Path planning method, electronic equipment and storage medium

Abstract

The invention provides a path planning method, electronic equipment and a storage medium, and is suitable for the technical field of path planning. The method comprises the following steps: acquiring an original grid map, and performing hierarchical processing on the original grid map to obtain at least two to-be-used grid maps with different resolutions; based on preset path information, performing path planning on the at least two to-be-used grid maps to obtain intermediate path information; based on the intermediate path information, performing path planning on the original grid map to obtain global path information; wherein layering processing is carried out on the original grid map and / or path planning is carried out on the at least two grid maps to be used, and a parallel processing mode of at least two threads is adopted. According to the embodiment of the invention, the real-time performance of path planning is guaranteed, the accuracy of path planning is improved, obstacles can be effectively avoided, the feasibility and safety of a navigation path in a narrow water area are guaranteed, and the global path planning method can be suitable for the water unmanned equipment.

Description

Technical Field

[0001] This application relates to the field of path planning technology, and in particular to a path planning method, electronic device and storage medium. Background Technology

[0002] Unmanned aerial vehicles (UAVs) are highly intelligent and technologically advanced unmanned aerial devices. In practical working environments, in order to achieve autonomous navigation, UAVs must first solve the problem of how to plan a safe and reliable global path.

[0003] There are two main common approaches: one is to use a graph search method to traverse all grid cells in the map, and then combine a heuristic cost function and constraints to calculate a relatively optimal, origin-endpoint related, safe, and traversable global path. While this method yields good planning results, it takes a long time to plan paths on high-resolution grid maps. During autonomous navigation, insufficient real-time performance may lead to collision avoidance failures, or even control program crashes and loss of control of the unmanned underwater vehicle. The other approach is to use a probabilistic search method, trading quantity for quality through random calculations to finally calculate a global path. This method can calculate planning results quickly on high-resolution grid maps, but it often fails to accurately plan optimal paths in traversable areas with obstacles, resulting in lower path planning accuracy.

[0004] Therefore, a new global path planning method suitable for unmanned watercraft needs to be designed. Summary of the Invention

[0005] In view of this, embodiments of this application provide a path planning method, an electronic device, and a storage medium to solve the problems of long path planning time or low path planning accuracy in the prior art.

[0006] The first aspect of this application provides a path planning method, including:

[0007] Obtain the original raster map, perform layer processing on the original raster map to obtain at least two raster maps with different resolutions to be used; wherein, the original raster map includes obstacles, and the resolution of the original raster map is greater than the resolution of each raster map to be used;

[0008] Based on the preset path information, path planning is performed on at least two grid maps to be used to obtain intermediate path information; wherein, the preset path information includes the target start point and the target end point, and the intermediate path information includes multiple path points, and the line connecting any two path points does not intersect with obstacles.

[0009] Based on intermediate path information, path planning is performed on the original raster map to obtain global path information;

[0010] The process involves layering the original raster map and / or performing path planning on at least two raster maps to be used, using at least two threads in parallel.

[0011] In one possible implementation, the original raster map is layered to obtain at least two raster maps of different resolutions to be used, including:

[0012] Using at least two threads to process in parallel, the original raster map is divided into at least two raster maps with different resolutions according to a preset layering strategy.

[0013] The obstacles in each grid map to be processed are preprocessed by using at least two threads in parallel to obtain each grid map to be used.

[0014] In one possible implementation, obstacles in each raster map to be processed are preprocessed to obtain each raster map to be used, including:

[0015] Based on the size of the obstacles in each grid map to be processed, the obstacles are filtered and selected to obtain each filtered grid map to be processed.

[0016] The obstacles in each of the filtered raster maps to be processed are eroded to reduce their size, thus obtaining each raster map to be used.

[0017] In one possible implementation, based on preset path information, path planning is performed on at least two raster maps to be used to obtain intermediate path information, including:

[0018] Sort the raster maps to be used in ascending order of resolution;

[0019] The first path planning operation is performed on each grid map to be used by using at least two threads in parallel until the sub-path information of the last grid map to be used is used as the intermediate path information.

[0020] The first path planning operation includes:

[0021] According to the preset path planning rules, the initial path information is determined; wherein, the path planning rules include: using the preset path information as the initial path information of the first grid map to be used, and using the sub-path information of the previous grid map to be used as the initial path information of the next grid map to be used.

[0022] Based on the initial path information, path planning is performed on the raster map to be used to obtain the sub-path information of the raster map to be used; wherein, the sub-path information includes at least two path points.

[0023] In one possible implementation, based on the initial path information, path planning is performed on the raster map to be used to obtain the sub-path information of the raster map to be used, including:

[0024] Extract two path points sequentially from the initial path information, and treat every two path points as a group of path points;

[0025] Based on each set of waypoints, path planning is performed in the raster map to be used to obtain sub-path information of the raster map to be used.

[0026] In one possible implementation, based on each set of waypoints, path planning is performed in the raster map to be used to obtain sub-path information of the raster map to be used, including:

[0027] Based on each set of path points, a screenshot of the raster map to be used is processed to obtain the first sub-raster map;

[0028] Using a graph search method, path planning is performed on the first sub-grid map based on each set of waypoints to obtain sub-path information of the grid map to be used.

[0029] In one possible implementation, path planning is performed on the original raster map based on intermediate path information to obtain global path information, including:

[0030] Based on intermediate path information, path planning is performed on the original raster map to obtain multiple target path points;

[0031] Global path information is obtained by splicing and smoothing multiple target path points.

[0032] In one possible implementation, path planning is performed on the original raster map based on intermediate path information to obtain multiple target waypoints, including:

[0033] Extract two path points sequentially from the intermediate path information, and treat every two path points as a group of path points;

[0034] Based on each set of path points, a screenshot of the original raster map is taken to obtain the second sub-raster map;

[0035] Using a graph search method, path planning is performed on the second sub-grid map based on each set of waypoints to obtain multiple target waypoints.

[0036] A second aspect of this application provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the method of the first aspect.

[0037] A third aspect of this application provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps of the method of the first aspect.

[0038] The beneficial effects of the embodiments in this application compared with the prior art are:

[0039] The path planning method of the first aspect of this application can acquire an original raster map, perform layered processing on the original raster map to obtain at least two raster maps of different resolutions to be used, and then perform path planning on the at least two raster maps to be used based on preset path information to obtain intermediate path information. Finally, based on the intermediate path information, perform path planning on the original raster map to obtain global path information. Since the layered processing of the original raster map and / or the path planning on the at least two raster maps to be used are performed in parallel using at least two threads, the time required for path planning can be greatly shortened. This reduces or avoids collision avoidance failures, or even control program crashes and loss of control of unmanned watercraft due to insufficient real-time performance during autonomous navigation.

[0040] Meanwhile, the original grid map in this application embodiment includes obstacles, the intermediate path information includes multiple path points, the line connecting any two path points does not intersect with the obstacles, and global path information is obtained by performing path planning on the original grid map based on the intermediate path information. This ensures real-time performance while improving the accuracy of path planning, effectively avoiding obstacles, ensuring the feasibility and safety of navigation paths in narrow waters, and is applicable to global path planning methods for unmanned watercraft.

[0041] It is understood that the beneficial effects of the second and third aspects mentioned above can be found in the relevant descriptions in the first aspect mentioned above, and will not be repeated here. Attached Figure Description

[0042] To more clearly illustrate the technical solutions in the embodiments of this application, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0043] Figure 1 This is a schematic diagram of the structure of a path planning system provided in an embodiment of this application;

[0044] Figure 2 This is a flowchart of a path planning method provided in an embodiment of this application;

[0045] Figure 3This is a flowchart of another path planning method provided in an embodiment of this application;

[0046] Figure 4 This is a flowchart of another path planning method provided in the embodiments of this application;

[0047] Figure 5 This is a schematic diagram of the structure of a path planning device provided in an embodiment of this application;

[0048] Figure 6 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Detailed Implementation

[0049] In the following description, specific details such as particular system architectures and techniques are set forth for illustrative purposes and not for limitation, in order to provide a thorough understanding of the embodiments of this application. However, those skilled in the art will understand that this application may also be implemented in other embodiments without these specific details. In other instances, detailed descriptions of well-known systems, apparatuses, circuits, and methods have been omitted so as not to obscure the description of this application with unnecessary detail.

[0050] It should be understood that, when used in this application specification and the appended claims, the term "comprising" indicates the presence of the described features, integrals, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, integrals, steps, operations, elements, components and / or a collection thereof.

[0051] It should also be understood that the term “and / or” as used in this application specification and the appended claims means any combination of one or more of the associated listed items and all possible combinations, and includes such combinations.

[0052] As used in this application specification and the appended claims, the term "if" may be interpreted, depending on the context, as "when," "once," "in response to determination," or "in response to detection." Similarly, the phrase "if determined" or "if detected [the described condition or event]" may be interpreted, depending on the context, as meaning "once determined," "in response to determination," "once detected [the described condition or event]," or "in response to detection [the described condition or event]."

[0053] Furthermore, in the description of this application and the appended claims, the terms "first," "second," "third," etc., are used only to distinguish descriptions and should not be construed as indicating or implying relative importance.

[0054] References to "one embodiment" or "some embodiments" as described in this specification mean that one or more embodiments of this application include a specific feature, structure, or characteristic described in connection with that embodiment. Therefore, the phrases "in one embodiment," "in some embodiments," "in other embodiments," "in still other embodiments," etc., appearing in different parts of this specification do not necessarily refer to the same embodiment, but rather mean "one or more, but not all, embodiments," unless otherwise specifically emphasized. The terms "comprising," "including," "having," and variations thereof mean "including but not limited to," unless otherwise specifically emphasized.

[0055] The technical solution of this application and how it solves the above-mentioned technical problems are described in detail below with specific embodiments. It should be noted that the following embodiments can be referenced, learned from, or combined with each other, and the same terms, similar features, and similar implementation steps in different embodiments will not be described again.

[0056] See Figure 1 As shown in the diagram, this application provides a schematic diagram of the structure of a path planning system. Figure 1 As shown, the path planning system includes an unmanned watercraft 11, a wireless base station 12, and a terminal device 13.

[0057] The path planning method of this application embodiment can be applied to terminal device 13, and wireless base station 12 connects terminal device 13 and unmanned surface vessel 11 for communication. By operating the control software on terminal device 13, control commands are sent to unmanned surface vessel 11 via wireless base station 12, thereby realizing remote navigation control and autonomous navigation task issuance of unmanned surface vessel 11.

[0058] The path planning method of this application embodiment can also be applied to the unmanned aerial vehicle 11, that is, it can be executed by the unmanned aerial vehicle 11. Furthermore, the path planning method of this application embodiment is applicable not only to path planning on water but also to path planning on land.

[0059] The path planning method provided in this application embodiment can be applied to terminal devices 13 such as mobile phones, tablets, wearable devices, in-vehicle devices, augmented reality (AR) / virtual reality (VR) devices, laptops, ultra-mobile personal computers (UMPCs), netbooks, and personal digital assistants (PDAs). This application embodiment does not impose any restrictions on the specific type of terminal device 13.

[0060] See Figure 2 As shown, this application provides a flowchart of a path planning method. Figure 2 As shown, the path planning method of this application embodiment includes steps S201 to S203.

[0061] S201. Obtain the original raster map, perform layer processing on the original raster map to obtain at least two raster maps with different resolutions to be used; wherein, the original raster map includes obstacles, and the resolution of the original raster map is greater than the resolution of each raster map to be used.

[0062] Optionally, the raster map to be used is obtained based on the layered processing of the original raster map, and also includes obstacles. In this application embodiment, both the raster map to be used and the original raster map are referred to as "raster map," meaning that the raster map in this application includes both the raster map to be used and the original raster map. The obstacles in the raster map are static obstacles.

[0063] S202. Based on the preset path information, perform path planning on at least two grid maps to be used to obtain intermediate path information; wherein, the preset path information includes the target start point and the target end point, and the intermediate path information includes multiple path points, and the line connecting any two path points does not intersect with obstacles.

[0064] Optionally, in the embodiments of this application, when performing path planning, the line connecting any two path points does not intersect with the obstacle, so as to ensure that the obstacle is avoided.

[0065] S203. Based on intermediate path information, perform path planning on the original raster map to obtain global path information.

[0066] The process involves layering the original raster map and / or performing path planning on at least two raster maps to be used, using at least two threads in parallel.

[0067] Specifically, the intermediate path information is a general route including multiple waypoints determined by the raster map to be used. Based on the intermediate path information, path planning can continue on the original raster map, which can shorten the time for path planning on the original raster map and thus improve the real-time performance of path planning.

[0068] Based on steps S201 to S203 above, the path planning method of this embodiment can obtain an original raster map, perform layered processing on the original raster map to obtain at least two raster maps with different resolutions to be used, and then perform path planning on the at least two raster maps to be used based on preset path information to obtain intermediate path information. Finally, based on the intermediate path information, perform path planning on the original raster map to obtain global path information. Since the layered processing of the original raster map and / or the path planning on the at least two raster maps to be used are performed in parallel using at least two threads, the time required for path planning can be greatly shortened. This reduces or avoids collision avoidance failures, or even control program crashes and loss of control of the unmanned aerial vehicle 11, due to insufficient real-time performance during autonomous navigation.

[0069] Meanwhile, the original grid map in this embodiment includes obstacles, the intermediate path information includes multiple path points, the line connecting any two path points does not intersect with the obstacles, and global path information is obtained by performing path planning on the original grid map based on the intermediate path information. This ensures real-time performance while improving the accuracy of path planning, effectively avoiding obstacles and ensuring the feasibility and safety of navigation paths in narrow waters. It can be applied to the global path planning method of the unmanned watercraft 11.

[0070] Furthermore, the embodiments of this application do not require path planning based directly on preset path information on a high-resolution original raster map. Graph search methods or other path planning methods can be used, and probabilistic search methods are not necessarily required, which further improves the accuracy of path planning.

[0071] In some embodiments, the original raster map is layered to obtain at least two raster maps of different resolutions to be used, including:

[0072] Using at least two threads to process in parallel, the original raster map is divided into at least two raster maps with different resolutions according to a preset layering strategy.

[0073] The obstacles in each grid map to be processed are preprocessed by using at least two threads in parallel to obtain each grid map to be used.

[0074] This application embodiment can, according to a predetermined layering strategy, divide a high-resolution raster map containing static obstacles into new raster maps with different resolutions but consistent scales, which can then be used as raster maps for future applications.

[0075] In some embodiments, obstacles in each raster map to be processed are preprocessed to obtain each raster map to be used, including:

[0076] Based on the size of the obstacles in each grid map to be processed, the obstacles are filtered and selected to obtain each filtered grid map to be processed.

[0077] The obstacles in each of the filtered raster maps to be processed are eroded to reduce their size, thus obtaining each raster map to be used.

[0078] The embodiments of this application can filter and screen static obstacles in the grid map to be used according to a predetermined optimization strategy, and then complete the erosion process.

[0079] In some embodiments, based on preset path information, path planning is performed on at least two raster maps to be used to obtain intermediate path information, including:

[0080] Sort the raster maps to be used in ascending order of resolution;

[0081] The first path planning operation is performed on each grid map to be used by using at least two threads in parallel until the sub-path information of the last grid map to be used is used as the intermediate path information.

[0082] The first path planning operation includes:

[0083] According to the preset path planning rules, the initial path information is determined; wherein, the path planning rules include: using the preset path information as the initial path information of the first grid map to be used, and using the sub-path information of the previous grid map to be used as the initial path information of the next grid map to be used.

[0084] Based on the initial path information, path planning is performed on the raster map to be used to obtain the sub-path information of the raster map to be used; wherein, the sub-path information includes at least two path points.

[0085] In this embodiment, the sub-path information of the previous grid map to be used can be used as the initial path information of the next grid map to be used, thereby obtaining intermediate path information through path planning of each grid map to be used in sequence.

[0086] In some embodiments, based on initial path information, path planning is performed on the raster map to be used to obtain sub-path information of the raster map to be used, including:

[0087] Extract two path points sequentially from the initial path information, and treat every two path points as a group of path points;

[0088] Based on each set of waypoints, path planning is performed in the raster map to be used to obtain sub-path information of the raster map to be used.

[0089] Optionally, the path planning for each grid map to be used is carried out in a separate thread. That is, when two path points are determined by the sub-path information of the previous grid map to be used, synchronous path planning can be carried out in the next grid map to be used based on these two path points.

[0090] In some embodiments, based on each set of waypoints, path planning is performed in the raster map to be used to obtain sub-path information of the raster map to be used, including:

[0091] Based on each set of path points, a screenshot of the raster map to be used is processed to obtain the first sub-raster map;

[0092] Using a graph search method, path planning is performed on the first sub-grid map based on each set of waypoints to obtain sub-path information of the grid map to be used.

[0093] Specifically, in this embodiment of the application, by cropping the first sub-grid map from the raster map to be used, redundant map information can be removed, which can reduce the computational requirements of the system for path planning.

[0094] In some embodiments, based on intermediate path information, path planning is performed on the original raster map to obtain global path information, including:

[0095] Based on intermediate path information, path planning is performed on the original raster map to obtain multiple target path points;

[0096] Global path information is obtained by splicing and smoothing multiple target path points.

[0097] In some embodiments, based on intermediate path information, path planning is performed on the original raster map to obtain multiple target path points, including:

[0098] Extract two path points sequentially from the intermediate path information, and treat every two path points as a group of path points;

[0099] Based on each set of path points, a screenshot of the original raster map is taken to obtain the second sub-raster map;

[0100] Using a graph search method, path planning is performed on the second sub-grid map based on each set of waypoints to obtain multiple target waypoints.

[0101] The principle of path planning on the original raster map in this embodiment is the same as that of path planning on the raster map to be used. The sub-raster map in this embodiment includes a first sub-raster map and a second sub-raster map. Since the planned path needs to be obtained from the original raster map in the end, this embodiment performs stitching and smoothing processing based on multiple target path points to obtain global path information.

[0102] Optionally, after splicing and smoothing multiple target path points to obtain global path information, the method further includes: sending the global path information to the unmanned watercraft 11 so that the unmanned watercraft 11 can move based on the global path information.

[0103] This application embodiment can, according to predetermined preset path information and combined with the optimized raster map to be used, mine sub-raster maps that can meet the path planning requirements, further reducing the redundancy of map information and completing global path planning. This application embodiment is a global path planning strategy for a map layering scheme, which not only ensures the rationality of the results but also reduces unnecessary map information, directly improving the real-time performance of global path planning for the unmanned watercraft 11.

[0104] This application provides a global path segmentation planning and splicing optimization scheme based on multi-threaded parallel technology. In practical applications, if the entire global path is to be planned serially in a short time, the computational requirements of the system are extremely high, which will reduce the economic efficiency of the unmanned watercraft system. To address this problem, this application arranges the grid maps to be used and the original grid maps according to coarse, slightly coarse, and fine dimensions, and performs path planning sequentially. This application adopts the following optimization strategy:

[0105] (1) Combine the predetermined preset path information and the coarse first sub-grid map after layering to make a rough plan and obtain a rough waypoint.

[0106] (2) Before the rough path points are fully planned, the first two rough path points can be extracted based on multi-threaded parallel technology, and then combined with the first sub-grid map which is slightly more refined in the layer to complete the fine planning.

[0107] (3) The first sub-grid map with a slightly coarse layer and the first sub-grid map with a fine layer, and the waypoints with a slightly coarse layer and the waypoints with a fine layer are all carried out simultaneously.

[0108] (4) After obtaining all the fine path points (i.e. target path points), the path points are then spliced ​​and smoothed.

[0109] This application utilizes multi-threaded parallel technology, which can greatly improve the real-time performance of path planning while reducing the computational requirements of the hardware, thus ensuring the system's economy. Furthermore, the segmented path planning can provide a segmented display scheme for the planned path, making the display on the human-machine interface more flexible.

[0110] Furthermore, the path planning method based on the embodiments of this application can take into account both the real-time performance of path planning for high-resolution original raster maps and the passability of narrow areas.

[0111] In practical applications, optimizing probabilistic search methods presents greater challenges in path planning within narrow areas. Therefore, simultaneously addressing the real-time performance issues of path planning on high-resolution raster maps and ensuring navigability in narrow areas requires resolving the real-time performance problem of graph search methods. To address this issue, this solution adopts the following strategy:

[0112] (1) Map layering is adopted. While removing redundant static obstacle information, the number of grids in the map is compressed, and the first sub-grid map is mined for path planning.

[0113] (2) Using multi-threaded parallel technology, both map layering and path planning are performed synchronously;

[0114] (3) The planning process is carried out iteratively, and in the final refined planning, the second sub-grid map mined from the original grid map is used to ensure the security of the planning results.

[0115] The strategies described in this application not only ensure the feasibility and safety of navigation routes in narrow waters, but also guarantee the real-time planning performance of the system when faced with high-resolution maps.

[0116] This application primarily focuses on designing a global path planning method applicable to unmanned aerial vehicles (UAVs) 11. For complex grid maps, whether low-resolution or high-resolution, containing open or narrow areas, the method utilizes existing static obstacles within the grid map. Based on graph search and map layering methods, combined with multi-threaded parallel technology in computers, it ultimately completes global path planning, providing a fundamental guarantee for the autonomous navigation function of the UAV 11, while ensuring real-time performance, accuracy, practicality, and economy.

[0117] The most common operational scenarios for unmanned aerial vehicles (UAVs) are in open environments. While this ensures safety, it also presents challenges such as poor navigation practicality, insufficient adaptability to different scenarios, and limitations on the types of tasks that can be performed. Therefore, navigating in narrow waterways is a navigation scenario that UAVs must face, which places high demands on their path planning capabilities.

[0118] This application embodiment uses a graph search method for global path planning. Even in complex scenarios like narrow waterways, it not only ensures a safe and reliable navigation path but also provides a relatively optimal navigation distance. Furthermore, the use of grid map layering and multi-threaded parallel processing techniques guarantees both planning accuracy and system real-time performance.

[0119] In practical applications, high-resolution raster maps contain more and more detailed map information than low-resolution raster maps. However, introducing more map information inevitably leads to redundant map data. While this improves the accuracy of global path planning, it also affects the real-time performance of global path planning and places higher demands on the system's computing power, thus reducing the system's economic efficiency.

[0120] In the scenario described in this application, the layering technology of the raster map can extract redundant map information to a certain extent. The iterative optimization approach to path planning can gradually improve the accuracy of the global path planning results, thereby ensuring security. The use of multi-threaded parallel technology can also ensure the real-time performance of global path planning. Finally, the segmented planning and stitching optimization scheme can ensure the integrity of the planning results.

[0121] Based on the path planning method of this application embodiment, the unmanned watercraft 11 can obtain a safe, reliable, complete, detailed and accurate global path in a timely manner in a high-resolution raster map, ensuring the autonomous navigation capability of the unmanned watercraft 11.

[0122] See Figure 3 As shown, this application provides a flowchart of another path planning method. Figure 3 As shown, the path planning method of this application embodiment includes the following steps:

[0123] Step 1A: Obtain a high-resolution original raster map that includes static obstacles but does not include dynamic obstacles.

[0124] Step 2A: Based on multi-threaded parallel technology, the high-resolution original raster map is divided into several raster maps of different resolutions and sizes but consistent scales for use.

[0125] The resolutions should be divided from coarse to fine, including: coarse raster map to be used, slightly coarse raster map to be used, and fine raster map to be used.

[0126] Step 3A: Based on multi-threaded parallel technology, filter and screen the obstacle information contained in several grid maps to be used, and perform erosion processing on several grid maps to be used.

[0127] Optionally, the filtering criteria can be based on the size of the obstacle, filtering out obstacles whose size is smaller than a preset threshold.

[0128] Optionally, the etching process can be categorized based on resolution. The size of the etched obstacle can be reduced to half its original size.

[0129] Step 4A: Based on multi-threaded parallel technology, path planning is performed sequentially on each grid map to be used by capturing the first sub-grid map.

[0130] Based on the distance between every two path points, several smaller first sub-grid maps are extracted from the raster map to be used.

[0131] Step 5A: Perform path planning on the original raster map to obtain global path information.

[0132] This application embodiment is based on multi-threaded parallel technology, combining sub-grid maps and path points used when mining sub-grid maps to perform path planning, from coarse to fine, and finally complete global path planning.

[0133] See Figure 4 As shown, this application provides a flowchart of yet another path planning method. Figure 4 As shown, the path planning method of this application embodiment includes the following steps:

[0134] Step 1B: Using preset path information, obtain a rough first sub-grid map from the rough raster map to be used.

[0135] Step 2B: Combine the preset path information and the rough first sub-grid map to perform rough path planning and obtain rough sub-path information (including a new rough series of waypoints). This step uses a separate thread.

[0136] Step 3B: Based on the coarse sub-path information obtained in Step 2, extract two path points in sequence and obtain the first slightly coarser sub-grid map from the slightly coarser raster map to be used. This step does not need to wait for Step 2B to complete all planning; it only needs that the coarse sub-path information in Step 2B contains two or more path points.

[0137] Step 4B: Combine the coarse sub-path information and the slightly coarser first sub-grid map to perform slightly coarser path planning and obtain slightly coarser sub-path information (including new slightly coarser series of waypoints, i.e. intermediate path information). This step uses a separate thread.

[0138] Step 5B: Based on the slightly coarser sub-path information obtained in Step 4B, extract two path points in sequence and obtain a fine second sub-grid map from the fine original grid map. This step does not require waiting for Step 4B to complete all planning; it only requires that the slightly coarser sub-path information in Step 4B contains two or more path points.

[0139] Step 6B: Combine the slightly coarser sub-path information with the finer second sub-grid map to perform fine path planning and obtain a new series of fine path points, i.e., multiple target path points. This step uses a separate thread.

[0140] Step 7B: There is no need to wait for Step 6B to complete all the planning. As long as the detailed target path point information in Step 6B contains three or more path points, path splicing and smoothing can begin. This step uses a separate thread.

[0141] Step 8B: After step 7B completes the splicing and smoothing of all target path points, the global path planning ends.

[0142] In practical applications, the division of raster maps is not necessarily done in a coarse, slightly coarse, or fine manner; the division strategy can be adjusted according to the actual situation.

[0143] See Figure 5 As shown, this application provides a schematic diagram of the structure of a path planning device 50. Figure 5 As shown, the path planning device 50 includes: a hierarchical processing module 501, a first path planning module 502, and a second path planning module 503.

[0144] The layering processing module 501 is used to obtain the original raster map, perform layering processing on the original raster map, and obtain at least two raster maps to be used with different resolutions; wherein, the original raster map includes obstacles, and the resolution of the original raster map is greater than the resolution of each raster map to be used.

[0145] The first path planning module 502 is used to perform path planning on at least two grid maps to be used based on preset path information to obtain intermediate path information; wherein, the preset path information includes the target start point and the target end point, and the intermediate path information includes multiple path points, and the line connecting any two path points does not intersect with obstacles.

[0146] The second path planning module 503 is used to perform path planning on the original raster map based on intermediate path information to obtain global path information. Specifically, it performs layered processing on the original raster map and / or path planning on at least two raster maps to be used, employing a parallel processing method with at least two threads.

[0147] Optionally, the layering processing module 501 is used to process in parallel with at least two threads, dividing the original raster map into at least two raster maps to be processed with different resolutions according to a preset layering strategy; and using at least two threads to process in parallel, preprocessing the obstacles in each raster map to be processed to obtain each raster map to be used.

[0148] Optionally, the layered processing module 501 is used to filter obstacles based on their size in each grid map to obtain each filtered grid map to be processed; and to perform erosion processing on the obstacles in each filtered grid map to reduce their size, thereby obtaining each grid map to be used.

[0149] Optionally, the first path planning module 502 is used to sort the raster maps to be used in ascending order of resolution;

[0150] The first path planning operation is performed on each grid map to be used by using at least two threads in parallel until the sub-path information of the last grid map to be used is used as the intermediate path information.

[0151] The first path planning operation includes:

[0152] According to the preset path planning rules, the initial path information is determined; wherein, the path planning rules include: using the preset path information as the initial path information of the first grid map to be used, and using the sub-path information of the previous grid map to be used as the initial path information of the next grid map to be used.

[0153] Based on the initial path information, path planning is performed on the raster map to be used to obtain the sub-path information of the raster map to be used; wherein, the sub-path information includes at least two path points.

[0154] Optionally, the first path planning module 502 is used to extract two path points sequentially from the initial path information, and take each pair of path points as a group of path points; based on each group of path points, perform path planning in the grid map to be used to obtain the sub-path information of the grid map to be used.

[0155] Optionally, the first path planning module 502 is used to perform screenshot processing on the raster map to be used based on each set of path points to obtain a first sub-raster map; and to perform path planning on the first sub-raster map based on each set of path points using a graph search method to obtain sub-path information of the raster map to be used.

[0156] Optionally, the second path planning module 503 is used to perform path planning on the original raster map based on intermediate path information to obtain multiple target path points; and to perform stitching and smoothing processing based on the multiple target path points to obtain global path information.

[0157] Optionally, the second path planning module 503 is used to extract two path points sequentially from the intermediate path information, and take each pair of path points as a group of path points; based on each group of path points, perform screenshot processing on the original raster map to obtain a second sub-raster map; and use a graph search method to perform path planning on the second sub-raster map based on each group of path points to obtain multiple target path points.

[0158] In applications, the modules in the path planning device 50 can be software program modules, or they can be implemented through different logic circuits integrated in the processor, or they can be implemented through multiple distributed processors.

[0159] The path planning device 50 of this application embodiment can execute the method provided in this application embodiment. The implementation principle is similar. The actions performed by each module in the path planning device 50 of each embodiment of this application correspond to the steps in the method of each embodiment of this application. For detailed functional descriptions of each module of the path planning device 50, please refer to the descriptions in the corresponding methods shown above, which will not be repeated here.

[0160] See Figure 6 As shown, this application provides a schematic diagram of the structure of an electronic device 6. Figure 6 As shown, the electronic device 6 of this application embodiment includes: a memory 61, a processor 60, and a computer program 62 stored in the memory 61 and executable on the processor 60. When the processor 60 executes the computer program, it implements the steps of the methods of the various embodiments of this application.

[0161] Electronic device 6 can be a desktop computer, laptop, handheld computer, or cloud server, etc., and can also be installed inside unmanned surface vessel 11. Electronic device 6 may include, but is not limited to, processor 60 and memory 61. Those skilled in the art will understand that... Figure 6 This is merely an example of electronic device 6 and does not constitute a limitation on electronic device 6. It may include more or fewer components than shown, or combine certain components, or different components, such as input / output devices, network access devices, etc.

[0162] The processor 60 can be a Central Processing Unit (CPU), but it can also be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or any conventional processor.

[0163] In some embodiments, memory 61 may be an internal storage unit, such as a hard disk or RAM. Memory 61 may be a removable / non-removable, volatile / non-volatile computer system storage medium; for example, memory 61 may be a non-volatile memory used for reading and writing non-volatile magnetic media. In other embodiments, memory 61 may also be an external storage device, such as a plug-in hard disk, Smart Media Card (SMC), Secure Digital (SD) card, or Flash Card equipped on electronic device 6. Memory 61 is used to store operating systems, applications, bootloaders, data, and other programs, such as program code for computer programs. Memory 61 may also be used to temporarily store data that has been output or will be output.

[0164] It should be noted that the information interaction and execution process between the above-mentioned devices / units are based on the same concept as the method embodiments of this application. For details on their specific functions and technical effects, please refer to the method embodiments section, and they will not be repeated here.

[0165] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described division of functional units and modules is merely an example. In practical applications, the above functions can be assigned to different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiments can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit. Furthermore, the specific names of the functional units and modules are only for easy differentiation and are not intended to limit the scope of protection of this application. The specific working process of the units and modules in the above system can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0166] This application also provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the steps in the above-described method embodiments.

[0167] If the integrated units described above are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include at least: any entity or device capable of carrying computer program code to a device / terminal equipment, a recording medium, a computer memory, a read-only memory (ROM), a random access memory (RAM), an electrical carrier signal, a telecommunication signal, and a software distribution medium. Examples include USB flash drives, portable hard drives, magnetic disks, or optical disks.

[0168] Those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware. The program can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above methods. 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 can also include combinations of the above types of memory.

[0169] This application provides a computer program product that, when run on a processor, enables the processor to execute the steps described in the various method embodiments above.

[0170] In the above embodiments, the descriptions of each embodiment have different focuses. For parts that are not described in detail or recorded in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0171] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0172] In the embodiments provided in this application, it should be understood that the disclosed apparatus / network devices and methods can be implemented in other ways. For example, the apparatus / network device embodiments described above are merely illustrative. For instance, the division of modules or units described above is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between devices or units may be electrical, mechanical, or other forms.

[0173] The units described above as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0174] The above embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application, and should all be included within the protection scope of this application.

Claims

1. A path planning method, characterized in that, include: Obtain an original raster map, perform layering processing on the original raster map to obtain at least two raster maps of different resolutions to be used; wherein, the original raster map includes obstacles, and the resolution of the original raster map is greater than the resolution of each of the raster maps to be used; Based on preset path information, path planning is performed on at least two grid maps to be used to obtain intermediate path information; wherein, the preset path information includes a target start point and a target end point, and the intermediate path information includes multiple path points, and the line connecting any two path points does not intersect the obstacle; Based on the intermediate path information, path planning is performed on the original grid map to obtain global path information; The process of performing layered processing on the original raster map and / or path planning on at least two raster maps to be used is carried out in parallel using at least two threads.

2. The path planning method according to claim 1, characterized in that, The original raster map is layered to obtain at least two raster maps of different resolutions to be used, including: The original raster map is divided into at least two raster maps with different resolutions according to a preset layering strategy, using at least two threads in parallel processing. The obstacles in each of the grid maps to be processed are preprocessed by using at least two threads in parallel to obtain each of the grid maps to be used.

3. The path planning method according to claim 2, characterized in that, The obstacles in each of the grid maps to be processed are preprocessed to obtain each of the grid maps to be used, including: Based on the size of the obstacles in each of the grid maps to be processed, the obstacles are filtered to obtain each filtered grid map to be processed. The obstacles in the filtered raster maps to be processed are subjected to erosion processing to reduce their size, thereby obtaining the raster maps to be used.

4. The path planning method according to claim 1, characterized in that, Based on preset path information, path planning is performed on at least two of the grid maps to be used to obtain intermediate path information, including: Sort the raster maps to be used in ascending order of resolution; The first path planning operation is performed on each of the grid maps to be used by using at least two threads in parallel, until the sub-path information of the last grid map to be used is used as the intermediate path information. The first path planning operation includes: According to the preset path planning rules, the initial path information is determined; wherein, the path planning rules include: using the preset path information as the initial path information of the first grid map to be used, and using the sub-path information of the previous grid map to be used as the initial path information of the next grid map to be used. Based on the initial path information, path planning is performed on the grid map to be used to obtain the sub-path information of the grid map to be used; wherein, the sub-path information includes at least two path points.

5. The path planning method according to claim 4, characterized in that, The step of performing path planning on the raster map to be used based on the initial path information to obtain the sub-path information of the raster map to be used includes: Two path points are sequentially extracted from the initial path information, and each pair of path points is taken as a group of path points. Based on each set of path points, path planning is performed in the raster map to be used to obtain the sub-path information of the raster map to be used.

6. The path planning method according to claim 5, characterized in that, Based on each set of waypoints, path planning is performed in the raster map to be used to obtain sub-path information of the raster map to be used, including: Based on each set of path points, the raster map to be used is captured to obtain the first sub-raster map; Using a graph search method, based on each set of path points, path planning is performed in the first sub-grid map to obtain the sub-path information of the grid map to be used.

7. The path planning method according to any one of claims 1-6, characterized in that, The step of performing path planning on the original raster map based on the intermediate path information to obtain global path information includes: Based on the intermediate path information, path planning is performed on the original grid map to obtain multiple target path points; Global path information is obtained by splicing and smoothing multiple target path points.

8. The path planning method according to claim 7, characterized in that, Based on the intermediate path information, path planning is performed on the original raster map to obtain multiple target path points, including: Two path points are extracted sequentially from the intermediate path information, and each pair of path points is taken as a group of path points. Based on each set of path points, the original raster map is cropped to obtain a second sub-raster map; Using a graph search method, based on each set of path points, path planning is performed in the second sub-grid map to obtain multiple target path points.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the method as described in any one of claims 1 to 8.

10. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method as described in any one of claims 1 to 8.

Images