Map change detection method, apparatus, device, and storage medium

Abstract

The application discloses a map change detection method and device, equipment and a storage medium. The map change detection method comprises the following steps: controlling a movable device to move and record a point cloud based on an acquired prior grid map, and obtaining a real-time grid map; determining an area that is overlapped in the prior grid map and the real-time grid map as a target prior map, and determining an area that is overlapped in the real-time grid map and the prior grid map as a target real-time map; and determining a map change rate of the target real-time map relative to the target prior map based on a grid difference comparison result between the target prior map and the target real-time map. The above scheme can accurately determine whether the current map has changed.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of map processing, and in particular to a map change detection method and device, equipment and a storage medium. BACKGROUND

[0002] Map construction is one of the most important technologies at present. In the navigation scenarios of robots, cars and other mobile devices, high-accuracy maps are needed to achieve precise navigation.

[0003] For example, mobile robots with autonomous navigation capabilities are widely used in factory, logistics, shopping mall and other scenarios, and they generally rely on environment maps to achieve navigation. However, these environments have complex and variable characteristics, and changes in walls, machines and other objects in the environment directly cause the environment map to be inconsistent with the actual environment, thereby affecting the accuracy and reliability of robot navigation and positioning. Relying on manual post-update of the environment map will also bring a relatively large cost burden and construction difficulty.

[0004] Therefore, how to determine whether the environment map has changed has become an important problem to be solved in the current map processing technology. SUMMARY

[0005] The present application provides at least a map change detection method, device, equipment and computer readable storage medium.

[0006] The first aspect of the present application provides a map change detection method, comprising: controlling a mobile device to move and record point clouds based on an acquired prior grid map, to obtain a real-time grid map; determining a region in the prior grid map that coincides with the real-time grid map as a target prior map, and determining a region in the real-time grid map that coincides with the prior grid map as a target real-time map; determining a map change rate of the target real-time map relative to the target prior map based on a grid difference comparison result between the target prior map and the target real-time map.

[0007] In an embodiment, after the step of determining the map change rate of the target real-time map relative to the target prior map based on the grid difference comparison result between the target prior map and the target real-time map, the method further comprises: if the map change rate is greater than a preset change threshold, updating the prior grid map to obtain an updated prior grid map; and controlling the mobile device to move and record point clouds based on the updated prior grid map.

[0008] In an embodiment, after the step of obtaining the real-time grid map by moving and recording the point cloud based on the obtained prior grid map, the method further comprises: generating a target detection map based on the detected grid and the undetected grid in the real-time grid map; and the step of determining the map change rate of the target real-time map relative to the target prior map based on the grid difference comparison result between the target prior map and the target real-time map comprises: determining the undetected grid in the target prior map based on the target detection map, and performing filtering processing on the undetected grid to obtain the filtered target prior map; and determining the map change rate of the target real-time map relative to the target prior map based on the grid difference comparison result between the filtered target prior map and the target real-time map.

[0009] In an embodiment, the step of generating a target detection map based on the detected grid and the undetected grid in the real-time grid map comprises: determining the detected grid and the undetected grid in the real-time grid map based on the obtained point cloud data; generating an initial detection map based on the detected grid and the undetected grid; and performing down-sampling processing on the initial detection map to obtain the target detection map.

[0010] In an embodiment, the undetected grid comprises a first detection value, the detected grid comprises a second detection value, and the grid in the target prior map comprises an occupancy value. The step of determining the undetected grid in the target prior map based on the target detection map and performing filtering processing on the undetected grid to obtain the filtered target prior map comprises: traversing the grid with a matched position between the target detection map and the target prior map; updating the occupancy value of the grid corresponding to the first detection value, and retaining the occupancy value of the grid corresponding to the second detection value to obtain the filtered target prior map.

[0011] In an embodiment, the step of determining the map change rate of the target real-time map relative to the target prior map based on the grid difference comparison result between the target prior map and the target real-time map comprises: performing an exclusive OR operation between the target prior map and the target real-time map to obtain a difference map, wherein the difference map comprises the grid with a change between the target prior map and the target real-time map; and performing ratio calculation between the number of target grids in the target prior map and the number of grids with a change to obtain the map change rate.

[0012] In an embodiment, the step of determining the area in the prior grid map and the real-time grid map as the target prior map and determining the area in the real-time grid map and the prior grid map as the target real-time map comprises: determining the area in the prior grid map and the real-time grid map as a prior sub-map; performing down-sampling processing on the prior sub-map to obtain the target prior map; determining the area in the real-time grid map and the prior grid map as a real-time sub-map; and performing down-sampling processing on the real-time sub-map to obtain the target real-time map.

[0013] The second aspect of the present application provides a map change detection apparatus, comprising: an acquisition module configured to control a movable device to move and record point clouds based on an acquired prior grid map to obtain a real-time grid map; a map determination module configured to determine an area in the prior grid map and the real-time grid map as a target prior map and determine an area in the real-time grid map and the prior grid map as a target real-time map; and a change calculation module configured to determine a map change rate of the target real-time map relative to the target prior map based on a comparison result of a grid difference between the target prior map and the target real-time map.

[0014] The third aspect of the present application provides an electronic device comprising a memory and a processor, wherein the processor is configured to execute program instructions stored in the memory to implement the above-described map change detection method.

[0015] The fourth aspect of the present application provides a computer-readable storage medium having program instructions stored thereon, wherein the program instructions are executed by a processor to implement the above-described map change detection method.

[0016] The above-described scheme controls a movable device to move and record point clouds based on an acquired prior grid map to obtain a real-time grid map; the area in the prior grid map and the real-time grid map is the area that needs to be determined whether there is a change, so the area in the prior grid map and the real-time grid map is determined as a target prior map, and the area in the real-time grid map and the prior grid map is determined as a target real-time map; a map change rate of the target real-time map relative to the target prior map is determined based on a comparison result of a grid difference between the target prior map and the target real-time map, so that whether the current scene changes compared with the prior map can be determined according to the map change rate, and the movable device is prevented from being positioned and navigated incorrectly.

[0017] It should be understood that the general description above and the detailed description below are only exemplary and explanatory, but not limiting the present application. BRIEF DESCRIPTION OF DRAWINGS

[0018] The drawings incorporated in and forming a part of the specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the application.

[0019] Figure 1 is a flowchart of an exemplary embodiment of the map change detection method of the present application;

[0020] Figure 2 is a simple schematic diagram of the connection relationship between the vehicle controller unit, the car machine system and the vehicle audio power amplifier in the map change detection method of the present application;

[0021] Figure 3 is an effect diagram of map change detection under straight line acceleration in the map change detection method of the present application;

[0022] Figure 4 is Figure 1 is a flowchart of an exemplary embodiment of step 130 in the map change detection method shown;

[0023] Figure 5 is an effect diagram of map change detection under straight line deceleration in the map change detection method of the present application;

[0024] Figure 6 is a block diagram of the map change detection device shown in an exemplary embodiment of the present application;

[0025] Figure 7 is a structural schematic diagram of an embodiment of the electronic device of the present application;

[0026] Figure 8 is a structural schematic diagram of an embodiment of the computer readable storage medium of the present application. DETAILED DESCRIPTION

[0027] The schemes of the embodiments of the present application will be described in detail below in conjunction with the drawings of the specification.

[0028] In the following description, specific details are set forth in order to provide a thorough understanding of the present application. The present application may, however, be practiced without these specific details. In other instances, well-known methods, structures and techniques have not been described in detail in order to avoid obscuring the present application.

[0029] The term "and / or", used in the present document, only describes the association relationship of the associated objects, which means that there can be three relationships, for example, A and / or B can represent the following three cases: A exists alone, A and B exist together, and B exists alone. In addition, the character " / " in the present document generally represents an "or" relationship between the front and rear associated objects. In addition, "multiple" in the present document means two or more than two. In addition, the term "at least one" in the present document means any one of multiple or any combination of at least two of multiple, for example, including at least one of A, B and C can mean including any one or more elements selected from the set consisting of A, B and C.

[0030] For the convenience of understanding, the common existing method in the application scenarios of positioning, navigation, etc. of the movable device will be exemplarily described. In the existing method, the movable device is usually moved and positioned according to the acquired prior map, wherein the prior map can be a grid map, that is, a grid composed of individual grids is used to represent the map, and different values can be stored in the grid to represent the different meanings of the grid, wherein the values can be probability values, gray values, or binary values (0 represents that the grid is free, and 1 represents that the grid is occupied).

[0031] In some complex and changeable environments, if the prior map does not conform to the actual environment, the positioning and navigation accuracy of the movable device will be affected. Therefore, if there is a difference between the prior map and the actual environment, the prior map will be updated by relevant personnel; but if relevant personnel are dispatched to update the prior map every time the actual environment changes, it will also bring a large cost burden and construction difficulty.

[0032] Please refer to Figure 1 , Figure 1 is a flowchart of an exemplary embodiment of the map change detection method of the present application. Specifically, it can include the following steps:

[0033] Step S110, controlling the movable device to move and record point clouds based on the acquired prior grid map, to obtain a real-time grid map.

[0034] The movable device can be a movable robot, a drone, a car, etc. In the present application, a movable robot is mainly taken as an example for description. The movable device is provided with a laser radar for acquiring laser point cloud data, and can also be provided with an odometer for preliminarily estimating the change amount of the angle and distance of the mobile robot. A common wheel encoder can estimate the pose of the robot at the current time according to the pose change amount at the front and rear time and the pose at the previous time.

[0035] The grid map of the present application can be a minimum rectangular envelope surface containing all obstacle grids. If the shape of the grid obstacle is not rectangular, a grid (free state) can be supplemented at the edge of the grid map until the grid map becomes rectangular. Exemplarily, the lower left corner coordinates of the grid map can be taken as the coordinate origin (x, y, thea), the resolution is r, the number of grid rows is rows, and the number of grid columns is cols.

[0036] It should be noted that the prior grid map can be set in advance or obtained through network communication; the method of the present application can be applied to a mobile device equipped with a processor, which can be internally implemented to control and process data by the mobile device, or applied to an external intelligent device in communication connection with the mobile device, which can control the mobile device and process data through the communication connection, which is not limited here.

[0037] Specifically, the mobile device takes the obtained prior grid map as a positioning map to move and record real-time laser point cloud data and its corresponding pose. Among them, it can be recorded synchronously in real time while moving, or it can be recorded after moving to the target position in the prior grid map, which is not limited here. In its running process, it can be based on the obtained point cloud data to generate a real-time grid map in response to the obtained map generation instruction (as previously described, it can be internally triggered or externally triggered); or based on a preset time interval, when the running time reaches the time interval each time, a real-time grid map is generated based on the point cloud data obtained in the running time; or based on a preset distance interval, when the running distance reaches the distance interval each time, a real-time grid map is generated based on the point cloud data obtained in the running distance. The resolution of the generated real-time grid map can be consistent with the resolution of the prior grid map.

[0038] Further, the real-time grid map Each key frame laser data obtained can be projected to the prior grid map coordinate system according to its corresponding pose, and a ray tracing or TSDF method is used to generate, wherein the value of each grid in the real-time grid map represents whether it is occupied (occupied is 1, free is 0). In addition, when generating the real-time grid map, an observation map (also referred to as a detection map hereinafter) is also generated, which represents whether each grid in the real-time grid map is observed by the mobile device (observed is 1, not observed is 0), wherein if the grid is not observed, the observation value of the grid in the observation map is 0, but it does not mean whether the grid is occupied.

[0039] Step S120, the area overlapped with the real-time grid map in the prior grid map is determined as a target prior map, and the area overlapped with the prior grid map in the real-time grid map is determined as a target real-time map.

[0040] In combination with the foregoing steps, the real-time grid map is generated by the movable device in the moving process, and thus the real-time grid map and the prior grid map may have a size difference, and thus a comparison analysis needs to be performed on the overlapped area (intersection area) in the real-time grid map and the prior grid map. As shown in Figure 2 , Figure 2 is an exemplary schematic diagram for analyzing the overlapped area between the prior grid map and the real-time grid map in the map change detection method of the present application. By analyzing the change of each grid in the overlapped area (from free to occupied or from occupied to free), the change amount of the real-time grid map relative to the prior grid map in the overlapped area can be obtained.

[0041] Exemplarily, the real-time grid map is projected into the coordinate system of the prior grid map to obtain the vertex coordinates of the lower left corner and the upper right corner of the prior grid map as rect1{( ),( )}. The vertex coordinates of the lower left corner and the upper right corner of the real-time grid map are obtained as rect2{( ),( )}. It can be known that the vertex coordinates of the lower left corner and the upper right corner of the intersection area of the two are rect3{( =max( ), =max( ), =min( ), =min( ), that is, the vertex coordinates of the intersection rectangular area are rect3{( ),( )}. Further, the prior map in the prior grid map and the real-time map in the real-time grid map can be determined according to the intersection area.

[0042] It should be noted that the prior map may be determined as the target prior map and the real-time map may be determined as the target real-time map; or after further optimization processing of the prior map and the real-time map , the two new maps obtained are taken as the target prior map and the target real-time map, which will not be described herein.

[0043] In addition, since the observation map is consistent with the real-time grid map in origin coordinates, size, and resolution, during the process of processing the real-time grid map as described above, the corresponding grid area of the observation map can also be cropped and processed in the same way as the real-time grid map, so as to obtain the observation map matching the target real-time map. .

[0044] In step S130, the map change rate of the target real-time map relative to the target prior map is determined based on the comparison result of the grid difference between the target prior map and the target real-time map.

[0045] In combination with the foregoing steps, if the target prior map and the target real-time map are determined as and , the change of the target real-time map relative to the target prior map in the same area can be obtained by comparing the grids in the target prior map and the target real-time map , and the map change rate is obtained. For example, the change of the grid can be represented by the grid value in the map, for example, the grid value of a certain grid in the prior map is 1, representing the occupied state, and the grid value of the grid in the real-time map is 0, representing the idle state, that is, the grid changes from occupied to idle, and the occupied object in the grid may have moved in the current period; similarly, if the grid value of a certain grid in the prior map is 0, representing the idle state, and the grid value of the grid in the real-time map is 1, representing the occupied state, that is, the grid changes from idle to occupied, and the originally idle grid has been put into the occupied object in the current period.

[0046] Specifically, the method of calculating the map change rate can be obtained by calculating the ratio between the number of grids whose grid values change between the target prior map and the target real-time map and the total number of grids in the intersection area. Wherein, whether the grid value changes can be determined by exclusive or operation (orthogonal calculation), for example, for the same grid, if the grid value of the grid in the target real-time map changes compared with the grid value of the grid in the target prior map, then the value obtained by exclusive or operation of the grid value of the grid in the target real-time map and the grid value of the grid in the target prior map is 1; similarly, if the grid value does not change, the value obtained is 0.

[0047] Specifically, the method of calculating the map change rate can be obtained by calculating the ratio between the number of grids whose grid values change between the target prior map and the target real-time map and the total number of grids in the intersection area. Wherein, whether the grid value changes can be determined by exclusive or operation (orthogonal calculation), for example, for the same grid, if the grid value of the grid in the target real-time map changes compared with the grid value of the grid in the target prior map, then the value obtained by exclusive or operation of the grid value of the grid in the target real-time map and the grid value of the grid in the target prior map is 1; similarly, if the grid value does not change, the value obtained is 0.

[0048] ​Optionally, after obtaining the above result, the map change rate and the grid with changes can be stored, and real-time grid map and other data can be deleted or subjected to other optimization processing to save data storage space. In subsequent processes, the mobile device, other electronic devices or related personnel can measure whether the prior map needs to be updated according to the map change rate and the grid with changes.

[0049] It can be seen that, by controlling the mobile device to move and record point clouds based on the obtained prior grid map, the real-time grid map is obtained; the area where the prior grid map and the real-time grid map coincide is the area where changes need to be determined, so the area where the prior grid map and the real-time grid map coincide is determined as the target prior map, and the area where the prior grid map and the real-time grid map coincide is determined as the target real-time map; the map change rate of the target real-time map relative to the target prior map is determined based on the grid difference comparison result between the target prior map and the target real-time map, so that whether the current scene has changed compared with the prior map can be determined according to the map change rate, and the mobile device is prevented from being positioned and navigated incorrectly.

[0050] Based on the above embodiment, the steps after determining the map change rate of the target real-time map relative to the target prior map based on the grid difference comparison result between the target prior map and the target real-time map are described in the embodiments of the present application. Specifically, the method of the present embodiment comprises the following steps:

[0051] If the map change rate is greater than the preset change threshold, the prior grid map is updated to obtain an updated prior grid map, and the mobile device is controlled to move and record point clouds based on the updated prior grid map.

[0052] In combination with the foregoing embodiments, in the conventional map updating method, the prior map is updated in real time when it is detected that the real-time map and the prior map have changes, but in a complex scene, the map can be updated incorrectly due to positioning errors. The present application can update the map with a map change rate greater than the change threshold after comparing the map change rate with the preset change threshold, thereby avoiding the problem of changing the prior map due to incorrect positioning and effectively improving the fault tolerance of map construction and positioning and navigation.

[0053] The change threshold can be one or more. For example, the movement scene of the mobile device can be divided into multiple sub-regions (i.e., the map can include multiple sub-regions), and the change thresholds in different sub-regions can be the same or different, so as to set different change thresholds for some regions with frequent changes and / or some regions with infrequent changes in the movement scene for separate judgment.

[0054] Further, after updating the map, the movable device can be controlled to move and record point clouds according to the updated map, and a real-time grid map is generated according to the method provided in the foregoing embodiments to detect map changes.

[0055] Therefore, after generating a new real-time grid map, the application calculates a map change rate and stores the changed grid to accurately determine whether the prior map needs to be changed or updated, and to reduce data redundancy. During the operation of the movable device, the prior map can be changed in a non-real-time manner, avoiding the problem of changing the prior map due to incorrect positioning, and effectively improving the fault tolerance.

[0056] In addition, the implementable manner of updating the map according to the application can be that after calculating the map change rate of the overlapping area between the currently generated real-time grid map and the prior grid map each time, it is determined whether the prior map needs to be updated according to the map change rate and the change threshold. It can also be that after calculating the map change rate each time, it is saved until the area covered by all the real-time grid maps generated by the movable device covers the area of the prior grid map (for example, the movable device completes a full drive on the prior grid map, or the movable device completes the route drive corresponding to the received task instruction), and then the average or weighted calculation (the maps generated in different areas can correspond to the same or different weights, for example, the frequently changed area can be set to a lower weight, and the infrequently changed area can be set to a higher weight) of the map change rates obtained by comparing the real-time grid maps and the prior map each time is performed to obtain a target change rate, and then it is determined whether to update the map according to the target change rate. Therefore, the determination of whether the map needs to be updated is more accurate.

[0057] On the basis of the foregoing embodiments, the application embodiment explains the steps of determining the map change rate of the target real-time map relative to the target prior map based on the comparison result of the grid difference between the target prior map and the target real-time map after moving and recording point clouds based on the acquired prior grid map to obtain the real-time grid map. Specifically, the method of the embodiment comprises the following steps:

[0058] generating a target detection map based on the detected grid and the undetected grid in the real-time grid map; determining the undetected grid in the target prior map based on the target detection map, and filtering the undetected grid to obtain a filtered target prior map; and determining the map change rate of the target real-time map relative to the target prior map based on the comparison result of the grid difference between the filtered target prior map and the target real-time map.

[0059] As explained in the foregoing embodiments, the target detection map can be equivalent to the observation map in the foregoing embodiments Or a map after a certain data processing such as Or there may be other data processing processes, which will not be described here. It is used to represent which grids in the real-time grid map are detected (observed to be 1) and which grids are not detected (not observed to be 0).

[0060] It can be understood that the movable device is limited by the route or the object in the environment during movement, and when generating a new map (generating a real-time grid map), the movable device cannot observe the state of some grid regions in the prior grid map in some period (may be blocked, etc.), at this time, it may be considered that the grid region in the real-time grid map is an unknown (free) region, and then the grid in the prior grid map which is in an occupied state is judged to be a free state when the real-time grid map is generated, it is determined that the object is removed, and finally the calculation accuracy of the map change rate is affected.

[0061] In the technical solution of the present application, during the generation of the real-time grid map, the detection state of each grid can be recorded to generate a target detection map (the observed grid is determined as a known grid, and its observation value is set to 1; the unobserved grid is determined as an unknown grid, and its observation value is set to 0). For the grids in the intersection region of the prior grid map and the real-time grid map, the unknown grids in the target detection map can be filtered to make the analysis and calculation result more accurate.

[0062] Exemplarily, the filtering manner can be that based on the observation value marked in the target detection map, the grid value of the undetected grid in the target prior map is set to 0 to obtain the filtered target prior map. Based on the grid difference comparison result between the filtered target prior map and the target real-time map (refer to the XOR operation process in the foregoing embodiment), the more accurate map change rate can be determined.

[0063] On the basis of the foregoing embodiment, the embodiment of the present application describes the step of generating a target detection map based on the detected grids and the undetected grids in the real-time grid map. Specifically, the method of the present embodiment comprises the following steps:

[0064] Based on the obtained point cloud data, the detected grids and the undetected grids in the real-time grid map are determined; based on the detected grids and the undetected grids, an initial detection map is generated; the initial detection map is down-sampled to obtain a target detection map.

[0065] In combination with the foregoing embodiments, in the process of generating the real-time grid map, the intersection region of the prior grid map and the real-time grid map can be determined based on the acquired point cloud data, and the detected grid and the undetected grid in the intersection region are determined, and then the initial detection map is generated based on the detected grid and the undetected grid. For ease of understanding, the initial detection map can be equivalent to the observation map in the foregoing embodiments , which includes the detected grid (known grid, observation value is 1) and the undetected grid (unknown grid, observation value is 0).

[0066] It can be understood that the prior grid map and the real-time grid map can be used for navigation positioning, and therefore the map is relatively fine and has a relatively high resolution. Due to factors such as sensor errors, map construction errors, and positioning errors, the contour grids generated by the same object will also have certain errors in the two maps, and there will also be a certain degree of position and size deviation between the grids. In order to avoid mistaking such a situation as a change in the map, and to improve the calculation efficiency, one or more times of down-sampling processing can be performed on the three maps (prior map, real-time map, and detection map). After pixel filtering down-sampling, the maps with a resolution of r1 are obtained, i.e., the prior map , the real-time map , and the detection map .

[0067] It should be noted that the initial detection map of the present embodiment can be obtained after the clipping processing , or obtained without the clipping processing . The specific type can refer to the description of the foregoing embodiments, and mainly depends on whether the real-time map is clipped. Therefore, in the present embodiment, the initial detection map may be clipped to obtain the detection map , and then the detection map is down-sampled to obtain the target detection map ; or the initial detection map is down-sampled to obtain the target detection map .

[0068] In addition, in another implementable manner, the execution order of the down-sampling processing and the clipping processing can also be exchanged, which will not be described here.

[0069] On the basis of the above embodiments, the step of determining the undetected grid in the target prior map based on the target detection map and filtering the undetected grid to obtain the filtered target prior map is described. The undetected grid includes the first detection value, the detected grid includes the second detection value, and the grid in the target prior map includes the occupancy value. Specifically, the method of the embodiment includes the following steps:

[0070] Traverse the grids with matched positions between the target detection map and the target prior map; update the occupancy value of the grid corresponding to the first detection value, and retain the occupancy value of the grid corresponding to the second detection value to obtain the filtered target prior map.

[0071] In combination with the foregoing embodiments, the undetected grid in the detection map is set to the first detection value (such as 0), and the detected grid is set to the second detection value (such as 1); and the grid in the prior map has an occupancy value for representing whether the grid in the prior map is occupied. Here, 0 represents unoccupied, and 1 represents occupied; similarly, the grid in the real-time map also has an occupancy value.

[0072] Reference can be made to Figure 3 , Figure 3 which is a grid filtering schematic diagram in the map change detection method of the present application. The target detection map is taken as an example. The target prior map is filtered as an example. Since the specifications of the target detection map and the target prior map remain the same, each corresponding grid in and is traversed. If the grid in the i-th row and the j-th column in , is , , the mathematical expression of the corresponding grid element in the filtered prior map is:

[0073]

[0074] It is indicated that for the same set of corresponding grids, if the occupancy value and the detection value are both 1, the occupancy value of the grid in the target prior map after filtering (and operation) is 1, which means that the grid is assigned a value of 1 in the case that the grid is observed and occupied; otherwise, it is 0. Traversing all the grids to calculate the above formula can obtain the filtered object in the unknown area and obtain the filtered target prior map .

[0075] On the basis of the above embodiments, the embodiments of the present application explain the step of determining the map change rate of the target real-time map relative to the target prior map based on the grid difference comparison result between the target prior map and the target real-time map. Specifically, the method of the present embodiment comprises the following steps:

[0076] XOR operation is performed between the target prior map and the target real-time map to obtain a difference map, the difference map including the grids that have changed between the target prior map and the target real-time map; ratio calculation is performed between the number of target grids in the target prior map and the number of grids that have changed to obtain a map change rate.

[0077] In combination with the foregoing embodiments, reference can be made to Figure 4 , Figure 4 is a schematic diagram of obtaining a grid difference comparison result in the map change detection method of the present application. The target real-time map is XOR operated with each grid element in the filtered target prior map to obtain a new map matrix , which is mathematically expressed as:

[0078] (i, j) = 1 (i, j) = 0 (i, j)

[0079] It can be known from the XOR operation that the grid value of the grid that will change in the obtained matrix is set to 1, and the grid value of the grid that will not change is set to 0.

[0080] Therefore, the number of grids with a value of 1 in the matrix is N, which represents the number of grids that have changed (including from free to occupied and from occupied to free) in the target real-time map compared with the filtered target prior map; the number of grids with a value of 1 in the matrix is the number M of occupied grids in the filtered target prior map. Then, the mathematical expression of the map change rate of the target real-time map relative to the filtered target prior map is CMR= , wherein γ is a preset coefficient, because the resolution of the map has been scaled, if the scaling is too much, the effect may be affected, therefore the preset coefficient is used for amplification; it can be obtained according to experimental experience, the greater the scaling rate of the previous process, the greater the coefficient here can be set, for example, the method can use 1.5 as the preset coefficient, wherein , =r1 / r, which can be referred to in the foregoing embodiments, r1 is the resolution of the down-sampled map, and r is the initial resolution of the map.

[0081] Therefore, the changed grid map Mc and the map change rate CMR are obtained. If the environment change rate of the current map is greater than the preset change threshold β (which can be set to 0.3 in the present application), it is considered that the map has changed, and the staff can be prompted to check whether the map has changed and update the prior map.

[0082] For example, as shown in Figure 5 , Figure 5 is a schematic diagram of a scenario for determining whether a map is updated in the map change detection method of the present application, Figure 5 In (a), the boxed area is the changed part of the real-time map relative to the prior map, and the change rate is about 41.92%. The change rate is greater than the threshold β, and the map needs to be updated at this time. Similarly, Figure 5 The change rate of (b) is about 13.9%, which is less than the threshold β, and the map does not need to be updated at this time.

[0083] On the basis of the above-mentioned embodiments, the present embodiment determines the area overlapping the prior grid map and the real-time grid map as the target prior map, and determines the area overlapping the prior grid map and the real-time grid map as the target real-time map. Specifically, the method of the present embodiment comprises the following steps:

[0084] The area overlapping the prior grid map and the real-time grid map is determined as a prior sub-map. The prior sub-map is subjected to down-sampling processing to obtain a target prior map. The area overlapping the prior grid map and the real-time grid map is determined as a real-time sub-map. The real-time sub-map is subjected to down-sampling processing to obtain a target real-time map.

[0085] In combination with the foregoing embodiments, the foregoing embodiments have described the method of down-sampling processing the detection map. Similarly, the prior map and the real-time map can also be subjected to down-sampling processing. That is, in one implementable manner of the present application, the movable device can be controlled to move and collect point cloud data according to the prior map , and generate a real-time map and a detection map based on the acquired point cloud data. The intersection area between the prior map and the real-time map is subjected to clipping processing to obtain a prior sub-map and a real-time sub-map , and the detection map is subjected to clipping processing according to the same clipping manner of the real-time map to obtain a detection map . The prior sub-map , the real-time sub-map and the detection map Downsampling is performed to obtain a target prior map , a target real-time map , and a target detection map .

[0086] In summary, the application designs an accurate and efficient map change rate calculation method: the intersection part of the prior map and the real-time map is obtained through rectangular intersection calculation; by map downsampling, false detection caused by map scale error, sensor error and algorithm error is avoided, and the calculation efficiency is improved; by recording whether each grid is observed, the unobserved grids in the prior map are filtered, so that the calculation result is more accurate; by performing XOR operation on the two map matrices, it can be quickly judged which grids have changed (including changing from free to occupied and from occupied to free); by calculating the map change rate and storing only the changed matrix , accurate judgment and measurement of whether the prior map needs to be changed or updated can be realized; during the running of the movable device, the prior map can not be changed in real time, which avoids the situation that the prior map is changed due to false positioning, and effectively improves the fault tolerance.

[0087] It should be further explained that the execution subject of the map change detection method can be a map change detection device, for example, the map change detection method can be executed by a terminal device or a server or other processing device, wherein the terminal device can be a user equipment (User Equipment, UE), a computer, a mobile device, a user terminal, a terminal, a cellular phone, a cordless phone, a personal digital assistant (Personal Digital Assistant, PDA), a handheld device, a computing device, a vehicle-mounted device, a wearable device, etc. In some possible implementation manners, the map change detection method can be realized by calling the computer readable instructions stored in the memory by the processor.

[0088] Figure 6 is a block diagram of a map change detection device according to an example embodiment of the application. As shown in Figure 6 , the example map change detection device 600 includes an acquisition module 610, a map determination module 620, and a change calculation module 630. Specifically:

[0089] The acquisition module 610 is configured to control the movable device to move and record point clouds based on the acquired prior grid map, to obtain a real-time grid map.

[0090] The map determination module 620 is configured to determine the area of the prior grid map that coincides with the real-time grid map as a target prior map, and determine the area of the real-time grid map that coincides with the prior grid map as a target real-time map.

[0091] The change calculation module 630 is configured to determine a map change rate of the target real-time map relative to the target prior map based on a comparison result of a grid difference between the target prior map and the target real-time map.

[0092] In the exemplary map change detection apparatus, the movable device is controlled to move and record point clouds based on the acquired prior grid map, so as to obtain a real-time grid map; the area where the prior grid map and the real-time grid map coincide is the area where it is needed to determine whether there is a change, therefore, the area where the prior grid map and the real-time grid map coincide is determined as the target prior map, and the area where the prior grid map and the real-time grid map coincide is determined as the target real-time map; the map change rate of the target real-time map relative to the target prior map is determined based on a comparison result of a grid difference between the target prior map and the target real-time map, so as to determine whether the current scene changes compared with the prior map according to the map change rate, and prevent the movable device from being positioned and navigated incorrectly.

[0093] It should be noted that the apparatus provided in the above embodiments and the method provided in the above embodiments belong to the same concept, and the specific manner in which each module and unit performs operations has been described in detail in the method embodiments, which will not be described here. In actual application, the functions of the apparatus can be completed by different functional modules according to needs, that is, the internal structure of the apparatus is divided into different functional modules to complete all or part of the functions described above, which is not limited here.

[0094] The functions of each module can be referred to the method embodiments of detecting a map change, which will not be described here.

[0095] Please refer to Figure 7 , Figure 7 is a structural schematic diagram of an embodiment of an electronic device. The electronic device 700 includes a memory 701 and a processor 702, and the processor 702 is configured to execute program instructions stored in the memory 701 to implement the steps in any of the above-described map change detection method embodiments. In one specific implementation scenario, the electronic device 700 can include but is not limited to a microcomputer, a server, and in addition, the electronic device 700 can also include a notebook computer, a tablet computer, and other mobile devices, which are not limited here.

[0096] In particular, the processor 702 is configured to control itself and the memory 701 to implement the steps in any of the above map change detection method embodiments. The processor 702 can also be referred to as a CPU (Central Processing Unit). The processor 702 can be an integrated circuit chip with processing capability. The processor 702 can also 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, discrete hardware components. The general purpose processor can be a microprocessor or the processor can be any conventional processor. In addition, the processor 702 can be a combination of the above devices or other devices. The processor 702 can be a combination of one or more of the above devices or other devices.

[0097] In the example electronic device, by controlling the movable device to move and record point clouds based on the acquired prior grid map, a real-time grid map is obtained; the area where the prior grid map and the real-time grid map coincide is the area that needs to be judged whether there is a change, so the area where the prior grid map and the real-time grid map coincide is determined as the target prior map, and the area where the real-time grid map and the prior grid map coincide is determined as the target real-time map; the map change rate of the target real-time map relative to the target prior map is determined based on the grid difference comparison result between the target prior map and the target real-time map, so that whether the current scene has changed compared with the prior map can be determined according to the map change rate, and the movable device is prevented from being positioned and navigated incorrectly.

[0098] Please refer to Figure 8 , Figure 8 is a structural schematic diagram of an embodiment of the computer readable storage medium of the present application. The computer readable storage medium 810 stores program instructions 811 capable of being executed by the processor, and the program instructions 811 are used to implement the steps in any of the above map change detection method embodiments.

[0099] In the exemplary storage medium, the movable device is controlled to move and record point clouds based on the acquired prior grid map to obtain a real-time grid map by running the program instructions in the storage medium; the area where the prior grid map and the real-time grid map coincide is the area that needs to be judged whether there is a change, so the area where the prior grid map and the real-time grid map coincide is determined as a target prior map, and the area where the prior grid map and the real-time grid map coincide is determined as a target real-time map; the map change rate of the target real-time map relative to the target prior map is determined based on the grid difference comparison result between the target prior map and the target real-time map, so that whether the current scene changes compared with the prior map can be determined according to the map change rate, and the movable device is prevented from being positioned and navigated incorrectly.

[0100] In some embodiments, the apparatus provided by the embodiments of the present disclosure has functions or includes modules that can be used to perform the methods described in the above method embodiments, and the specific implementation can refer to the description of the above method embodiments. For brevity, it will not be repeated here.

[0101] The above description of each embodiment tends to emphasize the differences between each embodiment, and the same or similar parts can be mutually referred to. For brevity, it will not be repeated here.

[0102] In several embodiments provided in the present application, it should be understood that the disclosed methods and devices can be implemented in other ways. For example, the device implementation described above is only schematic; for example, the division of modules or units is only a logical function division, and there can be another division in actual implementation; for example, a unit or component can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the shown or discussed mutual ones can be indirect coupling or communication connection through some interfaces, devices or units, and can be electrical, mechanical or other forms.

[0103] In addition, each of the functional units in the various embodiments of the present application can be integrated in one processing unit, or each unit can exist physically, or two or more units can be integrated in one unit. The integrated unit can be implemented in the form of hardware or in the form of a software functional unit. When the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer readable storage medium. Based on this understanding, the technical solutions of the present application, essentially or in other words, the part that contributes to the prior art or the whole or part of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a storage medium, and includes several instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) or a processor (processor) to execute all or part of the steps of the various embodiments of the method of the present application. The foregoing storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM, Read-Only Memory), a random access memory (RAM, Random Access Memory), a magnetic disk or an optical disk, and various media that can store program codes.

Claims

1. A map change detection method, characterized in that: The method comprises: Control the movable device to move and record point clouds based on the acquired prior grid map to obtain a real-time grid map; generating a target detection map based on detected grids and undetected grids in the real-time grid map; Determining an area in the priori grid map that overlaps with the real-time grid map as a target priori map, and determining an area in the real-time grid map that overlaps with the priori grid map as a target real-time map; determining a map change rate of the target real-time map relative to the target a priori map based on a grid difference comparison result between the target a priori map and the target real-time map; The step of determining the map change rate of the target real-time map relative to the target a priori map based on the grid difference comparison result between the target a priori map and the target real-time map includes: determining undetected grids in the target a priori map based on the target detection map, and filtering the undetected grids to obtain a filtered target a priori map; and determining the map change rate of the target real-time map relative to the target a priori map based on the grid difference comparison result between the filtered target a priori map and the target real-time map.

2. The method according to claim 1, characterized in that After the step of determining a map change rate of the target real-time map relative to the target a priori map based on a grid difference comparison result between the target a priori map and the target real-time map, the method further includes: If the map change rate is greater than a preset change threshold, the priori grid map is updated to obtain an updated priori grid map; The movable device is controlled to move and record point cloud based on the updated priori grid map.

3. The method according to claim 1, characterized in that The step of generating a target detection map based on detected grids and undetected grids in the real-time grid map comprises: Determining the detected grids and the undetected grids in the real-time grid map based on the acquired point cloud data; generating an initial detection map based on the detected grids and the undetected grids; Downsampling is performed on the initial detection map to obtain the target detection map.

4. The method according to claim 1, wherein The undetected grid includes a first detection value, the detected grid includes a second detection value, the grid in the target prior map includes an occupancy value, and the step of determining the undetected grid in the target prior map based on the target detection map and filtering the undetected grid to obtain the filtered target prior map includes: Traversing the grids whose positions match between the target detection map and the target prior map; The occupancy value of the grid corresponding to the first detection value is updated, and the occupancy value of the grid corresponding to the second detection value is retained to obtain the filtered target prior map.

5. The method according to claim 1, wherein The step of determining a map change rate of the target real-time map relative to the target a priori map based on a grid difference comparison result between the target a priori map and the target real-time map comprises: performing an exclusive OR operation between the target a priori map and the target real-time map to obtain a difference map, wherein the difference map includes grids where changes occur between the target a priori map and the target real-time map; The map change rate is obtained by calculating the ratio between the number of target grids in the target priori map and the number of grids with changes.

6. The method according to claim 1, characterized in that The steps of determining the area in the priori grid map that overlaps with the real-time grid map as the target priori map, and determining the area in the real-time grid map that overlaps with the priori grid map as the target real-time map, include: Determine the area in the priori grid map that overlaps with the real-time grid map as a priori sub-map; Downsampling the prior submap to obtain the target prior map; Determining an area in the real-time grid map that overlaps with the priori grid map as a real-time sub-map; Downsampling is performed on the real-time sub-map to obtain the target real-time map.

7. A map change detection device, characterized in that: include: An acquisition module is used to control the movable device to move and record point clouds based on the acquired prior grid map to obtain a real-time grid map; generating a target detection map based on detected grids and undetected grids in the real-time grid map; a map determination module, configured to determine an area in the priori grid map that overlaps with the real-time grid map as a target priori map, and to determine an area in the real-time grid map that overlaps with the priori grid map as a target real-time map; a change calculation module, configured to determine a map change rate of the target real-time map relative to the target a priori map based on a grid difference comparison result between the target a priori map and the target real-time map; The step of determining a map change rate of the target real-time map relative to the target a priori map based on a grid difference comparison result between the target a priori map and the target real-time map comprises: determining undetected grids in the target a priori map based on the target detection map, and filtering the undetected grids to obtain a filtered target a priori map; A map change rate of the target real-time map relative to the target a priori map is determined based on a grid difference comparison result between the filtered target a priori map and the target real-time map.

8. An electronic device, characterized in that: The method comprises a memory and a processor, wherein the processor is configured to execute program instructions stored in the memory to implement the method according to any one of claims 1 to 6.

9. A computer-readable storage medium having program instructions stored thereon, characterized in that: When the program instructions are executed by a processor, the method according to any one of claims 1 to 6 is implemented.

Images