Path planning method and device, electronic equipment and storage medium

Abstract

The present application relates to the technical field of path planning, and particularly relates to a path planning method and device, electronic equipment and a storage medium, the method comprising: acquiring region information of a region to be planned; determining a planning range based on the region information, and expanding the planning range to determine a first planning region in an original map; performing edge-attached path planning based on the first planning region and the planning range to determine a first edge-attached path; determining a bounding box of the region to be planned in the original map based on the region information, and determining a second planning region based on a region covered by the bounding box; performing full-coverage path planning on the second planning region to determine a full-coverage path; and merging the first edge-attached path and the full-coverage path to determine a target planning path of the region to be planned. Since the second planning region used for full-coverage path planning is within the first planning region used for edge-attached path planning, the repetition rate of the target planning path is avoided from being high.

Description

Technical Field

[0001] This invention relates to the field of path planning technology, specifically to path planning methods, apparatus, electronic devices, and storage media. Background Technology

[0002] When planning paths within a designated area, two types of paths are involved: edge-following paths and full-coverage paths. Existing solutions handle edge-following and full-coverage paths separately; that is, map reading, image processing, connectivity assessment, and path generation are all performed independently. In this approach, edge-following paths shrink the planning area, while full-coverage paths generate paths along the edges of the planning area when there are no obstacles. This results in edge-following paths being farther from obstacles than full-coverage paths, leading to higher path repetition rates and reduced machine cleaning efficiency. Summary of the Invention

[0003] In view of this, embodiments of the present invention provide a path planning method to solve the problem of high repetition rate of planned paths.

[0004] According to a first aspect, embodiments of the present invention provide a path planning method, comprising:

[0005] Obtain regional information for the area to be planned;

[0006] Based on the regional information, the planning scope is determined, and the planning scope is expanded to determine the first planning area in the original map;

[0007] Based on the first planning area, perform edge-fitting path planning to determine the first edge-fitting path;

[0008] Based on the regional information, the bounding box of the area to be planned is determined in the original map, and a second planning area is determined based on the area covered by the bounding box;

[0009] Perform full-coverage path planning for the second planning area to determine the full-coverage path;

[0010] The first edge-fitting path and the full-coverage path are merged to determine the target planning path for the area to be planned.

[0011] The path planning method provided in this invention expands the planning range to include the walls within the area to be planned into the first planning area, so that these walls are used for edge-fitting path planning rather than subsequent full-coverage path planning. The second planning area is the bounding box of the area to be planned based on the area information. At this time, the second planning area is smaller than the first planning area. The second planning area used for full-coverage path planning is within the first planning area used for edge-fitting path planning, ensuring that the full-coverage path is within the range of the edge-fitting path, thereby avoiding the problem of high repetition rate of the target planned path. At the same time, the first edge-fitting path and the full-coverage path are merged to obtain a target planned path. This method can avoid the situation where the robot cannot reach the starting point but keeps trying to reach the starting point when switching to the edge-fitting path after the full-coverage path is completed, resulting in continuous head shaking.

[0012] In some implementations, determining the planning scope based on the regional information and expanding the planning scope to determine a first planning area in the original map includes:

[0013] A first minimum bounding box is determined in the original map to enclose the region information, and the edges of the first minimum bounding box are parallel to the corresponding coordinate axes in the original map.

[0014] Expand the first minimum bounding box to determine the planning range;

[0015] The first map corresponding to the planning scope is extracted from the original map to determine the first planning area.

[0016] The path planning method provided in this embodiment of the invention can avoid the situation of only including part of the wall by expanding the first minimum bounding box, and ensure that the first planning area is a local map including complete obstacles, thereby providing a basic guarantee for subsequent edge-fitting path planning.

[0017] In some implementations, the step of planning the edge-hugging path based on the first planning area and the planning range, and determining the edge-hugging path, includes:

[0018] Extract the first outline of the first obstacle within the first planning area;

[0019] Based on the first contour and the boundary of the planned range, an edge-fitting path is planned to determine the edge-fitting path.

[0020] In some implementations, the step of planning the edge-fitting path based on the first contour and the boundary of the planned range, and determining the edge-fitting path, includes:

[0021] Based on the first contour and the boundary of the planned range, an edge-fitting path is planned to determine the first edge-fitting path;

[0022] Obtain the area of ​​the obstacles within the first planning area, and determine the target obstacles whose area is greater than the area threshold;

[0023] Filter out the second edge-fitting path corresponding to the target obstacle from the first edge-fitting path;

[0024] When there are at least two second edge-attaching paths, the second edge-attaching paths are connected to determine the edge-attaching path.

[0025] The path planning method provided in this invention removes obstacles with small areas from the first edge-fitting path, ensuring the accuracy of the obtained second edge-fitting path, as these obstacles do not require edge-fitting path planning. Furthermore, when at least two second edge-fitting paths exist, connecting these paths merges the connected regions, further guaranteeing the accuracy of the obtained edge-fitting path.

[0026] In some implementations, determining the bounding box of the area to be planned in the original map based on the area information, and determining the second planning area based on the area covered by the bounding box, includes:

[0027] A second minimum bounding box is determined in the original map to enclose the area information;

[0028] The second map corresponding to the second minimum bounding box is extracted from the original map to determine the second planning area.

[0029] The path planning method provided in this embodiment of the invention uses a second planning region that is a second minimum bounding box that encloses the region information. The second planning region obtained based on the second minimum bounding box is smaller than the first planning region, thereby ensuring that the full-coverage path is within the range enclosed by the edge path.

[0030] In some implementations, the step of performing full-coverage path planning for the second planning area and determining the full-coverage path includes:

[0031] The second obstacle within the second planning area is expanded to determine the third obstacle;

[0032] Extract the second contour of the third obstacle and perform dilation on the second contour to determine the third contour;

[0033] Based on the third contour, passable and impassable areas are determined in the second planning area;

[0034] Perform full-coverage path planning for the passable area to determine the full-coverage path.

[0035] The path planning method provided in this embodiment of the invention extracts a third contour based on the expansion of the second obstacle and expands it again, so that when the obstacle is expanded, a thick wall or the like is not needed. Furthermore, the expansion of the contour expands the range of the impassable area, further ensuring that the full-coverage path is within the range enclosed by the edge path.

[0036] In some implementations, merging the first edge-following path with the full-coverage path to determine the target planning path for the area to be planned includes:

[0037] Merge the first edge-fitting path with the full-coverage path to determine the optional planning path;

[0038] When there are at least two alternative planning paths, the longest alternative planning path is determined as the target planning path.

[0039] The path planning method provided in this embodiment of the invention merges the first edge-following path and the full-coverage path to obtain an optional planning path, realizes the merging of connectable areas, and finally obtains a target planning path, which can avoid the robot constantly shaking its head when returning to the starting point.

[0040] According to a second aspect, embodiments of the present invention also provide a path planning apparatus, comprising:

[0041] The acquisition module is used to obtain the area information of the area to be planned;

[0042] The first determining module is used to determine the planning scope based on the regional information, and to expand the planning scope to determine the first planning area in the original map;

[0043] The first planning module is used to plan the edge-fitting path based on the first planning area and the planning range, and to determine the first edge-fitting path.

[0044] The second determining module is used to determine the bounding box of the area to be planned in the original map based on the area information, and to determine the second planning area based on the area covered by the bounding box;

[0045] The second planning module is used to perform full-coverage path planning for the second planning area and determine the full-coverage path.

[0046] The merging module is used to merge the first edge-fitting path and the full-coverage path to determine the target planning path for the area to be planned.

[0047] According to a third aspect, embodiments of the present invention provide an electronic device, including: a memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the computer instructions to perform the path planning method described in the first aspect or any embodiment of the first aspect.

[0048] According to a fourth aspect, embodiments of the present invention provide a computer-readable storage medium storing computer instructions for causing the computer to perform the path planning method described in the first aspect or any embodiment of the first aspect.

[0049] It should be noted that the corresponding beneficial effects of the path planning device, electronic device and computer-readable storage medium provided in the embodiments of the present invention can be found in the description of the corresponding beneficial effects of the path planning method above, and will not be repeated here. Attached Figure Description

[0050] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0051] Figure 1 This is a flowchart of a path planning method according to an embodiment of the present invention;

[0052] Figure 2 This is a schematic diagram of the original map according to an embodiment of the present invention;

[0053] Figure 3 This is a flowchart of a path planning method according to an embodiment of the present invention;

[0054] Figure 4 This is a schematic diagram of the first minimum bounding box according to an embodiment of the present invention;

[0055] Figure 5 This is a flowchart of a path planning method according to an embodiment of the present invention;

[0056] Figure 6 This is a schematic diagram of the second minimum bounding box according to an embodiment of the present invention;

[0057] Figure 7 This is a structural block diagram of a path planning device according to an embodiment of the present invention;

[0058] Figure 8 This is a schematic diagram of the hardware structure of the electronic device provided in an embodiment of the present invention. Detailed Implementation

[0059] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0060] As mentioned above, in existing path planning methods, the generation of edge-fitting paths and full-coverage paths are performed separately. This leads to situations where, in a region containing two roughly sized, disconnected regions, the two planning algorithms sometimes select different regions. Furthermore, because edge-fitting path planning shrinks the input region to be planned, while full-coverage paths are generated along the edges of the region to be planned when there are no obstacles, edge-fitting paths can be farther from obstacles than full-coverage paths, which clearly does not meet the requirements of path planning. Moreover, the starting point of an edge-fitting path may sometimes be closer to an obstacle. When switching from full-coverage to edge-fitting tasks, the robot repeatedly attempts to reach the starting point, resulting in constant head-shaking. This head-shaking occurs because there are two paths. If the starting point of the edge-fitting path is close to an obstacle, when switching from full-coverage to edge-fitting paths, the robot cannot reach the starting point but keeps trying, leading to continuous head-shaking.

[0061] Based on this, embodiments of the present invention provide a common path planning method. This method generates a first edge-fitting path and a full-coverage path based on the region information of the area to be planned. Finally, the two paths are merged into a single path to obtain the target planned path for the area to be planned. This method ensures that the planned full-coverage path is always within the edge-fitting path. It also solves the problems of the previous edge-fitting and full-coverage planning results not being in the same region, as well as the robot head-swaying issue when switching from full-coverage to edge-fitting, thus improving the robustness of the algorithm.

[0062] The path planning method provided in this invention can be applied to mobile robots as well as other electronic devices such as servers and computers. When applied to a mobile robot, the robot receives area information from a host computer while moving through the area to be planned, and then performs initial edge-following path and full-coverage path planning, finally merging the two to obtain the target planned path for the area. When applied to a server, the mobile robot uploads collected data to the server while moving through the area to be planned. The server then performs path planning by executing the path planning method in this invention, determines the target planned path, and then sends the obtained target planned path back to the mobile robot.

[0063] It should be noted that mobile robots include, but are not limited to, cleaning robots, guidance robots, and handling robots.

[0064] Of course, the path planning method of this invention is not limited to the application scenarios described above. The specific application settings can be made according to actual needs, and no restrictions are imposed here.

[0065] According to an embodiment of the present invention, a path planning method embodiment is provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0066] This embodiment provides a path planning method that can be used in electronic devices such as mobile robots, computers, and servers. Figure 1 This is a flowchart of a path planning method according to an embodiment of the present invention, such as... Figure 1 As shown, the process includes the following steps:

[0067] S11, obtain the area information of the area to be planned.

[0068] The area information for the region to be planned includes its location information, etc. This area information can be used to determine the scope of the route planning process on the original map. For example, ... Figure 2 As shown, Figure 2 The area within rectangle 1 is the range determined based on the area information. This area information can be input by the user through interaction with the electronic device; it can also be sent from a host computer to the electronic device; it can be sent from other terminals to the electronic device; or it can be pre-stored in the electronic device, etc. There are no restrictions on the method of obtaining the area information for the planned area; it can be set according to actual needs.

[0069] S12, determine the planning scope based on regional information, and expand the planning scope to determine the first planning area in the original map.

[0070] Regional information refers to the area covered by the region to be planned. For example, regional information can be used to determine the planning scope on the original map. Figure 2 The area enclosed by rectangle 1 is then enlarged by a preset ratio to obtain the actual area used for edge path planning. For example... Figure 2 The area enclosed by rectangle 2 in the image is then mapped onto the original map to obtain the first planning area. Alternatively, based on the area information, a bounding box parallel to the map coordinate system is calculated for the area to be planned, and then this bounding box is expanded to determine the first planning area; and so on. The original map is a map that includes obstacle information. For example, if the original map is a grayscale image, the area of ​​the original map can be divided into passable and impassable areas based on the different grayscale values ​​of the image pixels. Impassable areas include walls or obstacles, etc.

[0071] The above method for determining the first planning area is merely an example. The specific method should be set according to actual needs, as long as the first planning area is determined based on regional information and obtained after scope expansion processing.

[0072] In some implementations, the first planning area can be determined by first expanding the planning scope, then using the expanded planning scope to extract a local map from the original map, and then inflating the obstacles in the local map; or, the original map can be inflated first, and then the expanded planning scope can be used to extract a local map from the inflated original map to determine the first planning area. There is no essential difference between these two methods; the difference lies in the order of inflating and extracting.

[0073] S13, perform edge-fitting path planning based on the boundary of the first planning area and the planning scope, and determine the first edge-fitting path.

[0074] The first planning area is obtained from the original map. This area includes obstacles, and the edge-fitting path is the path that follows the boundaries of the obstacles and the planning area. Therefore, the first edge-fitting path can be formed by extracting the outlines of the obstacles and the boundaries of the planning area within the first planning area. It should be noted that obstacles refer to objects that hinder the movement of the mobile robot, including but not limited to walls, placed objects, etc.

[0075] Alternatively, after obtaining the first planning area, the location of obstacles within the first planning area can be determined, the robot can be controlled to walk along the obstacles, and the corresponding data can be collected during the walking process to form the first edge-fitting path.

[0076] There are no restrictions on how the edge path is generated; the specific settings should be made according to actual needs.

[0077] S14. Based on the regional information, determine the bounding box of the area to be planned in the original map, and determine the second planning area based on the area covered by the bounding box.

[0078] In this implementation, the area to be planned is determined in the original map using regional information, and then the minimum bounding box of the area to be planned is calculated in the original map. After determining the minimum bounding box, the area enclosed by the minimum bounding box can be defined as the second planning area; or, after obtaining the minimum bounding box, it can be shrunken inward by a certain distance to define the shrunken bounding box as the second planning area; and so on.

[0079] S15, conduct full-coverage route planning for the second planning area and determine the full-coverage route.

[0080] During full-coverage path planning, obstacle areas in the second planning area need to be removed. This is because obstacle areas are impassable; removing them reveals the passable areas within the second planning area. Full-coverage path planning is then performed based on these passable areas to determine the final full-coverage path. Full-coverage paths include, but are not limited to, zigzag, bow-shaped, spiral, or other types.

[0081] S16, merge the first edge-attached path and the full-coverage path to determine the target planning path for the area to be planned.

[0082] After obtaining the first edge-following path and the full-coverage path, they are merged. The merging method includes, but is not limited to, searching for the two paths with the shortest connection distance, where the connection distance is the distance required to connect the two independent paths. No specific merging method is limited here; it can be set according to actual needs. After the merging process, a target planning path is obtained within the area to be planned. In some implementations, after determining the target planning path within the area to be planned, the target planning path is stored in the mobile robot to facilitate safe movement of the mobile robot within that area.

[0083] The path planning method provided in this embodiment expands the planning range to include walls within the area to be planned into the first planning area. This ensures that these walls are used for edge-fitting path planning, rather than the subsequent full-coverage path planning. The second planning area is the bounding box of the area to be planned, determined based on the area information. The second planning area is smaller than the first planning area. The second planning area used for full-coverage path planning is within the first planning area used for edge-fitting path planning, ensuring that the full-coverage path is within the edge-fitting path's range, thus improving the accuracy of the target planned path. Furthermore, as analyzed above, if the starting point of the edge-fitting path is close to an obstacle, when switching from the full-coverage path to the edge-fitting path, the robot cannot reach the starting point but keeps trying, resulting in continuous head-shaking. To address this issue, this solution merges the first edge-fitting path with the full-coverage path, resulting in a single target planned path. This avoids the continuous head-shaking caused by the robot not reaching the starting point but constantly trying when switching from the full-coverage path to the edge-fitting path.

[0084] In some implementations, S16 includes:

[0085] (1) Merge the first edge-attached path and the full-coverage path to determine the optional planning path.

[0086] (2) When there are at least two alternative planning paths, the longest alternative planning path shall be determined as the target planning path.

[0087] After processing by the merging algorithm, if there are at least two alternative planned paths, the lengths of each alternative planned path are compared, and the longest alternative planned path is determined as the target planned path. This step removes invalid paths within disconnected regions, ensuring the reliability of the final target planned path.

[0088] By merging the first edge-following path and the full-coverage path, an optional planning path is obtained, which merges the connectable areas and finally obtains a target planning path, thus avoiding the robot constantly shaking its head when returning to the starting point.

[0089] This embodiment provides a path planning method that can be used in electronic devices such as mobile robots, computers, and servers. Figure 3 This is a flowchart of a path planning method according to an embodiment of the present invention, such as... Figure 3 As shown, the process includes the following steps:

[0090] S21, Obtain regional information of the area to be planned.

[0091] Please see details Figure 1S11 shown here is not subject to any limitations.

[0092] S22, determine the planning scope based on regional information, and expand the planning scope to determine the first planning area in the original map.

[0093] Specifically, S22 includes:

[0094] S221, determine the first minimum bounding box for the bounding area information in the original map.

[0095] The edges of the first minimum bounding box are parallel to the corresponding coordinate axes in the original map.

[0096] The first minimum bounding box is the smallest rectangle parallel to the map coordinate system, where the map coordinate system is the original map's coordinate system. It should be noted that parallelism is not limited to absolute parallelism; a certain margin of error is allowed. The size of this margin of error is set according to actual needs and is not limited here.

[0097] S222, expand the first minimum bounding box to determine the planning range.

[0098] The expansion of the first minimum bounding box can be achieved by expanding it proportionally with its center point as the origin; alternatively, by setting expansion coefficients for the long and short sides of the first minimum bounding box and expanding it accordingly. Alternatively, the first minimum bounding box from the original map can be displayed on the electronic device's interface, and the expansion can be performed through user interaction with the device; and so on. After these expansion processes, the planning area can be determined.

[0099] like Figure 4 As shown, region A is the region to be planned, region B1 is the first minimum bounding box, and region C is the planned area obtained after expansion. Among them, Figure 4 It is described in a map coordinate system.

[0100] S223, Extract the first map corresponding to the planning scope from the original map to determine the first planning area.

[0101] After obtaining the planning scope, this scope is mapped onto the original map to obtain the area to be extracted. That is, the map corresponding to the extracted planning scope is the first map, which is used as the first planning area. This first planning area is used for subsequent edge-fitting path planning.

[0102] In some implementations, obstacles in the original map can be inflated before or after the cropping process.

[0103] S23, perform edge-fitting path planning for the first planning area and determine the first edge-fitting path.

[0104] Planning the edge-hugging path in the first planning area can be achieved by extracting the outlines of obstacles (including walls) in the first planning area, or by controlling the robot to walk along the obstacles in the first planning area to determine the first edge-hugging path, and so on.

[0105] In some embodiments, S23 includes:

[0106] (1) Extract the first outline of the first obstacle in the first planning area and the boundary of the planning range.

[0107] (2) Based on the first contour and the boundary of the planning range, perform edge-fitting path planning and determine the edge-fitting path.

[0108] The first contour can be extracted by calculating the bounding box of the first obstacle, or by other contour extraction methods, etc. Based on the first contour, edge-fitting path planning is performed by combining it with the boundary of the planning area to obtain the edge-fitting path. Specifically, for areas with obstacles, edge-fitting path planning is performed based on the contour of the obstacles; for areas without obstacles, edge-fitting path planning is performed based on the boundary of the planning area, and the two are then combined to obtain the edge-fitting path.

[0109] The first contour within the first planning area is extracted. Since this first contour is the precursor to the edge-fitting path, the subsequent edge-fitting path generation is also based on these first contours. Therefore, the purpose of extracting the first contour is twofold: first, to prepare for edge-fitting planning, and second, to use these contours as prior information for full-coverage planning.

[0110] In some alternative implementations, step (2) of S23 above includes:

[0111] 2.1) Based on the first contour and the boundary of the planning range, perform edge-fitting path planning to determine the first edge-fitting path.

[0112] 2.2) Obtain the area of ​​obstacles within the first planning area and identify target obstacles whose area is greater than the area threshold.

[0113] 2.3) Filter out the second edge path corresponding to the target obstacle from the first edge path.

[0114] 2.4) When there are at least two second edge-attaching paths, the second edge-attaching paths are connected to determine the edge-attaching path.

[0115] Specifically, since there may be multiple obstacles within the first planning area, there will be multiple first contours. Based on this, edge-fitting path planning is performed for each first contour, resulting in multiple first edge-fitting paths. For obstacles with smaller areas, edge-fitting path planning is unnecessary. Therefore, based on the obtained first edge-fitting paths, the first edge-fitting paths are filtered according to the area of ​​the obstacle, including only the first edge-fitting paths corresponding to target obstacles with areas larger than an area threshold. For ease of distinction, this filtered portion of first edge-fitting paths is referred to as the second edge-fitting paths.

[0116] After filtering by the aforementioned area threshold, if at least two second edge-attaching paths still exist, these second edge-attaching paths are then connected to form connected regions; that is, the second edge-attaching paths are merged. After the merging process, the edge-attaching paths can be determined.

[0117] It should be noted that the edge-fitting path determined here may be one or multiple. This is because there may be second edge-fitting paths that cannot be connected, and these second edge-fitting paths that cannot be connected are stored. Similarly, for ease of distinction, the second edge-fitting path that cannot be connected is also referred to as an edge-fitting path.

[0118] Since obstacles with small areas do not require edge-fitting path planning, they are removed from the first edge-fitting path to ensure the accuracy of the obtained second edge-fitting path. Simultaneously, when at least two second edge-fitting paths exist, connecting these paths merges the connected regions, further ensuring the accuracy of the obtained edge-fitting path.

[0119] S24. Based on the regional information, determine the bounding box of the area to be planned in the original map, and determine the second planning area based on the area covered by the bounding box.

[0120] Please see details Figure 1 S14 of the illustrated embodiment will not be described again here.

[0121] S25, conduct full-coverage route planning for the second planning area and determine the full-coverage route.

[0122] Please see details Figure 1 S15 of the illustrated embodiment will not be described again here.

[0123] S26, merge the first edge-attached path and the full-coverage path to determine the target planning path for the area to be planned.

[0124] Please see details Figure 1 S15 of the illustrated embodiment will not be described again here.

[0125] The path planning method provided in this embodiment, by expanding the first minimum bounding box, can encompass walls close to the boundary in the region information within the first planning area, ensuring that the first planning area is a local map including all obstacles, thus providing a basic guarantee for subsequent edge-fitting path planning. Specifically, in existing solutions, the first planning area is determined directly from the original map based on the region information of the area to be planned. If the boundary in the region information is close to the wall, such as... Figure 1 As shown in rectangle 1, directly determining the first planning area from the original map does not include the walls. Therefore, subsequent path planning for this area will be based on the boundary information rather than the walls, resulting in lower accuracy. Based on this, the first minimum bounding box is expanded in this solution, as shown... Figure 2 As shown in rectangle 2, this allows walls that are close to the boundary of the area information to be included in the first planning area.

[0126] This embodiment provides a path planning method that can be used in electronic devices such as mobile robots, computers, and servers. Figure 5 This is a flowchart of a path planning method according to an embodiment of the present invention, such as... Figure 5 As shown, the process includes the following steps:

[0127] S31, Obtain regional information of the area to be planned.

[0128] Please see details Figure 1 S11 shown here is not subject to any limitations.

[0129] S32, determine the planning scope based on regional information, and expand the planning scope to determine the first planning area in the original map.

[0130] Please see details Figure 3 S22 shown here is not subject to any limitations.

[0131] S33, plan the edge-fitting path based on the first planning area and the planning range, and determine the first edge-fitting path.

[0132] Please see details Figure 3 S23 shown here is not subject to any limitations.

[0133] S34. Based on the regional information, determine the bounding box of the area to be planned in the original map, and determine the second planning area based on the area covered by the bounding box.

[0134] Specifically, S34 includes:

[0135] S341, determine the second minimum bounding box for the bounding area information in the original map.

[0136] Figure 6 A schematic diagram of the second minimum bounding box is shown. Figure 6 It is described in a map coordinate system. Figure 6 Region A is the region to be planned, and Region B2 is the second minimum bounding box.

[0137] S342, extract the second map corresponding to the second minimum bounding box from the original map, and determine the second planning area.

[0138] Similar to the method used to determine the first planning region, the second minimum bounding box is mapped onto the obstacle map to obtain the second map corresponding to the second minimum bounding box. For ease of description, the second map is referred to as the second planning region, that is, the second planning region used for full-coverage path planning.

[0139] S35, conduct full-coverage route planning for the second planning area and determine the full-coverage route.

[0140] Specifically, S35 includes:

[0141] S351, expand the second obstacle in the second planning area to determine the third obstacle.

[0142] Since the second planning area is a local area in the original map, it includes second obstacles. The location and coverage area of ​​each second obstacle are determined within the second planning area, collision handling is performed on them, and the area is expanded to obtain third obstacles.

[0143] S352, extract the second contour of the third obstacle, and perform dilation processing on the second contour to determine the third contour.

[0144] After obtaining the third obstacle, its contour is extracted to obtain the second contour. Then, the second contour is expanded to obtain the third contour.

[0145] S353, based on the third contour, determines the passable and impassable areas in the second planning area.

[0146] The area enclosed by the third outline is designated as an impassable area, while the entire second planning area, excluding the impassable area, is designated as a traversable area. Subsequent planning of the full-coverage route will be conducted within the traversable areas.

[0147] S354, conducts full-coverage route planning for passable areas and determines full-coverage routes.

[0148] The specific implementation method for full-coverage route planning is not limited here; it can be set according to actual needs. It should be noted that the resulting full-coverage route can be one or multiple routes, depending on the division of the passable area.

[0149] Therefore, if at least two full-coverage paths are obtained, the full-coverage paths are merged first, and then the S36 processing is performed. The merging method of the full-coverage paths is similar to the merging method of the second edge-attaching path described above, and will not be repeated here.

[0150] S36, merge the first edge-attached path and the full-coverage path to determine the target planning path for the area to be planned.

[0151] Please see details Figure 1 S16 of the illustrated embodiment will not be described again here.

[0152] The path planning method provided in this embodiment uses a second planning region, which is the second minimum bounding box encompassing the region information. The second planning region, obtained based on the second minimum bounding box, is smaller than the first planning region, thus ensuring that the full-coverage path remains within the area enclosed by the edge-bound path. Based on the expansion of the second obstacle, a third contour is extracted and expanded again. This eliminates the need for thick walls when the obstacle is expanded, and the further expansion of the contour expands the area of ​​impassable regions, further ensuring that the full-coverage path remains within the area enclosed by the edge-bound path.

[0153] This embodiment also provides a path planning device for implementing the above embodiments and preferred embodiments; details already described will not be repeated. As used below, the term "module" can refer to a combination of software and / or hardware that implements a predetermined function. Although the device described in the following embodiments is preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated.

[0154] This embodiment provides a path planning device, such as Figure 7 As shown, it includes:

[0155] Module 41 is used to obtain the area information of the area to be planned;

[0156] The first determining module 42 is used to determine the planning range based on the regional information, and expand the planning range to determine the first planning area in the original map;

[0157] The first planning module 43 is used to plan the edge-fitting path based on the first planning area and the planning range, and to determine the first edge-fitting path.

[0158] The second determining module 44 is used to determine the bounding box of the area to be planned in the original map based on the area information, and to determine the second planning area based on the area covered by the bounding box;

[0159] The second planning module 45 is used to perform full-coverage path planning for the second planning area and determine the full-coverage path.

[0160] The merging module 46 is used to merge the first edge-attached path and the full-coverage path to determine the target planning path for the area to be planned.

[0161] In some implementations, the first determining module 42 includes:

[0162] The first determining unit is used to determine a first minimum bounding box that surrounds the region information in the original map, wherein the edges of the first minimum bounding box are parallel to the corresponding coordinate axes in the original map.

[0163] An expansion unit is used to expand the first minimum bounding box to determine the planning range;

[0164] The second determining unit is used to extract the first map corresponding to the planning range from the original map and determine the first planning area.

[0165] In some implementations, the first planning module 43 includes:

[0166] The first extraction unit is used to extract the first outline of the first obstacle within the first planning area and the boundary of the planning range;

[0167] The third determining unit is used to plan the edge-fitting path based on the first contour and the boundary of the planning range, and to determine the edge-fitting path.

[0168] In some implementations, the first planning module 43 includes:

[0169] The fourth determining unit is used to perform edge-fitting path planning based on the first contour and the boundary of the planning range, and to determine the first edge-fitting path;

[0170] The first acquisition unit is used to acquire the area of ​​the obstacle within the first planning area and determine the target obstacle whose area is greater than the area threshold.

[0171] A filtering unit is used to filter out the second edge-fitting path corresponding to the target obstacle from the first edge-fitting path;

[0172] A connection unit is used to connect the second edge-attaching paths when there are at least two second edge-attaching paths, so as to determine the edge-attaching paths.

[0173] In some implementations, the second determining module 44 includes:

[0174] The fifth determining unit is used to determine the second minimum bounding box that surrounds the area information in the original map;

[0175] The cropping unit is used to crop out the second map corresponding to the second minimum bounding box from the original map and determine the second planning area.

[0176] In some implementations, the second planning module 45 includes:

[0177] The first expansion unit is used to expand the second obstacle within the second planning area to determine the third obstacle;

[0178] The second extraction unit is used to extract the second contour of the third obstacle and perform dilation processing on the second contour to determine the third contour.

[0179] The sixth determining unit is used to determine the passable and impassable areas in the second planning area based on the third contour;

[0180] The seventh determining unit is used to perform full-coverage path planning for the passable area and determine the full-coverage path.

[0181] In some implementations, the merging module 46 includes:

[0182] A merging unit is used to merge the first edge-fitting path with the full-coverage path to determine an optional planning path;

[0183] The eighth determining unit is used to determine the longest optional planning path as the target planning path when there are at least two optional planning paths.

[0184] The path planning device in this embodiment is presented in the form of a functional unit. Here, a unit refers to an ASIC circuit, a processor and memory that execute one or more software or fixed programs, and / or other devices that can provide the above functions.

[0185] Further functional descriptions of the above modules are the same as those in the corresponding embodiments described above, and will not be repeated here.

[0186] This invention also provides an electronic device having the above-described features. Figure 7 The path planning device shown.

[0187] Please see Figure 8 , Figure 8 This is a schematic diagram of the structure of an electronic device provided in an optional embodiment of the present invention, such as... Figure 8As shown, the electronic device may include: at least one processor 51, such as a CPU (Central Processing Unit), at least one communication interface 53, memory 54, and at least one communication bus 52. The communication bus 52 is used to enable communication between these components. The communication interface 53 may include a display screen or a keyboard; optionally, the communication interface 53 may also include a standard wired interface or a wireless interface. The memory 54 may be high-speed RAM (Random Access Memory) or non-volatile memory, such as at least one disk storage device. Optionally, the memory 54 may also be at least one storage device located remotely from the aforementioned processor 51. The processor 51 may be combined with... Figure 7 The described apparatus has an application program stored in memory 54, and the processor 51 calls the program code stored in memory 54 to perform any of the above method steps.

[0188] The communication bus 52 can be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus, etc. The communication bus 52 can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 8 The bus is represented by a single thick line, but this does not mean that there is only one bus or one type of bus.

[0189] The memory 54 may include volatile memory, such as random-access memory (RAM); the memory may also include non-volatile memory, such as flash memory, hard disk drive (HDD) or solid-state drive (SSD); the memory 54 may also include a combination of the above types of memory.

[0190] The processor 51 can be a central processing unit (CPU), a network processor (NP), or a combination of CPU and NP.

[0191] The processor 51 may further include a hardware chip. This hardware chip may be an application-specific integrated circuit (ASIC), a programmable logic device (PLD), or a combination thereof. The PLD may be a complex programmable logic device (CPLD), a field-programmable gate array (FPGA), a generic array logic (GAL), or any combination thereof.

[0192] Optionally, memory 54 is also used to store program instructions. Processor 51 can invoke program instructions to implement the path planning method as shown in any embodiment of this application.

[0193] This invention also provides a non-transitory computer storage medium storing computer-executable instructions that can execute the path planning method in any of the above method embodiments. The storage medium can be a magnetic disk, optical disk, read-only memory (ROM), random access memory (RAM), flash memory, hard disk drive (HDD), or solid-state drive (SSD), etc.; the storage medium may also include combinations of the above types of memory.

[0194] Although embodiments of the invention have been described in conjunction with the accompanying drawings, those skilled in the art can make various modifications and variations without departing from the spirit and scope of the invention, and such modifications and variations all fall within the scope defined by the appended claims.

Claims

1. A path planning method, characterized in that, include: Obtain regional information for the area to be planned; Based on the regional information, the planning scope is determined, and the planning scope is expanded to determine the first planning area in the original map; Based on the first planning area and the planning range, a path-fitting method is planned to determine the first path-fitting method. Based on the regional information, the bounding box of the area to be planned is determined in the original map, and a second planning area is determined based on the area covered by the bounding box; Perform full-coverage path planning for the second planning area to determine the full-coverage path; The first edge-fitting path and the full-coverage path are merged to determine the target planning path for the area to be planned.

2. The method according to claim 1, characterized in that, The step of determining the planning scope based on the regional information and expanding the planning scope to determine the first planning area in the original map includes: A first minimum bounding box is determined in the original map to enclose the region information, and the edges of the first minimum bounding box are parallel to the corresponding coordinate axes in the original map. Expand the first minimum bounding box to determine the planning range; The first map corresponding to the planning scope is extracted from the original map to determine the first planning area.

3. The method according to claim 1, characterized in that, The step of planning the edge-hugging path based on the first planning area and the planning range, and determining the edge-hugging path, includes: Extract the first outline of the first obstacle within the first planning area and the boundary of the planning range; Based on the first contour and the boundary of the planned range, an edge-fitting path is planned to determine the edge-fitting path.

4. The method according to claim 3, characterized in that, The step of planning the edge-fitting path based on the first contour and the boundary of the planned range, and determining the edge-fitting path, includes: Based on the first contour and the boundary of the planned range, an edge-fitting path is planned to determine the first edge-fitting path; Obtain the area of ​​the obstacles within the first planning area, and determine the target obstacles whose area is greater than the area threshold; Filter out the second edge-fitting path corresponding to the target obstacle from the first edge-fitting path; When there are at least two second edge-attaching paths, the second edge-attaching paths are connected to determine the edge-attaching path.

5. The method according to claim 1, characterized in that, The step of determining the bounding box of the area to be planned in the original map based on the regional information, and determining the second planning area based on the area covered by the bounding box, includes: A second minimum bounding box is determined in the original map to enclose the area information; The second map corresponding to the second minimum bounding box is extracted from the original map to determine the second planning area.

6. The method according to claim 5, characterized in that, The step of performing full-coverage path planning for the second planning area and determining the full-coverage path includes: The second obstacle within the second planning area is expanded to determine the third obstacle; Extract the second contour of the third obstacle and perform dilation on the second contour to determine the third contour; Based on the third contour, passable and impassable areas are determined in the second planning area; Perform full-coverage path planning for the passable area to determine the full-coverage path.

7. The method according to claim 6, characterized in that, The step of merging the first edge-fitting path and the full-coverage path to determine the target planning path for the area to be planned includes: Merge the first edge-fitting path with the full-coverage path to determine the optional planning path; When there are at least two alternative planning paths, the longest alternative planning path is determined as the target planning path.

8. A path planning device, characterized in that, include: The acquisition module is used to obtain the area information of the area to be planned; The first determining module is used to determine the planning scope based on the regional information, and to expand the planning scope to determine the first planning area in the original map; The first planning module is used to plan the edge-fitting path for the first planning area and determine the first edge-fitting path. The second determining module is used to determine the bounding box of the area to be planned in the original map based on the area information, and to determine the second planning area based on the area covered by the bounding box; The second planning module is used to perform full-coverage path planning for the second planning area and determine the full-coverage path. The merging module is used to merge the first edge-fitting path and the full-coverage path to determine the target planning path for the area to be planned.

9. An electronic device, characterized in that, include: A memory and a processor are communicatively connected, the memory stores computer instructions, and the processor executes the path planning method of any one of claims 1-7 by executing the computer instructions.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions for causing the computer to perform the path planning method according to any one of claims 1-7.

Images