Method and system for active geo-feature oriented guidance of a drone flight path
By using local uniform grid coding and dynamic cost weight A* algorithm, the problems of low geographic feature fit and insufficient computational efficiency in UAV flight path planning are solved, achieving efficient and safe flight path planning and meeting real-time requirements.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- AEROSPACE AGE LOW AERIAL TECHNOLOGY CO LTD
- Filing Date
- 2026-01-30
- Publication Date
- 2026-05-15
AI Technical Summary
Existing UAV flight path planning technologies struggle to proactively adapt to geographical features such as rivers and roads that could improve flight safety. They also suffer from insufficient computational efficiency, difficulties in multi-source data fusion, a lack of precise directional guidance mechanisms, and high computational complexity in three-dimensional grids, making it difficult to meet the demands of real-time flight path planning.
By employing local uniform grid coding, multi-source geographic feature fusion, and dynamic cost weight A* algorithm, and combining vector key point extraction and two-dimensional grid coding processing with heuristic functions and search strategies, a high-efficiency and accurate route planning system is constructed by prioritizing safe routes such as those along rivers and roads.
It significantly improves the accuracy and efficiency of route planning, proactively adapts to safe geographical features, reduces collision risks, maintains stable communication, avoids sensitive areas, reduces computational complexity, and meets real-time planning requirements.
Smart Images
Figure CN121612307B_ABST
Abstract
Description
Technical Field
[0001] This application relates to the technical fields of unmanned aerial vehicles (UAVs), and in particular to a method and system for proactive UAV route planning guided by geographical features. Background Technology
[0002] In recent years, the widespread use of drones has made the safety of flight path planning increasingly prominent, and how to improve the safety of drone flight path planning has become a key research focus.
[0003] Related technologies propose a grid-based method for UAV regional flight path planning, which divides the operational area into continuous grid cells and plans flight paths covering the entire area using algorithms. However, this method is mainly designed for isometric coverage tasks and is difficult to meet the needs of specific scenarios. Furthermore, the planned flight paths do not closely match geographical features, resulting in low efficiency and accuracy. Summary of the Invention
[0004] The embodiments of this application aim to at least partially address one of the technical problems in the related art. To this end, the embodiments of this application propose a method, system, device, and medium for proactive, geographically-guided UAV flight path planning, improving the efficiency and accuracy of UAV flight path planning.
[0005] This application provides an active geographic feature-guided UAV flight path planning method, which includes: acquiring multi-source geographic data and planning parameter data for the flight path to be planned, wherein the multi-source geographic data includes at least one of planning start point data, planning end point data, terrain elevation data, obstacle data, and geographic feature data; performing grid coding and fusion processing on the multi-source geographic data based on the planning parameter data to obtain processed multi-source geographic data, wherein the grid coding and fusion processing includes at least extracting vector key points from the geographic feature data to obtain preprocessed multi-source geographic data, and performing grid coding and fusion processing on the preprocessed multi-source geographic data; and performing path search on the processed multi-source geographic data to obtain the planned flight path of the UAV.
[0006] In some implementations, multi-source geographic data is subjected to grid coding and fusion processing based on planning parameter data to obtain processed multi-source geographic data, including: determining the planning area based on planning start-point data and planning end-point data; performing grid coding processing on the planning area based on planning parameter data to obtain grid areas; and performing grid coding and fusion processing on the multi-source geographic data corresponding to the grid areas to obtain processed multi-source geographic data.
[0007] In some implementations, grid coding and fusion processing are performed on the multi-source geographic data corresponding to the grid area to obtain processed multi-source geographic data, including: acquiring reference planned flight route data; performing data preprocessing on the multi-source geographic data and reference planned flight route data corresponding to the grid area to obtain preprocessed multi-source geographic data and preprocessed reference planned flight route data; and performing grid coding and fusion processing on the preprocessed multi-source geographic data based on the preprocessed reference planned flight route data to obtain processed multi-source geographic data.
[0008] In some implementations, data preprocessing is performed on the multi-source geographic data and reference planned route data corresponding to the grid area to obtain preprocessed multi-source geographic data and preprocessed reference planned route data. This includes: extracting height information from the obstacle data corresponding to the grid area to obtain first height information; extracting vector key points from the geographic feature data corresponding to the grid area to obtain key point information; obtaining preprocessed multi-source geographic data based on the first height information and key point information; extracting height information and time information from the reference planned route data to obtain first time information and second height information; and obtaining preprocessed reference planned route data based on the first time information and second height information.
[0009] In some implementations, the processed multi-source geographic data includes no-fly zones, feature zones, and ordinary zones. Based on the preprocessed reference planned flight route data, the preprocessed multi-source geographic data undergoes grid coding and fusion processing to obtain processed multi-source geographic data, including: acquiring second time information and flight altitude range information for the flight route to be planned; performing overlap determination based on first altitude information, second altitude information, first time information, second time information, and flight altitude range information to obtain no-fly zones; performing grid coding processing on the no-fly zones to obtain no-fly zones; performing grid coding processing on key point information to obtain feature zones; and obtaining ordinary zones based on the no-fly zones and feature zones.
[0010] In some implementations, an overlap judgment is made based on first altitude information, second altitude information, first time information, second time information, and flight altitude range information to obtain a no-fly zone. This includes: extracting time information from obstacle data corresponding to a grid area to obtain third time information; making an overlap judgment based on the first altitude information and flight altitude range information, and when the first altitude information and flight altitude range information overlap, designating the grid area corresponding to the first altitude information as a no-fly zone; or, making an overlap judgment based on the first altitude information and flight altitude range information, and when the first altitude information and flight altitude range information overlap, and when the second time information and third time information overlap, designating the grid area corresponding to the first altitude information as a no-fly zone; making an overlap judgment based on the second altitude information, first time information, second time information, and flight altitude range information, and when the second altitude information and flight altitude range information overlap, and when the first time information and second time information overlap, designating the grid area corresponding to the first altitude information as a no-fly zone.
[0011] In some implementations, no-fly grids have a higher priority than feature grids, and feature grids have a higher priority than ordinary grids.
[0012] In some implementations, the processed multi-source geographic data includes no-fly grids, feature grids, and ordinary grids; the step of performing path search on the processed multi-source geographic data to obtain the planned flight path of the UAV includes: performing path search on the feature grids and ordinary grids based on a heuristic function to obtain the planned flight path of the UAV, wherein the heuristic function represents the cumulative cost of a first cost from the planning starting point data to the current node and a second cost from the current node to the planning ending point data, the first cost is obtained based on the cost data from the planning starting point data to the current node, and the second cost is obtained based on the Euclidean distance or Manhattan distance from the current node to the planning ending point data.
[0013] In some implementations, the cost data includes ordinary grid cost and feature grid cost; the first cost is obtained based on the cost data from the planning starting point data to the current node, including: multiplying the grid distance from the planning starting point data to the current node with a preset cost to obtain the ordinary grid cost; and multiplying the grid distance from the planning starting point data to the current node, the preset cost, and the target factor to obtain the feature grid cost, wherein the target factor is less than a preset value.
[0014] This application provides an active geographic feature-guided UAV flight path planning system, comprising: an acquisition module for acquiring multi-source geographic data and planning parameter data of the flight path to be planned, wherein the multi-source geographic data includes at least one of planning start point data, planning end point data, terrain elevation data, obstacle data, and geographic feature data; a processing module for performing grid encoding and fusion processing on the multi-source geographic data based on the planning parameter data to obtain processed multi-source geographic data, wherein the grid encoding and fusion processing includes at least extracting vector key points from the geographic feature data to obtain preprocessed multi-source geographic data, and performing grid encoding and fusion processing on the preprocessed multi-source geographic data; and a search module for performing path search on the processed multi-source geographic data to obtain the planned flight path of the UAV.
[0015] An embodiment of this application provides an electronic device, which includes: a memory, and one or more processors communicatively connected to the memory; the memory stores instructions executable by one or more processors, which are executed by one or more processors to cause the one or more processors to implement the steps of the method of any of the above embodiments.
[0016] Embodiments of this application provide a computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the steps of the method of any of the above embodiments.
[0017] In the above embodiments, the UAV route planning method actively guided by geographic features includes: acquiring multi-source geographic data and planning parameter data of the route to be planned, wherein the multi-source geographic data includes at least one of planning start point data, planning end point data, terrain elevation data, obstacle data, and geographic feature data; performing grid coding and fusion processing on the multi-source geographic data based on the planning parameter data to obtain processed multi-source geographic data, wherein the grid coding and fusion processing includes at least extracting vector key points from the geographic feature data to obtain preprocessed multi-source geographic data, and performing grid coding and fusion processing on the preprocessed multi-source geographic data; and performing path search on the processed multi-source geographic data to obtain the planned route of the UAV. By integrating multi-source geographic data such as planning start and end points, terrain elevation, obstacles, geographic features, and geofencing, and combining this with planning parameters for grid coding and fusion processing, the data format and coordinate system are effectively unified, enhancing the integrity and consistency of environmental information, thereby significantly improving the accuracy and reliability of path search. Through efficient path planning using the fused geographic data, terrain undulations, obstacles, and restricted spaces can be avoided, generating safe UAV flight paths that conform to actual constraints, greatly improving the accuracy and efficiency of flight path planning. Attached Figure Description
[0018] Figure 1 A flowchart illustrating an active, geographically-oriented UAV route planning method provided for an embodiment of this application;
[0019] Figure 2 An illustration of the active geographic feature-guided UAV route planning method provided in the embodiments of this application;
[0020] Figure 3 An illustration of another active geographic feature-guided UAV route planning method provided for an embodiment of this application;
[0021] Figure 4 A block diagram of an electronic device provided for another embodiment of this application. Detailed Implementation
[0022] The embodiments of this application are described in detail below. Examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and intended to explain this application, and should not be construed as limiting this application.
[0023] In recent years, the widespread use of unmanned aerial vehicles (UAVs) has made the safety of flight path planning increasingly prominent, and improving the safety of UAV flight path planning has become a key research focus. Spatial partitioning and path search are two core components in the field of UAV flight path planning.
[0024] In conventional flight route planning, prioritizing flights along geographical features such as rivers and roads has become an important strategy for improving safety. Flying along fixed geographical features like rivers and roads can significantly improve the safety and stability of UAV operations, mainly for the following three reasons: First, rivers and roads are usually relatively flat with fewer obstacles, reducing the probability of encountering sudden obstacles and effectively lowering the risk of collisions, ensuring flight safety; second, rivers and roads often have well-developed communication infrastructure, such as base stations, making it easier for UAVs to maintain stable communication signal connections when flying in these areas, which is conducive to real-time data transmission and receiving control commands, avoiding flight malfunctions or mission failures due to signal interruptions; third, it can avoid flying into densely populated areas or sensitive areas such as hospitals and schools, reducing safety hazards.
[0025] Related technologies propose a grid-based UAV regional flight path planning method, which divides the operation area into continuous grid cells and plans flight paths covering the entire area through algorithms. Grid-based spatial representation is one of the more widely used technologies. The planar flight path planning algorithms adopted by mainstream UAV manufacturers are also based on similar ideas, but are mainly applied to scenarios such as agriculture and photography. The main features of grid-based spatial representation include: (1) using regular or irregular grids to divide the planning area into spatial regions; (2) mainly using search algorithms to find the optimal path from the starting point to the end point; (3) emphasizing obstacle avoidance and path length optimization; and (4) having wide applications in fields such as agricultural plant protection, topographic mapping, and power line inspection.
[0026] However, grid-based UAV regional flight path planning methods are mainly designed for area coverage tasks and do not take linear geographical features such as rivers and roads as active guiding factors for planning. This makes it difficult to meet the needs of specific scenarios and results in low efficiency and accuracy. Specifically, this is reflected in: (1) Inability to actively adapt to safe geographical features: The main focus is on obstacle avoidance and path length optimization. Geographical features such as rivers and roads that can improve flight safety are not taken as active guiding factors for planning. As a result, the planned flight path cannot make full use of the safety advantages of rivers and roads (such as flat terrain, good communication, and avoidance of sensitive areas). In practice, flying along rivers and roads has been proven to be an effective way to improve the safety of UAV operations, but related technologies lack active guidance mechanisms for such safety features. Even the area flight path planning algorithms of mainstream manufacturers are mainly designed for scenarios such as agricultural spraying and photogrammetry, and do not specifically optimize for the safety of linear geographical features such as rivers and roads. (2) Insufficient processing efficiency in local areas: When the global grid-based planning technology is used to process local small-scale flight path planning, it will introduce unnecessary computational overhead, resulting in insufficient processing efficiency. In urban low-altitude scenarios, due to the complex environment and frequent interaction between air and ground elements, this inefficiency problem is more prominent. (3) Difficulty in multi-source data fusion: When fusion of multi-source heterogeneous data such as terrain obstacles, no-fly zones, and geographical features, related technologies lack a unified and efficient fusion mechanism, resulting in inaccurate and incomplete construction of planning environment models. This makes flight route planning in complex environments (such as urban low-altitude and mountainous river channels) a safety hazard. (4) Lack of direction guidance mechanism: Related technologies lack a precise analysis and guidance mechanism for the direction of geographical features, and cannot dynamically adjust the flight route direction according to the actual direction of linear features such as rivers and roads, resulting in a low degree of fit between the planned flight route and geographical features. (5) High three-dimensional computational complexity: Although some related technologies attempt to introduce three-dimensional meshes for spatial representation, the computational complexity of three-dimensional meshes is high and the data storage volume is large, making it difficult to meet the needs of real-time flight route planning.
[0027] In view of the shortcomings of related UAV flight path planning technologies, this application aims to solve the following specific technical problems: (1) How to realize flight path planning based on safe geographical features: solve the problem that related technologies cannot actively conform to geographical features such as rivers and roads that can improve flight safety, and provide a flight path planning method that can make full use of the safety advantages of rivers and roads (flat terrain, good communication, avoidance of sensitive areas, etc.), and combine the successful experience of flying along rivers and roads in industry practice to improve the safety of UAV routine operations; (2) How to improve the computational efficiency of local area flight path planning: solve the problem that the computational efficiency of global grid-based planning technology is insufficient when dealing with local small-scale flight path planning, and realize efficient local area flight path planning processing, especially for complex environments and air-ground elements. (3) How to achieve efficient fusion of multi-source geographic data: solve the difficulties of related technologies in fusion of multi-source heterogeneous data such as terrain obstacles, no-fly zones, and geographic features, construct an accurate and comprehensive planning environment model, and improve the safety of route planning in complex environments (such as urban low-altitude and mountainous river channels); (4) How to construct an accurate direction guidance mechanism: solve the problem that related technologies lack accurate analysis and guidance mechanisms for geographic feature orientation, and provide a method that can dynamically adjust the route direction according to the actual orientation of linear features such as river channels and roads; (5) How to reduce computational complexity while ensuring accuracy: solve the problem of high computational complexity and large data storage of three-dimensional grids, and provide a path planning scheme that takes into account both efficiency and accuracy to meet the needs of real-time route planning.
[0028] Therefore, this application proposes an active UAV route planning method guided by geographic features. This method achieves efficient, accurate and geographically relevant route planning through local uniform grid coding, multi-source geographic feature fusion, and dynamic cost weight A* algorithm.
[0029] Figure 1 A flowchart illustrating an active, geographically-oriented UAV route planning method provided for an embodiment of this application.
[0030] like Figure 1 As shown, the active UAV route planning method guided by geographical features includes steps S110-S130, for example.
[0031] Step S110: Obtain multi-source geographic data and planning parameter data of the route to be planned, wherein the multi-source geographic data includes at least one of the following: planning start point data, planning end point data, terrain elevation data, obstacle data, and geographic feature data.
[0032] For example, obstacle data may include no-fly zones (such as military control zones, government offices, etc.), terrain obstacles (steep cliffs, deep valleys, etc.), building obstacles (the outline and height of buildings, etc.), high-voltage power lines, communication towers, and geofencing data (including height-restricted fences, such as restricting flight altitude in densely populated areas), etc. Geographic feature data may include rivers, roads, etc. Planning parameter data may include grid spacing, safety distance, etc. Grid spacing includes the interval between adjacent grids when dividing the grid, and safety distance includes the buffer distance between the planned flight path and obstacle data, etc.
[0033] Step S120: Based on the planning parameter data, perform grid coding and fusion processing on the multi-source geographic data to obtain the processed multi-source geographic data. The grid coding and fusion processing includes at least extracting vector key points from the geographic feature data to obtain the preprocessed multi-source geographic data, and performing grid coding and fusion processing on the preprocessed multi-source geographic data.
[0034] For example, by performing grid coding on the planning area according to the grid interval of the planning parameter data, a uniform grid area corresponding to the planning area can be obtained. The planning area is determined based on the planning start point data and the planning end point data. The grid area can include a square grid. By extracting vector key points from the geographic feature data, data redundancy is reduced, thereby reducing the storage and computing costs of geographic feature data. While compressing the data, the main features of the original geometric shape are maintained, and the key points serve as the benchmark for feature matching, used for spatial alignment of data from different sources, providing a structured set of feature points for grid coding and fusion. The grid coding process uses two-dimensional coding. The three-dimensional regions corresponding to the multi-source geographic data are transformed to obtain two-dimensional regions, and the two-dimensional regions are grid-labeled in the grid area corresponding to the planning area. The grid areas corresponding to the multi-source geographic data can include no-fly grids, feature grids, ordinary grids, etc.
[0035] Step S130: Perform path search on the processed multi-source geographic data to obtain the planned flight path of the UAV.
[0036] For example, path search is implemented based on the dynamic cost weight A* algorithm, heuristic function and search strategy. The heuristic function represents the cumulative cost from the planning starting point data to the planning ending point data. The search strategy includes feature grid priority queue, dual queue alternating expansion, neighborhood priority order and direction guidance mechanism, etc.
[0037] As can be seen, the UAV flight path planning method based on proactive geographic features proposed in this application integrates multi-source geographic data such as the planning start point, end point, terrain elevation, obstacles, geographic features, and geofences, and combines this with planning parameters for grid coding and fusion processing. This effectively unifies the data format and coordinate system, enhances the integrity and consistency of environmental information, and thus significantly improves the accuracy and reliability of path search. By extracting vector key points and standardizing the preprocessing of geographic feature data (such as point, line, and polygon elements) from different sources and in different formats, the method can retain key features in the geographic feature data, reduce data redundancy, and provide standardized geographic feature data for subsequent grid coding and fusion processing. Furthermore, by performing efficient path planning on the fused geographic data, the method can avoid terrain undulations, obstacles, and restricted spaces, generating safe UAV flight paths that conform to actual constraints, greatly improving the accuracy and efficiency of flight path planning.
[0038] This application provides an active geographic feature-guided UAV route planning system, which includes: an acquisition module (data input module), a processing module (geographic feature processing module, grid coding and fusion module), and a search module (path search module, output module).
[0039] The acquisition module (data input module) is used to acquire multi-source geographic data and planning parameter data of the route to be planned. The multi-source geographic data includes at least one of the following: planning start point data, planning end point data, terrain elevation data, obstacle data, and geographic feature data.
[0040] Specifically, it receives the starting point (planning starting point data) and the ending point coordinates (planning ending point data); acquires terrain elevation data; acquires obstacle data (including no-fly zones, terrain obstacles, geofence data, etc.); acquires geographic feature data (including rivers, roads, etc.); and receives planning parameters set by the user (such as safety distance, grid interval, etc.).
[0041] The processing module (geographic feature processing module, grid coding and fusion module) is used to perform grid coding and fusion processing on multi-source geographic data based on planning parameter data to obtain processed multi-source geographic data.
[0042] Specifically, the geographic feature processing module is used to preprocess geographic feature data such as rivers and roads, converting geographic feature data into a list of vector key points and extracting attribute information such as direction and curvature of geographic features; the grid coding and fusion module is used to construct a two-dimensional uniform grid coding system in a local coordinate system, converting terrain obstacles, no-fly zones (obstacle data) into no-fly grids, converting geographic feature data such as rivers and roads into passable grids, and setting a low passable cost to achieve unified coding and fusion of multi-source data.
[0043] The search module (path search module, output module) is used to perform path search on the processed multi-source geographic data to obtain the planned flight path of the UAV.
[0044] Specifically, the path search module is used to search for paths based on the dynamic cost weight A* algorithm, and adopts a feature-first expansion strategy to prioritize the selection of paths that fit geographical features; the output module is used to generate the final route planning results, and supports multiple output formats such as KML and JSON.
[0045] In one example, multi-source geographic data is processed by grid coding and fusion based on planning parameter data to obtain processed multi-source geographic data, including: determining the planning area based on planning start-point data and planning end-point data; performing grid coding on the planning area based on planning parameter data to obtain grid areas; and performing grid coding and fusion on the multi-source geographic data corresponding to the grid areas to obtain processed multi-source geographic data.
[0046] Specifically, the latitude and longitude data corresponding to the planning start and end points are mapped to a Cartesian coordinate system and transformed into two-dimensional coordinates in a local coordinate system. A minimum rectangular area is determined based on the two-dimensional coordinates of the planning start and end points, and this rectangular area is expanded outwards by a buffer zone to obtain the planning area. The planning area is then grid-coded according to the grid interval of the planning parameter data to obtain a uniform grid area corresponding to the planning area. The grid area can include square grids. Two-dimensional coding is used for the grid coding process. The multi-source geographic data corresponding to the grid area is then subjected to grid coding and fusion processing to obtain the processed multi-source geographic data.
[0047] For example, a transformed local airspace is established within the range of minimum latitude and longitude [min(lon), min(lat)] to maximum latitude and longitude [max(lon), max(lat)] of the planning area, and the area outside the local airspace is designated as a no-fly zone. The system divides latitude and longitude at equal intervals to construct a uniform grid, and the interval of division is determined according to the spatial granularity requirements. The latitude and longitude conversion code is shown in formula (1):
[0048] (1)
[0049] Where tinterval is the minimum interval for dividing the latitude and longitude grid, which can be adjusted according to actual needs (e.g., 5 meters, 10 meters, 20 meters, etc.), [lon,lat] represents the original geographic coordinates of a point, and [x,y] represents the transformed grid coordinates. Within a small local area, this division method can ensure that the grid is approximately a uniform square.
[0050] In the above embodiments, by mapping to a Cartesian coordinate system, the local airspace within the planning area is divided into equidistant two-dimensional grids, achieving efficient conversion between latitude and longitude and grid encoding, and ensuring the uniformity of the grid within the local area. Compared with three-dimensional grids, this significantly reduces computational complexity and data storage requirements, while ensuring sufficient accuracy, effectively overcoming the limitations of three-dimensional grids in real-time flight path planning.
[0051] In one example, grid coding and fusion processing are performed on the multi-source geographic data corresponding to the grid area to obtain processed multi-source geographic data, including: obtaining reference planned flight route data; performing data preprocessing on the multi-source geographic data and reference planned flight route data corresponding to the grid area to obtain preprocessed multi-source geographic data and preprocessed reference planned flight route data; and performing grid coding and fusion processing on the preprocessed multi-source geographic data based on the preprocessed reference planned flight route data to obtain processed multi-source geographic data.
[0052] Specifically, data preprocessing includes information extraction, coordinate transformation, and format unification. The reference planned route data includes planned route data. By judging whether there is height and time overlap between the preprocessed reference route data and the preprocessed multi-source geographic data, the overlapping area is used as the preprocessed obstacle data. The preprocessed multi-source geographic data is then transformed into two-dimensional plane and grid to obtain the processed multi-source geographic data.
[0053] In the above embodiments, a multi-source geographic feature fusion mechanism is adopted to dynamically convert the list of vector key points of rivers and roads into grid data, and encode it in a unified manner with the terrain grid to construct a two-layer environmental model of "baseline grid + feature enhancement grid", thereby realizing the efficient fusion of multi-source heterogeneous geographic data and providing a basis for prioritizing the selection of safe paths.
[0054] In one example, data preprocessing is performed on the multi-source geographic data and reference planned flight route data corresponding to the grid area to obtain preprocessed multi-source geographic data and preprocessed reference planned flight route data. This includes: extracting height information from the obstacle data corresponding to the grid area to obtain first height information; extracting vector key points from the geographic feature data corresponding to the grid area to obtain key point information; obtaining preprocessed multi-source geographic data based on the first height information and key point information; extracting height information and time information from the reference planned flight route data to obtain first time information and second height information; and obtaining preprocessed reference planned flight route data based on the first time information and second height information.
[0055] Specifically, altitude information is extracted from no-fly zone (obstacle data), terrain obstacle (obstacle data), and geofence (obstacle data) data to obtain first altitude information. The first altitude information is then subjected to coordinate transformation and format unification to obtain preprocessed multi-source geographic data. Time and altitude information are extracted from planned flight route data (reference planned flight route data). The first time information and second altitude information are then subjected to coordinate transformation and format unification to obtain preprocessed reference planned flight route data. Vector key points are extracted from linear geographic features such as rivers and roads to obtain key point information. The key point information is then subjected to coordinate transformation and format unification to obtain preprocessed multi-source geographic data.
[0056] In one example, the processed multi-source geographic data includes no-fly grids, feature grids, and ordinary grids. Based on the preprocessed reference planned flight route data, the preprocessed multi-source geographic data undergoes grid coding and fusion processing to obtain processed multi-source geographic data, including: acquiring the second time information and flight altitude range information of the flight route to be planned; performing overlap judgment based on the first altitude information, second altitude information, first time information, second time information, and flight altitude range information to obtain no-fly zones; performing grid coding processing based on the no-fly zones to obtain no-fly grids; performing grid coding processing based on key point information to obtain feature grids; and obtaining ordinary grids based on the no-fly grids and feature grids.
[0057] Specifically, the flight altitude range [min_alt, max_alt] and second time information of the flight route to be planned are obtained. Overlap judgment is performed on the first altitude information, second altitude information, first time information, second time information, and flight altitude range information. When overlapping is judged, corresponding areas can be merged to obtain the no-fly zone. A two-dimensional planar transformation (grid encoding processing) is performed on the no-fly zone, projecting it as a planar area on a two-dimensional plane to obtain a no-fly grid, with the passage cost set to infinity. All grids traversed by linear geographical features such as rivers and roads are marked as feature grids, with a lower passage cost (e.g., 50% of ordinary grids). Areas not marked as no-fly grids or feature grids remain as ordinary grids, with a basic passage cost (e.g., 1.0). Here, no-fly grids correspond to impassable areas such as terrain obstacles and no-fly zones, ordinary grids correspond to normally traversable areas, and feature grids correspond to geographical feature areas such as rivers and roads.
[0058] It is important to note that when performing 2D plane conversion, latitude and longitude information is retained while height information is ignored, thus converting a three-dimensional region in space into a covered region on a 2D plane.
[0059] In the above embodiments, by projecting three-dimensional space into a two-dimensional plane and constructing a locally uniform grid coding system, the computational complexity and data storage requirements are greatly reduced compared to a three-dimensional grid. At the same time, sufficient accuracy is ensured through localization, effectively overcoming the limitations of three-dimensional grids in real-time route planning. Furthermore, considering that the route itself is not very long (usually a few kilometers to tens of kilometers), the error is completely acceptable through the local gridding method, and it can guarantee that the grid is a uniform square.
[0060] In one example, an overlap judgment is made based on first altitude information, second altitude information, first time information, second time information, and flight altitude range information to obtain a no-fly zone. This includes: extracting time information from obstacle data corresponding to the grid area to obtain third time information; making an overlap judgment based on the first altitude information and flight altitude range information, and when the first altitude information and flight altitude range information overlap, designating the grid area corresponding to the first altitude information as a no-fly zone; or, making an overlap judgment based on the first altitude information and flight altitude range information, and when the first altitude information and flight altitude range information overlap, and when the second time information and third time information overlap, designating the grid area corresponding to the first altitude information as a no-fly zone; making an overlap judgment based on the second altitude information, first time information, second time information, and flight altitude range information, and when the second altitude information and flight altitude range information overlap, and when the first time information and second time information overlap, designating the grid area corresponding to the first altitude information as a no-fly zone.
[0061] Specifically, for no-fly zones, terrain obstacles, and geofences (first altitude information), it is determined whether their altitude range overlaps with the altitude range of the route to be planned (flight altitude range information). Alternatively, for no-fly zones, terrain obstacles, and geofences (first altitude information and third time information), it is determined whether their altitude and time ranges overlap with the altitude range of the route to be planned (flight altitude range information and second time information). For reference planned route data, it is determined whether their second altitude information and first time information overlap with the altitude range of the route to be planned (flight altitude range information) and second time information. Three-dimensional spatial areas such as no-fly zones, terrain obstacles, geofences, and planned routes that overlap with the flight altitude range information and time range (second time information) of the route to be planned are designated as no-fly zones.
[0062] In one example, no-fly grids have higher priority than feature grids, and feature grids have higher priority than regular grids.
[0063] Specifically, when marking grids, no-fly grids have the highest priority and can cover both feature grids and ordinary grids. Feature grids have the next highest priority and can cover ordinary grids. Ordinary grids have the lowest priority. The passage cost of feature grids is set based on the attenuation factor. The passage cost of no-fly grids is set to infinity. Feature grids are set to a lower passage cost (e.g., if the attenuation factor is 0.5, the passage cost is 50% of that of ordinary grids). Ordinary grids are set to a basic passage cost (e.g., 1.0).
[0064] In one example, the processed multi-source geographic data includes no-fly grids, feature grids, and ordinary grids; the step of performing path search on the processed multi-source geographic data to obtain the planned flight path of the UAV includes: performing path search on the feature grids and ordinary grids based on a heuristic function to obtain the planned flight path of the UAV, wherein the heuristic function represents the cumulative cost of a first cost from the planning starting point data to the current node and a second cost from the current node to the planning ending point data, the first cost is obtained based on the cost data from the planning starting point data to the current node, and the second cost is obtained based on the Euclidean distance or Manhattan distance from the current node to the planning ending point data.
[0065] Specifically, path search is implemented based on the dynamic cost weight A* algorithm, heuristic function, and search strategy. The search strategy includes feature grid priority queue, alternating expansion of dual queues, neighborhood priority order, and direction guidance mechanism. Among them, the feature grid priority queue is included in the open list of the A* algorithm, and feature grid nodes are maintained in a separate priority queue. Alternating expansion of dual queues means that during the search process, nodes are selected from the feature grid queue for expansion first. When the feature grid queue is empty, nodes are selected from the ordinary grid queue.
[0066] For example, the heuristic function is shown in formula (2):
[0067] f(n) = g(n) + h(n)(2)
[0068] Where g(n) represents the actual cost from the starting point to the current node (first cost), and h(n) represents the estimated cost from the current node to the end point (second cost), calculated using Euclidean distance or Manhattan distance.
[0069] In one example, the cost data includes ordinary grid cost and feature grid cost; the first cost is obtained based on the cost data from the planning starting point data to the current node, including: multiplying the grid distance from the planning starting point data to the current node with a preset cost to obtain the ordinary grid cost; and multiplying the grid distance from the planning starting point data to the current node, the preset cost, and the target factor to obtain the feature grid cost, wherein the target factor is less than a preset value.
[0070] Specifically, for ordinary grids, the calculation method is as shown in formula (3):
[0071] g(n) = g(parent) + base cost × grid distance (3)
[0072] Where g(parent) represents the cumulative cost from the planning starting point to the previous node, the basic cost represents the preset cost, such as 1.0, and the grid distance represents the distance between two grids.
[0073] For the feature grid, the calculation method is as shown in formula (4):
[0074] g(n) = g(parent) + base cost × grid distance × decay factor (4)
[0075] Where g(parent) represents the cumulative cost from the planning starting point to the previous node, the base cost represents the preset cost, such as 1.0, the grid distance represents the distance between two grids, and the decay factor represents the target factor, such as 0.5.
[0076] The planned flight path of the UAV is transformed into three dimensions to obtain latitude and longitude data, as shown in formula (5):
[0077] (5)
[0078] Where tinterval is the minimum interval for dividing the latitude and longitude grid, which can be adjusted according to actual needs (such as 5 meters, 10 meters, 20 meters, etc.), [lon,lat] represents the converted geographic coordinates, [x,y] represents the two-dimensional grid coordinates, [min(lon), min(lat)] represents the minimum latitude and longitude of the planning area, and [max(lon), max(lat)] represents the maximum latitude and longitude. The latitude and longitude of the grid center is used as the representative coordinates of that grid. The final UAV flight path is obtained based on the latitude and longitude data.
[0079] In the above embodiments, based on the A* algorithm, a feature grid cost attenuation factor is introduced, and search strategies such as feature grid priority queues, alternating expansion of dual queues, neighborhood priority order, and direction guidance mechanisms are employed for optimization. Node costs are dynamically calculated, prioritizing paths along safe geographical features such as rivers and roads, thus fully utilizing these features to improve flight safety. Through these search strategy optimizations, the algorithm can significantly increase the probability of conforming to safe geographical features such as rivers and roads while ensuring path optimality, achieving proactive safe route planning that conforms to geographical features, which aligns with successful experience in flying along rivers and roads in industry practice.
[0080] The UAV route planning method proposed in this application, which is guided by geographical features, achieves the following: (1) Actively aligning with safe geographical features: Through the fusion of multi-source geographical features and dynamic cost weighting mechanism, the route planning is made to actively align with geographical features such as rivers and roads that can improve flight safety. This allows the planned route to make full use of the safety advantages of these geographical features (flat terrain with few obstacles, complete communication facilities, and avoidance of sensitive areas), solving the problem that existing technologies cannot actively align with safe geographical features. (2) Significantly improving flight safety: By prioritizing the selection of routes along safe geographical features such as rivers and roads, the risk of UAV collisions is effectively reduced (flat terrain with few obstacles), stable communication connections are maintained (complete communication infrastructure along the route), and flying into densely populated or sensitive areas (such as hospitals and schools) is avoided. This is consistent with the successful experience of flying along rivers and roads in industry practice. (3) Advantage of local grid uniformity: By adopting a local grid coding system, the grid can be guaranteed to be a uniform square within a small local area (usually a few kilometers to tens of kilometers), solving the problem of non-uniform grid and inconsistent distances in different directions in existing global grid codes in high-latitude regions. (4) Efficient fusion of multi-source data: Through a unified grid coding system, efficient fusion of heterogeneous data from multiple sources such as terrain obstacles, no-fly zones, and geographical features is achieved, constructing an accurate and comprehensive planning environment model and solving the problem of difficulty in multi-source data fusion in existing technologies. (5) High computational efficiency: The combination of the local grid coding system and the dynamic cost weight A* algorithm greatly improves the computational efficiency of flight route planning, especially when dealing with local small-scale flight route planning, avoiding unnecessary computational overhead of global grid codes and meeting the needs of real-time planning. (6) Significant advantages of two-dimensional grids: Compared with the three-dimensional grids in existing technologies, the two-dimensional grid coding method has significant advantages: it greatly reduces computational complexity and data storage requirements, while ensuring sufficient accuracy through localized processing, effectively overcoming the application limitations of three-dimensional grids in real-time flight route planning.
[0081] For ease of understanding, the following specific embodiments are provided in this application:
[0082] Planned Scenario: Starting point: [105.224980°, 25.491203°, 300°], Ending point: [105.227567°, 25.497852°, 300°], Flight altitude: 300m-320m. There are two no-fly zones, the planned flight path is empty, and there is one river. No-fly zone 1: POLYGON ((
[0083] 106.57645 29.64579,
[0084] 106.57645 29.63681,
[0085] 106.58675 29.63681,
[0086] 106.58675 29.64579, 106.57645 29.64579
[0088] )), height 400-500 meters
[0089] No-fly zone 2: POLYGON
[0090] 106.580690 29.667139,
[0091] 106.578690 29.612408,
[0092] 106.585392 29.612408, 106.580690 29.667139
[0094] ), height 200-350 meters
[0095] River is LINESTRING (
[0096] 106.574909 29.738344,
[0097] 106.539300 29.696673,
[0098] 106.521023 29.641651,
[0099] 106.525119 29.626277,
[0100] 106.571127 29.615354, 106.688983 29.592698 )
[0103] For ease of display, the grid is set to be relatively large, 200m*200m; cost weight settings: feature grid cost coefficient is 0.5, ordinary grid cost coefficient is 1.0, and no-fly zone grid cost coefficient is infinite; directional guidance parameters: Hough transform angle accuracy is 1 degree, neighborhood priority matrix is 3×3, and directional continuity threshold is 3 grids.
[0104] Step 1: Import the geographic data of the planning area into the system, including river vector data (Shapefile format), terrain elevation data (DEM (Digital Elevation Model) format), and no-fly zone data (GeoJSON format).
[0105] Step 2: Based on the minimum latitude and longitude (106.46722428690897, 29.50823263373298) and maximum latitude and longitude (106.71723143022193, 29.74844188992969) of the planning area, establish a local coordinate system. The grid size of the entire area is 122*135.
[0106] Step 3: Set Feature Grid: Perform gridding on the river channel vector data to obtain all path grids, and set them as feature grids, such as... Figure 2 As shown in the yellow square.
[0107] Step 4: Set the no-fly zone grid: There are two no-fly zones. No-fly zone 1 does not overlap with the altitude of this flight path, so it is not considered. No-fly zone 2 overlaps with this flight path, so the grid contained within it is set as the no-fly zone grid, such as... Figure 2 As shown in black grid 20.
[0108] Step 5: Start the dynamic cost weight A* algorithm for path search. The algorithm maintains two priority queues: feature grid and ordinary grid. Nodes are expanded from the feature grid queue first.
[0109] With an Intel Core i7 processor and 16GB of RAM, a single planning session takes 0.35 seconds, and the drone's planned flight path is as follows: Figure 2 As shown by the red lines, this allows for the planning of drone flight paths along the river. Figure 3 The diagram shows another active geographic feature-guided UAV route planning method provided in this application. The red line represents the planned route of the UAV in the related technology. Since it only considers a simple obstacle avoidance planning algorithm, it cannot achieve planning along the river.
[0110] As can be seen from this embodiment, the UAV route planning method with active geographic feature guidance proposed in this application can achieve accurate matching of geographic features while ensuring path optimization, thus significantly improving the quality and efficiency of route planning.
[0111] The UAV route planning method proposed in this application, which is guided by active geographic features, adopts the following: (1) a multi-source safe geographic feature fusion mechanism, which dynamically converts the list of vector key points of geographic features such as rivers / roads that can improve flight safety into grid data and encodes them in a unified manner with the terrain grid to construct a two-layer environment model of "baseline grid + feature enhancement grid", thereby realizing the efficient fusion of multi-source heterogeneous geographic data and providing a basis for prioritizing the selection of safe paths. (2) a dynamic cost weight A* algorithm, which introduces a feature grid cost attenuation factor (such as 50%) in the path search and optimizes the search strategy by using a feature grid priority queue, double queue alternating expansion, neighborhood priority order and direction guidance mechanism. The algorithm dynamically calculates the node cost and prioritizes the selection of paths along safe geographic features such as rivers and roads, thus solving the problem that existing technologies cannot actively conform to safe geographic features. (3) a local uniform grid coding method, which establishes a transformed local airspace within the range of minimum to maximum latitude and longitude of the planning area. The system divides latitude and longitude at equal intervals to construct a uniform grid. Through the conversion formula, it ensures that the grid is approximately a uniform square in a small local area, thus solving the problem of grid deformation in high-latitude regions of existing global grid codes. This method uses two-dimensional grid encoding, which greatly reduces computational complexity and data storage requirements compared to three-dimensional grids, while ensuring sufficient accuracy, effectively overcoming the application limitations of three-dimensional grids in real-time route planning.
[0112] Figure 4 A block diagram of an electronic device provided for another embodiment of this application.
[0113] An embodiment of this application provides an electronic device, which includes: a memory, and one or more processors communicatively connected to the memory; the memory stores instructions executable by one or more processors, which are executed by one or more processors to cause the one or more processors to implement the steps of the method of any of the above embodiments.
[0114] like Figure 4 As shown, for ease of understanding, embodiments of this application illustrate a specific electronic device.
[0115] Electronic devices are intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. Electronic devices can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the present disclosure described and / or claimed herein.
[0116] like Figure 4As shown, the electronic device includes a computing unit 401, which can perform various appropriate actions and processes based on a computer program stored in a read-only memory (ROM) 402 or a computer program loaded from a storage unit 408 into a random access memory (RAM) 403. The RAM 403 may also store various programs and data required for the operation of the electronic device. The computing unit 401, ROM 402, and RAM 403 are interconnected via a bus 404. An input / output (I / O) interface 405 is also connected to the bus 404.
[0117] Multiple components in the electronic device are connected to the input / output (I / O) interface 405. These components include: an input unit 406, such as a keyboard or mouse; an output unit 407, such as various types of displays or speakers; a storage unit 408, such as a disk or optical disk; and a communication unit 409, such as a network interface card (NIC), a modem, or a wireless transceiver. The communication unit 409 allows the electronic device to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.
[0118] The computing unit 401 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the computing unit 401 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 401 performs the various methods described above. For example, in some embodiments, any one or more of the methods described above can be implemented as a computer software program tangibly contained in a machine-readable medium, such as storage unit 408. In some embodiments, part or all of the computer program can be loaded and / or installed on an electronic device via ROM 402 and / or communication unit 409. When the computer program is loaded into RAM 403 and executed by the computing unit 401, one or more steps of any one or more of the methods described above can be performed. Alternatively, in other embodiments, the computing unit 401 can be configured to perform any one or more of the methods described above by any other suitable means (e.g., by means of firmware).
[0119] Embodiments of this application provide a computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the steps of the method of any of the above embodiments.
[0120] The UAV flight path planning system and method based on active geographic features proposed in this application have broad application prospects and can be widely applied in the following fields, especially in scenarios where flight safety needs to be improved, with significant advantages: (1) Conventional safe flight: In complex environments such as cities and densely populated areas, flight paths are planned by prioritizing safe geographic features such as rivers and roads, which can effectively reduce collision risks, maintain communication stability, and avoid sensitive areas. (2) River inspection: Plan inspection routes that fit the river, which can improve inspection efficiency and data collection quality while making full use of the safety advantages of flat river terrain and few obstacles. (3) Road monitoring: Plan monitoring routes along roads for traffic monitoring, road maintenance, and other tasks, and make full use of the advantages of well-developed communication infrastructure along roads to ensure stable data transmission. (4) Pipeline inspection: Plan inspection routes along oil and gas pipelines to improve inspection efficiency and safety. (5) Border patrol: Plan patrol routes along the border line to improve patrol efficiency and coverage. (6) Logistics distribution: Plan distribution routes along roads in specific areas to improve distribution efficiency and safety.
[0121] With the continuous development of drone technology and the expansion of application scenarios, the technical solution of this application will play an important role in more fields and provide strong support for the intelligent and automated flight of drones.
[0122] It should be noted that the logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be specifically implemented in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a processor-included system, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this application, "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of computer-readable media include: electrical connections (electronic devices) having one or more wires, portable computer disk drives (magnetic devices), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). Furthermore, computer-readable media can even be paper or other suitable media on which programs can be printed, because programs can be obtained electronically, for example, by optically scanning the paper or other media, followed by editing, interpreting, or otherwise processing as necessary, and then stored in computer memory.
[0123] It should be understood that various parts of this application can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented using software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.
[0124] In the description of this application, the references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of this application. In this application, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.
[0125] In the description of this application, it should be understood that the terms "center", "longitudinal", "lateral", "length", "width", "thickness", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", "clockwise", "counterclockwise", "axial", "radial", "circumferential", etc., indicating the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings, are only for the convenience of describing this application and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation, and therefore should not be construed as a limitation of this application.
[0126] Furthermore, the terms "first," "second," etc., used in the embodiments of this application are for descriptive purposes only and should not be construed as indicating or implying relative importance, or implicitly specifying the number of technical features indicated in this embodiment. Therefore, features defined with terms such as "first" and "second" in the embodiments of this application can explicitly or implicitly indicate that the embodiment includes at least one of those features. In the description of this application, the word "multiple" means at least two or more, such as two, three, four, etc., unless otherwise explicitly and specifically defined in the embodiments.
[0127] In this application, unless otherwise explicitly specified or limited in the embodiments, the terms "installation," "connection," "joining," and "fixing" appearing in the embodiments should be interpreted broadly. For example, a connection can be a fixed connection, a detachable connection, or an integral part; it can also be a mechanical connection, an electrical connection, etc. Of course, it can also be a direct connection, or an indirect connection through an intermediate medium, or it can be the internal communication between two components, or the interaction between two components. Those skilled in the art can understand the specific meaning of the above terms in this application based on the specific implementation.
[0128] In this application, unless otherwise expressly specified and limited, "above" or "below" the second feature can mean that the first feature is in direct contact with the second feature, or that the first feature is in indirect contact with the second feature through an intermediate medium. Furthermore, "above," "on top of," and "over" the second feature can mean that the first feature is directly above or diagonally above the second feature, or simply that the first feature is at a higher horizontal level than the second feature. "Below," "below," and "under" the second feature can mean that the first feature is directly below or diagonally below the second feature, or simply that the first feature is at a lower horizontal level than the second feature.
Claims
1. A method for proactive UAV route planning guided by geographic features, characterized in that, The method includes: Acquire multi-source geographic data and planning parameter data of the route to be planned, wherein the multi-source geographic data includes at least one of the following: planning start point data, planning end point data, terrain elevation data, obstacle data, and geographic feature data; Based on the planning parameter data, the multi-source geographic data is subjected to grid coding and fusion processing to obtain processed multi-source geographic data. The grid coding and fusion processing includes at least extracting vector key points from the geographic feature data to obtain preprocessed multi-source geographic data, and performing grid coding and fusion processing on the preprocessed multi-source geographic data. The processed multi-source geographic data includes no-fly grids, feature grids, and ordinary grids. The planned flight path of the UAV is obtained by performing path search on the feature grid and ordinary grid based on the heuristic function. The heuristic function represents the cumulative cost of the first cost from the planning starting point data to the current node and the second cost from the current node to the planning ending point data. The first cost is obtained based on the cost data from the planning starting point data to the current node, and the second cost is obtained based on the Euclidean distance or Manhattan distance from the current node to the planning ending point data. The cost data includes ordinary grid cost and feature grid cost; the first cost is obtained based on the cost data from the planning starting point data to the current node, including: The ordinary grid cost is obtained by multiplying the grid distance from the planning starting point data to the current node with the preset cost. The feature grid cost is obtained by multiplying the grid distance from the planning starting point data to the current node, the preset cost, and the target factor, wherein the target factor is less than the preset value.
2. The method according to claim 1, characterized in that, The process of performing grid coding and fusion processing on the multi-source geographic data based on the planning parameter data to obtain processed multi-source geographic data includes: Based on the aforementioned planning start-point and planning end-point data, the planning area is determined; Based on the planning parameter data, the planning area is subjected to grid coding to obtain a grid area; The multi-source geographic data corresponding to the grid area is subjected to grid coding and fusion processing to obtain the processed multi-source geographic data.
3. The method according to claim 2, characterized in that, The process of performing grid coding and fusion processing on the multi-source geographic data corresponding to the grid area to obtain processed multi-source geographic data includes: Obtain reference planned route data; Data preprocessing is performed on the multi-source geographic data corresponding to the grid area and the reference planned route data to obtain preprocessed multi-source geographic data and preprocessed reference planned route data; Based on the preprocessed reference planned route data, the preprocessed multi-source geographic data is subjected to grid coding and fusion processing to obtain the processed multi-source geographic data.
4. The method according to claim 3, characterized in that, The step of preprocessing the multi-source geographic data corresponding to the grid area and the reference planned flight route data to obtain preprocessed multi-source geographic data and preprocessed reference planned flight route data includes: Height information is extracted from the obstacle data corresponding to the grid area to obtain first height information; Vector keypoints are extracted from the geographic feature data corresponding to the grid area to obtain keypoint information; Preprocessed multi-source geographic data is obtained based on the first altitude information and the key point information; Altitude and time information are extracted from the reference planned route data to obtain first time information and second altitude information, and preprocessed reference planned route data is obtained based on the first time information and second altitude information.
5. The method according to claim 4, characterized in that, The preprocessed multi-source geographic data is subjected to grid coding and fusion processing based on the preprocessed reference planned route data to obtain processed multi-source geographic data, including: Obtain the second time information and flight altitude range information of the route to be planned; The no-fly zone is determined by overlapping the first altitude information, the second altitude information, the first time information, the second time information, and the flight altitude range information. The no-fly zone is then subjected to grid coding to obtain the no-fly grid. The feature grid is obtained by performing grid encoding processing based on the key point information; The ordinary grid is obtained based on the no-fly zone grid and the feature grid.
6. The method according to claim 5, characterized in that, The no-fly zone is determined by overlapping the first altitude information, the second altitude information, the first time information, the second time information, and the flight altitude range information, including: Temporal information is extracted from the obstacle data corresponding to the grid area to obtain third temporal information; Based on the overlap determination of the first altitude information and the flight altitude range information, when there is an overlap between the first altitude information and the flight altitude range information, the grid area corresponding to the first altitude information is designated as a no-fly zone; or, based on the overlap determination of the first altitude information and the flight altitude range information, when there is an overlap between the first altitude information and the flight altitude range information, and when there is an overlap between the second time information and the third time information, the grid area corresponding to the first altitude information is designated as a no-fly zone. Based on the overlap determination of the second altitude information, the first time information, the second time information, and the flight altitude range information, when there is an overlap between the second altitude information and the flight altitude range information, and when there is an overlap between the first time information and the second time information, the grid area corresponding to the first altitude information is designated as a no-fly zone.
7. The method according to claim 5 or 6, characterized in that, The no-fly grid has a higher priority than the feature grid, and the feature grid has a higher priority than the ordinary grid.
8. A proactive UAV route planning system guided by geographical features, characterized in that, The system includes: The acquisition module is used to acquire multi-source geographic data and planning parameter data of the route to be planned, wherein the multi-source geographic data includes at least one of the following: planning start point data, planning end point data, terrain elevation data, obstacle data, and geographic feature data; The processing module is used to perform grid coding and fusion processing on the multi-source geographic data based on the planning parameter data to obtain processed multi-source geographic data. The grid coding and fusion processing includes at least extracting vector key points from the geographic feature data to obtain preprocessed multi-source geographic data, and performing grid coding and fusion processing on the preprocessed multi-source geographic data. The processed multi-source geographic data includes no-fly grids, feature grids, and ordinary grids. The search module is used to perform path search on the feature grid and ordinary grid based on a heuristic function to obtain the planned flight path of the UAV. The heuristic function represents the cumulative cost of a first cost from the planning starting point data to the current node and a second cost from the current node to the planning ending point data. The first cost is obtained based on the cost data from the planning starting point data to the current node, and the second cost is obtained based on the Euclidean distance or Manhattan distance from the current node to the planning ending point data. The cost data includes ordinary grid cost and feature grid cost. Obtaining the first cost based on the cost data from the planning starting point data to the current node includes: multiplying the grid distance from the planning starting point data to the current node with a preset cost to obtain the ordinary grid cost; and multiplying the grid distance from the planning starting point data to the current node, the preset cost, and a target factor to obtain the feature grid cost, wherein the target factor is less than a preset value.