A loitering trajectory planning method of an unmanned aerial vehicle and related devices

Abstract

Embodiments of the present application disclose a loitering track planning method of an unmanned aerial vehicle and related equipment, the method comprising: acquiring target region data of an unmanned aerial vehicle operation and generating a navigation map; planning a first track from a launch point of the unmanned aerial vehicle to each node in the navigation map and a second track from each node in the navigation map to a target point based on the launch point and the target point of the unmanned aerial vehicle using an LCALR algorithm, and acquiring a usefulness cost of the first track and the second track; constructing a loitering loop based on a genetic algorithm and the usefulness cost; and constructing a loitering track of the unmanned aerial vehicle based on the first track, the second track and the loitering loop. In view of the low search efficiency of the loitering loop of LCALR, the genetic algorithm is used to replace the improved LCA to search for an optimal loitering loop, thereby improving the search efficiency of the loitering loop.

Description

Technical Field

[0001] This invention relates to the field of trajectory planning technology, and more particularly to a method and related equipment for planning the loitering trajectory of an unmanned aerial vehicle. Background Technology

[0002] As a typical representative of unmanned aerial vehicles (UAVs), cruise unmanned aerial vehicles (UAVs), supported by satellite communication data links and human-in-the-loop guidance technology, possess the capabilities to perform multiple support missions, engage targets undergoing change, conduct target reconnaissance, and assess damage. The new capabilities of controllable UAVs dictate that their flight paths, in addition to the path from launch point to target point, also include loitering paths used for tactical loitering, and the evaluation criteria for these paths extend beyond just flight distance and safety.

[0003] Existing flight path planning methods for unmanned aerial vehicles (UAVs) can generate relatively satisfactory wandering paths using LCALR. However, the wandering loops generated by LCALR require searching for nodes in the planning space until the algorithm finds a closed loop. The search for wandering loops takes a long time, resulting in low efficiency in flight path planning for UAVs. Summary of the Invention

[0004] In view of this, the present invention provides a method and related equipment for planning the loitering trajectory of an unmanned aerial vehicle (UAV), which solves the problems of high computational load and low efficiency when using methods such as LCALR to plan flight trajectories in the prior art. To achieve one, some, or all of the above objectives, or other objectives, the present invention proposes a method for planning the loitering trajectory of an UAV, comprising: acquiring target area data of the UAV's operation and generating a navigation map, wherein the navigation map includes a threat zone and a flexible target emergence zone;

[0005] Based on the launch point and target point of the unmanned aerial vehicle, the LCALR algorithm is used to plan the first path from the launch point to each node in the navigation map and the second path from each node in the navigation map to the target point, and the usefulness cost of the first path and the second path and the parent node linked list are obtained.

[0006] The target wandering cycle is determined by combining a genetic algorithm with the aforementioned usefulness cost;

[0007] The loitering trajectory of the unmanned aerial vehicle is constructed based on the launch point, the target point, and the target loitering loop.

[0008] Optionally, the steps of planning a first path from the launch point to each node in the navigation map and a second path from each node in the navigation map to the target point using the LCALR algorithm based on the launch point and target point of the unmanned aerial vehicle, and obtaining the usefulness cost and parent node list of the first path and the second path according to the threat zone and the flexible target emergence zone, include:

[0009] The LCALR algorithm is used to plan the minimum risk trajectory from the launch point to the target point;

[0010] Based on the minimum risk trajectory, a first trajectory from the launch point to each node in the navigation map and a second trajectory from each node in the navigation map to the target point are determined.

[0011] Obtain the distance cost of the first track and the second track;

[0012] The usefulness cost and parent node list of the first and second tracks are obtained based on the distance cost and the emergence probability of flexible targets within the threat zone and / or the flexible target emergence zone.

[0013] Optionally, the step of determining the target wandering cycle based on the genetic algorithm and the usefulness cost includes:

[0014] A real-number-based gene encoding method was used to represent each wandering loop individual in a linked list structure, thus completing the encoding of each wandering loop individual;

[0015] Individual evaluations are performed on each lingering loop that has been coded to obtain initial lingering loops that meet preset conditions;

[0016] The initial wandering cycle is searched using a target selection operator, an arithmetic crossover operator, and a uniform mutation operator to obtain the target wandering cycle.

[0017] Optionally, before the step of searching the initial wandering cycle using the target selection operator, arithmetic crossover operator, and uniform mutation operator to obtain the target wandering cycle, the method further includes:

[0018] The random league selection strategy and the optimal retention strategy are used as the target selection operators.

[0019] Optionally, the step of searching the initial wandering cycle using a target selection operator, an arithmetic crossover operator, and a uniform mutation operator to obtain the target wandering cycle includes:

[0020] Using a random league selection strategy and an optimal retention strategy, the selection operation of track individuals is performed according to the random league selection method, and the structure of the track individual with the highest fitness in the current group is completely copied to the next generation group;

[0021] The arithmetic crossover operator is used to add new individuals to the next generation population;

[0022] The intersection point of the initial wandering loop and the uniform mutation operator are respectively used as the center point coordinates and magnitude of the newly added wandering loop;

[0023] When the search process meets the preset lingering loop search termination criterion, the search for the initial lingering loop is stopped, and the target lingering loop is obtained.

[0024] Optionally, the step of constructing the loitering trajectory of the unmanned aerial vehicle based on the launch point, the target point, and the target loitering loop includes:

[0025] The parent node linked list of the minimum risk track storage is used to backtrack the track from the launch point to the target lingering loop and the track from the target lingering loop to the target point;

[0026] The loitering trajectory of the unmanned aerial vehicle is constructed based on the target loitering loop, the trajectory from the launch point to the target loitering loop, and the trajectory from the target loitering loop to the target point.

[0027] Optionally, the step of backtracking the track from the launch point to the target lingering loop and from the target lingering loop to the target point using the parent node linked list of the minimum risk track storage includes:

[0028] Based on the principle of minimizing the Euclidean distance from the launch point to the navigation point on the target lingering ring, a first target point is selected on the target lingering ring.

[0029] Based on the principle of minimizing the Euclidean distance from the target point to the navigation point on the target lingering loop, a second target point is selected on the target lingering loop;

[0030] Based on the first target point and the second target point, backtracking is performed in the parent node linked list to obtain the track from the launch point to the target lingering loop and the track from the target lingering loop to the target point.

[0031] On the other hand, this application provides a loitering trajectory planning device for an unmanned aerial vehicle, the planning device comprising:

[0032] The data receiving module is used to acquire target area data of the unmanned aerial vehicle and generate a navigation map, which includes a threat zone and a flexible target emergence zone.

[0033] The usefulness cost calculation module is used to plan a first trajectory from the launch point to each node in the navigation map and a second trajectory from each node in the navigation map to the target point based on the launch point and target point of the unmanned aerial vehicle using the LCALR algorithm, and to obtain the usefulness cost of the first trajectory and the second trajectory and the parent node linked list.

[0034] The target wandering loop determination module is used to determine the target wandering loop by employing a genetic algorithm combined with the aforementioned usefulness cost;

[0035] The planning module is used to construct the loitering trajectory of the unmanned aerial vehicle based on the launch point, the target point, and the target loitering loop.

[0036] Thirdly, embodiments of this application provide an electronic device, including: a processor, a memory, and a bus. The memory stores machine-readable instructions executable by the processor. When the electronic device is running, the processor communicates with the memory through the bus. When the machine-readable instructions are executed by the processor, the steps of the hovering trajectory planning method for unmanned aerial vehicles described above are performed.

[0037] Fourthly, embodiments of this application provide a computer-readable storage medium storing a computer program, which, when executed by a processor, performs the steps of the above-described unmanned aerial vehicle loitering trajectory planning method.

[0038] Implementing the embodiments of the present invention will have the following beneficial effects:

[0039] By acquiring target area data for the unmanned aerial vehicle (UAV) and generating a navigation map, the LCALR algorithm is used to plan a first path from the launch point to each node in the navigation map and a second path from each node in the navigation map to the target point, based on the UAV's launch point and target point. The usefulness cost and parent node list of the first and second paths are obtained. A genetic algorithm is used in conjunction with the usefulness cost to determine the target lingering loop. The lingering path of the UAV is constructed based on the launch point, the target point, and the target lingering loop. Based on the LCALR-planned path, a genetic algorithm is used instead of the improved LCA algorithm to search for the optimal lingering loop, thereby improving the search efficiency. A lingering loop with the optimal lingering usefulness cost value is generated based on the lingering usefulness cost value of the path segment. Attached Figure Description

[0040] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0041] in:

[0042] Figure 1 This is a flowchart of a hovering trajectory planning method for an unmanned aerial vehicle provided in an embodiment of this application;

[0043] Figure 2 This is a flowchart of another method for planning the loitering trajectory of an unmanned aerial vehicle provided in the embodiments of this application;

[0044] Figure 3 This is a schematic diagram of a loitering trajectory in a loitering trajectory planning method for an unmanned aerial vehicle provided in an embodiment of this application;

[0045] Figure 4 This is a diagram of the individual structure of a loitering loop in a loitering trajectory planning method for an unmanned aerial vehicle provided in an embodiment of this application;

[0046] Figure 5 This is a schematic diagram illustrating the selection of the first and second target points in a loitering trajectory planning method for an unmanned aerial vehicle provided in an embodiment of this application.

[0047] Figure 6 This is a schematic diagram of loitering trajectory synthesis in a loitering trajectory planning method for an unmanned aerial vehicle provided in an embodiment of this application;

[0048] Figure 7 This is a schematic diagram of the structure of a loitering trajectory planning device for an unmanned aerial vehicle provided in an embodiment of this application;

[0049] Figure 8 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application;

[0050] Figure 9 This is a schematic diagram of the structure of a storage medium provided in an embodiment of this application. Detailed Implementation

[0051] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0052] like Figure 1 As shown in the figure, this application provides a method for planning the loitering trajectory of an unmanned aerial vehicle, including:

[0053] S101. Acquire target area data for the unmanned aerial vehicle and generate a navigation map, which includes a threat zone and a flexible target emergence zone;

[0054] For example, based on the battlefield environment, a directed graph G(V,E,W) marked with information needed for trajectory planning is generated, and threat zones and flexible target emergence areas are set;

[0055] S102. Based on the launch point and target point of the unmanned aerial vehicle, the LCALR algorithm is used to plan the first trajectory from the launch point to each node in the navigation map and the second trajectory from each node in the navigation map to the target point, and the usefulness cost of the first trajectory and the second trajectory is obtained according to the threat zone and the flexible target emergence zone.

[0056] For example, LCALR is used to plan the minimum risk path from the launch point to the target point, and the distance cost and parent node pointer list corresponding to each node from the launch point in the navigation graph G are stored to calculate the distance cost E that can be used for unmanned vehicle loitering flight. L This is equivalent to the maximum fuel value that can be used for unmanned aerial vehicle loitering flight; similarly, calculate and store the distance cost from the target point to each node in the navigation graph G, as well as the parent node pointer list.

[0057] S103. Use a genetic algorithm combined with the aforementioned usefulness cost to determine the target wandering cycle;

[0058] For example, applying GA to wandering cycle search requires determining the following issues: the encoding method for wandering cycle individuals, the evaluation method for wandering cycle individuals, and the determination of genetic operation operators.

[0059] S104. Construct the loitering trajectory of the unmanned aerial vehicle based on the launch point, the target point, and the target loitering loop.

[0060] By acquiring target area data for the unmanned aerial vehicle (UAV) and generating a navigation map, the LCALR algorithm is used to plan a first path from the launch point to each node in the navigation map and a second path from each node in the navigation map to the target point, based on the UAV's launch point and target point. The usefulness cost and parent node list of the first and second paths are obtained. A genetic algorithm is used in conjunction with the usefulness cost to determine the target lingering loop. The lingering path of the UAV is constructed based on the launch point, the target point, and the target lingering loop. Based on the LCALR-planned path, a genetic algorithm is used instead of the improved LCA algorithm to search for the optimal lingering loop, thereby improving the search efficiency. A lingering loop with the optimal lingering usefulness cost value is generated based on the lingering usefulness cost value of the path segment.

[0061] In one possible implementation, the steps of planning a first path from the launch point to each node in the navigation map and a second path from each node in the navigation map to the target point using the LCALR algorithm based on the launch point and target point of the unmanned aerial vehicle, and obtaining the usefulness cost of the first path and the second path and the parent node linked list according to the threat zone and the flexible target emergence zone, include:

[0062] The LCALR algorithm is used to plan the minimum risk trajectory from the launch point to the target point;

[0063] Based on the minimum risk trajectory, a first trajectory from the launch point to each node in the navigation map and a second trajectory from each node in the navigation map to the target point are determined.

[0064] Obtain the distance cost of the first track and the second track;

[0065] The usefulness cost and parent node list of the first and second tracks are obtained based on the distance cost and the emergence probability of flexible targets within the threat zone and / or the flexible target emergence zone.

[0066] For example, the usefulness cost u is used to measure the probability that an unmanned aerial vehicle (UAV) will receive a valid instruction to change its attack target during flight, change its attack target, and reach the designated target within a specified time. If the cost of all flight segments is positive, i.e. The aforementioned trajectory planning model will not yield trajectories containing loops, and directed loops in graph G will be disregarded. Therefore, to obtain loitering trajectories containing loops, this paper designs the loitering usefulness cost as a negative value. When planning loitering trajectories, using trajectory segments with negative loitering usefulness costs will help improve the target value of the loitering trajectory planning; if the usefulness cost of a trajectory segment is zero, it indicates no effect; while using a positive usefulness cost indicates damage to the target value. For trajectory segments within the threat range, if an UAV would be destroyed if flying in this segment, then tactical loitering flights within areas containing such trajectory segments are meaningless. Therefore, any trajectory segment with significant threat risk must be assigned a large positive value to ensure that the loitering trajectory does not include these segments.

[0067] For ease of explanation, the following definition is used to measure the cost of hesitating, specifically:

[0068] N a The number of emerging flexible targets

[0069] (x ai, y ai ): The coordinates of the suddenly appearing flexible target i (i = 1, 2, ..., N) a )

[0070] p ai : Indicates the position coordinates (x, y) of a suddenly appearing, flexible target. ai ,y ai The probability of occurrence

[0071] T a Effective time threshold for unmanned aerial vehicles (UAVs) to strike suddenly appearing, flexible targets.

[0072] t ijk : Expected time from the track segment connecting node j and node k to the default target

[0073] t jk The time taken for the unmanned vehicle to travel from node j to node k.

[0074] E jw The distance cost corresponding to the minimum risk trajectory from the launch point to node j.

[0075] E jd The distance cost corresponding to the minimum risk path from the target point to node j.

[0076] Among them, t ijk It is the distance from the midpoint of track segment jk to the flexible target divided by the theoretical speed of the unmanned vehicle.

[0077] In the following discussion, the following assumptions are made:

[0078] (x ai ,y ai The targets are uniformly distributed within the Emergent Target Area (ETA).

[0079] T a It follows an exponential distribution;

[0080] The expected location of the UAV receiving the attack target change command is the center position of the track segment ij.

[0081] If the probability of the i-th flexible target being selected is uniformly distributed, then p ai =1 / N a .

[0082] Assume that the flexible target i has been selected when the unmanned vehicle passes through the track segment jk, and let p ijk p represents the probability that the unmanned vehicle will reach the target on time. ijk The calculation method is shown in the formula:

[0083]

[0084] If the UAV changes its attack target while passing through flight path segment jk, the probability of the UAV successfully attacking the suddenly appearing agile target is:

[0085]

[0086] The minimum risk path distance from the launch point to node j and from node j to the target point may be greater than the minimum risk path distance from the launch point to the target point. In this case, assuming the UAV can change its target while performing tactical loitering flight, the probability of reaching the flexible target will decrease for all path segments starting from node j, because the loitering time spent by the UAV on these path segments cannot be the same as the loitering time spent on the minimum risk path segment from the launch point to the target point. Therefore, the loitering usefulness corresponding to path segment jk can be calculated according to the following formula:

[0087]

[0088] In one possible implementation, the step of determining the target wandering cycle based on the genetic algorithm and the usefulness cost includes:

[0089] A real-number-based gene encoding method was used to represent each wandering loop individual in a linked list structure, thus completing the encoding of each wandering loop individual;

[0090] Individual evaluations are performed on each lingering loop that has been coded to obtain initial lingering loops that meet preset conditions;

[0091] The initial wandering cycle is searched using a target selection operator, an arithmetic crossover operator, and a uniform mutation operator to obtain the target wandering cycle.

[0092] For example, assuming the same result accuracy, the computation time of the real-number encoded genetic algorithm can be reduced by an order of magnitude, such as... Figures 3-4 As shown, based on the characteristics of a wandering circle, its shape can generally be described by a rectangle, and the rectangle can be represented by its center point O. p (x o ,y o ,z o The length 'a' and width 'b' of the rectangle are used to represent the lingering loop individuals, and a linked list structure is used to represent them. (x) o ,y o ,z o O is the center point of the wandering loop. p Position, a ph Let a be the length of the rectangle corresponding to the wandering ring. ph =n1×d w b ph The width b of the rectangle corresponding to the wandering ring ph =n2×d w (d w (where n1 and n2 are integers, representing the grid width of the navigation map);

[0093] For example, in the search process for wandering cycles, there exist feasible and infeasible wandering cycles, and the goal of evolutionary search is to obtain the feasible optimal wandering cycle. Therefore, the individual evaluation methods differ for feasible and infeasible wandering cycles.

[0094] Assuming the population size is n, there are m feasible wandering cycles (m≤n), the i-th wandering cycle contains k track segments, and the wandering usefulness cost value corresponding to track segment j in the wandering cycle is u. j The corresponding elevation value is h j If the i-th wandering cycle is feasible, then the following condition must be met:

[0095] For each track segment j that makes up the wandering circle, z satisfies o ≥h j +h min , where h min The minimum altitude required for an aircraft to fly;

[0096] For each track segment j within the loitering loop, it is not within the threat zone.

[0097] The fitness f(i) of an individual in a wandering loop is calculated as follows:

[0098] When it is a feasible wandering cycle, f(i) = ff (i) and f f (i) The calculation method is as follows:

[0099]

[0100] When it is an infeasible wandering cycle, f(i) = f u (i) and f u (i) The calculation method is as follows:

[0101] Count the number of flight path segments n that do not meet the elevation feasibility conditions. h (i) and the number of track segments n that do not meet the threat feasibility condition t (i).

[0102]

[0103] Where μ is the penalty coefficient when elevation is infeasible, and η is the penalty coefficient when threat is infeasible. This represents the maximum fitness value of a feasible wandering cycle in the population.

[0104] In one possible implementation, before the step of searching the initial wandering cycle using the target selection operator, arithmetic crossover operator, and uniform mutation operator to obtain the target wandering cycle, the method further includes:

[0105] The random league selection strategy and the optimal retention strategy are used as the target selection operators.

[0106] For example, a genetic algorithm includes three basic operations: selection, crossover, and mutation. The selection operator employs a random league selection strategy and an optimal retention strategy. Specifically, it first performs the selection operation on track individuals using the random league selection method, and then completely replicates the structure of the individual with the highest fitness in the current population to the next generation, ensuring that the final result obtained by the algorithm at the end of the search is the track individual with the highest fitness ever encountered. The random league selection method is a selection method based on the fitness of individuals, which selects the individual with the highest fitness from several individuals each time and passes it on to the next generation.

[0107] In one possible implementation, the step of searching the initial wandering cycle using a target selection operator, an arithmetic crossover operator, and a uniform mutation operator to obtain the target wandering cycle includes:

[0108] Using a random league selection strategy and an optimal retention strategy, the selection operation of track individuals is performed according to the random league selection method, and the structure of the track individual with the highest fitness in the current group is completely copied to the next generation group;

[0109] The arithmetic crossover operator is used to add new individuals to the next generation population;

[0110] The intersection point of the initial wandering loop and the uniform mutation operator are respectively used as the center point coordinates and magnitude of the newly added wandering loop;

[0111] When the search process meets the preset lingering loop search termination criterion, the search for the initial lingering loop is stopped, and the target lingering loop is obtained.

[0112] For example, the crossover operator uses the arithmetic crossover operator, where the method for generating new individuals is as shown in the following equation:

[0113]

[0114] In the formula, X A (i), X B (i) is the parent individual, X A (i+1)X B (i+1) represents the newly generated offspring individual, and λ is a random number within [0,1] that conforms to a uniform distribution probability. The mutation operator is a uniform mutation operator, which replaces the original gene values ​​at each locus in the individual's encoding string with random numbers conforming to a uniform distribution within a certain range, each with a certain mutation probability. The calculation method for the new gene values ​​at the mutation points is shown in the following formula:

[0115] X′(i)=X min λ×(X max -X min )

[0116] In the formula, X′(i) is the new individual after mutation, X min X max Let be the minimum and maximum values ​​of the new individual variation, respectively, and let λ be a random number in [0,1] that conforms to a uniform probability distribution.

[0117] The crossover and variation parameters of the wandering cycle are the coordinates of the center point of the wandering cycle (x... o ,y o ,z o ) and the magnitude of the wandering ring a ph b ph In the early stages of evolution, there are many infeasible wandering cycles, so a larger crossover and mutation probability is adopted. As evolution progresses and the number of feasible wandering cycles increases, the crossover and mutation probabilities are correspondingly reduced. When backtracking the trajectory from the launch point to the wandering cycle using the parent node linked list Listfm stored in the minimum risk trajectory storage, a node on the wandering cycle needs to be given so that the trajectory can be backtracked in the parent node linked list Listfm. Based on the principle of the shortest Euclidean distance from the launch point to the navigation point on the wandering cycle, the appropriate planning endpoint is selected, such as... Figure 5In the planning process, the end point should be the first target point on the wandering loop, navigation point pp1. Similarly, the initial data for the trajectory planning from the wandering loop to the target point can be obtained, and the starting point of the planning should be the second target point on the wandering loop, navigation point pp2.

[0118] In one possible implementation, the step of constructing the loitering trajectory of the unmanned aerial vehicle based on the launch point, the target point, and the target loitering loop includes:

[0119] The parent node linked list of the minimum risk track storage is used to backtrack the track from the launch point to the target lingering loop and the track from the target lingering loop to the target point;

[0120] The loitering trajectory of the unmanned aerial vehicle is constructed based on the target loitering loop, the trajectory from the launch point to the target loitering loop, and the trajectory from the target loitering loop to the target point.

[0121] For example, when the positions of the launch point, target point, and loitering loop are as follows: Figure 6 As shown, the lingering loop generated by the GA algorithm can be represented as (pp1, pp2, pp3, pp4, pp1), and the trajectory from the launch point to the lingering loop generated by backtracking through the parent node linked list Listfm can be represented as (S, wp1, wp2, ..., wp). k The trajectory from the wandering loop to the target point generated by backtracking through the parent node linked list Listmf can be represented as (pp2, wp). k+1 wp k+2 ..., wp n If T), then the generated wandering track can be represented as follows: Figure 6 As shown.

[0122] In one possible implementation, the step of backtracking the track from the launch point to the target lingering loop and from the target lingering loop to the target point using the parent node linked list of the minimum risk track storage includes:

[0123] Based on the principle of minimizing the Euclidean distance from the launch point to the navigation point on the target lingering ring, a first target point is selected on the target lingering ring.

[0124] Based on the principle of minimizing the Euclidean distance from the target point to the navigation point on the target lingering loop, a second target point is selected on the target lingering loop;

[0125] Based on the first target point and the second target point, backtracking is performed in the parent node linked list to obtain the track from the launch point to the target lingering loop and the track from the target lingering loop to the target point.

[0126] In one possible implementation, such as Figure 2As shown, a method for planning the loitering trajectory of an unmanned aerial vehicle (UAV) includes: generating a directed graph G(V,E,W) marked with information required for trajectory planning based on the battlefield environment; setting threat zones and flexible target emergence zones; using LCALR to plan the minimum risk trajectory from the launch point to the target point; storing the distance cost from the launch point to each node and the parent node pointer list in the navigation graph G; and calculating the distance cost E that can be used for UAV loitering flight. L (Equivalent to the maximum fuel value usable for unmanned vehicle loitering flight), using the same method, the distance cost from the target point to each node in the navigation graph G, along with the parent node pointer list, is calculated and stored. Based on the calculated distance cost value and the flexible target emergence probability, the loitering usefulness cost of each track segment in graph G is calculated. Based on the loitering usefulness cost value of the track segment, a loitering loop with the optimal loitering usefulness cost value is generated. Combining the track generated from the start point to the loitering loop and from the loitering loop to the end point using the LCALR algorithm, a loitering track is finally generated.

[0127] On the other hand, such as Figure 7 As shown, this application provides a loitering trajectory planning device for an unmanned aerial vehicle, the planning device comprising:

[0128] The data receiving module 201 is used to acquire target area data of the unmanned aerial vehicle and generate a navigation map;

[0129] The usefulness cost calculation module 202 is used to plan a first trajectory from the launch point to each node in the navigation map and a second trajectory from each node in the navigation map to the target point based on the launch point and target point of the unmanned aerial vehicle using the LCALR algorithm, and to obtain the usefulness cost of the first trajectory and the second trajectory and the parent node linked list.

[0130] The target wandering loop determination module 203 is used to determine the target wandering loop by using a genetic algorithm combined with the usefulness cost;

[0131] Planning module 204 is used to construct the loitering trajectory of the unmanned aerial vehicle based on the launch point, the target point, and the target loitering loop.

[0132] One possible implementation, such as Figure 8As shown, this application embodiment provides an electronic device 300, including: a memory 310, a processor 320, and a computer program 311 stored in the memory 310 and executable on the processor 320. When the processor 320 executes the computer program 311, it performs the following steps: acquiring target area data of the unmanned aerial vehicle (UAV) and generating a navigation map; planning a first path from the launch point to each node in the navigation map and a second path from each node in the navigation map to the target point using the LCALR algorithm based on the launch point and target point of the UAV, and acquiring the usefulness cost and parent node list of the first path and the second path; determining the target lingering loop using a genetic algorithm combined with the usefulness cost; and constructing the lingering path of the UAV based on the launch point, the target point, and the target lingering loop.

[0133] In one possible implementation, such as Figure 9 As shown, this application embodiment provides a computer-readable storage medium 400, on which a computer program 411 is stored. When the computer program 411 is executed by a processor, it implements the following steps: acquiring target area data of the unmanned aerial vehicle (UAV) and generating a navigation map; planning a first path from the launch point to each node in the navigation map and a second path from each node in the navigation map to the target point using the LCALR algorithm based on the launch point and target point of the UAV, and acquiring the usefulness cost and parent node list of the first path and the second path; determining the target lingering cycle using a genetic algorithm combined with the usefulness cost; and constructing the lingering path of the UAV based on the launch point, the target point, and the target lingering cycle.

[0134] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. Computer-readable signal media may also be any computer-readable medium other than computer-readable storage media, capable of sending, propagating, or transmitting programs for use by or in connection with an instruction execution system, apparatus, or device.

[0135] Program code contained on a computer-readable medium may be transmitted using any suitable medium, including but not limited to: wireless, wire, optical fiber, RF, etc., or any suitable combination thereof.

[0136] Computer program code for performing the operations of this invention can be written in one or more programming languages ​​or a combination thereof. These programming languages ​​include object-oriented programming languages ​​such as Java, Smalltalk, and C++, as well as conventional procedural programming languages—such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0137] Those skilled in the art will understand that the modules or steps of the present invention described above can be implemented using general-purpose computing devices. They can be centralized on a single computing device or distributed across a network of multiple computing devices. Optionally, they can be implemented using computer-executable program code, thereby allowing them to be stored in a storage device for execution by a computing device, or they can be fabricated as separate integrated circuit modules, or multiple modules or steps can be fabricated as a single integrated circuit module. Thus, the present invention is not limited to any particular combination of hardware and software.

[0138] Note that the above description is merely a preferred embodiment of the present invention and the technical principles employed. Those skilled in the art will understand that the present invention is not limited to the specific embodiments described herein, and various obvious changes, readjustments, and substitutions can be made without departing from the scope of protection of the present invention. Therefore, although the present invention has been described in detail through the above embodiments, the present invention is not limited to the above embodiments, and may include many other equivalent embodiments without departing from the concept of the present invention, the scope of which is determined by the scope of the appended claims.

[0139] The above description discloses only preferred embodiments of the present invention and should not be construed as limiting the scope of the present invention. Therefore, equivalent variations made in accordance with the claims of the present invention are still within the scope of the present invention.

Claims

1. A method for planning the loitering trajectory of an unmanned aerial vehicle, characterized in that, include: Acquire target area data for the unmanned aerial vehicle and generate a navigation map, which includes a threat zone and a flexible target emergence zone; Based on the launch point and target point of the unmanned aerial vehicle, the LCALR algorithm is used to plan the first path from the launch point to each node in the navigation map and the second path from each node in the navigation map to the target point, and the usefulness cost of the first path and the second path and the parent node linked list are obtained. The target wandering cycle is determined using a genetic algorithm combined with the aforementioned usefulness cost; The loitering trajectory of the unmanned aerial vehicle is constructed based on the launch point, the target point, and the target loitering loop.

2. The method for planning the loitering trajectory of an unmanned aerial vehicle as described in claim 1, characterized in that, The steps of planning a first path from the launch point to each node in the navigation map and a second path from each node in the navigation map to the target point using the LCALR algorithm based on the launch point and target point of the unmanned aerial vehicle, and obtaining the usefulness cost and parent node list of the first path and the second path according to the threat zone and the flexible target emergence zone, include: The LCALR algorithm is used to plan the minimum risk trajectory from the launch point to the target point; Based on the minimum risk trajectory, a first trajectory from the launch point to each node in the navigation map and a second trajectory from each node in the navigation map to the target point are determined. Obtain the distance cost of the first track and the second track; The usefulness cost and parent node list of the first and second tracks are obtained based on the distance cost and the emergence probability of flexible targets within the threat zone and / or the flexible target emergence zone.

3. The method for planning the loitering trajectory of an unmanned aerial vehicle as described in claim 1, characterized in that, The step of determining the target wandering cycle using a genetic algorithm combined with the usefulness cost includes: A real-number-based gene encoding method was used to represent each wandering loop individual in a linked list structure, thus completing the encoding of each wandering loop individual; Individual evaluations are performed on each lingering loop that has been encoded to obtain initial lingering loops that meet preset conditions; The initial wandering cycle is searched using a target selection operator, an arithmetic crossover operator, and a uniform mutation operator to obtain the target wandering cycle.

4. The method for planning the loitering trajectory of an unmanned aerial vehicle as described in claim 3, characterized in that, Before the step of searching the initial wandering cycle using the target selection operator, arithmetic crossover operator, and uniform mutation operator to obtain the target wandering cycle, the method further includes: The random league selection strategy and the optimal retention strategy are used as the target selection operators.

5. The method for planning the loitering trajectory of an unmanned aerial vehicle as described in claim 4, characterized in that, The step of searching for the initial wandering cycle using a target selection operator, an arithmetic crossover operator, and a uniform mutation operator to obtain the target wandering cycle includes: Using a random league selection strategy and an optimal retention strategy, the selection operation of track individuals is performed according to the random league selection method, and the structure of the track individual with the highest fitness in the current group is completely copied to the next generation group; The arithmetic crossover operator is used to add new individuals to the next generation population; The intersection point of the initial wandering loop and the uniform mutation operator are respectively used as the center point coordinates and magnitude of the newly added wandering loop; When the search process meets the preset lingering loop search termination criterion, the search for the initial lingering loop is stopped, and the target lingering loop is obtained.

6. The method for planning the loitering trajectory of an unmanned aerial vehicle as described in claim 1, characterized in that, The step of constructing the loitering trajectory of the unmanned aerial vehicle based on the launch point, the target point, and the target loitering loop includes: The parent node linked list of the minimum risk track storage is used to backtrack the track from the launch point to the target lingering loop and the track from the target lingering loop to the target point; The loitering trajectory of the unmanned aerial vehicle is constructed based on the target loitering loop, the trajectory from the launch point to the target loitering loop, and the trajectory from the target loitering loop to the target point.

7. The hovering trajectory planning method for an unmanned aerial vehicle as described in claim 6, characterized in that, The steps of backtracking the trajectory from the launch point to the target lingering loop and from the target lingering loop to the target point using the parent node linked list stored in the minimum risk trajectory storage include: Based on the principle of minimizing the Euclidean distance from the launch point to the navigation point on the target lingering ring, a first target point is selected on the target lingering ring. Based on the principle of minimizing the Euclidean distance from the target point to the navigation point on the target lingering loop, a second target point is selected on the target lingering loop; Based on the first target point and the second target point, backtracking is performed in the parent node linked list to obtain the track from the launch point to the target lingering loop and the track from the target lingering loop to the target point.

8. A loitering trajectory planning device for an unmanned aerial vehicle, characterized in that, The planning device includes: The data receiving module is used to acquire target area data of the unmanned aerial vehicle and generate a navigation map, which includes a threat zone and a flexible target emergence zone. The usefulness cost calculation module is used to plan a first trajectory from the launch point to each node in the navigation map and a second trajectory from each node in the navigation map to the target point based on the launch point and target point of the unmanned aerial vehicle using the LCALR algorithm, and to obtain the usefulness cost of the first trajectory and the second trajectory and the parent node linked list. The target wandering loop determination module is used to determine the target wandering loop by employing a genetic algorithm combined with the aforementioned usefulness cost; The planning module is used to construct the loitering trajectory of the unmanned aerial vehicle based on the launch point, the target point, and the target loitering loop.

9. An electronic device, comprising: The device includes a processor, a memory, and a bus. The memory stores machine-readable instructions executable by the processor. When the electronic device is running, the processor communicates with the memory via the bus. When the machine-readable instructions are executed by the processor, the steps of the loitering trajectory planning method for an unmanned aerial vehicle as described in any one of claims 1 to 7 are performed.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, performs the steps of the unmanned aerial vehicle loitering trajectory planning method as described in any one of claims 1 to 7.

Images