An unmanned aerial vehicle multi-task point close reconnaissance online route planning method
By combining a greedy algorithm and an improved heuristic A* algorithm with the UAV's maneuverability and obstacle avoidance, the real-time performance and efficiency issues of autonomous reconnaissance at multiple mission points by UAVs were solved, and efficient route planning in complex environments was achieved.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- XIAN MODERN CONTROL TECH RES INST
- Filing Date
- 2025-05-28
- Publication Date
- 2026-07-24
AI Technical Summary
Existing technologies struggle to achieve efficient, real-time online route planning for multiple mission points on drones, especially in complex electromagnetic interference environments, where they cannot effectively combine mission point distribution, no-fly zones, and drone performance for autonomous planning.
A greedy algorithm and an improved heuristic A* algorithm are combined with the UAV's maneuverability and obstacle avoidance. An equivalent task point set is generated through dense point preprocessing to determine the reconnaissance order. Route planning is performed on the airborne platform, taking into account turning radius and flight speed constraints.
It enables UAVs to conduct efficient, reliable, and real-time reconnaissance of multiple mission points in complex environments, reduces the planned flight range, improves reconnaissance efficiency, and is applicable to military and civilian unmanned autonomous flight platforms.
Smart Images
Figure CN120668121B_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of unmanned autonomous flight platform route planning technology, specifically to an online route planning method for multi-mission point close-in reconnaissance of unmanned aerial vehicles (UAVs), which can be used for fixed-wing UAVs, rotary-wing UAVs, ground unmanned vehicles, etc. Background Technology
[0002] With the rapid development of autonomous unmanned systems, UAVs, as long-endurance unmanned equipment, play a crucial role in reconnaissance and search, replacing manned platforms in reconnaissance and detection of dangerous areas. For reconnaissance UAVs, it is typically necessary to receive multiple mission points and complete autonomous reconnaissance of each point. Route planning technology can guide UAVs to quickly traverse multiple points and acquire regional information, which is key to completing reconnaissance missions. Efficient multi-mission point close-range reconnaissance online route planning technology is paramount for UAVs to leverage their reconnaissance advantages. When conducting multi-mission point close-range reconnaissance online route planning, constraints such as mission point distribution, no-fly zone distribution, UAV detection performance, and UAV maneuverability must be comprehensively considered. Currently, planning is usually performed on a ground-based high-performance computing platform, and the plan is then uploaded to an onboard computer for execution via wireless communication devices, relying on a reliable communication link. However, the actual mission area may have various types of electromagnetic interference. Therefore, it is necessary to design a multi-mission point close-range reconnaissance online route planning method that can be deployed and run on an onboard low-resource computing platform to improve the autonomous reconnaissance capabilities of UAVs. Summary of the Invention
[0003] The purpose of this invention is to provide an online route planning method for multi-mission point close-range reconnaissance of unmanned aerial vehicles (UAVs), enabling a single UAV to conduct efficient close-range reconnaissance of multiple dispersed-dense points within a mission area. The planning process needs to comprehensively consider the regional distribution of mission points, the distribution of no-fly zones, the detection performance of the UAV, and the maneuverability of the UAV, while also meeting the real-time requirements of online UAV planning.
[0004] To achieve the above objectives, the present invention employs the following technical solution: A method for online route planning for multi-mission point close-range reconnaissance by unmanned aerial vehicles (UAVs) includes: First, identify all the task points to be reconnoitered within the task area. Based on the distribution of the task points and the detection swath of the UAV's onboard detection device, merge the dense task points and determine the equivalent task points to obtain the equivalent task point set. Secondly, based on the positional distribution relationship between the UAV and the equivalent task point set, a greedy algorithm is used to determine the reconnaissance order of the equivalent task points; Finally, based on the reconnaissance order of equivalent mission points, the maneuverability constraints of UAV turning radius and flight speed direction are added to the heuristic A* method, and obstacle avoidance in no-fly zones along the way are considered to complete the close reconnaissance route planning for all equivalent mission points in the mission area.
[0005] Furthermore, based on the distribution of task points and the detection swath of the UAV-borne detection device, dense task points are merged and equivalent task points are determined, resulting in an equivalent task point set, including: Calculate every two task points within the task area relative distance between ; Based on task points relative distance between Make a judgment if Then the task point For densely packed task points, at this time, the task points will be... As a mission point Dense points; among them This is a preset proportional coefficient. This refers to the detection swath width of the UAV-borne detection device; Calculate the number of dense points corresponding to each task point in turn, and construct a dense point information matrix. Sort the dense point information matrix in descending order to obtain task point numbers sorted from most to least numerous. ; Sort by task point number ,Depend on arrive The equivalent task points are calculated sequentially based on the corresponding task point numbers; where , These represent the task point numbers with the most and fewest dense points, respectively. Total number of task points; For task points with dense clusters, the average of the north and east directions of all task points is calculated as the coordinates of the equivalent task point; for task points without dense clusters, the equivalent task point is itself. Construct an equivalent task point set from all equivalent task points.
[0006] Furthermore, in the process of calculating the equivalent task point, if the dense point sequence corresponding to task point A contains dense point C, and the dense point sequence corresponding to task point B also contains dense point C, and the number of dense points corresponding to A is greater than the number of dense points corresponding to B, then when calculating the equivalent task point of task point A and all its dense points, dense point C is considered to participate in the calculation, while when calculating the equivalent task point of task point B and its dense point sequence, dense point C is not considered.
[0007] Furthermore, based on the positional distribution relationship between the UAV and the equivalent task point set, a greedy algorithm is used to determine the reconnaissance order of the equivalent task points, including: Construct a relative distance matrix, which includes the distance between the UAV’s current position and each equivalent task point, as well as the distance between any two equivalent task points; The optimal solution is found using a greedy algorithm based on the relative distance matrix: Initially, select the equivalent mission point closest to the drone as the first approach point; Once the first approach point is determined, the next equivalent task point is selected as the approach point based on the principle that the current equivalent task point is closest to other equivalent task points, and so on, until all equivalent task points are traversed, and finally the set of equivalent task points after the order decision is obtained.
[0008] Furthermore, the heuristic A* method sets a heuristic cost function, node expansion direction, and node expansion step size. Under constraints, it expands nodes from the starting point to the ending point, and finally backtracks to obtain the optimal route. The starting point is the previous equivalent task point or the starting point of the UAV, and the ending point is the current equivalent task point. In each step of node expansion, the node with the smallest substitution function is taken as the effective node. The cumulative distance from the starting point to the current node and the Euclidean distance between the current node and the destination are used. When expanding a node in each step, the expansion direction is selected, and the expansion step size is used as the distance increment for each expansion. Then, the path cost of the node after expansion in each direction is calculated to determine the optimal path. After the node expands to the destination, the node sequence from the starting point to the destination is obtained by backtracking according to the correspondence between each node and its "parent node" recorded. This sequence forms the reconnaissance waypoint between the current equivalent task point and the previous equivalent task point.
[0009] Furthermore, with turning radius As the node expansion step size The calculation is as follows:
[0010] in, This indicates the expected flight speed of the drone. It is the acceleration due to gravity. This represents the desired roll angle when turning.
[0011] Furthermore, when expanding nodes, the directional strategy is as follows:
[0012] in, Represents a node The expandable directions are: [1,0]; [0,1]; [-1,0]; [0,-1]; [1,1]; [-1,-1]; [1,-1]; [-1,1], which represent the directions of due north, due east, due south, due west, northeast, southwest, northwest, and southeast respectively in the North-East coordinate system.
[0013] Furthermore, a safe distance is reserved at the edge of the no-fly zone. Each time a node is expanded, the distance between the node and the center of the no-fly zone is checked. The safety of the node is determined based on the distance, and only nodes that are safe are considered valid nodes.
[0014] in, Represents a node With the The distance between the no-fly zones , , They represent the first The northward and eastward locations and radius of each no-fly zone. This indicates that a safe distance has been reserved. Represents a node Safety.
[0015] Furthermore, after completing the close-range reconnaissance route planning for the last equivalent mission point, the terminal flight speed direction is considered. ,by A rectangular circling, standby flight path is planned based on the side length. The calculation is as follows:
[0016] in, and These represent the northward and eastward positions of the last reconnaissance waypoint relative to the last equivalent mission point, respectively. and These represent the north and east positions of the penultimate reconnaissance waypoint relative to the last equivalent mission point, respectively; The circling route is calculated as follows:
[0017] in, Indicates the first The coordinates of the reconnaissance waypoint in the North-East coordinate system.
[0018] A terminal device includes a processor, a memory, and a computer program stored in the memory; when the processor executes the computer program, it implements the online route planning method for UAV multi-mission point close-range reconnaissance.
[0019] A computer-readable storage medium storing a computer program; when executed by a processor, the computer program implements the online route planning method for multi-task point close-in reconnaissance of the UAV.
[0020] Compared with the prior art, the present invention has the following technical features: The method of this invention reduces the planned flight path and improves reconnaissance efficiency by preprocessing dense points and deciding the proximity order of mission points. Based on the performance of the aircraft, the step size and direction of the A* algorithm for expanding nodes are specifically improved to enhance the real-time performance of the algorithm. Ultimately, it realizes the function of UAV for close reconnaissance route planning for multiple mission points and can meet the real-time deployment requirements of airborne low-resource platforms, which has broad application prospects. Attached Figure Description
[0021] Figure 1 Flowchart of online flight path planning for multi-mission point close-range reconnaissance by unmanned aerial vehicles; Figure 2 Route planning result 1 (preprocessing of dense points + proximity order decision + improved A* + circling); Figure 3 Route planning result 2 (preprocessing of dense points + proximity order decision + A*); Figure 4 Route planning result 3 (preprocessing of dense points + A*); Figure 5 Route planning result 4(A*). Detailed Implementation
[0022] See appendix Figure 1 This invention provides an online route planning method for multi-mission point close-range reconnaissance by unmanned aerial vehicles (UAVs), comprising the following steps: First, identify all the task points to be reconnoitered within the task area. Based on the distribution of the task points and the detection swath of the UAV's onboard detection device, merge the dense task points and determine the equivalent task points to obtain the equivalent task point set, thus avoiding repeated reconnaissance of dense task points. Secondly, based on the positional distribution relationship between the UAV and the equivalent task point set, a greedy algorithm is used to determine the reconnaissance order of the equivalent task points; thereby reducing the invalid flight path and improving the traversal efficiency of the equivalent task points. Finally, based on the reconnaissance order of equivalent mission points, the maneuverability constraints of UAV turning radius and flight speed direction are added to the heuristic A* method, and obstacle avoidance in no-fly zones along the way are considered to complete the close reconnaissance route planning for all equivalent mission points in the mission area.
[0023] The UAV multi-mission point close-range reconnaissance route planning method provided by this invention has high reliability and strong real-time performance. It has strong engineering practicality and wide application scenarios. It can be extended to various military and civilian unmanned autonomous flight platforms for use in scenarios such as situation building and search and rescue, and has broad application prospects.
[0024] The specific design process of the present invention will be described in detail below with reference to the accompanying drawings.
[0025] 1. Determine dense task points based on the distribution of task points, and construct equivalent task points.
[0026] When multiple mission points to be reconnoitered are located in a relatively concentrated area within the mission region, i.e., multiple mission points are clustered together in the area of... Within a circle with radius , these task points are considered densely packed task points; among them, This is a preset proportional coefficient. This refers to the detection swath of the UAV-borne detection device.
[0027] To improve reconnaissance efficiency, the geometric center of dense mission points is used. As an equivalent mission point, subsequent close-in reconnaissance flight path planning will be carried out as follows: (1.1) Calculate every two task points within the task area relative distance between ,as follows:
[0028] in, and Indicates the first The northward and eastward positions of each task point in the North-East coordinate system. (1.2) Based on task points relative distance between Make a judgment if Then the task point For densely packed task points, at this time, the task points will be... As a mission point Dense points.
[0029] Calculate the number of dense points corresponding to each task point in turn, and construct a dense point information matrix. , Indicates the first The number of dense points for each task point; and the dense point index matrix corresponding to each task point. ,in Including the The numbering information of the dense points of each task point. (1.3) Information matrix of dense points Sort the task points in descending order to get the task point numbers sorted from most to least dense point. ;in , These represent the task point numbers with the most and fewest dense points, respectively. This represents the total number of task points.
[0030] (1.4) Sort by task point number ,Depend on arrive The equivalent task points are calculated sequentially based on the corresponding task point numbers: For task points with dense points ( ), calculate the average of the north and east positions of all task points as the coordinates of the equivalent task point; for task points without dense points ( If a task is a distributed task point, then the equivalent task point of that task point is itself.
[0031] By following the steps above, an equivalent task point set is constructed from all equivalent task points. ,in and They represent the first The northward and eastward positions of the equivalent task points in the North-East coordinate system.
[0032] During the calculation of equivalent task points, the index of the dense points that have already been calculated is marked, and they are not recalculated when calculating subsequent equivalent task points. For example, if the dense point sequence corresponding to task point A contains dense point C, and the dense point sequence corresponding to task point B also contains dense point C, and the number of dense points corresponding to A is greater than the number of dense points corresponding to B, then dense point C is considered in the calculation when calculating the equivalent task point of task point A and all its dense points, but dense point C is not considered when calculating the equivalent task point of task point B and its dense point sequence.
[0033] 2. Decision on the order of close reconnaissance of equivalent mission points.
[0034] Determine the equivalent task point set Subsequently, to reduce the planned flight path distance and improve reconnaissance efficiency, a greedy algorithm is used to determine the optimal approach order for reconnaissance of equivalent mission points. Based on this idea, the specific steps are as follows, using the distance between the UAV and the equivalent mission points, and the distance between each equivalent mission point, as input: Construct the relative distance matrix ;matrix In Indicates the current position of the drone and the number of... The distance between equivalent task points Indicates the first The equivalent task point and the first The distance between equivalent task points.
[0035] Considering the limited flight time of UAVs and the limited number of equivalent mission points, based on the relative distance matrix Use a greedy algorithm to find the optimal solution: Initially, select the closest equivalent mission point to the drone as the first approach point:
[0036] in, For the first The serial number of the equivalent task point that needs to be reconnoitered. Indicates taking The Middle The index corresponding to the minimum value in the row. and These represent the north and east positions of the equivalent task points selected after the order decision, respectively.
[0037] Once the first approach point is determined, the next equivalent task point is selected as the approach point based on the principle of being closest to other equivalent task points, and this process continues until all equivalent task points have been traversed.
[0038] Finally, the equivalent task point set after the order decision is obtained. .
[0039] 3. Planning of close-range reconnaissance routes for equivalent mission points.
[0040] The approach reconnaissance route is planned based on the order of approach reconnaissance of equivalent mission points; to ensure the flyability and real-time nature of the planned route, a heuristic planning method is used for route planning between adjacent equivalent mission points.
[0041] Because traditional heuristic A* methods do not consider the maneuverability of UAVs when planning routes, the turning radius of the UAV is used as the basis for route planning. Improve the node expansion step size and constrain the node expansion direction with the UAV flight direction to avoid sharp angles between the two flight paths and meet the UAV flight requirements; in addition, plan a hovering and standby flight path after completing the reconnaissance of the last equivalent mission point.
[0042] The A* method sets a heuristic cost function, node expansion direction, and node expansion step size. Under constraints, it expands nodes from the starting point to the ending point, and finally backtracks to obtain the optimal route. The specific process is as follows: Cost function As the basis for node expansion, each step of node expansion uses the node with the smallest cost function as the effective node. The cost function is set considering both the actual path cost and the expected cost, using the cumulative distance from the starting point (the previous equivalent task point) to the current node. Euclidean distance between the current node and the endpoint (current equivalent task point) The sum is as follows:
[0043]
[0044]
[0045] in, Indicates the first The north and east positions of each node. , Indicates the first The northward and eastward positions of the equivalent mission points that need to be reconnoitered.
[0046] The traditional A* algorithm selects eight directions as expansion directions at each step to increase the step size. As the distance increment for each expansion, the path cost of the node after expanding in each direction is then calculated. This leads to the determination of the optimal path, with the following expansion directions:
[0047] in, Representing all extended directions, {[1,0]; [0,1]; [-1,0]; [0,-1]; [1,1]; [-1,-1]; [1,-1]; [-1,1]} in the North-East coordinate system represent due north, due east, due south, due west, northeast, southwest, northwest, and southeast directions respectively.
[0048] Once the nodes have expanded to the endpoint, the node sequence from the starting point to the endpoint is obtained by backtracking based on the correspondence between each recorded node and its "parent node", forming the reconnaissance waypoints between the current equivalent task point and the previous equivalent task point.
[0049] (3.1) Expand node step size.
[0050] To ensure that the drone has sufficient maneuvering distance along a single flight path, with a turning radius As the node expansion step size The calculation is as follows:
[0051] in, This indicates the expected flight speed of the drone. It is the acceleration due to gravity. This represents the desired roll angle when turning.
[0052] (3.2) Extend node direction.
[0053] Considering that UAVs are unlikely to make sharp-angle turns during actual flight, waypoint design must ensure that continuous routes satisfy an angle of no less than 90°. Therefore, the direction strategy for node expansion using the heuristic algorithm is as follows:
[0054] in, Represents a node The scalable direction.
[0055] (3.3) Obstacle avoidance.
[0056] A safe distance is reserved at the edge of the no-fly zone. Each time a node is expanded, the distance between the node and the center of the no-fly zone is checked. The safety of the node is determined based on the distance, and only nodes that are safe are considered valid.
[0057] in, Represents a node With the The distance between the no-fly zones , , They represent the first The northward and eastward locations and radius of each no-fly zone. This indicates that a safe distance has been reserved. Represents a node Safety.
[0058] (3.4) Planning of the terminal circling and waiting route.
[0059] Due to the long endurance of UAVs, in order to enable them to receive new mission instructions after completing the current reconnaissance mission, the terminal flight speed direction is considered after the close-range reconnaissance route planning for the last equivalent mission point is completed. (i.e., the direction of the reconnaissance route), with A rectangular circling, standby flight path is planned based on the side length. The calculation is as follows:
[0060] in, and These represent the northward and eastward positions of the last reconnaissance waypoint relative to the last equivalent mission point, respectively. and These represent the northward and eastward positions of the penultimate reconnaissance waypoint relative to the last equivalent mission point, respectively.
[0061] The circling route is calculated as follows:
[0062] in, Indicates the first The coordinates of the reconnaissance waypoint in the North-East coordinate system.
[0063] Ultimately, multiple equivalent mission point close reconnaissance routes were obtained. .
[0064] In summary, this method first filters dense task points within a region based on the detection performance of the UAV's onboard detection device, obtaining an equivalent task point set to avoid redundant reconnaissance of multiple dense task points. Then, based on the positional distribution relationship between the UAV and the task point set, a greedy algorithm is used to determine the reconnaissance order, reducing ineffective flight paths. Finally, based on the reconnaissance order, maneuverability constraints are added to the heuristic route planning method to complete the close-range reconnaissance route planning for task points within the region. This UAV multi-task-point close-range reconnaissance route planning method exhibits high reliability, strong real-time performance, and strong engineering practicality. It has a wide range of applications and can be extended to various military and civilian unmanned autonomous flight platforms for use in scenarios such as regional situational awareness and search and rescue, demonstrating broad application prospects.
[0065] See Figures 2 to 5 ,in Figure 2 The result of using the present invention for route planning in one embodiment of the present invention is as follows: first, dense task points are preprocessed and converted into equivalent task points; second, the order of close reconnaissance of equivalent task points is decided; finally, an improved heuristic A* method is used to plan the close reconnaissance route, and the route is hovered and waited at the terminal.
[0066] Figure 3 This is for route planning results involving dense mission point preprocessing, equivalent mission point close-in reconnaissance order decision-making, and traditional heuristic A* methods.
[0067] Figure 4 The results of route planning are obtained by performing dense task point preprocessing and using the traditional heuristic A* method.
[0068] Figure 5 This represents the route planning results from the traditional heuristic A* method.
[0069] from Figures 2 to 5 It can be seen that the method of the present invention can effectively reduce the planned flight distance and improve reconnaissance efficiency.
[0070] The above embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application, and should all be included within the protection scope of this application.
Claims
1. A method for online route planning for multi-mission point close-range reconnaissance by unmanned aerial vehicles (UAVs), characterized in that, include: First, identify all task points to be reconnoitered within the task area. Based on the distribution of task points and the detection swath of the UAV's onboard detection device, merge densely packed task points and determine equivalent task points, resulting in an equivalent task point set, including: Calculate every two task points within the task area relative distance between ; Based on task points relative distance between Make a judgment if Then the task point For densely packed task points, at this time, the task points will be... As a mission point Dense points; among them This is a preset proportional coefficient. This refers to the detection swath width of the UAV-borne detection device; Calculate the number of dense points corresponding to each task point in turn, and construct a dense point information matrix. Sort the dense point information matrix in descending order to obtain task point numbers sorted from most to least numerous. ; Sort by task point number ,Depend on arrive The equivalent task points are calculated sequentially based on the corresponding task point numbers; where , These represent the task point numbers with the most and fewest dense points, respectively. Total number of task points; For task points with dense clusters, the average of the north and east directions of all task points is calculated as the coordinates of the equivalent task point; for task points without dense clusters, the equivalent task point is itself. Construct a set of equivalent task points from all equivalent task points; Secondly, based on the positional distribution relationship between the UAV and the equivalent task point set, a greedy algorithm is used to determine the reconnaissance order of the equivalent task points; Finally, based on the reconnaissance order of equivalent mission points, the maneuverability constraints of UAV turning radius and flight speed direction are added to the heuristic A* method, and obstacle avoidance in no-fly zones along the way are considered to complete the close reconnaissance route planning for all equivalent mission points in the mission area.
2. The online flight path planning method for multi-mission point close-range reconnaissance of unmanned aerial vehicles according to claim 1, characterized in that, In the process of calculating the equivalent task point, if the dense point sequence corresponding to task point A contains dense point C, and the dense point sequence corresponding to task point B also contains dense point C, and the number of dense points corresponding to A is greater than the number of dense points corresponding to B, then dense point C is considered in the calculation when calculating the equivalent task point of task point A and all its dense points, while dense point C is not considered when calculating the equivalent task point of task point B and its dense point sequence.
3. The online flight path planning method for UAV multi-mission point close-range reconnaissance according to claim 1, characterized in that, Based on the positional distribution relationship between the UAV and the equivalent task point set, a greedy algorithm is used to determine the reconnaissance order of the equivalent task points, including: Construct a relative distance matrix, which includes the distance between the UAV’s current position and each equivalent task point, as well as the distance between any two equivalent task points; The optimal solution is found using a greedy algorithm based on the relative distance matrix: Initially, select the equivalent mission point closest to the drone as the first approach point; Once the first approach point is determined, the next equivalent task point is selected as the approach point based on the principle that the current equivalent task point is closest to other equivalent task points, and so on, until all equivalent task points are traversed, and finally the set of equivalent task points after the order decision is obtained.
4. The online flight path planning method for multi-mission point close-range reconnaissance of unmanned aerial vehicles according to claim 1, characterized in that, The heuristic A* method sets a heuristic cost function, node expansion direction, and node expansion step size. Under constraints, it expands nodes from the starting point to the ending point and finally backtracks to obtain the optimal route. The starting point is the previous equivalent task point or the starting point of the UAV, and the ending point is the current equivalent task point. In each step of node expansion, the node with the smallest substitution function is taken as the effective node. The cumulative distance from the starting point to the current node and the Euclidean distance between the current node and the destination are used. When expanding a node in each step, the expansion direction is selected, and the expansion step size is used as the distance increment for each expansion. Then, the path cost of the node after expansion in each direction is calculated to determine the optimal path. After the node expands to the destination, the node sequence from the starting point to the destination is obtained by backtracking according to the correspondence between each node and its parent node, which constitutes the reconnaissance waypoint between the current equivalent task point and the previous equivalent task point.
5. The online flight path planning method for UAV multi-mission point close-range reconnaissance according to claim 4, characterized in that, With turning radius As the node expansion step size The calculation is as follows: ； in, This indicates the expected flight speed of the drone. It is the acceleration due to gravity. This represents the desired roll angle when turning.
6. The online route planning method for multi-mission point close-range reconnaissance of unmanned aerial vehicles according to claim 4, characterized in that, When expanding nodes, the direction strategy is as follows: ； in, Represents a node The expandable directions are: [1,0]; [0,1]; [-1,0]; [0,-1]; [1,1]; [-1,-1]; [1,-1]; [-1,1], which represent the directions of due north, due east, due south, due west, northeast, southwest, northwest, and southeast respectively in the North-East coordinate system.
7. The online flight path planning method for UAV multi-mission point close-range reconnaissance according to claim 4, characterized in that, A safe distance is reserved at the edge of the no-fly zone. Each time a node is expanded, the distance between the node and the center of the no-fly zone is checked. The safety of the node is determined based on the distance, and only nodes that are safe are considered valid. ； in, Represents a node With the The distance between the no-fly zones , , They represent the first The northward and eastward locations and radius of each no-fly zone. This indicates that a safe distance has been reserved. Represents a node Safety.
8. The online route planning method for multi-mission point close-range reconnaissance of unmanned aerial vehicles according to claim 5, characterized in that, After completing the close-range reconnaissance route planning for the last equivalent mission point, the terminal flight speed direction is considered. ,by A rectangular circling, standby flight path is planned based on the side length. The calculation is as follows: ； in, and These represent the northward and eastward positions of the last reconnaissance waypoint relative to the last equivalent mission point, respectively. and These represent the north and east positions of the penultimate reconnaissance waypoint relative to the last equivalent mission point, respectively; The circling route is calculated as follows: ； in, Indicates the first The coordinates of the reconnaissance waypoint in the North-East coordinate system.
9. A terminal device, comprising a processor, a memory, and a computer program stored in the memory; characterized in that, When the processor executes the computer program, it implements the online route planning method for UAV multi-mission point close-range reconnaissance as described in any one of claims 1-8.