n) + h(n) (Equation 1)

[0130] Where n is the specified node; f(n) is the cost from the initial node to each path node; g(n) is the cost already paid from the starting node to the specified node; and h(n) is a heuristic function that represents the predicted cost from the specified node n to the target node.

[0131] The specified node n can be any path node, or any path node between the starting node and a path node; there is no specific restriction. When the specified node n is any path node between the starting node and a path node, h(n) is the predicted cost value from the specified node n to the target node. This predicted cost value can be the distance from the specified node n to the target node.

[0132] Optionally, for multiple motion directions with multiple paths, the above heuristic function can be the Chebyshev distance function.

[0133] Optionally, the above heuristic function can also be the Manhattan distance function, and the embodiments of the present invention do not impose specific limitations on this.

[0134] Furthermore, it should be noted that the nodes stored in the open and closed lists above are merely examples. In practical applications, the obstacle nodes corresponding to the obstacle grid area in the grid map can also be stored in the closed list. In this case, the closed list can contain nodes that are no longer needed and can be reused. The starting node can also be stored in the open list, with the starting node as the parent node. Using the movement cost algorithm, the cost between the starting node and each adjacent node in the open list is calculated. If the cost of the target path node (i.e., the f(n) value) is the smallest, the target path node can be stored in the open list to indicate that the corresponding path has been found. The target path node is then used as the parent node, and the movement cost algorithm is used again for calculation. This process continues until the target node is determined and stored in the open list. The nodes stored in the open list can then be traced back to determine the target path from the starting node to the target node.

[0135] It should also be noted that when the target area includes multiple sub-regions, if the target node and the starting node are not located in the same sub-region, in order to facilitate determining the target path from the starting node to the target node, the sub-raster maps of each sub-region between the sub-raster map corresponding to the starting node and the sub-raster map corresponding to the target node can be integrated. This results in a raster map containing sub-raster maps of each sub-region between the sub-raster map corresponding to the starting node and the sub-raster map corresponding to the target node.

[0136] The connecting paths of each sub-region (such as stairs, elevators, etc.) can be labeled with specific attributes, so that the object can clearly know the connecting paths of each sub-region.

[0137] In this case, optionally, for each sub-region sub-raster map between the starting node and the target node, the path of the target object in the sub-raster map is determined, and the path of the target object in each sub-raster map is determined as the target path.

[0138] Taking the sub-grid map where the target object is located at the starting node as an example, the nodes of the connecting path between this area and the next layer sub-area can be determined in the sub-grid map. Based on the sub-grid map of the sub-area corresponding to the starting node, the path from the starting node to the node of the connecting path between this area and the sub-grid map can be determined.

[0139] Step 207: Based on the target path, navigate to the target object according to the preset navigation method.

[0140] In one embodiment, when the target area includes multiple sub-regions, the target path may include the height information of the sub-region corresponding to the starting node and the height information of the sub-region corresponding to the target node. Based on this, the target object can be navigated according to a preset navigation method.

[0141] For example, suppose the height information of the sub-region corresponding to the starting node is one layer, and the height information of the sub-region corresponding to the target node is three layers. Then, the target object can be navigated according to voice navigation or image display navigation, so that the target object can move from the current one-layer sub-region to the three-layer sub-region according to the target path.

[0142] For a detailed description of step 207, please refer to the detailed explanation of step 104 above, which will not be repeated here.

[0143] See Figure 3 This is a flowchart illustrating another embodiment of the navigation method provided by the present invention. In one embodiment, the target area is a building containing multiple floors. Figure 3 As shown, the process may include the following steps:

[0144] Step 1: Obtain the building's floor plan and rasterize it.

[0145] Specifically, the process involves obtaining the building's floor plans and areas, and then rasterizing them. Rasterization divides the map into several squares, the size of which can be customized. Smaller squares result in higher precision, while larger squares result in lower precision.

[0146] For floors with large areas, the grid can be refined; while for floors with small areas, the grid does not need to be very small. The advantage of rasterization is that it can draw floor plans with arbitrary shapes and outlines. Furthermore, in this embodiment of the invention, each grid can be represented by different colors to indicate different meanings. For example, black represents the obstacle grid area in the grid map, yellow represents the starting node of the target object in the grid map, and red represents the target node of the target object in the grid map. For instance, based on the door markings on the floor plan, the doorway can be designated as the target node.

[0147] To automate the gridding process, the grid area with the highest color proportion is automatically identified as a passable grid area. Grids with a continuous color within the passable grid area are considered walkable (i.e., passable grids). Black grids represent obstacles that need to be avoided.

[0148] Step 2: Enter the user's face and match it with the corresponding room.

[0149] Specifically, the process involves collecting users' facial images, extracting facial feature information using convolutional layers in a pre-trained convolutional neural network, and storing the extracted information in a database. Abstracting the facial images (i.e., extracting features from them) and only saving facial feature information reduces storage space, ensures guest privacy, and allows for matching users with appropriate rooms.

[0150] Step 3: Start searching for a path from the starting point.

[0151] In this embodiment of the invention, the starting node can be set as the entry point. Optionally, it can be set to other values. An open list and a closed list can be pre-set, defining the starting node as the parent node and adding it to the open list. Currently, the open list only contains the parent node; more nodes will be added later. Taking a 3x3 grid as an example, with the parent node as the center, there are 8 possible directions of movement starting from the parent node, and the surrounding 8 nodes are marked as child nodes. Reachable or passable child nodes are added to the open list; obstacles are added to the closed list. Each square in the closed list is no longer needed and can be reused in subsequent pathfinding.

[0152] Step 4: Calculate the advantages and disadvantages of different paths.

[0153] Specifically, the quality of a path can be judged by its movement cost. The higher the movement cost, the worse the path; the lower the movement cost, the better the path.

[0154] The movement cost function is defined as f(n) = g(n) + h(n). f(n) is the cost output by the total cost function, g(n) is the cost of moving from the starting point to the specified node, and h(n) is a heuristic function used to constrain the direction of the path.

[0155] Based on the example in step three above, for paths with eight directions of movement, Chebyshev distance is used as the heuristic function. The node with the smallest f(n) is selected from the current open list. This allows for the calculation of the merits of each path.

[0156] Step 5: Continue searching until the optimal path is found.

[0157] For the 8 adjacent squares of the starting node, ignore any squares in the closed list; if it is a walkable node, add it to the open list. If it is already in the open list, check if the path is better—that is, if it's better to reach a walkable node already in the open list via the starting node—using the f-value (the cost output by the movement cost algorithm) as a reference. If the f-value is smaller, it means the path from the starting node to a walkable node already in the open list is better. The parent node of this node can then be set as the starting node. Adding the destination to the open list indicates that the path has been found. Using a backtracking method, starting from the destination, each square moves along its parent node back to the starting point to obtain the target path, and this target path is saved.

[0158] For example, see Figure 4 This is a schematic diagram illustrating various nodes in an embodiment of the present invention. Figure 4 As shown, assume point S is the starting node and point G is the target node, and Figure 4 The table provides the h-values ​​from each node to the target node, and the g-values ​​of the lines connecting each node. The movement cost function, defined as f(n) = g(n) + h(n), can be used to calculate the advantages and disadvantages of each path, thus determining the optimal path, which is the target path.

[0159] based on Figure 4 The diagram shows point S as the parent node, and its next node as either point a or point b. It can be seen that both points are equidistant from the destination, meaning their h values ​​are equal. However, the number of steps to point a (i.e., the g value) is less than the number of steps to point b, indicating that the cost of traveling from point S to point a is lower. Choosing the minimum g and h values ​​during the search process means reaching the point closest to the destination with the fewest steps, thus achieving the optimal search path.

[0160] Specifically, the cost from point S to point a is 1, and the cost already paid is 1. The child nodes of a are point b, point d, and point e. The cost of point b is 8 = 1 + 1 + 6; the cost of point d is 6 = 1 + 3 + 2; and the cost of point e is 7 = 1 + 5 + 1. Therefore, the cost consumed from point a to point d is the minimum. Thus, the next step from point a can be determined to be point d.

[0161] Step six: Display the best path found to the user.

[0162] Preferably, the user's location is determined and voice or image navigation is provided.

[0163] Optionally, the searched paths can be displayed to the user.

[0164] Corresponding to the embodiments of the aforementioned navigation methods, the present invention also provides embodiment block diagrams of the apparatus.

[0165] See Figure 5 This is a block diagram illustrating an embodiment of a navigation device provided by an embodiment of the present invention. Figure 5 As shown, the device includes:

[0166] The map acquisition module 501 is used to acquire a raster map of the target area, wherein the raster map is obtained by rasterizing a plan view of the target area.

[0167] The node determination module 502 is used to determine the target node of the target object in the floor grid diagram, and to determine the starting node of the target object in the floor grid diagram.

[0168] The path determination module 503 is used to determine the target path of the target object from the starting node to the target node;

[0169] The navigation module 504 is used to navigate the target object according to a preset navigation method based on the target path.

[0170] In an optional implementation, the map acquisition module 501 is specifically used for:

[0171] Obtain a plan view and area information of the target region;

[0172] The grid size of the plan is determined based on the area information of the region;

[0173] Based on the grid size and pre-set grid division information, the plan view of the target area is rasterized to obtain a raster map of the target area.

[0174] In an optional implementation, when the target area includes multiple sub-regions, the map acquisition module 501 is specifically used for:

[0175] Obtain sub-planar maps and corresponding regional feature information for each sub-region in the target region. The regional feature information includes at least: area information and / or height information for each sub-region.

[0176] For each sub-region within the target region, the grid size of the sub-planar map is determined based on the area information of the sub-region;

[0177] Obtain the grid division information set for the sub-planar diagram;

[0178] The sub-planar map is rasterized according to the grid size and the set grid division information to obtain a sub-raster map of the sub-region, and the sub-raster map carries the height information of the sub-region;

[0179] The sub-raster map of the multi-layered sub-region is determined as the raster map of the target region.

[0180] In an optional implementation, the map acquisition module 501 is further specifically used for:

[0181] The plan view of the target area is identified to determine the obstacles and passable areas contained in the plan view;

[0182] Determine the obstacle grid area and the passable grid area in the grid map of the target area that correspond to the obstacles and passable areas contained in the plan view;

[0183] The obstacle grid area and the passable grid area in the grid map are marked according to the preset attribute information to obtain the marked grid map.

[0184] In an optional implementation, the node determination module 502 includes (not shown in the figure):

[0185] An information acquisition unit is used to acquire object information of a target object, wherein the object information is acquired through a preset information acquisition module.

[0186] A grid determination unit is used to search a preset database to determine the target grid in the grid map of the target area that matches the object information. The database includes the correspondence between the object information and the grids in the grid map.

[0187] A node determination unit is used to determine the node of the target grid in the grid map as a target node.

[0188] In an optional implementation, the object information includes the facial information of the target object; the grid determination unit is specifically used for:

[0189] Feature extraction is performed on the facial information of the target object to obtain facial feature information;

[0190] Search a preset database to determine the target grid in the grid map of the target area that matches the facial feature information.

[0191] In an optional implementation, the path determination module 503 includes (not shown in the figure):

[0192] An attribute recognition unit is used to perform attribute recognition on the labeled raster map, determine the passable raster area in the raster map, and determine the passable node corresponding to the passable raster area in the raster map. The passable node includes the target node of the target object in the raster map.

[0193] The path determination unit is used to perform calculations on the passable nodes and the initial node of the target object based on a preset movement cost algorithm to determine the target path of the target object from the starting node to the target node.

[0194] In an optional implementation, the path determination unit is specifically used for:

[0195] Store the starting node of the target object in the grid map into a preset open list;

[0196] Determine the path nodes adjacent to the initial node from the passable nodes, and store the adjacent path nodes in the open list;

[0197] By using a preset movement cost algorithm, the cost from the initial node to each path node in the open list is calculated.

[0198] Select the target path node with the minimum cost value from the cost values ​​as the next node, and store the target path node in a preset closed list;

[0199] For the target path node, perform the step of determining the path node adjacent to the target path node from the passable nodes;

[0200] If the target path node corresponding to the minimum cost value is selected from the cost values, and it is the target node of the target object in the grid map, the target node is stored in the closed list.

[0201] Obtain the target path node saved in the closed list, and determine that the path corresponding to the target path node is the target path of the target object from the starting node to the target node.

[0202] Figure 6 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention. Figure 6 The illustrated electronic device 600 includes at least one processor 601, a memory 602, at least one network interface 604, and a user interface 603. The various components in the electronic device 600 are coupled together via a bus system 605. It is understood that the bus system 605 is used to implement communication between these components. In addition to a data bus, the bus system 605 also includes a power bus, a control bus, and a status signal bus. However, for clarity, in… Figure 6 The general designated all buses as Bus System 605.

[0203] The user interface 603 may include a display, keyboard or clicking device (e.g., mouse, trackball), touchpad or touch screen.

[0204] It is understood that the memory 602 in this embodiment of the invention can be volatile memory or non-volatile memory, or may include both volatile and non-volatile memory. The non-volatile memory can be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory. The volatile memory can be random access memory (RAM), which is used as an external cache. By way of example, but not limitation, many forms of RAM are available, such as Static Random Access Memory (SRAM), Dynamic Random Access Memory (DRAM), Synchronous DRAM (SDRAM), Double Data Rate SDRAM (DDRSDRAM), Enhanced Synchronous DRAM (ESDRAM), Synchlink DRAM (SLDRAM), and Direct Rambus RAM (DRRAM). The memory 602 described herein is intended to include, but is not limited to, these and any other suitable types of memory.

[0205] In some implementations, memory 602 stores elements, executable units or data structures, or subsets thereof, or extended sets thereof: operating system 6021 and application program 6022.

[0206] The operating system 6021 includes various system programs, such as the framework layer, core library layer, and driver layer, used to implement various basic business functions and handle hardware-based tasks. The application program 6022 includes various applications, such as a media player and a browser, used to implement various application functions. The program implementing the method of this embodiment can be included in the application program 6022.

[0207] In this embodiment of the invention, by calling the program or instructions stored in memory 602, specifically the program or instructions stored in application program 6022, processor 601 executes the method steps provided in each method embodiment, including, for example:

[0208] Obtain a raster map of the target area, wherein the raster map is obtained by rasterizing a plan view of the target area;

[0209] Determine the target node of the target object in the grid map, and determine the starting node of the target object in the grid map;

[0210] Determine the target path of the target object from the starting node to the target node;

[0211] Based on the target path, the target object is navigated according to a preset navigation method.

[0212] The methods disclosed in the above embodiments of the present invention can be applied to processor 601, or implemented by processor 601. Processor 601 may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method can be completed by the integrated logic circuit of the hardware in processor 601 or by instructions in the form of software. The processor 601 may be a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. It can implement or execute the methods, steps, and logic block diagrams disclosed in the embodiments of the present invention. The general-purpose processor may be a microprocessor or any conventional processor. The steps of the methods disclosed in the embodiments of the present invention can be directly embodied in the execution of a hardware decoding processor, or executed by a combination of hardware and software units in the decoding processor. The software units may be located in random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, registers, or other mature storage media in the art. The storage medium is located in memory 602. Processor 601 reads the information in memory 602 and, in conjunction with its hardware, completes the steps of the above method.

[0213] It is understood that the embodiments described herein can be implemented in hardware, software, firmware, middleware, microcode, or a combination thereof. For hardware implementation, the processing unit can be implemented in one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field-programmable gate arrays (FPGAs), general-purpose processors, controllers, microcontrollers, microprocessors, other electronic units for performing the functions described herein, or combinations thereof.

[0214] For software implementation, the techniques described herein can be implemented by units that perform the functions described herein. The software code can be stored in memory and executed by a processor. The memory can be implemented in the processor or external to the processor.

[0215] The electronic device provided in this embodiment may be as follows: Figure 6 The electronic device shown can perform the following: Figure 1-3 All steps of the navigation method are then implemented. Figure 1-3 For details on the technical effects of the navigation method, please refer to [link / reference]. Figure 1-3 The relevant descriptions are presented concisely and will not be elaborated upon here.

[0216] This invention also provides a storage medium (computer-readable storage medium). This storage medium stores one or more programs. The storage medium may include volatile memory, such as random access memory; the memory may also include non-volatile memory, such as read-only memory, flash memory, hard disk, or solid-state drive; the memory may also include combinations of the above types of memory.

[0217] When one or more programs in the storage medium can be executed by one or more processors to implement the navigation method described above that is executed on the electronic device side.

[0218] The processor is used to execute a navigation program stored in memory to implement the following steps of a navigation method executed on the electronic device side:

[0219] Obtain a raster map of the target area, wherein the raster map is obtained by rasterizing a plan view of the target area;

[0220] Determine the target node of the target object in the grid map, and determine the starting node of the target object in the grid map;

[0221] Determine the target path of the target object from the starting node to the target node;

[0222] Based on the target path, the target object is navigated according to a preset navigation method.

[0223] Those skilled in the art will further recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components and steps of the various examples have been generally described in terms of functionality in the foregoing description. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this invention.

[0224] The steps of the methods or algorithms described in conjunction with the embodiments disclosed herein can be implemented in hardware, a software module executed by a processor, or a combination of both. The software module can be located in random access memory (RAM), main memory, read-only memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, removable disk, CD-ROM, or any other form of storage medium known in the art.

[0225] The specific embodiments described above further illustrate the purpose, technical solution, and beneficial effects of the present invention. It should be understood that the above description is only a specific embodiment of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A navigation method, characterized in that, The method includes: A raster map of the target area is obtained, wherein the raster map is obtained by rasterizing a plan view of the target area; wherein, if the target area includes multiple sub-regions, the sub-raster maps of the multiple sub-regions are determined as the raster map of the target area; the sub-raster map carries the height information of each sub-region. The method involves determining the target node of a target object in the grid map and determining the current starting node of the target object in the grid map. Specifically, when the target area includes multiple sub-regions, the method obtains the current height information of the target object within the target area and determines the sub-region matching the height information in each sub-region of the target area. It also obtains the current position of the target object within the sub-region, determines the grid cell corresponding to the current position in the sub-grid map of the sub-region, and determines the starting node of the corresponding grid cell in the current grid map. Furthermore, it obtains height information matching the object information of the target object, determines the sub-region within the target area that matches the height information, and determines the target grid cell of the target object in the sub-grid map to which the sub-region belongs. The node of the target grid cell in the grid map is the target node. Determine the target path of the target object from the starting node to the target node; wherein, when the target area includes multiple sub-areas, if the target node and the starting node are not in the same sub-area, then for each sub-area sub-area between the sub-raster map corresponding to the starting node and the sub-raster map corresponding to the target node, determine the path of the target object in the sub-raster map respectively, and determine the path of the target object in each sub-raster map as the target path; Based on the target path, the target object is navigated according to a preset navigation method, and the nodes of the target object in the grid map of the target area are monitored in real time. When the target object goes astray, a reminder is issued to the target object.

2. The method according to claim 1, characterized in that, The acquisition of the raster map of the target area includes: Obtain a plan view and area information of the target region; The grid size of the plan is determined based on the area information of the region; Based on the grid size and pre-set grid division information, the plan view of the target area is rasterized to obtain a raster map of the target area.

3. The method according to claim 1, characterized in that, When the target area includes multiple sub-regions, obtaining the raster map of the target area includes: Obtain sub-planar maps and corresponding regional feature information for each sub-region in the target region. The regional feature information includes at least: area information and / or height information for each sub-region. For each sub-region within the target region, the grid size of the sub-planar map is determined based on the area information of the sub-region; Obtain the grid division information set for the sub-planar diagram; The sub-planar map is rasterized according to the grid size and the set grid division information to obtain a sub-raster map of the sub-region, and the sub-raster map carries the height information of the sub-region; The sub-raster map of the multi-layered sub-region is determined as the raster map of the target region.

4. The method according to claim 1, characterized in that, The process of obtaining a raster map of the target area also includes: The plan view of the target area is identified to determine the obstacles and passable areas contained in the plan view; Determine the obstacle grid area and the passable grid area in the grid map of the target area that correspond to the obstacles and passable areas contained in the plan view; The obstacle grid area and the passable grid area in the grid map are marked according to the preset attribute information to obtain the marked grid map.

5. The method according to claim 1, characterized in that, Determining the target node of the target object in the grid map includes: Obtain object information of the target object, wherein the object information is collected by a preset information acquisition module; Search a preset database to determine the target grid in the grid map of the target area that matches the object information. The database includes the correspondence between the object information and the grid in the grid map. The node of the target grid in the grid map is determined as the target node.

6. The method according to claim 5, characterized in that, The object information includes the facial information of the target object; the step of searching a preset database to determine the target raster that matches the object information includes: Feature extraction is performed on the facial information of the target object to obtain facial feature information; Search a preset database to determine the target grid in the grid map of the target area that matches the facial feature information.

7. The method according to claim 4, characterized in that, Determining the target path from the starting node to the target node for the target object includes: The labeled raster map is subjected to attribute recognition to determine the passable raster area in the raster map, and the passable node corresponding to the passable raster area in the raster map is determined. The passable node includes the target node of the target object in the raster map. Based on a preset movement cost algorithm, calculations are performed on the passable nodes and the initial node of the target object to determine the target path from the starting node to the target node.

8. The method according to claim 7, characterized in that, The preset movement cost algorithm calculates the path from the starting node to the target node based on the passable nodes and the initial node of the target object, including: Store the starting node of the target object in the grid map into a preset open list; Determine the path nodes adjacent to the initial node from the passable nodes, and store the adjacent path nodes in the open list; By using a preset movement cost algorithm, the cost from the initial node to each path node in the open list is calculated. Select the target path node with the minimum cost value from the cost values ​​as the next node, and store the target path node in a preset closed list; For the target path node, perform the step of determining the path node adjacent to the target path node from the passable nodes; If the target path node corresponding to the minimum cost value is selected from the cost values, and it is the target node of the target object in the grid map, the target node is stored in the closed list. Obtain the target path node saved in the closed list, and determine that the path corresponding to the target path node is the target path of the target object from the starting node to the target node.

9. A navigation device, characterized in that, The device includes: The map acquisition module is used to acquire a raster map of a target area, wherein the raster map is obtained by rasterizing a plan view of the target area; wherein, if the target area includes multiple sub-regions, the sub-raster maps of the multiple sub-regions are determined as the raster map of the target area; the sub-raster maps carry the height information of each sub-region. A node determination module is used to determine the target node of a target object in the grid map, and to determine the starting node of the target object in the grid map. Specifically, when the target area includes multiple sub-areas, the module obtains the height information of the target object within the target area and determines the sub-area matching the height information in each sub-area of ​​the target area; obtains the current position of the target object within the sub-area, determines the grid corresponding to the current position in the sub-grid map of the sub-area, and determines the starting node of the corresponding grid in the current grid map; and obtains height information matching the object information of the target object, determines the sub-area matching the height information within the target area, and determines the target grid of the target object in the sub-grid map to which the sub-area belongs. The node of the target grid in the grid map is the target node. A path determination module is used to determine the target path of the target object from the starting node to the target node; wherein, when the target area includes multiple sub-areas, if the target node and the starting node are not in the same sub-area, then for each sub-area sub-area between the sub-raster map corresponding to the starting node and the sub-raster map corresponding to the target node, the path of the target object in each sub-raster map is determined, and the path of the target object in each sub-raster map is determined as the target path; The navigation module is used to navigate the target object according to the target path and a preset navigation method, and to monitor the nodes of the target object in the grid map of the target area in real time, and to issue a reminder to the target object when the target object goes astray.

10. An electronic device, characterized in that, include: A processor and a memory, the processor being configured to execute a navigation program stored in the memory to implement the navigation method according to any one of claims 1 to 8.

11. A storage medium, characterized in that, The storage medium stores one or more programs, which can be executed by one or more processors to implement the navigation method according to any one of claims 1 to 8.

Images