CN114543808A - Indoor relocation method, device, equipment and storage medium - Google Patents

Abstract

The embodiment of the application discloses an indoor relocation method, an indoor relocation device, indoor relocation equipment and a storage medium, which are applied to intelligent equipment; the method comprises the following steps: constructing an initialization exploration map corresponding to the target space; the target space comprises a plurality of areas, and obstacles are arranged among the areas; controlling the intelligent equipment to move in a target area in a target space, and acquiring target point cloud data of the target area in the moving process of the intelligent equipment; updating the initialized exploration map according to the target point cloud data to generate a local exploration map corresponding to the target area; and matching the local exploration map with a space map corresponding to the target space, and determining the pose information of the intelligent equipment in the target space according to the matching result. The scheme can avoid the condition that a base map (namely a space map) is inaccurate when the environment is changed, thereby improving the accuracy of relocation; in addition, when the intelligent equipment is relocated, space global search is not needed, so that the relocation efficiency of the intelligent equipment is improved.

Description

Indoor relocation method, device, equipment and storage medium

Technical Field

The present application relates to the field of relocation technologies, and in particular, to an indoor relocation method, apparatus, device, and storage medium.

Background

In the related art, when indoor relocation is performed on a movable device, relocation is generally performed in a manner of performing global traversal matching on an indoor base map. For example, the mobile device collects point cloud data of the indoor environment at the current position, and then performs global traversal on the indoor base map based on the point cloud data to traverse a position matched with the collected point cloud data, so as to determine the current pose of the mobile device. Obviously, the existing relocation method needs to perform global traversal matching on the indoor base map, so that the relocation efficiency is low. Moreover, the data on which the global traversal depends is only one frame of point cloud data or a small number of frames of point cloud data, which makes the data on which the relocation depends incomplete, resulting in a low accuracy of the relocation result.

Disclosure of Invention

The embodiment of the application aims to provide an indoor relocation method, device, equipment and storage medium, which are beneficial to solving the problems of low accuracy and low efficiency of relocation of intelligent equipment in the prior art.

In order to solve the above technical problem, the embodiment of the present application is implemented as follows:

on one hand, the embodiment of the application provides an indoor relocation method which is applied to intelligent equipment; the method comprises the following steps:

constructing an initialization exploration map corresponding to the target space; the target space comprises a plurality of areas, and obstacles exist among the areas for separation;

controlling the intelligent equipment to move in a target area in the target space, and acquiring target point cloud data of the target area in the moving process of the intelligent equipment;

updating the initialized exploration map according to the target point cloud data to generate a local exploration map corresponding to the target area;

and matching the local exploration map with a space map corresponding to the target space, and determining the pose information of the intelligent equipment in the target space according to a matching result.

On the other hand, the embodiment of the present application provides an indoor relocation device, including:

the construction module is used for constructing an initialized exploration map corresponding to the target space; the target space comprises a plurality of areas, and obstacles exist among the areas for separation;

the acquisition module is used for acquiring target point cloud data of the target area;

the generation module is used for updating the initialized exploration map according to the target point cloud data so as to generate a local exploration map corresponding to the target area;

and the matching module is used for matching the local exploration map with a space map corresponding to the target space and determining the pose information of the intelligent equipment on the space map according to a matching result.

In another aspect, an embodiment of the present application provides an indoor relocation apparatus, including a processor and a memory electrically connected to the processor, where the memory stores a computer program, and the processor is configured to invoke and execute the computer program from the memory to implement the indoor relocation method according to the above aspect.

In yet another aspect, an embodiment of the present application provides a storage medium for storing a computer program, where the computer program is executable by a processor to implement the indoor relocation method according to the above aspect.

By adopting the technical scheme of the embodiment of the application, the initial exploration map corresponding to the target space is constructed, wherein the target space comprises a plurality of areas, and the areas are separated by the barriers. And then controlling the intelligent equipment to move in a target area in the target space, and acquiring target point cloud data of the target area in the moving process of the intelligent equipment. And updating the initialized exploration map according to the target point cloud data to generate a local exploration map corresponding to the target area. And matching the local exploration map with a space map corresponding to the target space, and determining the pose information of the intelligent equipment in the target space according to the matching result. Therefore, the technical scheme realizes the effect of actively exploring the indoor space by controlling the intelligent equipment to acquire the target point cloud data of the target area in real time while moving and updating the initialized exploration map in real time, avoids the condition that a base map (namely a space map) is inaccurate when the environment in the target space changes, and improves the accuracy of relocation in the space; and the pose information of the intelligent equipment is relocated through the matching result between the local exploration map and the base map, so that the intelligent equipment does not need to be searched for in a space global manner when being relocated, and the efficiency of the relocation of the intelligent equipment in the space is improved.

Drawings

In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly introduced below, it is obvious that the drawings in the following description are only some embodiments described in the present application, and for those skilled in the art, other drawings can be obtained according to the drawings without any creative effort.

FIG. 1 is a schematic flow chart diagram of an indoor relocation method according to an embodiment of the present application;

fig. 2 is a schematic diagram of an initialized exploration map in an indoor relocation method according to an embodiment of the present application;

FIG. 3 is a schematic diagram of a probability grid map in an indoor repositioning method according to an embodiment of the present application;

fig. 4 is a schematic diagram of a local exploration map in an indoor relocation method according to an embodiment of the present application;

FIG. 5 is a schematic diagram of a space map in an indoor repositioning method according to an embodiment of the present application;

FIG. 6 is a schematic flow chart diagram of an indoor relocation method according to another embodiment of the present application;

FIG. 7 is a schematic flow chart diagram of an indoor relocation method according to another embodiment of the present application;

FIG. 8 is a schematic block diagram of an indoor relocating device in accordance with an embodiment of the present application;

FIG. 9 is a schematic block diagram of an indoor relocation apparatus according to an embodiment of the present application.

Detailed Description

The embodiment of the application aims to provide an indoor relocation method, device, equipment and storage medium, which are beneficial to solving the problems of low accuracy and low efficiency of relocation of intelligent equipment in the prior art.

In order to make those skilled in the art better understand the technical solutions in the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.

Fig. 1 is a schematic flow chart of an indoor relocation method according to an embodiment of the present application, which is applied to an intelligent device. As shown in fig. 1, the method includes:

and S102, constructing an initialization exploration map corresponding to the target space. The target space comprises a plurality of areas, and obstacles are arranged among the areas.

In one embodiment, the initialized exploration map corresponding to the target space may be a probability grid map. The probability grid map can rasterize the map and draw the map color of the corresponding grid according to the probability that the obstacle exists in each grid, for example, the higher the probability value that the obstacle exists in the grid is, the darker the color of the grid in the map is; the lower the probability value of the presence of an obstacle within the grid, the lighter the grid is in color in the map.

At an initial position of the intelligent device, the intelligent device can acquire a first frame of point cloud data of the target space, and an initialized exploration map corresponding to the target space can be constructed according to the first frame of point cloud data, namely, the first frame of point cloud data is converted into a probability grid map. As shown in fig. 2, a in fig. 2 is a first frame of collected point cloud data, and b in fig. 2 is a probability grid map generated according to the first frame of radar point cloud data, that is, an initial exploration map. The initial exploration map includes an unexplored area and an explored area, the explored area includes an explored obstacle area and an explored barrier-free area, it should be noted that the obstacle area and the barrier-free area in this embodiment both refer to the height of the probability value of the existence of an obstacle, and the position of the obstacle and the probability value corresponding to the grid can be determined through the probability grid map.

S104, controlling the intelligent equipment to move in a target area in the target space, and acquiring target point cloud data of the target area in the moving process of the intelligent equipment.

Optionally, when the target point cloud data is acquired, since an unexplored area exists in the target area, a moving path of the smart device may be determined according to the unexplored area in the target space, so as to control the smart device to continue exploring the unexplored area based on the moving path. The process of how to control the movement of the smart device in the target area will be explained in the following embodiments.

And S106, updating the initialized exploration map according to the target point cloud data to generate a local exploration map corresponding to the target area.

In the step, the intelligent device collects the target point cloud data in the moving process, namely, the initialized exploration map is updated in real time according to the collected target point cloud data every time the target point cloud data is collected, so that the effect of continuously improving the local exploration map is achieved. If the intelligent device collects the target point cloud data for multiple times, the map can be updated on the basis of the exploration map obtained after the previous updating for the target point cloud data collected for the second time, the third time and other follow-up collection when the initial exploration map is updated according to the first collected target point cloud data, and therefore after the target point cloud data collection is finished, the exploration map obtained by the last updating is the local exploration map.

And S108, matching the local exploration map with a space map corresponding to the target space, and determining the pose information of the intelligent equipment in the target space according to the matching result.

Optionally, a radar device is installed on the smart device in this embodiment, where the radar device may be a laser radar. The radar device is used for transmitting radar beams and receiving the radar beams reflected by the obstacles, and target point cloud data of the obstacles in the target area can be acquired through the radar device based on the radar beams.

By adopting the technical scheme of the embodiment of the application, the initial exploration map corresponding to the target space is constructed, wherein the target space comprises a plurality of areas, and the areas are separated by the barriers. And then controlling the intelligent equipment to move in a target area in the target space, and acquiring target point cloud data of the target area in the moving process of the intelligent equipment. And updating the initialized exploration map according to the target point cloud data to generate a local exploration map corresponding to the target area. And matching the local exploration map with a space map corresponding to the target space, and determining the pose information of the intelligent equipment in the target space according to the matching result. Therefore, the technical scheme realizes the effect of actively exploring the indoor space by controlling the intelligent equipment to acquire the target point cloud data of the target area in real time while moving and updating the initialized exploration map in real time, avoids the condition that a base map (namely a space map) is inaccurate when the environment in the target space changes, and improves the accuracy of relocation in the space; and the pose information of the intelligent equipment is relocated through the matching result between the local exploration map and the base map, so that the intelligent equipment does not need to be searched for in a space global manner when being relocated, and the efficiency of the relocation of the intelligent equipment in the space is improved.

In one embodiment, the intelligent device adopts a mode of collecting point cloud data while moving when moving in the target space. Accordingly, S104-S106 may be implemented by performing the following steps A1-A4, generating a local exploration map corresponding to the target area:

step A1, when the intelligent device is located in the first area, collecting first point cloud data of the first area, and updating the initialized exploration map according to the first point cloud data to obtain the first exploration map.

In this embodiment, the target area includes a first area, and the first area is an area where the smart device is currently located.

Step a2, it is determined whether the first search map satisfies the space search completion condition.

Wherein the space exploration completion condition comprises at least one of the following conditions: the quantity of the searched target areas is larger than or equal to a first preset threshold value, and the total search area of the searched target areas is larger than or equal to a second preset threshold value.

Optionally, a first preset threshold may be determined according to the total number of areas on the spatial map, where the first preset threshold is smaller than the total number of areas. The magnitude of the first preset threshold depends on whether the relative positional relationship between all the areas can be determined based on the local exploration map, and of course, the greater the first preset threshold, the higher the accuracy of determining the relative positional relationship between all the areas based on the local exploration map. In practical applications, the first preset threshold may be determined comprehensively by combining the accuracy and the exploration efficiency. For example, when the total number of the areas on the space map is 3, after 2 areas in the target space are searched, the relative position relationship between the 3 areas can be determined, so that only 2 areas can be searched, that is, the first preset threshold is 2.

Alternatively, the second preset threshold may be preset according to the actual area corresponding to the target space, for example, if the total search area of the searched target area is determined as S_{General exploration}The actual area corresponding to the target space is S_{Practice of}If it is preset that the total search area occupies 60% of the actual area, it is considered that the space search completion condition is satisfied, and the second preset threshold is 0.6S_{Practice of}。

In step a3, if the first search map satisfies the space search completion condition, the first search map is determined to be the local search map.

Step A4, if the first exploration map does not meet the space exploration completion condition, the intelligent device is controlled to move from the first area to the second area, second point cloud data of the second area are collected, and the first exploration map is updated according to the second point cloud data until the updated exploration map meets the space exploration completion condition.

In this step, the target area further includes a second area, which is an area to be searched except for the first area. And under the condition that the first exploration map does not meet the space exploration completion condition, the intelligent equipment is controlled to move from the current area to another area, so that the target space is continuously explored. In this embodiment, the second area may be understood as one area or a plurality of areas, and if the updated search map satisfies the space search completion condition after searching the first second area, the search of other areas is stopped; and if the updated exploration map does not meet the space exploration completion condition after the first second area is explored, controlling the intelligent equipment to move from the first second area to the second area for exploration until the updated exploration map meets the space exploration completion condition.

In one embodiment, when the obstacle is a passable passage, the intelligent device can be controlled to move from the first area to the second area by the following means: the method comprises the steps of firstly determining a second area to be searched in the space map according to the area of each area in the space map, then identifying a passable channel between the first area and the second area, and determining the position information of the passable channel. And then according to the position information of the passable passage, the intelligent equipment is controlled to move to the second area through the passable passage.

In this embodiment, when determining the second region, a region that is larger than the first region and has the smallest area among all regions larger than the first region may be used as the second region according to the region area of each region in the space map. For example, there are 4 regions on the space map, and the area of the region corresponding to each region is S in descending order₁、S₂、S₃、S₄The first region has an area S, which may be S₁、S₂、S₃、S₄Any one of them. If the S and the S are determined through comparison₁Approximately equal (i.e., the first region may be a region area S)₁Corresponding region), S is greater than S₂And S is respectively less than S₃、S₄Then the area in the division area is S₁、S₂Selecting the second region in other regions than the first region, and selecting the second region due to S₃Less than S₄I.e. the area of the other region S₃Minimum, thus defining a region area of S₃Is the second region. It should be noted that, since there is a certain error in acquiring or calculating the area of the region, the area of each region predetermined on the space map may be equal to the search areaThe area of the first region is not completely equal, so when the area of the first region is matched, the matching can be considered to be successful within a certain error range, for example, S is not equal to S1, but the difference between the two is within a certain error range, i.e., the area S of the first region is considered to be₁The corresponding region is the first region.

Alternatively, the passable channel may be a door frame. After determining the second area to explore, the passable corridor between the first area and the second area may be identified according to the following: the method comprises the steps of recognizing and shooting images of passable channels (such as door frames) between areas by using a vision sensor installed on a smart device, and processing the images through an image processing function of the vision sensor to determine position information of the door frames on a first exploration map, wherein the position information can be relative coordinate information of the door frames on the first exploration map and comprises coordinates of two endpoints of the door frames on the first exploration map.

In this embodiment, when the first exploration map does not satisfy the space exploration completion condition, the intelligent device is controlled to move to the second area, and the second point cloud data of the second area is collected to update the first exploration map, so that the searched local exploration map is ensured to satisfy the space exploration completion condition, the problem of low matching accuracy with the space map due to the fact that the completion condition of the exploration target space is not satisfied is avoided, and accuracy of matching the local exploration map with the space map is improved.

In one embodiment, when the smart device is located in the first area, the initialized exploration map is updated by collecting first point cloud data of the first area until the exploration of the first area is completed. Whether the search in the first area is completed or not can be determined based on the preset area search completion condition, which is specifically shown in the following steps B1-B4:

and step B1, when the intelligent device is located at a first exploration position in the first area, collecting first point cloud data of the first area, and updating the initialized exploration map according to the first point cloud data to obtain an area exploration subgraph.

In step B2, it is determined whether or not the first area satisfies the area search completion condition.

Wherein the area exploration completion condition may include at least one of: the current exploration area is not provided with an unexplored area, and the exploration area in the current exploration area is larger than or equal to a third preset threshold value.

Optionally, the target space includes at least one region that is larger than the first region. The third preset threshold may be determined by: first, all regions with a region area larger than the first region are determined, and then the region with the smallest region area in all the regions is determined as the second region.

And secondly, multiplying the area of the second region by a preset proportion to obtain a third preset threshold. The third preset threshold may be determined by equation (1):

S_T＝λS₂ (1)

wherein S is_TThe third predetermined threshold is S2, the area of the second region is S, and λ is a predetermined ratio.

In step B3, if the first area satisfies the area search completion condition, the area search sub-map is determined as the first search map.

And step B4, if the first area does not meet the area exploration completion condition, controlling the intelligent equipment to move in the first area, continuously acquiring first point cloud data of the first area in the moving process, updating the area exploration subgraph according to the acquired first point cloud data, and obtaining a first exploration map when the first area meets the area exploration completion condition.

In this embodiment, when the first area explored by the intelligent device does not satisfy the area exploration completion condition, the intelligent device is controlled to continue exploring in the first area, and the first point cloud data of the first area is collected in real time to update the area exploration subgraph, so that the intelligent device can complete exploring the first area, an accurate first exploration map is constructed, and the problem that the intelligent device cannot be accurately matched with the space map when the environment of the first area in the target space changes, such as the environment becomes more complex, is prevented.

In one embodiment, after step B2 is executed, if it is determined that the first area does not satisfy the area exploration completion condition, the smart device is controlled to move in the first area, and the first cloud data of the first area is continuously acquired during the movement. Specifically, a second exploration position in the first area is determined according to an unexplored area existing in the first area, then the intelligent device is controlled to move from the first exploration position to the second exploration position, and when the intelligent device is located at the second exploration position, first point cloud data of the first area are collected.

Fig. 3 is a schematic diagram of a probability grid map in an indoor repositioning method according to an embodiment of the present application, and as shown in fig. 3, when determining a second search position, a boundary between a grid corresponding to an unexplored area and a grid corresponding to a searched non-obstacle area in an initialized search map (i.e., the probability grid map) is determined as the second search position, where a white grid is the searched non-obstacle area, a black grid is the searched obstacle area, and a gray grid is the unexplored area. The size of the individual grids may be preset, for example, to 0.5 meters on a side. The smaller the size of the grid, the higher the accuracy of the probability grid map.

In this embodiment, when the initialized exploration map is a probability grid map, the second exploration position is determined according to the adjacent grid between the unexplored area and the explored barrier-free area, so that the intelligent device is controlled to continue exploring the first area according to the second exploration position, the intelligent device can accurately move to the unexplored area, and then the first cloud data in the unexplored area is obtained, thereby avoiding the situation that the unexplored area exists in the first area.

In one embodiment, in performing S108, pose information of the smart device on the space map may be determined by:

first, first feature information of a first key location on a local exploration map and second feature information of a second key location on a spatial map are determined.

Wherein the first feature information or the second feature information includes at least one of: position orientation, position size, position shape. The position orientation may be the orientation of the key location (i.e., the first key location or the second key location) relative to the smart device; the position size may be the length of the key position, for example, when the obstacle is a door frame, the first characteristic information or the second characteristic information may be the length of the door frame; the position shape may be a shape corresponding to the key position, for example, if the key position is a table, the position shape of the key position may be a square shape, a circle shape, or the like.

In this embodiment, the key position (i.e., the first key position or the second key position) may be a position corresponding to an obstacle in each area on the local exploration map or the space map, or a position corresponding to at least one passable passage (when the obstacle is a passable passage) between each area on the local exploration map or the space map.

Optionally, when the first key position is a position corresponding to at least one passable channel between the regions on the local exploration map, if there are a plurality of regions in the target space, there are a plurality of first key positions on the local exploration map. The second key position may be a position corresponding to a key obstacle on the spatial map, such as a passable channel, a table and a chair in each area, a door, a position corresponding to a potted plant on the spatial map, and the like.

And secondly, matching the first characteristic information with the second characteristic information, and determining a first mapping relation between the first key position and the second key position according to a matching result.

And thirdly, determining the pose information of the intelligent device on the space map according to the first mapping relation between the first key position and the second key position and the pose information of the intelligent device on the local exploration map.

Wherein the pose information of the intelligent device on the local exploration map comprises the relative pose information of the intelligent device in the current exploration area. Alternatively, it may be determined by: the intelligent device searches in a current searching area (such as a first area), when the intelligent device moves in the current searching area, point cloud data of the current searching area are collected in the moving process, an initialized searching map is updated according to the collected point cloud data, and optionally, the updated initialized searching map is a probability grid map. And then, matching the point cloud data acquired in real time with the probability grid map, and determining the relative pose information of the intelligent equipment in the current exploration area according to the matching result. The relative pose information may be characterized as any one of: coordinate information in a specified coordinate system with respect to distance information and/or direction information of a specified obstacle in the current search area.

In the embodiment, the intelligent equipment is controlled to move and collect the point cloud data of the current exploration area, the point cloud data collected in real time is matched with the probability grid map, and then the relative pose information of the intelligent equipment in the current exploration area can be determined according to the matching result. Furthermore, first feature information of a first key position on the local exploration map and second feature information of a second key position on the space map are extracted, and the first feature information and the second feature information are matched to determine the mapping relation between the local exploration map and the space map. The position of the local exploration map corresponding to the space map can be accurately determined according to the relative pose information of the intelligent equipment in the current exploration area and the mapping relation between the local exploration map and the space map, so that the pose information of the intelligent equipment on the space map can be conveniently determined, and the effect of accurately repositioning the intelligent equipment is realized.

In one embodiment, the first and second key locations each comprise a plurality; in determining the first mapping relationship between the first key location and the second key location, it may be implemented by the following steps C1-C3:

and step C1, determining a first relative pose relationship between the first key positions according to the first characteristic information corresponding to the first key positions respectively.

For example, the local exploration map includes a plurality of areas, and the first key location is a plurality of. Fig. 4 is a schematic diagram of a local search map in an indoor relocation method according to an embodiment of the present application, where as shown in fig. 4, a first key location is a location of a passable passage (e.g., a door frame) between areas on the local search map, and as shown in fig. 4, a line segment M on the local search map is a line segment M_iM_i+1Is composed of M₁M₂And M₃M₄. The intelligent device collects the target point cloud data while moving, so that the coordinates of each endpoint of the first key position relative to the intelligent device, namely the coordinates under the local coordinate system, are obtained according to the collected target point cloud data, and before the first characteristic information is extracted, the coordinates of the first key position under the local coordinate system can be converted into the coordinates on the global coordinate system with the initial exploration position of the intelligent device as the origin, so that the first characteristic information of the first key position can be extracted subsequently. The specific conversion process is detailed in formula (2):

wherein i is a certain end point of a certain first key position on the local exploration map,

g represents the global coordinate system;

is the coordinate of the end point under the local coordinate system, and l represents the local coordinate system.

As can be seen, after obtaining the coordinates of each endpoint of the first key position in the global coordinate system through the formula (2), the first feature information may include the endpoint coordinates of the first key position and the corresponding coordinate vector, where the endpoint coordinate of the first key position is M₁(x₁，y₁)、M₂(x₂，y₂)、M₃(x₃，y₃)、M₄(x₄，y₄) First critical position M₁M₂Corresponding coordinate vector is

First critical position M₃M₄Corresponding coordinate vector is

Further, a first relative pose relationship of each first key position can be determined according to the coordinate vector of each first key position, as detailed in formula (3):

wherein R is₁₃Is the first critical position M₁M₂And M₃M₄A rotation matrix of T₁₃Is the first critical position M₁M₂And M₃M₄The relationship between the displacement of the two components,

is the first key location M₁M₂The corresponding coordinate vector is then calculated from the coordinate vectors,

first critical position M₃M₄The corresponding coordinate vector.

Fig. 5 is a schematic diagram of a space map in an indoor relocation method according to an embodiment of the present application, where, as shown in fig. 5, a plurality of second key locations are included on the space map. When the first key position is the passable passage on the local exploration map in fig. 4, the second key position is the position line segment N corresponding to the passable passage between all the areas on the space map in fig. 5_iN_i+1Including N₁N₂、N₃N₄、N₅N₆、N₇N₈And N₉N₁₀. The second feature information is coordinates of two endpoints corresponding to each second key position and a coordinate vector corresponding to each second key position, and the coordinates include N_i(x_i，y_i) And N_i+1(x_i+1，y_i+1) I is an integer greater than or equal to 0 and the coordinate vector is

The second relative pose relationship between the second key positions can be determined by equation (4) (only the second relative pose relationship between two of the second key positions is listed below):

wherein R is₂₄Is the second key position N₁N₂And N₃N₄A rotation matrix of T₂₄Is the second key position N₁N₂And N₃N₄The relationship between the displacement of the two parts,

second key position N₁N₂The corresponding coordinate vector is then calculated from the coordinate vectors,

is the second key position N₃N₄The corresponding coordinate vector.

Step C2, for a first target key location of the plurality of first key locations, determining a second target key location in the spatial map that matches the first target key location. In this step, the first target key location may be any first key location in the local exploration map. When determining a second target key position matched with the first target key position, comparing first feature information corresponding to the first target key position with second feature information corresponding to each second key position, and if the feature information is matched, determining the matched second key position as the second target key position. For example, the position size corresponding to the first target key position (i.e., the corresponding segment length on the local search map) is compared with the position size corresponding to each second key position (i.e., the corresponding segment length on the spatial map), and the second key position with the same position size is determined as the second target key position.

Note that when comparing the first feature information corresponding to the first target key position with the second feature information corresponding to each second key position, there may be a plurality of second feature information corresponding to the second key position matching the first feature information corresponding to the first target key position, and therefore, the second target key position matching the first target key position may include one or more second target key positions.

And step C3, determining a first mapping relation between each first key position and each second key position according to the first relative pose relation and a second mapping relation between the key positions of the first target and the key positions of the second target.

In this step, when determining a second key target location in the spatial map that matches the first key target location, the first key target location is first determined (e.g., M)₁M₂) And a second target key position N on the space map_iN_i+1A second mapping relationship (also can be understood as a pose transformation relationship) between the first and second images; suppose that the second target key position is determined to be N₁N₂Then the second target key location N₁N₂And a first target key position M₁M₂The pose conversion relationship is shown in the formula (5):

secondly, mapping other first key positions to the space map according to a second mapping relation between the first target key positions and the second target key positions to obtain third key positions.

When mapping each first key position into the space map, using the first key position M₃M₄For example, the first key location M may be₃M₄Substituting into the above pose transformation relation (i.e. formula (5)) to obtain the first key position M₃M₄Corresponding third key position N_zN_z+1Wherein z is an integer greater than or equal to 0 and not equal to i, as detailed in formula (6):

and then, judging whether the second key position is matched with the third key position in the space map or not according to the first relative pose relationship among the first key positions. When the second key position is matched with the third key position, the following conditions are met: the characteristic information (such as position orientation, position size and/or position shape) corresponding to the second key position and the third key position respectively is consistent. For example, all the second key positions N_iN_i+1Respectively with a third key position N_zN_z+1Comparing, specifically, comparing each second key position N_iN_i+1Size of (e.g. line segment N)_iN_i+1Length of) and third key position N_zN_z+1Size of (e.g. line segment N)_zN_z+1Length of) to determine the third key position N_zN_z+1Matching second key position N_iN_i+1。

And mapping all the second key positions to the space map according to a second mapping relation shown in formula (5), and if one second key position can be found on the space map to be matched with one third key position for each mapped third key position, indicating that the currently determined second target key position is matched with the first target key position. At this time, according to the second mapping relationship between the first key target position and the second key target position, the first mapping relationship between each first key position and each second key position, that is, the mapping relationship between the local exploration map and the space map, may be determined.

If all the second key positions N are located_iN_i+1Respectively with a third key position N_zN_z+1After comparison, any second key position NiNi +1 is found not to be equal to the third key position N_zN_z+1And if the first target key position is matched with the second target key position, the currently determined second target key position is not matched with the first target key position. At this point, the second target key location corresponding to the first target key location may be re-determined.

In one embodiment, if the second target key positions corresponding to the first target key positions include a plurality of second target key positions, the first mapping relationship between each first key position and each second key position also includes a plurality of mapping relationships accordingly. Furthermore, when the pose information of the intelligent device on the space map is determined according to the first mapping relations, candidate pose information of the intelligent device on the space map can be determined according to the first mapping relations, then traversal search is carried out on any candidate pose information in a preset area range corresponding to the candidate pose information, and probability scores corresponding to the candidate position information are determined according to search results; and determining candidate pose information corresponding to the highest value in the probability scores to serve as pose information of the intelligent device on the space map. And the probability score is used for representing the probability that the candidate pose information belongs to the finally determined pose information. The preset area range may be a preset distance range, a preset angle range, and/or a range of the corresponding target area.

In this embodiment, when candidate pose information of the intelligent device on the space map is determined for each first mapping relationship, the pose conversion relationship of the intelligent device relative to each first key position may be determined according to the pose information of the intelligent device on the local exploration map; and then according to the pose conversion relation and each first mapping relation, respectively mapping the pose information of the intelligent equipment on the local exploration map to a space map to obtain a plurality of candidate pose information of the intelligent equipment on the space map.

Assume that the first mapping includes the following two mappings, where the symbol "→" represents the mapping between key locations:

the first method comprises the following steps: m₁M₂→N₁N₂，M₃M₄→N₃N₄；

And the second method comprises the following steps: m₁M₂→N₇N₈，M₃M₄→N₉N₁₀。

And aiming at the two mapping relations, two candidate pose information can be determined. For example,aiming at the first mapping relation, the intelligent equipment is firstly calculated relative to a first key position M₁M₂、M₃M₄According to the pose conversion relation and the first mapping relation, mapping the pose information of the intelligent equipment on the local exploration map onto a space map to obtain candidate pose information, wherein the candidate pose information and the second key position N are obtained₁N₂、N₃N₄The second positional translation relationship therebetween should be the same as the first positional translation relationship. Similarly, if the second mapping relation is aimed at, the determined candidate pose information and the second key position N are determined₇N₈、N₉N₁₀The second positional translation relationship therebetween should be the same as the first positional translation relationship.

Optionally, performing traversal search in a preset area range corresponding to the candidate pose information, when determining probability scores corresponding to the candidate pose information respectively according to search results, collecting point cloud data in the preset area range, generating a preset area map corresponding to the preset area range according to the collected point cloud data, comparing the preset area map with a corresponding area map on the space map, and determining a matching rate between the preset area map and the corresponding area map according to the comparison results; and calculating the probability score corresponding to the candidate position information according to the matching degree. The preset area map and the corresponding area map can be probability grid maps. Therefore, the probability grid map corresponding to the preset area range can be compared with the probability grid map in the corresponding area on the space map to determine the matching rate (namely the coincidence rate) between the two probability grid maps, and then the probability score corresponding to the candidate pose information is determined according to the matching rate.

Optionally, when determining the matching rate between the two probability grid maps, a specific grid (for example, a grid with a darker color, a grid with a probability value of an obstacle reaching a certain threshold in the grid, etc.) may be selected from the probability grid maps for comparison, and the matching rate between the specific grids may be determined.

Optionally, the matching rate corresponding to each specific grid may be calculated, and then the probability score corresponding to the current candidate pose information is calculated according to the matching rate corresponding to each specific grid. For example, the probability score corresponding to the candidate pose information can be calculated by formula (7):

wherein, O is the matching rate corresponding to each specific grid, and n is the total number of the specific grids.

And further, determining candidate pose information with the highest probability score as pose information of the intelligent device on the space map.

In this embodiment, through the matching process, the mapping relationship between the accurate local exploration map and the space map can be determined, so that the accuracy of indoor relocation is improved conveniently.

Fig. 6 is a schematic flow chart of an indoor relocation method according to another embodiment of the present application, in this embodiment, a target space is an indoor space, each area in the target space is each room, and an obstacle spaced between each area is a door between each room. As shown in fig. 5, the space map of the indoor space is obtained by dividing each room in advance according to the position of the door frame. As shown in fig. 6, the indoor relocation method includes:

s601, constructing an initialization exploration map corresponding to the indoor space.

At an initial position of the intelligent device, the intelligent device can acquire first frame point cloud data of an indoor space, and an initialized exploration map corresponding to the indoor space can be constructed according to the first frame point cloud data, namely, the first frame point cloud data is converted into a probability grid map.

S602, when the intelligent device is located in a first room in the indoor space, collecting first point cloud data of the first room, and updating the initialized exploration map according to the first point cloud data to obtain a first exploration map.

Wherein the target area comprises a first room.

S603, determine whether the first search map satisfies the space search completion condition. If yes, go to S604; if not, go to S605.

Wherein the space exploration completion condition comprises at least one of the following conditions: the quantity of the searched target areas is larger than or equal to a first preset threshold value, and the total search area of the searched target areas is larger than or equal to a second preset threshold value.

S604, the first search map is determined to be a local search map of the indoor space.

And S605, controlling the intelligent equipment to move from the first room to the second room, collecting second point cloud data of the second room, updating the first exploration map according to the second point cloud data until the updated exploration map meets space exploration completion conditions, and generating a local exploration map corresponding to the target area.

Wherein the target area further comprises a second room.

S606, determining first characteristic information of the door frames on the local exploration map and second characteristic information of the door frames on the space map.

Wherein the first feature information or the second feature information includes at least one of: position orientation, position size, position shape.

S607, determining a first relative pose relationship between the door frames on the local exploration map according to the first characteristic information corresponding to the door frames on the local exploration map.

And S608, aiming at the first target door frame on the local exploration map, determining a second target door frame matched with the first target door frame in the space map.

And S609, determining the mapping relation between the local exploration map and the space map according to the first relative pose relation and the mapping relation between the first target door frame and the second target door frame.

And S610, determining the pose information of the intelligent device on the space map according to the mapping relation between the local exploration map and the space map and the pose information of the intelligent device on the local exploration map.

In this step, how to determine the pose information of the intelligent device on the space map is described in detail in the above embodiments, and details are not described here.

In this embodiment, when it is determined that the first exploration map does not satisfy the space exploration completion condition, the intelligent device is controlled to actively explore the next room in the target space, so that the space exploration completion condition is ensured to be satisfied, the problem that the local exploration map cannot be matched with the space map due to the fact that the space exploration completion condition is not satisfied is avoided, and accuracy in matching the local exploration map with the space map is improved. In addition, the first characteristic information of the door frame (first key position) on the local exploration map and the second characteristic information of the door frame (second key position) on the space map are extracted, and then the first characteristic information and the second characteristic information are matched to determine the mapping relation between the local exploration map and the space map, so that the matching of the local exploration map and the characteristic information on the space map is facilitated, the position of the local exploration map corresponding to the space map is accurately determined, the pose information of the intelligent device on the space map is accurately determined, and the effect of accurate relocation of the intelligent device is achieved.

Fig. 7 is a schematic flowchart of an indoor relocation method according to another embodiment of the present application, where in this embodiment, the target space is an indoor space, each area in the target space is a room, and the barrier between the areas is a door between the rooms. As shown in fig. 7, the indoor relocation method includes:

s701, when the intelligent device is located at a first exploration position in a first room, collecting first point cloud data of the first room, and updating an initialization exploration map according to the first point cloud data to obtain a regional exploration subgraph; the target area includes a first room.

S702, determines whether the first room satisfies the area search completion condition. If yes, executing S703; if not, go to S704.

Wherein the area exploration completion condition comprises at least one of the following conditions: no unexplored area exists in the current exploration area (namely, in the current exploration room), and the exploration area in the current exploration area is larger than or equal to a third preset threshold value.

And S703, determining the area exploration subgraph as a first exploration map.

S704, controlling the intelligent device to move in the first room, continuously collecting the first point cloud data of the first room in the moving process, updating the regional exploration subgraph according to the collected first point cloud data, and obtaining a first exploration map when the first room meets the regional exploration completion condition.

S705, determining whether the first search map satisfies the space search completion condition. If yes, go to S706; if not, S707 is executed.

Wherein the space exploration completion condition comprises at least one of the following conditions: the number of searched rooms is greater than or equal to a first preset threshold value, and the total searched area of the searched rooms is greater than or equal to a second preset threshold value.

And S706, determining the first search map as a local search map.

And S707, controlling the intelligent device to move from the first room to the second room, acquiring second point cloud data of the second room, and updating the first exploration map according to the second point cloud data until the updated exploration map meets the space exploration completion condition to obtain a local exploration map.

In the embodiment, a second room to be explored in the space map is determined according to the area of each room in the space map; identifying a door frame between a first room and a second room, and determining position information of the door frame; and then according to the position information of the door frame, the intelligent equipment is controlled to move to a second room through the position of the door frame.

It should be noted that, the first room and the second room are only used for exemplary illustration, when the indoor space includes a plurality of rooms larger than the currently searched room and all the rooms are not searched rooms, S701-S707 are repeatedly executed, that is, the active search is performed on a plurality of rooms such as the third room and the fourth room until the number of rooms searched by the smart device is greater than or equal to the first preset threshold and/or the total search area of the searched rooms is greater than or equal to the second preset threshold.

Therefore, the intelligent device is controlled to actively explore in the first room to update the region exploration subgraph, so that the region exploration completion conditions of the first room of the intelligent device are ensured, and an accurate first exploration map is constructed. Furthermore, whether the first exploration map meets the space exploration completion condition or not is judged, and the intelligent device is controlled to continue to actively explore to update the first exploration map when the space exploration completion condition is not met, so that the space exploration completion condition is met, the effect of actively exploring the indoor space is achieved, the problem that the local exploration map cannot be matched with the space map due to the fact that the completion condition of an exploration target space is not met is solved, and accuracy of matching the local exploration map with the space map is improved.

In summary, particular embodiments of the present subject matter have been described. Other embodiments are within the scope of the following claims. In some cases, the actions recited in the claims can be performed in a different order and still achieve desirable results. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing may be advantageous.

Based on the same idea, the indoor relocation method provided by the embodiment of the present application further provides an indoor relocation device. FIG. 8 is a schematic block diagram of an indoor relocation apparatus according to an embodiment of the application, as shown in FIG. 8, applied to a smart device; the device comprises:

the building module 810 is configured to build an initial exploration map corresponding to the target space; the target space comprises a plurality of areas, and obstacles exist among the areas for separation;

an acquisition module 820, configured to acquire target point cloud data of the target area;

a generating module 830, configured to update the initialized exploration map according to the target point cloud data to generate a local exploration map corresponding to the target area;

the matching module 840 is configured to match the local exploration map with a space map corresponding to the target space, and determine pose information of the smart device on the space map according to a matching result.

By adopting the device of the embodiment of the application, the initial exploration map corresponding to the target space is constructed, wherein the target space comprises a plurality of areas, and the areas are separated by the barriers. And collecting target point cloud data of a target area. And updating the initialized exploration map according to the target point cloud data to generate a local exploration map corresponding to the target area. And matching the local exploration map with a space map corresponding to the target space, and determining the pose information of the intelligent equipment in the target space according to the matching result. Therefore, the intelligent equipment is controlled to move and acquire target point cloud data of a target area in real time, and the initialized exploration map is updated in real time, so that the effect of actively exploring an indoor space is realized, the condition that a base map (namely a space map) is inaccurate when the environment in the target space changes is avoided, and the accuracy of repositioning in the space is improved; and the pose information of the intelligent equipment is relocated through the matching result between the local exploration map and the base map, so that the intelligent equipment does not need to be searched for in a space global manner when being relocated, and the efficiency of the relocation of the intelligent equipment in the space is improved.

In one embodiment, the indoor relocating device further comprises a power module for driving the smart device to move within a target area within the target space;

correspondingly, the collecting module 820 is further configured to collect the target point cloud data of the target area during the moving process of the smart device.

In one embodiment, the acquisition module 820 includes:

the intelligent device comprises an acquisition unit, a searching unit and a searching unit, wherein the acquisition unit is used for acquiring first point cloud data of a first area when the intelligent device is located in the first area, and updating the initialized searching map according to the first point cloud data to obtain a first searching map; the target region comprises the first region;

the generating module 830 includes:

the judging unit is used for judging whether the first exploration map meets a space exploration completion condition or not; the space exploration completion condition comprises at least one of the following conditions: the quantity of the explored target areas is greater than or equal to a first preset threshold value, and the total explored area of the explored target areas is greater than or equal to a second preset threshold value;

a first determining unit, configured to determine that the first exploration map is the local exploration map if the first exploration map is the local exploration map;

the control and acquisition unit is used for controlling the intelligent equipment to move from the first area to a second area if the intelligent equipment does not move from the first area to the second area, acquiring second point cloud data of the second area, and updating the first exploration map according to the second point cloud data until the updated exploration map meets the space exploration completion condition; the target region further includes the second region.

In one embodiment, the control and acquisition unit is further configured to acquire the first point cloud data of the first area when the smart device is located at a first exploration position in the first area, and update the initialized exploration map according to the first point cloud data to obtain an area exploration subgraph; judging whether the first area meets an area exploration completion condition or not; the area exploration completion condition includes at least one of: an unexplored area does not exist in the current exploration area, and the exploration area in the current exploration area is larger than or equal to a third preset threshold; if so, determining the area exploration subgraph as the first exploration map; if not, controlling the intelligent equipment to move in the first area, continuously acquiring the first point cloud data of the first area in the moving process, updating the area exploration subgraph according to the acquired first point cloud data, and obtaining the first exploration map when the first area meets the area exploration completion condition.

In one embodiment, the control and acquisition unit is further configured to determine a second explored location within the first area, based on the unexplored area present within the first area; controlling the smart device to move from the first exploration location to the second exploration location; when the smart device is located at the second exploration position, the first point cloud data of the first area is collected.

In one embodiment, the barrier is a passable channel;

the control and acquisition unit is further configured to determine the second area to be explored in the space map according to the area of each area in the space map; identifying the passable passage between the first area and the second area, and determining position information of the passable passage; and controlling the intelligent equipment to move to the second area through the passable passage according to the position information.

In one embodiment, the matching module 840 includes:

a second determining unit, configured to determine first feature information of a first key location on the local exploration map and second feature information of a second key location on the spatial map; the first feature information or the second feature information includes at least one of: position orientation, position size, position shape;

the matching unit is used for matching the first characteristic information with the second characteristic information and determining a first mapping relation between the local exploration map and the space map according to a matching result;

and a third determining unit, configured to determine, according to the first mapping relationship and pose information of the smart device on the local exploration map, pose information of the smart device on the space map.

In one embodiment, the first and second key locations each comprise a plurality;

the matching unit is further configured to determine a first relative pose relationship between the first key positions according to the first feature information corresponding to each first key position; determining, for a first target key location of a plurality of the first key locations, a second target key location in the spatial map that matches the first target key location; and determining a first mapping relation between the local exploration map and the space map according to the first relative pose relation and a second mapping relation between the first target key position and the second target key position.

In an embodiment, the matching unit is further configured to map, according to the second mapping relationship, each of the other first key positions onto the space map to obtain a third key position; judging whether the second key position is matched with the third key position in the space map or not according to the first relative pose relation; if so, determining the first mapping relation between each first key position and each second key position according to the second mapping relation; if not, re-determining the second target key position corresponding to the first target key position.

In one embodiment, the second target key position corresponding to the first target key position comprises a plurality of target key positions;

the third determining unit is further configured to determine, for each of the first mapping relationships, a plurality of candidate pose information of the smart device on the spatial map respectively; for any candidate pose information, performing traversal search in a preset area range corresponding to the candidate pose information, and determining probability scores corresponding to the candidate position information according to search results; and determining the candidate pose information corresponding to the highest value in the probability scores as the pose information of the intelligent equipment on the space map.

In one embodiment, the third determining unit is further configured to determine a pose transformation relationship of the smart device with respect to each of the first key locations according to pose information of the smart device on the local exploration map; and mapping the pose information of the intelligent equipment on the local exploration map to the space map according to the pose conversion relation and the first mapping relation to obtain the candidate pose information of the intelligent equipment on the space map.

In one embodiment, the third determining unit is further configured to control the intelligent device to move within the preset area range, and collect point cloud data within the preset area range during the moving process; generating a preset area map corresponding to the preset area range according to the point cloud data; comparing the preset area map with a corresponding area map on the space map, and determining the matching rate between the preset area map and the corresponding area map according to the comparison result; and calculating the probability score corresponding to the candidate pose information according to the matching degree.

Based on the same idea, the embodiment of the present application further provides an indoor relocation device, as shown in fig. 9. The indoor relocation apparatus may vary greatly in configuration or performance, and may include one or more processors 901 and memory 902, where the memory 902 may store one or more stored applications or data. Memory 902 may be, among other things, transient storage or persistent storage. The application program stored in memory 902 may include one or more modules (not shown), each of which may include a series of computer-executable instructions for the indoor relocation apparatus. Still further, the processor 901 may be arranged in communication with the memory 902 for executing a series of computer executable instructions in the memory 902 on the indoor relocation device. The indoor relocation apparatus may also include one or more power supplies 903, one or more wired or wireless network interfaces 904, one or more input-output interfaces 905, one or more keyboards 906.

In particular, in this embodiment, the indoor relocation apparatus includes a memory, and one or more programs, where the one or more programs are stored in the memory, and the one or more programs may include one or more modules, and each module may include a series of computer-executable instructions for the indoor relocation apparatus, and the one or more programs configured to be executed by the one or more processors include computer-executable instructions for:

constructing an initialization exploration map corresponding to the target space; the target space comprises a plurality of areas, and obstacles exist among the areas for separation;

controlling the intelligent equipment to move in a target area in the target space, and acquiring target point cloud data of the target area in the moving process of the intelligent equipment;

updating the initialized exploration map according to the target point cloud data to generate a local exploration map corresponding to the target area;

and matching the local exploration map with a space map corresponding to the target space, and determining the pose information of the intelligent equipment on the space map according to a matching result.

The embodiment of the present application further provides a storage medium, where the storage medium stores one or more computer programs, where the one or more computer programs include instructions, and when the instructions are executed by an electronic device including multiple application programs, the electronic device can execute each process of the above-mentioned embodiment of the indoor relocation method, and can achieve the same technical effect, and in order to avoid repetition, details are not repeated here.

The systems, devices, modules or units illustrated in the above embodiments may be implemented by a computer chip or an entity, or by a product with certain functions. One typical implementation device is a computer. In particular, the computer may be, for example, a personal computer, a laptop computer, a cellular telephone, a camera phone, a smartphone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.

For convenience of description, the above devices are described as being divided into various units by function, and are described separately. Of course, the functionality of the units may be implemented in one or more software and/or hardware when implementing the present application.

As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.

The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

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

The memory may include forms of volatile memory in a computer readable medium, Random Access Memory (RAM) and/or non-volatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM). Memory is an example of a computer-readable medium.

Computer-readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), Static Random Access Memory (SRAM), Dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), Read Only Memory (ROM), Electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), Digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information that can be accessed by a computing device. As defined herein, a computer readable medium does not include a transitory computer readable medium such as a modulated data signal and a carrier wave.

It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.

The application may be described in the general context of computer-executable instructions, such as program modules, being executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform particular tasks or implement particular abstract data types. The application may also be practiced in distributed computing environments where tasks are performed by remote processing devices that are linked through a communications network. In a distributed computing environment, program modules may be located in both local and remote computer storage media including memory storage devices.

The embodiments in the present specification are described in a progressive manner, and the same and similar parts among the embodiments are referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, for the system embodiment, since it is substantially similar to the method embodiment, the description is simple, and for the relevant points, reference may be made to the partial description of the method embodiment.

The above description is only an example of the present application and is not intended to limit the present application. Various modifications and changes may occur to those skilled in the art to which the present application pertains. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.

Claims (15)

1. An indoor relocation method is characterized by being applied to intelligent equipment; the method comprises the following steps:

constructing an initialization exploration map corresponding to the target space; the target space comprises a plurality of areas, and obstacles exist among the areas for separation;

controlling the intelligent equipment to move in a target area in the target space, and acquiring target point cloud data of the target area in the moving process of the intelligent equipment;

updating the initialized exploration map according to the target point cloud data to generate a local exploration map corresponding to the target area;

and matching the local exploration map with a space map corresponding to the target space, and determining the pose information of the intelligent equipment in the target space according to a matching result.

2. The method according to claim 1, wherein the intelligent device is controlled to move in a target area in the target space, and target point cloud data of the target area is acquired during the movement of the intelligent device; updating the initialized exploration map according to the target point cloud data to generate a local exploration map corresponding to the target area, wherein the local exploration map comprises the following steps:

when the intelligent equipment is located in a first area, collecting first point cloud data of the first area, and updating the initialized exploration map according to the first point cloud data to obtain a first exploration map; the target region comprises the first region;

judging whether the first exploration map meets a space exploration completion condition or not; the space exploration completion condition comprises at least one of the following conditions: the quantity of the explored target areas is greater than or equal to a first preset threshold value, and the total explored area of the explored target areas is greater than or equal to a second preset threshold value;

if so, determining the first exploration map as the local exploration map;

if not, controlling the intelligent equipment to move from the first area to a second area, acquiring second point cloud data of the second area, and updating the first exploration map according to the second point cloud data until the updated exploration map meets the space exploration completion condition; the target region further includes the second region.

3. The method of claim 2, wherein the collecting first point cloud data for the first area and updating the initialized exploration map according to the first point cloud data to obtain a first exploration map comprises:

when the intelligent equipment is located at a first exploration position in the first area, acquiring the first point cloud data of the first area, and updating the initialized exploration map according to the first point cloud data to obtain an area exploration subgraph;

judging whether the first area meets an area exploration completion condition or not; the area exploration completion condition includes at least one of: an unexplored area does not exist in the current exploration area, and the exploration area in the current exploration area is larger than or equal to a third preset threshold;

if so, determining the area exploration subgraph as the first exploration map;

if not, controlling the intelligent equipment to move in the first area, continuously acquiring the first point cloud data of the first area in the moving process, updating the area exploration subgraph according to the acquired first point cloud data, and obtaining the first exploration map when the first area meets the area exploration completion condition.

4. The method of claim 3, wherein the controlling the smart device to move within the first area and continue to collect the first point cloud data of the first area during the moving comprises:

determining a second exploration position in the first area according to the unexplored area existing in the first area;

controlling the smart device to move from the first exploration location to the second exploration location;

when the smart device is located at the second exploration position, the first point cloud data of the first area is collected.

5. The method of claim 2, wherein the obstacle is a passable lane;

the controlling the smart device to move from the first zone to a second zone includes:

determining the second area to be explored in the space map according to the area of each area in the space map;

identifying the passable passage between the first area and the second area, and determining position information of the passable passage;

and controlling the intelligent equipment to move to the second area through the passable passage according to the position information.

6. The method according to claim 1, wherein the matching the local exploration map and a space map corresponding to the target space, and determining pose information of the smart device on the space map according to a matching result comprises:

determining first feature information of a first key position on the local exploration map and second feature information of a second key position on the space map; the first feature information or the second feature information includes at least one of: position orientation, position size, position shape;

matching the first characteristic information with the second characteristic information, and determining a first mapping relation between the first key position and the second key position according to a matching result;

and determining the pose information of the intelligent device on the space map according to the first mapping relation and the pose information of the intelligent device on the local exploration map.

7. The method of claim 6, wherein the first and second key locations each comprise a plurality;

the matching the first feature information and the second feature information, and determining a first mapping relationship between the first key position and the second key position according to a matching result includes:

determining a first relative pose relationship between the first key positions according to the first characteristic information corresponding to the first key positions respectively;

determining, for a first target key location of a plurality of the first key locations, a second target key location in the spatial map that matches the first target key location;

and determining the first mapping relation between each first key position and each second key position according to the first relative pose relation and the second mapping relation between the first target key position and the second target key position.

8. The method according to claim 7, wherein determining the first mapping relationship between each of the first key positions and each of the second key positions according to the first relative pose relationship and the second mapping relationship between the first key positions and the second key positions of the target comprises:

mapping other first key positions to the space map according to the second mapping relation to obtain a third key position;

judging whether the second key position is matched with the third key position in the space map or not according to the first relative pose relation;

if so, determining the first mapping relation between each first key position and each second key position according to the second mapping relation;

if not, re-determining the second target key position corresponding to the first target key position.

9. The method according to claim 7 or 8, wherein the second target key location corresponding to the first target key location comprises a plurality;

the determining the pose information of the intelligent device on the space map according to the first mapping relation and the pose information of the intelligent device on the local exploration map comprises the following steps:

determining a plurality of candidate pose information of the intelligent device on the space map respectively according to the first mapping relations;

for any candidate pose information, performing traversal search in a preset region range corresponding to the candidate pose information, and determining probability scores corresponding to the candidate pose information according to search results;

and determining the candidate pose information corresponding to the highest value in the probability scores as the pose information of the intelligent equipment on the space map.

10. The method according to claim 9, wherein the determining a plurality of candidate pose information of the smart device on the spatial map for each of the first mapping relationships comprises:

determining a pose conversion relation of the intelligent equipment relative to each first key position according to pose information of the intelligent equipment on the local exploration map;

and mapping the pose information of the intelligent equipment on the local exploration map to the space map according to the pose conversion relation and the first mapping relation to obtain the candidate pose information of the intelligent equipment on the space map.

11. The method according to claim 9, wherein performing traversal search in a preset area range corresponding to the candidate pose information and determining probability scores corresponding to the candidate pose information according to search results comprises:

controlling the intelligent equipment to move in the preset area range, and acquiring point cloud data in the preset area range in the moving process;

generating a preset area map corresponding to the preset area range according to the point cloud data;

comparing the preset area map with a corresponding area map on the space map, and determining the matching rate between the preset area map and the corresponding area map according to the comparison result;

and calculating the probability score corresponding to the candidate pose information according to the matching degree.

12. An indoor relocating device, characterized in that, is applied to smart machine, the device includes:

the construction module is used for constructing an initialized exploration map corresponding to the target space; the target space comprises a plurality of areas, and obstacles exist among the areas for separation;

the acquisition module is used for acquiring target point cloud data of the target area;

the generation module is used for updating the initialized exploration map according to the target point cloud data so as to generate a local exploration map corresponding to the target area;

and the matching module is used for matching the local exploration map with a space map corresponding to the target space and determining the pose information of the intelligent equipment on the space map according to a matching result.

13. The indoor relocating device according to claim 12 further comprising a power module for driving movement of the smart device at a target area within the target space;

the acquisition module is further used for acquiring target point cloud data of the target area in the moving process of the intelligent device.

14. An indoor relocation apparatus comprising a processor and a memory electrically connected to the processor, the memory storing a computer program, the processor being configured to invoke and execute the computer program from the memory to implement the indoor relocation method of any one of claims 1-11.

15. A storage medium for storing a computer program executable by a processor for implementing the indoor relocation method according to any one of claims 1 to 11.

Images