Mesh-based UAV route planning methods, systems, equipment, and media
By constructing a mesh graph and defining a set of policy primitives, static spatial attributes and temporary dynamic constraints are quantified as passage costs, which solves the problem that existing technologies fail to effectively balance multi-dimensional attributes and slow dynamic event response, and enables rapid optimization of UAV route planning.
Patent Information
- Application Number
- CN202611585029.X
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2026-10-14
- Publication Date
- 2026-11-10
AI Technical Summary
Existing raster map-based UAV route planning methods fail to effectively take into account multiple attributes such as airspace type, terrain elevation, and sensitive targets, and are slow to respond to dynamic events such as temporary traffic control and conflicts.
A mesh graph-based UAV route planning method is adopted. By constructing a mesh graph with a pure attribute storage architecture, a set of policy primitives is defined, and static spatial attributes and temporary dynamic constraints are uniformly quantified as passage costs. Policy semantic tags are used to regulate search behavior, enabling rapid response to multi-dimensional static constraints and dynamic events.
It achieves the ability to quickly respond to dynamic events such as temporary controls and conflicts while taking into account multidimensional static constraints, and generate optimized route plans.
Smart Images

Figure CN123065481A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of low-altitude flight path planning technology, and more specifically to a method, system, device, and medium for UAV flight path planning based on a grid map. Background Technology
[0002] With the rapid development of the low-altitude economy and the large-scale application of urban air traffic, the flight density and operational complexity of low-altitude airspace continue to rise, placing higher demands on the precision and automation of low-altitude route delineation and flight path planning. Unlike traditional civil aviation, the urban low-altitude flight environment is characterized by dense obstacles, complex airspace structure, variable weather conditions, and numerous sensitive ground targets. Route planning not only needs to consider the performance constraints of the aircraft itself, but also needs to take into account multiple factors such as airspace safety, ground personnel and property safety, noise impact, and corridor utilization.
[0003] Currently, a common technical solution is UAV route planning based on grid maps. This type of method discretizes a continuous space into a regular grid, and performs A / B navigation on the grid. Alternatively, Dijkstra's algorithm can be used for pathfinding. However, the grid only represents binary information about obstacle occupancy and does not incorporate multi-dimensional attributes such as airspace type, terrain elevation, sensitive targets, and underlying surface into a unified cost model. The planned route cannot take into account both airspace control and avoidance of sensitive ground areas, and it requires a complete recalculation in the face of emergencies such as temporary control or conflicts, resulting in a slow response. Summary of the Invention
[0004] The purpose of this invention is to provide a method, system, device, and medium for UAV route planning based on a grid graph, which realizes route planning that takes into account both multi-dimensional static constraints and rapid response to dynamic events.
[0005] To achieve the above objectives, embodiments of the present invention provide a UAV route planning method based on a grid graph, comprising: Construct a mesh graph and define a set of policy primitives; wherein the mesh graph adopts a pure attribute storage architecture, and each mesh cell contains static spatial attribute information; the policy primitives include policy type identifiers, scope description parameters, and policy semantic tags; Obtain a route planning task containing a start point, an end point, and at least one policy primitive instance; map the scope description parameters to the corresponding set of grid cells in the grid graph; and convert the policy semantic labels into temporary dynamic constraint attributes and associate them with the corresponding set of grid cells. Traverse each grid cell in the search space, read the static spatial attribute information and associated temporary dynamic constraint attributes of each grid cell, and convert them into passage cost according to the preset cost quantization rules; Heuristic path search is performed based on the grid topology relationship of the search space. During the search process, the cost is accumulated according to the passage cost of the grid cell, heuristic estimation is performed based on the spatial distance, and the expansion conditions of the corresponding grid cell are adjusted according to the policy semantic label to generate the optimal grid cell sequence. The optimal grid cell sequence is restored to a geographic coordinate sequence to generate the target route.
[0006] Optionally, the process of constructing the mesh diagram includes: The target spatial domain is recursively divided into multi-level grid cells according to the preset spatial subdivision hierarchy. Each grid cell is assigned a spatial code; and the static spatial attribute information is configured, wherein the static spatial attribute information includes at least the airspace type identifier, terrain elevation value, obstacle type and height, land cover type and sensitive target identifier; Calculate the neighborhood relationship of each grid cell, wherein the neighborhood relationship includes planar neighborhood relationships within the same height layer and vertical neighborhood relationships between different height layers; The grid diagram is generated by fusing each grid cell with its corresponding spatial code, static spatial attribute information, and neighborhood relationship.
[0007] Optionally, the set of policy primitives includes at least: The prohibition policy has a policy semantic label indicating that the corresponding set of grid cells is prohibited from passing. The temporary dynamic constraint attribute includes a prohibition flag. In the heuristic path search, grid cells associated with the prohibition flag are excluded from the search space. The avoidance strategy, whose strategy semantic label indicates that the corresponding set of grid cells suggests detours but does not forcibly prohibit them, the temporary dynamic constraint attribute includes an avoidance level parameter, and the heuristic path search adds an avoidance offset to the sorting key value of the corresponding grid cell according to the avoidance level parameter; The preference strategy, whose policy semantic label indicates the priority selection of the corresponding set of grid cells, includes a preference weight parameter in the temporary dynamic constraint attribute. In the heuristic path search, a preference offset is added to the sorting key value of the corresponding grid cell according to the preference weight parameter, wherein the preference offset is a negative value. The slowdown strategy, whose strategy semantic label indicates that the corresponding set of grid cells should reduce the passage speed or increase the passage interval, includes a slowdown coefficient in the temporary dynamic constraint attribute, and the heuristic path search adds a slowdown offset to the time cost of passing through the grid cell according to the slowdown coefficient.
[0008] Optionally, the static spatial attribute information and the temporary dynamic constraint attributes are converted into passage costs according to a preset cost quantification rule, including: Each attribute item in the static spatial attribute information is mapped to a basic cost component, wherein the basic cost component includes at least a hard constraint cost component, a penalty cost component, and a preference cost component; wherein the mesh cell corresponding to the hard constraint cost component is marked as impassable, the penalty cost component is positive, and the preference cost component is negative. The temporary dynamic constraint attributes are mapped to dynamic cost correction amounts according to the policy type to which their policy semantic labels belong. The passage cost is obtained by weighted summation of the basic cost component and the dynamic cost correction.
[0009] Optionally, the passage cost is calculated using the following formula:
[0010]
[0011]
[0012] In the formula, For grid cells The cost of passage This is the basic cost obtained by mapping based on the static spatial attribute information. This is the dynamic correction amount obtained based on the mapping of the temporary dynamic constraint attributes. w is the cost component corresponding to the i-th static attribute item. i The weight coefficient corresponding to the i-th static attribute item. For temporary restriction type fields, For the spatiotemporal conflict marker field, For wind speed field, For wind direction field, For the precipitation field, For visibility field; For temporary constraint cost function, For the cost function of spatiotemporal conflict, For meteorological composite cost function; , , These are the corresponding weighting coefficients.
[0013] Optionally, during the search process, the cumulative cost G(n) from the starting grid to the current grid is calculated using the following recursive formula:
[0014] in, This represents the cumulative cost from the starting grid to the current grid m, where m is the parent grid of the current grid n during the current search expansion process. Let C(n) be the spatial distance between grid m and grid n, and let C(n) be the passage cost of grid n. Let n be the change in heading angle from grid m to grid n. Let α be the height change from grid m to grid n, β be the turning penalty coefficient, and β be the climb or descent penalty coefficient.
[0015] Optionally, the UAV route planning method based on grid graphs further includes: When a dynamic event is detected, a new policy primitive instance is generated based on the type and scope of the dynamic event; Update the temporary dynamic constraint attributes associated with the corresponding grid cell based on the new strategy primitive instance, and while keeping the static spatial attribute information of the grid graph unchanged, re-execute the steps of traversing the search space, converting to passage cost and heuristic path search based on the updated temporary dynamic constraint attributes to generate the updated target route.
[0016] Secondly, the present invention also provides a UAV route planning system based on a grid graph, comprising: A mesh graph construction module is used to construct a mesh graph and define a set of policy primitives; wherein, the mesh graph adopts a pure attribute storage architecture, and each mesh cell contains static spatial attribute information; the policy primitives include policy type identifiers, scope description parameters, and policy semantic tags; The task acquisition module is used to acquire a route planning task containing a start point, an end point, and at least one instance of a policy primitive, map the scope description parameters to the corresponding set of grid cells in the grid diagram, and convert the policy semantic tags into temporary dynamic constraint attributes and associate them with the corresponding set of grid cells. The attribute mapping module is used to traverse each grid cell in the search space, read the static spatial attribute information and associated temporary dynamic constraint attributes of each grid cell, and convert them into passage costs according to preset cost quantization rules. The cost mapping module is used to perform heuristic path search based on the grid topology relationship of the search space. During the search process, the cost is accumulated according to the passage cost of the grid cell, heuristically estimated according to the spatial distance, and the expansion conditions of the corresponding grid cell are adjusted according to the policy semantic label to generate the optimal grid cell sequence. The path generation module is used to restore the optimal grid cell sequence to a geographic coordinate sequence and generate the target route.
[0017] Thirdly, the present invention also 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 program to implement the steps of the above-described mesh-based UAV route planning method.
[0018] Fourthly, the present invention also provides a storage medium storing a computer program thereon, which, when executed by a processor, implements the steps of the above-described mesh-based UAV route planning method.
[0019] By constructing a grid graph with pure attribute storage and a dynamic constraint injection mechanism driven by policy primitives, static spatial attribute information and temporary dynamic constraint attributes are uniformly quantified into passage costs for participation in the search. Furthermore, the search behavior is regulated by policy semantic tags, enabling route planning to quickly respond to dynamic events such as temporary control and conflicts while integrating multi-dimensional static attributes such as airspace type, terrain elevation, and sensitive targets.
[0020] Other features and advantages of the embodiments of the present invention will be described in detail in the following detailed description section. Attached Figure Description
[0021] The accompanying drawings are provided to further illustrate embodiments of the present invention and form part of the specification. They are used together with the following detailed description to explain the embodiments of the present invention, but do not constitute a limitation thereof. In the drawings: Figure 1 This is a flowchart of a UAV route planning method based on a grid graph provided in an embodiment of the present invention; Figure 2 This is a detailed flowchart of a UAV route planning method based on a grid graph provided in an embodiment of the present invention; Figure 3 This is a schematic diagram of the structure of a UAV route planning system based on a grid graph provided in an embodiment of the present invention; Figure 4 This is a schematic diagram of the hardware structure of a terminal provided in an embodiment of the present invention. Detailed Implementation
[0022] Various embodiments of this disclosure will be described more fully in the following detailed description. This disclosure may have various embodiments, and adjustments and changes may be made therein. However, it should be understood that there is no intention to limit the various embodiments of this disclosure to the specific embodiments disclosed herein, but rather this disclosure should be understood to cover all adjustments, equivalents, and / or alternatives falling within the spirit and scope of the various embodiments of this disclosure.
[0023] In the following, the terms “comprising” or “may include”, which may be used in various embodiments of this disclosure, indicate the presence of the disclosed functions or operations and do not limit the addition of one or more functions or operations. Furthermore, as used in various embodiments of this disclosure, the terms “comprising,” “having,” and their cognates are intended only to indicate a specific feature, number, step, operation, or combination of the foregoing and should not be construed as primarily excluding the presence of one or more other features, numbers, steps, operations, or combinations of the foregoing, or the possibility of adding one or more features, numbers, steps, operations, or combinations of the foregoing.
[0024] In various embodiments of this disclosure, the expression "or" or "at least one of A and / or B" includes any combination or all combinations of the words listed simultaneously. For example, the expression "A or B" or "at least one of A and / or B" may include A, may include B, or may include both A and B.
[0025] 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, and 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.
[0026] See Figure 1 The diagram shows a flowchart of a UAV route planning method based on a grid graph in a specific embodiment, including the following execution steps: Step 100: Construct a mesh graph and define a set of policy primitives.
[0027] The mesh graph adopts a pure attribute storage architecture, and each mesh cell contains static spatial attribute information; the policy primitives include policy type identifiers, scope description parameters, and policy semantic tags.
[0028] Specifically, when constructing the mesh diagram in step 100, the following steps can be performed: S1000: Recursively divides the target spatial domain into multi-level grid cells according to the preset spatial subdivision hierarchy.
[0029] S1001: Assign a spatial code to each grid cell; and configure the static spatial attribute information.
[0030] The static spatial attribute information includes at least the airspace type identifier, terrain elevation value, obstacle type and height, land cover type and sensitive target identifier.
[0031] S1002: Calculate the neighborhood relationship of each grid cell.
[0032] The neighborhood relationships include planar neighborhood relationships within the same height layer and vertical neighborhood relationships between different height layers.
[0033] S1003: The grid diagram is generated by fusing each grid cell and its corresponding spatial code, static spatial attribute information and neighborhood relationship.
[0034] Specifically, the set of policy primitives includes at least the following four types: The prohibition policy has a policy semantic label indicating that the corresponding set of grid cells is prohibited from passing. The temporary dynamic constraint attribute includes a prohibition flag. In the heuristic path search, grid cells associated with the prohibition flag are excluded from the search space. The avoidance strategy, whose strategy semantic label indicates that the corresponding set of grid cells suggests detours but does not forcibly prohibit them, the temporary dynamic constraint attribute includes an avoidance level parameter, and the heuristic path search adds an avoidance offset to the sorting key value of the corresponding grid cell according to the avoidance level parameter; The preference strategy, whose policy semantic label indicates the priority selection of the corresponding set of grid cells, includes a preference weight parameter in the temporary dynamic constraint attribute. In the heuristic path search, a preference offset is added to the sorting key value of the corresponding grid cell according to the preference weight parameter, wherein the preference offset is a negative value. The slowdown strategy, whose strategy semantic label indicates that the corresponding set of grid cells should reduce the passage speed or increase the passage interval, includes a slowdown coefficient in the temporary dynamic constraint attribute, and the heuristic path search adds a slowdown offset to the time cost of passing through the grid cell according to the slowdown coefficient.
[0035] Step 101: Obtain a route planning task containing a start point, an end point, and at least one policy primitive instance; map the scope description parameters to the corresponding set of grid cells in the grid graph; and convert the policy semantic labels into temporary dynamic constraint attributes and associate them with the corresponding set of grid cells.
[0036] Specifically, the upper-level decision-making system submits a route planning request, inputting a waypoint sequence, a route altitude range, and at least one policy primitive instance. The policy primitive instance is generated based on dynamic events, and each policy primitive instance contains a policy type identifier, a scope description parameter, and a policy semantic tag.
[0037] The initial search boundary is determined based on the starting and ending points of the route planning task, and the extreme values of waypoint latitude and longitude are calculated. The correspondence between latitude and longitude and distance is converted using the center latitude, and the boundary is expanded outwards by a preset distance to obtain the search boundary. Grid cells whose spatial codes fall within the search boundary are selected from the grid map to form the search space. The BeiDou grid code relies on the Earth subdivision theory to divide the Earth's space into multi-scale grids, each with a unique code. In this embodiment, an 8-meter resolution grid level is used as the basic spatial unit for route finding.
[0038] The scope description parameters of the policy primitive instances are mapped to the corresponding set of grid cells in the mesh graph. Specifically, the polygonal boundaries or rectangular bounding boxes of the temporary control areas are converted into mesh space encoding ranges, and the affected set of grid cells is located by matching the mesh encoding.
[0039] The policy semantic labels are converted into temporary dynamic constraint attributes and then associated with the corresponding set of mesh cells. The temporary dynamic constraint attribute is a mapping table {geoNum: {rs, cf, ws, wd, pr, vs}} with mesh codes as keys. For example: Temporary airspace control events: Mapping the polygonal boundaries of the controlled area to a set of grid codes, policy semantic labels. Convert to Associated with the corresponding grid cell; Flight plan spatiotemporal conflict events: Map the route grid occupied by the approved flight plan to cf=1 and associate it with the corresponding conflict grid cell; Severe weather events: Meteorological forecast data is converted into corresponding temporary attribute field values and associated with the set of grid cells affected by the weather.
[0040] Step 102: Traverse each grid cell in the search space, read the static spatial attribute information and associated temporary dynamic constraint attributes of each grid cell, and convert them into passage cost according to the preset cost quantization rules.
[0041] Specifically, the search space is obtained in the following way: an initial search boundary is determined based on the start and end points of the route planning task; based on the initial search boundary, the search boundary is expanded in all directions according to a preset outward expansion distance to obtain an expanded search boundary; the grid cells located within the expanded search boundary are extracted to form the search space.
[0042] Specifically, in step 102, when converting the static spatial attribute information and the temporary dynamic constraint attribute into passage cost according to the preset cost quantification rule, the following steps can be performed: S1020: Map each attribute item in the static spatial attribute information to a basic cost component.
[0043] The basic cost components include at least a hard constraint cost component, a penalty cost component, and a preference cost component; wherein the grid cells corresponding to the hard constraint cost component are marked as impassable, the penalty cost component is positive, and the preference cost component is negative.
[0044] S1021: Map the temporary dynamic constraint attribute to a dynamic cost correction amount according to the policy type to which its policy semantic label belongs.
[0045] S1022: The basic cost component and the dynamic cost correction amount are weighted and summed to obtain the passage cost.
[0046] Specifically, the passage cost is calculated using the following formula:
[0047]
[0048]
[0049] In the formula, For grid cells The cost of passage This is the basic cost obtained by mapping based on the static spatial attribute information. This is the dynamic correction amount obtained based on the mapping of the temporary dynamic constraint attributes. w is the cost component corresponding to the i-th static attribute item. i The weight coefficient corresponding to the i-th static attribute item. For temporary restriction type fields, For the spatiotemporal conflict marker field, For wind speed field, For wind direction field, For the precipitation field, For visibility field; For temporary constraint cost function, For the cost function of spatiotemporal conflict, For meteorological composite cost function; , , These are the corresponding weighting coefficients.
[0050] Furthermore, the weighted effective cost includes the following terms:
[0051] A grid with an infinite cost is marked as impassable.
[0052] Combined meteorological costs:
[0053] Among them, the wind speed cost is graded according to wind speed and superimposed with crosswind component. Additional penalties for exceeding thresholds: precipitation costs are tiered by 5-minute precipitation amounts, and visibility costs are tiered by visibility levels.
[0054] Step 103: Perform heuristic path search based on the grid topology relationship of the search space. During the search process, the cost is accumulated according to the passage cost of the grid cell, heuristic estimation is performed according to the spatial distance, the expansion conditions of the corresponding grid cell are adjusted according to the policy semantic label, and the optimal grid cell sequence is generated.
[0055] Specifically, during the search process, the grid closest to the starting waypoint is taken as the starting grid, and the grid closest to the ending waypoint is taken as the ending grid. A is then executed on the grid topology. Search. During the search process, the cost is accumulated based on the passage cost of the grid cells, heuristic estimation is performed based on spatial distance, and the expansion conditions of the corresponding grid cells are adjusted according to the policy semantic labels to generate the optimal grid cell sequence.
[0056] The core search formula is ,in, Integrating multi-dimensional costs, turning penalties, and climb / descent penalties, A three-dimensional Euclidean distance heuristic is used. The OpenList expands by minimizing the f-value, and for each non-null neighbor: skips the ClosedList, skips the cost-∞ grid, and verifies the turning angle. Update g / f / parent; if the two-dimensional search fails, try the upper / lower three-dimensional climbing or descending bypass.
[0057] During the search, when expanding to mesh cells with associated temporary dynamic constraint attributes, the expansion conditions or priority of that mesh cell are adjusted according to the policy semantic label corresponding to that temporary dynamic constraint attribute. After the search, the optimal mesh cell sequence consisting of the expanded mesh cells is output. A Ensure the optimal path is taken when the heuristic is acceptable.
[0058] The weighted effective cost of searching each grid within the chessboard. Calculate and cache all at once; A When searching for an expanded node, the pre-calculated value is read directly using the g-value increment formula.
[0059] In a preferred embodiment of the present invention, the cumulative cost G(n) from the starting grid to the current grid is calculated using the following recursive formula:
[0060] in, This represents the cumulative cost from the starting grid to the current grid m, where m is the parent grid of the current grid n during the current search expansion process. Let C(n) be the spatial distance between grid m and grid n, and let C(n) be the passage cost of grid n. Let n be the change in heading angle from grid m to grid n. Let α be the height change from grid m to grid n, β be the turning penalty coefficient, and β be the climb or descent penalty coefficient.
[0061] Step 104: Restore the optimal grid cell sequence to a geographic coordinate sequence to generate the target route.
[0062] Specifically, A The output grid code sequence is processed by reading the latitude and longitude of each grid center point, assigning suggested flight altitudes, and marking waypoint types, resulting in a list of latitude and longitude waypoints containing serial numbers, latitude and longitude, altitudes, and waypoint types. The grid code sequence is then converted back into a list of latitude and longitude waypoints usable by the flight control system.
[0063] For latitude and longitude waypoint sequences, perform Douglas-Peucker thinning to remove collinear redundant waypoints; for turning angles > Waypoints are replaced with smooth transitions using circular interpolation; after smoothing, they are remapped back to the costless grids in the grid verification sequence; finally, the route is split into segments according to turning points, each segment is assigned a width and height range, and the smoothed final route is output.
[0064] In one specific embodiment, the UAV route planning method based on a grid graph further includes: When a dynamic event is detected, a new policy primitive instance is generated based on the type and scope of the dynamic event; Update the temporary dynamic constraint attributes associated with the corresponding grid cell based on the new strategy primitive instance, and while keeping the static spatial attribute information of the grid graph unchanged, re-execute the steps of traversing the search space, converting to passage cost and heuristic path search based on the updated temporary dynamic constraint attributes to generate the updated target route.
[0065] In this embodiment, by using a pure attribute storage grid graph and a dynamic injection mechanism driven by policy primitives, static spatial attributes and temporary dynamic constraints are uniformly quantified into passage costs, and policy semantic tags directly regulate search expansion behavior, thereby realizing scalable route planning under multi-dimensional constraint fusion and rapid replanning driven by dynamic events.
[0066] In one embodiment, Figure 2This is a detailed flowchart of a UAV route planning method based on a grid graph according to an embodiment of the present invention. This embodiment is further optimized and expanded based on the above embodiments.
[0067] S200: The target spatial domain is recursively divided into multi-level grid cells according to the preset spatial partitioning hierarchy. Each grid cell is assigned a unique spatial code, static spatial attribute information is configured and neighborhood relationships are calculated. The grid cells are then merged to generate a grid graph and a set of policy primitives is defined.
[0068] S201: Obtain a route planning task containing a start point, an end point, and at least one policy primitive instance; determine the initial search boundary based on the start point and the end point, expand it outward, and extract the grid cells located within the boundary to form the search space; map the policy primitive instances to the corresponding set of grid cells in the grid graph, and convert the policy semantic labels into temporary dynamic constraint attributes and associate them with the corresponding grid cells.
[0069] S202: Traverse the search space and read the static spatial attribute information of the current grid cell; if there is a temporary dynamic constraint attribute, read the temporary dynamic constraint attribute.
[0070] S203: Map static spatial attribute information to basic cost components, map temporary dynamic constraint attributes to dynamic cost corrections, and sum them by weight to obtain the passage cost; if there are hard constraint cost components, mark the current grid cell as impassable.
[0071] S204: Determine if there are any unprocessed grid cells in the search space. If so, return to S202 to retrieve the next grid cell; otherwise, execute S205.
[0072] S205: Initialize the open list and closed list using the grid closest to the starting point as the starting grid and the grid closest to the ending point as the ending grid, and add the starting grid to the open list.
[0073] S206: Determine if the open list is empty. If it is, the search fails and outputs "No available routes". Otherwise, execute S207.
[0074] S207: Remove the grid with the lowest cost estimate from the open list as the current expanded grid and move it into the closed list.
[0075] S208: Determine if the current extended mesh is the endpoint mesh. If yes, jump to S215; otherwise, execute S209.
[0076] S209: Obtain all neighboring grids of the current extended grid, and determine whether the current neighboring grids meet all the extension conditions. If so, execute S210; otherwise, jump to S213.
[0077] S210: Calculate the cumulative cost from the starting point through the current extended grid to the current neighboring grid, and make a heuristic estimate based on the spatial distance; if the current path is better than the existing path, update the parent node pointer and cumulative cost of the current neighboring grid.
[0078] S211: Determine whether the current neighboring grid is associated with an avoidance strategy, preference strategy, or slowdown strategy. If so, execute S212; otherwise, output "No available route".
[0079] S212: Adjust the sorting key or time cost of the neighbor grid according to the policy type, and add the current neighbor grid to the open list.
[0080] S213: Determine if there are any unprocessed neighboring grids. If yes, proceed to S214; otherwise, return to S206.
[0081] S214: Trace back the parent node pointer and output the optimal grid cell sequence; restore the optimal grid cell sequence to the geographic coordinate sequence, configure the flight altitude and mark the waypoint type.
[0082] S215: Perform polyline simplification and curve smoothing interpolation on the geographic coordinate sequence; remap the smoothed geographic coordinate sequence to the grid map.
[0083] S216: Verify whether the corresponding grid cell is passable. If the verification passes, proceed to S217. If the verification fails, mark the route segment that failed the verification and trigger local replanning, then return to S201.
[0084] S217: Output the smoothed geographic coordinate sequence as the target route.
[0085] like Figure 3 As shown, the following are embodiments of the UAV route planning system based on grid graphs provided in this disclosure. These embodiments belong to the same inventive concept as the UAV route planning methods based on grid graphs described above. For details not described in detail in the embodiments of the UAV route planning system based on grid graphs, please refer to the embodiments of the UAV route planning methods based on grid graphs described above.
[0086] A grid-based UAV route planning system includes: A mesh graph construction module is used to construct a mesh graph and define a set of policy primitives; wherein, the mesh graph adopts a pure attribute storage architecture, and each mesh cell contains static spatial attribute information; the policy primitives include policy type identifiers, scope description parameters, and policy semantic tags; The task acquisition module is used to acquire a route planning task containing a start point, an end point, and at least one instance of a policy primitive, map the scope description parameters to the corresponding set of grid cells in the grid diagram, and convert the policy semantic tags into temporary dynamic constraint attributes and associate them with the corresponding set of grid cells. The attribute mapping module is used to traverse each grid cell in the search space, read the static spatial attribute information and associated temporary dynamic constraint attributes of each grid cell, and convert them into passage costs according to preset cost quantization rules. The cost mapping module is used to perform heuristic path search based on the grid topology relationship of the search space. During the search process, the cost is accumulated according to the passage cost of the grid cell, heuristically estimated according to the spatial distance, and the expansion conditions of the corresponding grid cell are adjusted according to the policy semantic label to generate the optimal grid cell sequence. The path generation module is used to restore the optimal grid cell sequence to a geographic coordinate sequence and generate the target route.
[0087] Figure 4 This is a schematic diagram of the structure of a terminal 300 provided in an embodiment of the present invention. The terminal 300 can be used to execute the UAV route planning method based on grid graph provided in the embodiment of the present invention.
[0088] The terminal 300 may include a processor 310, a memory 320, and a communication module 330. These components communicate via one or more buses. Those skilled in the art will understand that the server structure shown in the figure does not constitute a limitation of the present invention. It may be a bus topology or a star topology, and may include more or fewer components than shown, or combine certain components, or have different component arrangements.
[0089] The memory 320 can be used to store the execution instructions of the processor 310. The memory 320 can be implemented by any type of volatile or non-volatile memory terminal or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk. When the execution instructions in the memory 320 are executed by the processor 310, the terminal 300 is able to perform some or all of the steps in the above method embodiments.
[0090] The processor 310 serves as the control center of the storage terminal, connecting various parts of the electronic terminal via various interfaces and lines. It executes software programs and / or modules stored in the memory 320, and calls data stored in the memory to perform various functions of the electronic terminal and / or process data. The processor can be composed of integrated circuits (ICs), such as a single packaged IC or multiple packaged ICs with the same or different functions connected together. For example, the processor 310 may consist only of a central processing unit (CPU). In this embodiment of the invention, the CPU may have a single processing core or include multiple processing cores.
[0091] The communication module 330 is used to establish a communication channel, enabling the storage terminal to communicate with other terminals. It receives user data sent by other terminals or sends user data to other terminals.
[0092] The present invention also provides a computer storage medium, wherein the computer storage medium may store a program, which, when executed, may include some or all of the steps provided in the embodiments of the present invention. The storage medium may be a magnetic disk, an optical disk, read-only memory (ROM), or random access memory (RAM), etc.
[0093] Those skilled in the art will clearly understand that the techniques in the embodiments of the present invention can be implemented using software plus necessary general-purpose hardware platforms. Based on this understanding, the technical solutions in the embodiments of the present invention, or the parts that contribute to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium such as a USB flash drive, mobile hard drive, read-only memory (ROM), random access memory (RAM), magnetic disk, or optical disk, or other media capable of storing program code. It includes several instructions to cause a computer terminal (which may be a personal computer, server, or a second terminal, network terminal, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention.
[0094] The same or similar parts between the various embodiments in this specification can be referred to mutually. In particular, the terminal embodiments are basically similar to the method embodiments, so the description is relatively simple, and the relevant parts can be referred to the description in the method embodiments.
[0095] In the embodiments provided by this invention, it should be understood that the disclosed systems and methods can be implemented in other ways. For example, the system embodiments described above are merely illustrative. For instance, the division of modules is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple modules 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 systems or modules may be electrical, mechanical, or other forms.
[0096] The modules described as separate components may or may not be physically separate. The components shown as modules may or may not be physical modules; that is, they may be located in one place or distributed across multiple network modules. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.
[0097] In addition, the functional modules in the various embodiments of the present invention can be integrated into one processing module, or each module can exist physically separately, or two or more modules can be integrated into one module.
[0098] Although the present invention has been described in detail with reference to the accompanying drawings and preferred embodiments, the present invention is not limited thereto. Various equivalent modifications or substitutions can be made to the embodiments of the present invention by those skilled in the art without departing from the spirit and essence of the invention, and such modifications or substitutions should all be within the scope of the present invention. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in the present invention should also be covered within the protection scope of the present invention.
Claims
1. A method for unmanned aerial vehicle (UAV) route planning based on a grid graph, characterized in that, include: Construct a mesh graph and define a set of policy primitives; wherein the mesh graph adopts a pure attribute storage architecture, and each mesh cell contains static spatial attribute information; the policy primitives include policy type identifiers, scope description parameters, and policy semantic tags; Obtain a route planning task containing a start point, an end point, and at least one policy primitive instance; map the scope description parameters to the corresponding set of grid cells in the grid graph; and convert the policy semantic labels into temporary dynamic constraint attributes and associate them with the corresponding set of grid cells. Traverse each grid cell in the search space, read the static spatial attribute information and associated temporary dynamic constraint attributes of each grid cell, and convert them into passage cost according to the preset cost quantization rules; Heuristic path search is performed based on the grid topology relationship of the search space. During the search process, the cost is accumulated according to the passage cost of the grid cell, heuristic estimation is performed based on the spatial distance, and the expansion conditions of the corresponding grid cell are adjusted according to the policy semantic label to generate the optimal grid cell sequence. The optimal grid cell sequence is restored to a geographic coordinate sequence to generate the target route.
2. The UAV route planning method based on a grid graph according to claim 1, characterized in that, The process of constructing the grid diagram includes: The target spatial domain is recursively divided into multi-level grid cells according to the preset spatial subdivision hierarchy. Each grid cell is assigned a spatial code; and the static spatial attribute information is configured, wherein the static spatial attribute information includes at least the airspace type identifier, terrain elevation value, obstacle type and height, land cover type and sensitive target identifier; Calculate the neighborhood relationship of each grid cell, wherein the neighborhood relationship includes planar neighborhood relationships within the same height layer and vertical neighborhood relationships between different height layers; The grid diagram is generated by fusing each grid cell with its corresponding spatial code, static spatial attribute information, and neighborhood relationship.
3. The UAV route planning method based on a grid graph according to claim 1, characterized in that, The set of policy primitives includes at least: The prohibition policy has a policy semantic label indicating that the corresponding set of grid cells is prohibited from passing. The temporary dynamic constraint attribute includes a prohibition flag. In the heuristic path search, grid cells associated with the prohibition flag are excluded from the search space. The avoidance strategy, whose strategy semantic label indicates that the corresponding set of grid cells suggests detours but does not forcibly prohibit them, the temporary dynamic constraint attribute includes an avoidance level parameter, and the heuristic path search adds an avoidance offset to the sorting key value of the corresponding grid cell according to the avoidance level parameter; The preference strategy, whose policy semantic label indicates the priority selection of the corresponding set of grid cells, includes a preference weight parameter in the temporary dynamic constraint attribute. In the heuristic path search, a preference offset is added to the sorting key value of the corresponding grid cell according to the preference weight parameter, wherein the preference offset is a negative value. The slowdown strategy, whose strategy semantic label indicates that the corresponding set of grid cells should reduce the passage speed or increase the passage interval, includes a slowdown coefficient in the temporary dynamic constraint attribute, and the heuristic path search adds a slowdown offset to the time cost of passing through the grid cell according to the slowdown coefficient.
4. The UAV route planning method based on a grid graph according to claim 1, characterized in that, The static spatial attribute information and the temporary dynamic constraint attributes are converted into passage costs according to a preset cost quantification rule, including: Each attribute item in the static spatial attribute information is mapped to a basic cost component, wherein the basic cost component includes at least a hard constraint cost component, a penalty cost component, and a preference cost component; wherein the mesh cell corresponding to the hard constraint cost component is marked as impassable, the penalty cost component is positive, and the preference cost component is negative. The temporary dynamic constraint attributes are mapped to dynamic cost correction amounts according to the policy type to which their policy semantic labels belong. The passage cost is obtained by weighted summation of the basic cost component and the dynamic cost correction.
5. The UAV route planning method based on a grid graph according to claim 1, characterized in that, The passage cost is calculated using the following formula: In the formula, For grid cells The cost of passage This is the basic cost obtained by mapping based on the static spatial attribute information. This is the dynamic correction amount obtained based on the mapping of the temporary dynamic constraint attributes. w is the cost component corresponding to the i-th static attribute item. i The weight coefficient corresponding to the i-th static attribute item. For temporary restriction type fields, For the spatiotemporal conflict marker field, For wind speed field, For wind direction field, For the precipitation field, For visibility field; For temporary constraint cost function, For the cost function of spatiotemporal conflict, For meteorological composite cost function; , , These are the corresponding weighting coefficients.
6. The UAV route planning method based on a grid graph according to claim 5, characterized in that, During the search process, the cumulative cost G(n) from the starting grid to the current grid is calculated using the following recursive formula: in, This represents the cumulative cost from the starting grid to the current grid m, where m is the parent grid of the current grid n during the current search expansion process. Let C(n) be the spatial distance between grid m and grid n, and let C(n) be the passage cost of grid n. Let n be the change in heading angle from grid m to grid n. Let α be the height change from grid m to grid n, β be the turning penalty coefficient, and β be the climb or descent penalty coefficient.
7. The UAV route planning method based on a grid graph according to claim 1, characterized in that, The grid-based UAV route planning method also includes: When a dynamic event is detected, a new policy primitive instance is generated based on the type and scope of the dynamic event; Update the temporary dynamic constraint attributes associated with the corresponding grid cell according to the new strategy primitive instance, and while keeping the static spatial attribute information of the grid graph unchanged, re-execute the steps of traversing the search space, converting to passage cost and heuristic path search in claim 1 based on the updated temporary dynamic constraint attributes to generate the updated target route.
8. A UAV route planning system based on a grid graph, characterized in that, include: A mesh graph construction module is used to construct a mesh graph and define a set of policy primitives; wherein, the mesh graph adopts a pure attribute storage architecture, and each mesh cell contains static spatial attribute information; the policy primitives include policy type identifiers, scope description parameters, and policy semantic tags; The task acquisition module is used to acquire a route planning task containing a start point, an end point, and at least one instance of a policy primitive, map the scope description parameters to the corresponding set of grid cells in the grid diagram, and convert the policy semantic tags into temporary dynamic constraint attributes and associate them with the corresponding set of grid cells. The attribute mapping module is used to traverse each grid cell in the search space, read the static spatial attribute information and associated temporary dynamic constraint attributes of each grid cell, and convert them into passage costs according to preset cost quantization rules. The cost mapping module is used to perform heuristic path search based on the grid topology relationship of the search space. During the search process, the cost is accumulated according to the passage cost of the grid cell, heuristically estimated according to the spatial distance, and the expansion conditions of the corresponding grid cell are adjusted according to the policy semantic label to generate the optimal grid cell sequence. The path generation module is used to restore the optimal grid cell sequence to a geographic coordinate sequence and generate the target route.
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 program, it implements the steps of the UAV route planning method based on a grid graph as described in any one of claims 1 to 7.
10. A storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the steps of the UAV route planning method based on a grid graph as described in any one of claims 1 to 7.
