Map optimization method and device, electronic equipment and storage medium

Abstract

The present disclosure provides a map optimization method, device, electronic equipment and storage medium. The map optimization method comprises: obtaining an original map, wherein the original map comprises an exploration area, a coverage area and an obstacle area; and determining and deleting an error area in the exploration area in combination with the coverage area and the obstacle area. The scheme of the present disclosure determines and deletes the error area in combination with the points in the areas with different properties in the original map and the positioning principle thereof, optimizes the original map, makes it closer to the actual map, and enables the autonomous mobile device to perform tasks more efficiently according to the optimized map.

Description

TECHNICAL FIELD

[0001] The present disclosure relates to data processing technology, and in particular, to a map optimization method and device, electronic equipment and storage medium. BACKGROUND

[0002] With the progress of science and technology and the improvement of living standards, autonomous mobile devices with different functions, such as cleaning robots, companion mobile robots, etc., have entered more and more people's homes, making people's lives more comfortable and convenient.

[0003] An autonomous mobile device refers to an intelligent device that autonomously performs a preset task in a set working area. Currently, autonomous mobile devices generally include, but are not limited to, cleaning robots (such as intelligent sweeping robots, intelligent mopping robots, window-cleaning robots), companion mobile robots (such as intelligent electronic pets, nanny robots), service mobile robots (such as reception robots in hotels, inns, meeting places), industrial inspection intelligent devices (such as power inspection robots, intelligent forklifts, etc.), security robots (such as household or commercial security robots), etc.

[0004] Autonomous mobile devices usually move autonomously in a limited space, such as cleaning robots and companion mobile robots, which usually operate indoors, and service mobile robots, which usually operate in specific limited spaces such as hotels and meeting places. The limited space can be referred to as the working area of the autonomous mobile device.

[0005] Many times, the working area of the autonomous mobile device is not an open space, but is divided into different areas such as multiple rooms by walls, doors or other obstacles. The autonomous mobile device creates a map of the target area while moving in the target area. In the subsequent working process, the movement direction and route can also be adjusted based on the created map.

[0006] In the process of creating a map, due to factors such as algorithm positioning error and positioning device accuracy, erroneous positioning data may be generated, which may result in errors in the created map, such as incorrect areas, incorrect walls, and different wall thicknesses. This results in errors in the map, which affects the adjustment of the movement direction and route based on the created map, and makes incorrect adjustments, reducing the running efficiency of the autonomous mobile device. SUMMARY

[0007] The present disclosure provides a map optimization method, device, electronic equipment and storage medium to solve the above technical problems.

[0008] In a first aspect, the present disclosure provides a map optimization method, comprising:

[0009] acquire an original map, the original map including an exploration area, a coverage area, and an obstacle area;

[0010] determine and delete an error area in the exploration area in combination with the coverage area and the obstacle area.

[0011] Optionally, the method further includes:

[0012] distinguish a wall area from the obstacle area and optimize the wall area to obtain an optimized map.

[0013] Optionally, the determining and deleting the error area in the exploration area in combination with the coverage area and the obstacle area includes:

[0014] extract an external contour of the exploration area to obtain an exploration area contour line;

[0015] extract an external contour of the coverage area to obtain a coverage area contour line;

[0016] for a plurality of key points on the coverage area contour line, expand the coverage area outward based on the key points until the coverage area contacts the obstacle area and / or the exploration area contour line to obtain an expanded coverage area;

[0017] for a plurality of key points on the exploration area contour line, find inside the exploration area based on the key points to determine a first error area, the first error area being located between the exploration area contour line and the obstacle area and having no intersection with the expanded coverage area;

[0018] delete the first error area from the exploration area to obtain a first optimized map.

[0019] Optionally, the method further includes:

[0020] delete the area corresponding to the obstacle area from the exploration area in the first optimized map to obtain a block map, the block map including a plurality of exploration area blocks;

[0021] from the plurality of exploration area blocks, determine a second error area, the second error area having no intersection with the coverage area and at least one side not adjacent to the obstacle area;

[0022] delete the second error area from the exploration area in the first optimized map to obtain a second optimized map.

[0023] Optionally, the obstacle area further includes a common obstacle area.

[0024] the optimizing the wall area includes:

[0025] performing an inflation operation or a contour filling operation on a position corresponding to a common obstacle region in the second optimized map to fill in holes in the second optimized map, and performing a smoothing operation on edges of an exploration region in the second optimized map, to obtain a third optimized map;

[0026] extracting an external contour of the exploration region in the third optimized map to obtain a new exploration region contour line;

[0027] performing a straightening operation on edges of the new exploration region contour line within an error tolerance range, to obtain a new external wall region contour line;

[0028] based on the key points, searching inside the third optimized map to obtain a new wall region contour line.

[0029] Optionally, the optimizing the wall region to obtain an optimized map further includes:

[0030] based on the new external wall region contour line, expanding the exploration region in the third optimized map to the new external wall region contour line to obtain an optimized exploration region, to obtain an optimized map.

[0031] Optionally, the expanding the exploration region in the third optimized map to the new external wall region contour line to obtain an optimized exploration region based on the new external wall region contour line includes:

[0032] based on the key points, searching inside the third optimized map in a preset direction to mark a non-exploration region point searched as a new exploration region point, until a point of the exploration region in the third optimized map is searched, the new exploration region point and the point of the exploration region in the third optimized map constituting an optimized exploration region.

[0033] In a second aspect, the present disclosure provides a map optimization device, including:

[0034] an original map acquisition module configured to acquire an original map, the original map including an exploration region, a coverage region, and an obstacle region;

[0035] an error region deletion module configured to determine and delete an error region in the exploration region in combination with the coverage region and the obstacle region.

[0036] Optionally, the device further includes:

[0037] The wall optimization module is configured to distinguish a wall region from the obstacle region and optimize the wall region to obtain an optimized map.

[0038] Optionally, the error region deletion module is specifically configured to:

[0039] extract an external contour of the exploration region to obtain an exploration region contour line;

[0040] extract an external contour of the coverage region to obtain a coverage region contour line;

[0041] for a plurality of key points on the coverage region contour line, expand the coverage region outward based on the key points until the coverage region is in contact with the obstacle region and / or the exploration region contour line to obtain an expanded coverage region;

[0042] for a plurality of key points on the exploration region contour line, search inside the exploration region based on the key points to determine a first error region, the first error region being located between the exploration region contour line and the obstacle region and having no intersection with the expanded coverage region;

[0043] delete the first error region from the exploration region to obtain a first optimized map.

[0044] Optionally, the error region deletion module is further configured to:

[0045] delete the region corresponding to the obstacle region from the exploration region in the first optimized map to obtain a block map, the block map including a plurality of exploration region blocks;

[0046] determine a second error region from the plurality of exploration region blocks, the second error region having no intersection with the coverage region and at least one side not being adjacent to the obstacle region;

[0047] delete the second error region from the exploration region in the first optimized map to obtain a second optimized map.

[0048] Optionally, the obstacle region further includes a normal obstacle region.

[0049] The wall optimization module is specifically configured to:

[0050] perform an inflation operation or a contour filling operation on a position corresponding to the normal obstacle region in the second optimized map to fill the holes in the second optimized map, and perform a smoothing operation on the edge of the exploration region in the second optimized map to obtain a third optimized map;

[0051] extract an external contour of the exploration region in the third optimized map to obtain a new exploration region contour line.

[0052] For the new exploration area contour line, straighten the edges of the new exploration area contour line within the error allowable range to obtain a new external wall area contour line;

[0053] For the new external wall area contour line, search inside the third optimization map based on the key points to obtain a new wall area contour line.

[0054] Optionally, the wall optimization module is further configured to:

[0055] Based on the new external wall area contour line, expand the exploration area in the third optimization map to the new external wall area contour line to obtain an optimized exploration area, and obtain an optimized map.

[0056] Optionally, when the wall optimization module expands the exploration area in the third optimization map to the new external wall area contour line based on the new external wall area contour line to obtain an optimized exploration area, the wall optimization module is specifically configured to:

[0057] For the new external wall area contour line, search inside the third optimization map based on the key points in a preset direction, mark the searched non-exploration area points as new exploration area points, and search until the points of the exploration area in the third optimization map are searched, wherein the new exploration area points and the points of the exploration area in the third optimization map constitute an optimized exploration area.

[0058] In a third aspect, the present disclosure provides an electronic device, comprising: a memory configured to store program instructions; and a processor configured to invoke and execute the program instructions in the memory to execute the method of the first aspect.

[0059] In a fourth aspect, the present disclosure provides a computer-readable storage medium, the storage medium storing a computer program, the computer program being executed by a processor to implement the method of the first aspect.

[0060] In a fifth aspect, the present disclosure provides a program product, comprising a computer program, the computer program being executed by a processor to implement the method of the first aspect.

[0061] The disclosure provides a map optimization method, device, electronic equipment and storage medium. The map optimization method comprises: obtaining an original map, wherein the original map comprises an exploration area, a coverage area and an obstacle area; and determining and deleting an error area in the exploration area in combination with the coverage area and the obstacle area. The scheme of the disclosure determines and deletes the error area in combination with the points in the areas with different properties in the original map and the positioning principle thereof, optimizes the original map, makes it closer to the actual map, so that the autonomous mobile device can execute the task more efficiently according to the optimized map. BRIEF DESCRIPTION OF DRAWINGS

[0062] In order to more clearly illustrate the technical solutions in the disclosure or the prior art, the drawings needed in the embodiments or the prior art description will be briefly introduced. Obviously, the drawings in the following description are some embodiments of the disclosure, and other drawings can be obtained by those skilled in the art without creative labor.

[0063] Figure 1 A schematic diagram of an application scenario provided by the disclosure;

[0064] Figure 2 A flowchart of a map optimization method provided by an embodiment of the disclosure;

[0065] Figure 3 A schematic diagram of extending the coverage area provided by an embodiment of the disclosure;

[0066] Figure 4 A schematic diagram of extending the exploration area in the third optimized map provided by an embodiment of the disclosure;

[0067] Figures 5-1 to 5-16 A schematic diagram of an actual processing process provided by an embodiment of the disclosure;

[0068] Figure 6 A structural schematic diagram of a map optimization device provided by an embodiment of the disclosure;

[0069] Figure 7 A structural schematic diagram of an electronic equipment provided by an embodiment of the disclosure;

[0070] Figure 8 A certain profile schematic diagram of an embodiment of the disclosure. DETAILED DESCRIPTION

[0071] In order to make the purposes, technical solutions and advantages of the present disclosure clearer, the technical solutions in the present disclosure will be clearly and completely described below with reference to the drawings in the present disclosure. Obviously, the described embodiments are some but not all of the embodiments of the present disclosure. Based on the embodiments in the present disclosure, all other embodiments obtained by those of ordinary skill in the art without creative work fall within the protection scope of the present disclosure.

[0072] Various types of sensors are generally provided on the autonomous mobile device to explore the internal space of the working area, and to construct a working area map or adjust the motion direction and route based on the sensor data.

[0073] In the process of constructing the map, direct positioning and indirect positioning can be involved. Direct positioning refers to directly taking the positioning information of the autonomous mobile device as a point in the map, such as using the code disc, gyroscope, accelerometer and other dead reckoning sensors (sometimes equipped with a camera or laser ranging sensor) on the autonomous mobile device to calculate the coordinate position (positioning information) of the current position of the autonomous mobile device in real time through the SLAM (Simultaneous Localization And Mapping) algorithm, and correspond it to the corresponding point in the map, or detecting the coordinate position of the obstacle (an object that hinders the movement of the autonomous mobile device in the working area, including walls and ordinary obstacles such as furniture) contacted by the autonomous mobile device through the collision sensor arranged at the front of the autonomous mobile device, and corresponding it to the corresponding point in the map. Indirect positioning refers to indirectly calculating the point in the map based on the positioning information of the autonomous mobile device and the working principle of the ranging sensor, such as obtaining the coordinate position (positioning information) of the autonomous mobile device itself through the above method, and then non-contact detecting the obstacle at a certain relative angle and distance from the autonomous mobile device through the ranging sensor (such as laser radar, TOF (Time of flight, time of flight ranging sensor) or infrared pair tube) arranged on the upper and / or side of the autonomous mobile device, thereby indirectly calculating the coordinate position of the detected obstacle according to the coordinate position of the autonomous mobile device itself and the relative angle and distance of the detected obstacle relative to the autonomous mobile device, and corresponding it to the corresponding point in the map. And the space between the autonomous mobile device itself and the detected obstacle will also be corresponded to the corresponding point in the map due to the detection light of the ranging sensor. However, both of these positioning methods can have certain errors, which will cause the final created map to differ from the actual map, i.e. the map is not accurate. For example, there are some redundant areas in the created map, or the walls in the map are irregular, etc. Therefore, when using the constructed map as the basis for route planning or running direction adjustment, it can lead to incorrect planning and reduce the working efficiency of the autonomous mobile device.

[0074] Due to the errors in positioning by algorithm or the factors of the positioning device itself, the original map of the autonomous mobile device can have errors, such as incorrect areas or incorrect walls, or walls of different thicknesses, curved walls, etc. The technical problems to be solved by the present application mainly include:

[0075] 1) deleting the areas established by the original map errors while ensuring the integrity of the original map information.

[0076] 2) optimizing the walls of the original map to make the thickness of the walls consistent, which is convenient for display.

[0077] 3) Straighten the walls in the map within a certain error range, solve the problem of the walls in the map not being straight caused by positioning errors.

[0078] In the prior art, wall information in the obstacles of the original map is generally extracted, and a line segment fitting or straight line detection method is used to optimize the walls. However, due to the relatively complex working area environment, especially when a large number of obstacles are placed in the room, line segment fitting is prone to error and it is also difficult to detect straight lines. At the same time, the positioning of the autonomous mobile device may deviate, resulting in error areas in the original map, and the prior art cannot identify these error areas, so it is also impossible to delete these error areas.

[0079] Based on this, the present disclosure proposes a map optimization method, device, electronic device and storage medium, which further optimizes and adjusts the constructed map to make it closer to the actual map, thereby avoiding the inaccuracy of the map caused by errors and low working efficiency.

[0080] Figure 1 An application scenario diagram is provided for the present disclosure. As shown in Figure 1 , if the autonomous mobile device is a cleaning robot 101, it is used to perform cleaning work indoors. In the early stage of use, the cleaning robot 101 traverses to cover the indoor space (i.e., cleans the indoor floor) to create an original map of the working area. After creating the original map in combination with the information of various sensors, the original map is optimized by the method of the present disclosure to obtain an optimized map. Then, the route planning can be performed based on the optimized map, and the subsequent cleaning task can be performed. The specific optimization process can be referred to the following embodiments.

[0081] Figure 2 A flowchart of a map optimization method is provided for an embodiment of the present disclosure, as shown in Figure 2 , the method of the present embodiment can include:

[0082] S201, obtaining an original map, the original map including an exploration area, a coverage area, and an obstacle area (including a wall area).

[0083] In some embodiments, the map optimization method can be executed after the autonomous mobile device runs in the working area and maps. At this time, the original map obtained refers to the map created by the autonomous mobile device while running.

[0084] Specifically, in the process of map creation, all position points are initially set as unexplored areas. The autonomous mobile device runs in the working area, and the nature of each position point is determined again when the autonomous mobile device reaches a position point, or the nature of each position point on a trajectory can be determined again according to the trajectory passed by the autonomous mobile device within a period of time.

[0085] In the original map being created or created, the properties of each position point can be one or several of unexplored, explored, covered, existence of obstacles, etc. Among them, the unexplored position point is the position point that the autonomous mobile device has not detected through direct positioning or indirect positioning. Correspondingly, the explored position point is the position point that the autonomous mobile device detects through direct positioning or indirect positioning, such as the position point that the autonomous mobile device actually reaches and the space that the ranging sensor of the autonomous mobile device can pass through, and the position point of the obstacle that can reflect the detection light. The covered position point is the position point detected by direct positioning, which is also the position point actually reached by the autonomous mobile device. As can be seen from the above description, the covered position point is also the explored position point, but the explored position point is not necessarily the covered position point. The position point with obstacles is the position point that the autonomous mobile device can detect through direct positioning or indirect positioning and is identified as an obstacle, which generally includes the position point positioned in combination with collision sensors, wheel drop sensors and other components. In order to realize the map optimization method of the present disclosure, it is necessary to distinguish the position point with wall from the position point with obstacles. From the above definition of the position point with obstacles, it can be deduced that the position point with wall is the position point that the autonomous mobile device can detect through direct positioning or indirect positioning and is identified as a wall. After distinguishing the position point with wall from the position point with obstacles, the remaining points are the points with ordinary obstacles. In fact, the wall is a special obstacle, and the position point with wall can be distinguished from the position point with obstacles based on the information obtained by different sensors, such as distinguishing whether the obtained position point with obstacles is a position point with wall according to the definitions of direct positioning and indirect positioning, and assigning different values to the two, such as assigning a value of 100 to the position point with wall and a value of 85 to the position point with other obstacles, to distinguish them. In some embodiments, the position points with ordinary obstacles and the position points with walls have been distinguished and marked in the obtained original map or in the process of establishing the original map. In some other embodiments, the position points with walls are separated from the position points with obstacles in the original map after the original map is obtained. The specific distinguishing method of the position points with ordinary obstacles and the position points with walls is not the problem to be solved by the present disclosure, but the premise of the map optimization method of the present disclosure; the related distinguishing method has various ways in the prior art, such as the Chinese patent applications with publication numbers CN113064413A and CN111862133A.

[0086] As can be seen from the above description, the properties of each position point can be determined in combination with various data generated in the map construction process.

[0087] The autonomous mobile device moves within the target area while simultaneously creating a map of that area. To distinguish between unexplored, explored, covered, and obstacle-prone locations (including those with walls and those with regular obstacles), different pixel values ​​are displayed on the map. For example, an unexplored location has a pixel value of 75, an explored location has a pixel value of 25, a covered location has a pixel value of 0, a location with regular obstacles has a pixel value of 85, and a location with walls has a pixel value of 100. The original map is as follows: Figure 5-1 As shown.

[0088] Furthermore, based on the nature of each location point, all locations on the map can be divided into multiple regions, including at least an exploration region, a coverage region, and an obstacle region (including wall regions and / or ordinary obstacle regions). The exploration region comprises all explored location points and represents the maximum range detectable by the autonomous mobile device (including areas determined through direct and indirect positioning). The coverage region comprises all covered location points and represents the area actually reachable by the autonomous mobile device. The obstacle region comprises all location points with obstacles, representing areas that the autonomous mobile device cannot pass through, regardless of whether it has attempted to pass through them. The obstacle region can be further divided into wall regions and ordinary obstacle regions; the wall region comprises all location points with walls. Figure 5-2 The example describes the exploration area, coverage area, common obstacle area, and wall area. It should be noted that in actual maps, the shapes and distribution of these areas are often very complex. Figure 5-2 This is merely an example and does not exhaustively list all exploration areas, coverage areas, common obstacle areas, and wall areas. Some selection boxes also include more than one type of area, but rather a mixture or overlap of multiple areas. The area displayed is only the main or representative area type present in the selection box, therefore it cannot be taken as a definitive representation. Figure 5-2 No restrictions are imposed on the above-mentioned types of regions.

[0089] In some embodiments, the map optimization method can be performed independently in a working area where the autonomous mobile device has run before and a map has been established. In this case, the obtained original map can be a map that has been constructed. The constructed map (or historical map) can be constructed by the autonomous mobile device before and stored in the autonomous mobile device or a server. The constructed map can also be a historical map constructed by other autonomous mobile devices in the same working area before and stored in the server. For example, there is a sweeping robot and a mopping robot in a certain family, both of which clean the floor in the same family house, and the working areas of the two devices are the same. The sweeping robot can store the map of the family house that it has constructed after running in the server, and the mopping robot can directly obtain the historical map of the working area of the family house from the server, although it has not run in the working area.

[0090] The naming of each position point and the naming of each area are used in the present disclosure, and other definitions can also be used, but the source of the data they refer to is determined.

[0091] S202, in combination with the coverage area and the obstacle area (at least including the wall area), determine and delete the error area in the exploration area.

[0092] According to the above description of the properties of each position point, it can be determined that there can be overlap between each area. Among them, the exploration area has the largest area and must overlap with the coverage area and the obstacle area. The wall area in the obstacle area is the boundary of the working area, and the coverage area must exist inside the working area surrounded by the wall area. Because the exploration area contains the position points detected or calculated by the autonomous mobile device through all sensors, the error area caused by environmental influence, sensor error and / or calculation error is most likely to exist in this area. In fact, affected by the working principle of the sensor, the position points determined by the ranging sensor such as laser radar are easily affected by the environment of the working area. For example, if there is a mirror in the direction of the detection light emission, the laser radar may be affected by the mirror reflection and refraction of the detection light, causing the ranging to be wrong. Therefore, the exploration area in the original map can be mainly optimized.

[0093] According to the above analysis, it can be determined that the position points in the exploration area beyond the obstacle area belong to the error area, and these position points are deleted, which can complete the optimization of the exploration area.

[0094] The map optimization method provided by the present disclosure comprises: obtaining an original map, wherein the original map comprises an exploration area, a covered area, and an obstacle area (at least comprising a wall area); determining and deleting an error area in the exploration area in combination with the covered area and the obstacle area. The scheme of the present disclosure determines and deletes the error area in combination with the points in the areas of different attributes in the original map and the positioning principle thereof, realizes optimization of the original map, and makes the original map closer to the actual map, so that the autonomous mobile device can execute tasks more efficiently according to the optimized map.

[0095] In order to further optimize the map, the wall area can also be distinguished from the obstacle area, and the wall area can be optimized to obtain an optimized map.

[0096] By optimizing the wall, the wall in the original map can be made closer to the actual situation, and the map can be further improved.

[0097] In some embodiments, the above-mentioned determination and deletion of the error area in the exploration area in combination with the covered area and the obstacle area can comprise: extracting the outer contour of the exploration area as shown in FIG. 1B to obtain the exploration area contour line as shown in FIG. 1C; extracting the outer contour of the covered area as shown in FIG. 1D to obtain the covered area contour line as shown in FIG. 1E; expanding the covered area outward based on the key points on the covered area contour line until the covered area contacts the obstacle area and / or the exploration area contour line to obtain the expanded covered area as shown in FIG. 1F; searching inside the exploration area based on the key points on the exploration area contour line to determine a first error area, wherein the first error area is located between the exploration area contour line and the obstacle area and has no intersection with the expanded covered area as shown in FIG. 1G; and deleting the first error area from the exploration area to obtain a first optimized map as shown in FIG. 1H. Figure 5-3 Figure 5-4 Figure 5-5 Figure 5-5 Figure 5-6 Figure 5-3 Figure 5-7 The key points refer to the points or points near the points that play a key role in constituting the contour of a certain area; the key points refer to the key points that can at least constitute the contour of the certain area if the contour of the certain area is to be constituted. For example, for the contour of a triangle, the three corner points / corner point near points of the triangle contour are the key points, and the key points that can constitute the contour of the triangle are at least the three points; for the contour of a rectangle, the four corner points / corner point near points of the rectangle are the key points, and the key points that can constitute the contour of the rectangle are at least the four points; for the contour of a shape as shown in FIG. 2B, the key points that can constitute the contour of the shape are at least the two points as shown in FIG. 2C. Figure 8 Figure 8 ​​​​​​​The A1, B1, C1, D1, E1, F1 six corner points shown in the middle or the A2, B2, C2, D2, E2, F2 points near them are key points, and the several key points that can form the contour are at least six of the following: at least one of A1, A2, at least one of B1, B2, at least one of C1, C2, at least one of D1, D2, at least one of E1, E2, and at least one of F1, F2.

[0098] Specifically, several pixels can be taken as the width standard of the contour line. For example, the position points in the exploration area adjacent to the unexplored area are selected as the exploration area contour line (with a width of one pixel).

[0099] Further, the coverage area is expanded. Similarly, the position points in the coverage area adjacent to other areas are extracted as the coverage area contour line (with a width of one pixel), and the coverage area is expanded outward based on at least several key points on the coverage area contour line, and the stopping condition of the expansion is that the obstacle area and / or the exploration area contour line is contacted.

[0100] In the present disclosure, the outward expansion based on a point means that the properties of the point are assigned to all position points on the line segment that extends from the point to the target point in a predetermined direction. The following is a specific description with Figure 3 as an example. As shown in a of Figure 3 each grid represents a pixel, and "1" is used as the identifier of the position points in the coverage area (also used to represent the "covered" property), and "2" is used as the identifier of the position points in the wall area (also used to represent the "wall exists" property). It can be predetermined to expand the points on the coverage area contour line in the horizontal direction. The result of the expansion based on one of the points on the coverage area contour line is shown in b of Figure 3 , which is only an example of one of the expansion methods and does not limit the specific expansion method.

[0101] In other scenarios, the coverage area can also be expanded based on the points on the coverage area contour line in a certain angle or in multiple angles. The advantage of this expansion method is that even if the wall area is discontinuous and has breakpoints, the expanded coverage area will not extend indefinitely.

[0102] The points in the coverage area are the positions actually reached by the autonomous mobile device, but are not necessarily all the spaces in the working area except the obstacle area. Therefore, the extended coverage area obtained by extension is the position actually reachable by the autonomous mobile device based on the original map determined by an algorithm. Further, for several key points on the contour line of the exploration area, the inside of the exploration area is searched based on the key points. In the searching process, if the obstacle area is first encountered, the area between the contour line of the exploration area and the encountered obstacle area is determined as the first error area. For several key points on the contour line of the exploration area, the inside of the exploration area is searched based on the key points. In the searching process, if the extended coverage area is first encountered, the area between the contour line of the exploration area and the encountered extended coverage area does not belong to the extended coverage area. The first error area is deleted from the exploration area to obtain a first optimized map.

[0103] It should be noted that "first error area" is used here only to represent the error area with this characteristic, to distinguish from the error area determined by other conditions, and does not constitute any limitation.

[0104] In the process of extending the coverage area, if the obstacle area is discontinuous and has a breakpoint, the extended coverage area may extend out, so that a part of the error area intersects with the extended coverage area and cannot be deleted by the above steps. Therefore, the following steps can be further performed: the area corresponding to the obstacle area is deleted from the exploration area in the first optimized map to obtain a block map, as shown in Figure 5-9 The area corresponding to the obstacle area in the first optimized map is an obstacle area map, as shown in Figure 5-8 The block map includes several exploration area blocks. From the several exploration area blocks, a second error area is determined. The second error area has no intersection with the coverage area and at least one side is not adjacent to the obstacle area, as shown in Figure 5-9 The second error area is deleted from the exploration area in the first optimized map, and is superimposed with the obstacle area map to obtain a second optimized map, as shown in Figure 5-10

[0105] First, the exploration area is changed into a block map by deleting the area corresponding to the obstacle area, i.e., the obstacle area map, as shown in Figure 5-8 The exploration area is changed into a block map, as shown in Figure 5-9 It can be understood that if a block is correct, it must be located inside the working area surrounded by the wall area, i.e., each side is adjacent to the obstacle area. Therefore, the block with no intersection with the coverage area and at least one side not adjacent to the obstacle area is the second error area. The second error area is deleted from the exploration area to obtain a second optimized map, as shown in Figure 5-10 Figure 5-10 ​

[0106] In some embodiments, in order to make the distinction between the blocks more clear, an erosion operation can also be performed after the region corresponding to the obstacle region is deleted from the exploration region in the first optimized map. Correspondingly, an inflation operation is performed after the second error region is deleted.

[0107] After the error region is deleted, the wall can be further optimized. The optimization of the obstacle region described above can specifically include: performing an inflation operation or a contour filling operation on the position corresponding to the ordinary obstacle region in the second optimized map to fill the holes in the second optimized map, and performing smoothing processing on the edge of the exploration region in the second optimized map to obtain a third optimized map, as shown in Figure 5-11 ; extracting the outer contour of the exploration region in the third optimized map to obtain a new exploration region contour line, as shown in Figure 5-12 ; performing a straightening operation on the edge of the new exploration region contour line within an error allowable range to obtain a new outer wall region contour line, as shown in Figure 5-13 ; and based on a plurality of key points on the new outer wall region contour line, searching inward from the key points to obtain a new wall region contour line, as shown in Figure 5-14 .

[0108] After the region corresponding to the obstacle region is deleted, the positions corresponding to the wall region and the ordinary obstacle region are both deleted, that is, some holes are generated in the region corresponding to the ordinary obstacle in the second optimized map. By performing an inflation operation to fill the gaps and holes in the exploration region in the second optimized map and performing smoothing processing on the edge of the filled exploration region, the optimization of the exploration region can be completed. As described in the above embodiments, if the optimized exploration region is correct, it must be located within the working region surrounded by the wall region, that is, each edge is adjacent to the wall region. Therefore, the new exploration region contour line can be approximately regarded as the new wall region contour line. In an ideal state in the actual map, the edge of the exploration region should be consistent with the wall, and the wall in the actual map is generally a straight line and may also include a smooth curve in a few cases. Therefore, by modifying the exploration region contour line in the second optimized map, the new outer wall region contour line can be obtained. The outer wall region contour line refers to the contour line of the outermost wall region of the working region. Based on a plurality of key points on the outer wall region contour line, the position of the wall region in the working region is searched, and a straightening operation is performed on the position to obtain a new wall region contour line, as shown in Figure 5-14 .

[0109] The optimization of the wall region is performed to obtain an optimized map, and the method further includes: based on the new external wall region contour line, expanding the exploration region in the third optimized map to the new external wall region contour line to obtain an optimized exploration region, and obtaining the optimized map.

[0110] After the wall region contour line is corrected, a gap can be generated between the exploration region in the third optimized map. Therefore, the exploration region in the third optimized map can be further expanded to complete the optimization of the exploration region and obtain an exploration region optimized map, as shown in Figure 5-15 . At this point, the exploration region and the wall region are both optimized.

[0111] Specifically, the method of expanding the exploration region in the third optimized map to the new external wall region contour line based on the new external wall region contour line to obtain the optimized exploration region includes: for a plurality of key points on the new external wall region contour line, searching in a preset direction based on the key points to the inside of the third optimized map, marking a non-exploration region point searched as a new exploration region point, and searching until a point of the exploration region in the third optimized map is searched, and the new exploration region point and the point of the exploration region in the third optimized map constitute the optimized exploration region.

[0112] The preset direction can be a direction perpendicular to the new external wall region contour line, a direction at an angle to the external wall region contour line, or the like.

[0113] The process of searching to the inside is similar to the process of expanding to the outside shown in Figure 3 , and is described by taking Figure 4 as an example. As shown in Figure 4 a, each grid represents a pixel, and “3” is used as an identifier of a position point in the exploration region in the third optimized map (also used to represent the property of “having been explored”), and “4” is used as an identifier of a position point in the new external wall region contour line (also used to represent the property of “having a wall”). It can be preset to search to the inside based on the points on the new external wall region contour line in the horizontal direction. The result of the expansion based on one of the points on the new external wall region contour line is shown in Figure 4 b. The newly marked points are still marked as 3, but the description of “new” is used only to distinguish between steps. This is only an example of one of the expansion methods, and does not limit the specific expansion method.

[0114] In the exploration region optimized map Figure 5-15 , the coverage region shown in Figure 5-5 and the new wall region contour line shown in Figure 5-14 are superimposed to obtain the final optimized map shown in Figure 5-16 .

[0115] Figure 6 A structural schematic diagram of a map optimization apparatus provided for an embodiment of the present disclosure is shown in FIG. 6. The map optimization apparatus 600 of the present embodiment includes an original map acquisition module 601 and an error region deletion module 602. Figure 6

[0116] The original map acquisition module 601 is configured to acquire an original map, which includes an exploration region, a coverage region, and an obstacle region.

[0117] The error region deletion module 602 is configured to determine and delete an error region in the exploration region in combination with the coverage region and the obstacle region.

[0118] Optionally, the apparatus 600 further includes:

[0119] A wall optimization module 603 is configured to distinguish a wall region from the obstacle region and optimize the wall region to obtain an optimized map.

[0120] Optionally, the error region deletion module 602 is specifically configured to:

[0121] extract an external contour of the exploration region to obtain an exploration region contour line;

[0122] extract an external contour of the coverage region to obtain a coverage region contour line;

[0123] for a plurality of key points on the coverage region contour line, expand the coverage region outward based on the key points until the coverage region contour line is contacted to obtain an expanded coverage region;

[0124] for a plurality of key points on the exploration region contour line, search inside the exploration region based on the key points to determine a first error region, the first error region is located between the exploration region contour line and the obstacle region, and has no intersection with the expanded coverage region;

[0125] delete the first error region from the exploration region to obtain a first optimized map.

[0126] Optionally, the error region deletion module 602 is further configured to:

[0127] delete the region corresponding to the obstacle region from the exploration region in the first optimized map to obtain a block map, the block map includes a plurality of exploration region blocks;

[0128] determine a second error region from the plurality of exploration region blocks, the second error region has no intersection with the coverage region and at least one side is not adjacent to the obstacle region;

[0129] delete the second error region from the exploration region in the first optimized map to obtain a second optimized map. ​

[0130] Optionally, the obstacle region further comprises a common obstacle region.

[0131] The wall optimization module 603 is specifically configured to:

[0132] perform an inflation operation or a contour filling operation on a position corresponding to the common obstacle region in the second optimized map to fill the holes in the second optimized map, and perform a smoothing operation on an edge of the exploration region in the second optimized map, to obtain a third optimized map;

[0133] extract an external contour of the exploration region in the third optimized map to obtain a new exploration region contour line;

[0134] for the new exploration region contour line, perform a straightening operation on edges of the new exploration region contour line within an error allowable range to obtain a new external wall region contour line;

[0135] for a plurality of key points on the new external wall region contour line, search inside the third optimized map based on the key points to obtain a new wall region contour line.

[0136] Optionally, the wall optimization module 603 is further configured to:

[0137] based on the new external wall region contour line, expand the exploration region in the third optimized map to the new external wall region contour line to obtain an optimized exploration region, and obtain an optimized map.

[0138] Optionally, when the wall optimization module 603 expands the exploration region in the third optimized map to the new external wall region contour line based on the new external wall region contour line to obtain the optimized exploration region, the wall optimization module 603 is specifically configured to:

[0139] for a plurality of key points on the new external wall region contour line, search inside the third optimized map based on the key points in a preset direction, mark a non-exploration region point searched as a new exploration region point, and search until a point of the exploration region in the third optimized map is searched, the new exploration region point and the point of the exploration region in the third optimized map constitute the optimized exploration region.

[0140] The device provided in the embodiment can be used to execute the method of any of the above embodiments, and has similar implementation principles and technical effects, which will not be described here.

[0141] Figure 7 A structural schematic diagram of an electronic device provided in an embodiment of the present disclosure is shown in FIG. 7. Figure 7 As shown in FIG. 7, the electronic device 700 of the present embodiment can include a memory 701 and a processor 702.

[0142] The memory 701 is configured to store program instructions.

[0143] The processor 702 is configured to invoke and execute program instructions in the memory 701 to perform the method of any of the above embodiments, which has similar implementation principles and technical effects, and thus will not be repeated here.

[0144] The electronic device of the embodiment can be specifically an autonomous mobile device or a management system of the autonomous mobile device.

[0145] The disclosure also provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, the method of any of the above embodiments is implemented.

[0146] The disclosure also provides a computer program product, which includes a computer program. When the computer program is executed by a processor, the method of any of the above embodiments is implemented.

[0147] Those skilled in the art can understand that all or part of the steps of the above-mentioned method embodiments can be completed by program instruction related hardware. The foregoing program can be stored in a computer readable storage medium. When the program is executed, the steps of the above-mentioned method embodiments are executed; and the foregoing storage medium includes ROM, RAM, magnetic disk or optical disk and various media that can store program codes.

[0148] Finally, it should be noted that: the above embodiments are only used to illustrate the technical solutions of the disclosure, rather than limit them; although the disclosure has been described in detail with reference to the above embodiments, those skilled in the art should understand that: they can still modify the technical solutions recorded in the above embodiments, or make equivalent replacement for part or all of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the scope of the technical solutions of the embodiments of the disclosure.

Claims

1. A map optimization method, characterized in that, include: Obtain the original map, which includes an exploration area, a coverage area, and an obstacle area; the exploration area is the area determined by direct and indirect positioning; the coverage area is the area determined by direct positioning. Extract the outer contour of the exploration area to obtain the exploration area contour line; Extract the outer contour of the covered area to obtain the outline of the covered area; For several key points on the outline of the coverage area, the coverage area is expanded outward based on the key points until it contacts the outline of the obstacle area and / or the exploration area, thus obtaining the expanded coverage area; For several key points on the outline of the exploration area, the first error area is determined by searching inside the exploration area based on the key points. The first error area is located between the outline of the exploration area and the obstacle area, and has no intersection with the expanded coverage area. The first erroneous region is deleted from the exploration area to obtain the first optimized map; The wall area is distinguished from the obstacle area, and the wall area is optimized to obtain an optimized map.

2. The method according to claim 1, characterized in that, Also includes: The obstacle area is removed from the exploration area in the first optimized map to obtain a tiled map; The segmented map includes several exploration area blocks; From the plurality of exploration area blocks, a second error region is determined, which has no intersection with the coverage area and at least one side is not adjacent to the obstacle area; The second erroneous region is deleted from the exploration area of ​​the first optimized map to obtain the second optimized map.

3. The method according to claim 2, characterized in that, The obstacle area also includes a general obstacle area; The optimization of the wall area includes: The locations corresponding to ordinary obstacle areas in the second optimized map are expanded or filled with outlines to fill the holes in the second optimized map, and the edges of the exploration areas in the second optimized map are smoothed to obtain the third optimized map. Extract the outer contour of the exploration area from the third optimized map to obtain the new exploration area contour line; For the new exploration area outline, the edges of the new exploration area outline are straightened within the allowable error range to obtain the new external wall area outline. For several key points on the new external wall area outline, a search is performed within the third optimized map based on these key points to obtain the new wall area outline.

4. The method according to claim 3, characterized in that, The optimization of the wall area to obtain the optimized map also includes: Based on the new external wall region outline, the exploration area in the third optimized map is expanded to the new external wall region outline to obtain the optimized exploration area; thus, the optimized map is obtained.

5. The method according to claim 4, characterized in that, Based on the new external wall region outline, the exploration area in the third optimized map is expanded to the new external wall region outline to obtain an optimized exploration area, including: For several key points on the outline of the new external wall area, a search is performed in a preset direction into the third optimized map based on the key points. The non-exploration area points found in the search are marked as new exploration area points, until the points in the exploration area of ​​the third optimized map are found. The new exploration area points and the points in the exploration area of ​​the third optimized map constitute the optimized exploration area.

6. A map optimization device, characterized in that, include: The original map acquisition module is used to acquire the original map, which includes an exploration area, a coverage area, and an obstacle area. The exploration area is the area determined by direct and indirect positioning; the coverage area is the area determined by direct positioning. The error region deletion module is used to extract the outer contour of the exploration region to obtain the exploration region contour line; extract the outer contour of the coverage region to obtain the coverage region contour line; and expand the coverage region outward based on several key points on the coverage region contour line until it contacts the obstacle region and / or the exploration region contour line to obtain the expanded coverage region. For several key points on the outline of the exploration area, the first error area is determined by searching inside the exploration area based on the key points. The first error area is located between the outline of the exploration area and the obstacle area, and has no intersection with the expanded coverage area. The first erroneous region is deleted from the exploration area to obtain the first optimized map; The wall optimization module is used to distinguish wall areas from obstacle areas and optimize the wall areas to obtain an optimized map.

7. An electronic device, characterized in that, include: Memory, used to store program instructions; A processor for calling and executing program instructions in the memory to perform the method as described in any one of claims 1-5.

8. A computer-readable storage medium, characterized in that, The storage medium stores a computer program, which, when executed by a processor, implements the method as described in any one of claims 1-5.

9. A computer program product, comprising a computer program, characterized in that, When executed by a processor, the computer program implements the method described in any one of claims 1-5.

Images