A loitering trajectory planning method and related equipment for unmanned aerial vehicle

Abstract

The embodiment of the present invention discloses a method for planning a wandering trajectory of an unmanned aerial vehicle and related equipment. The method includes: obtaining target area data of the operation of the unmanned aerial vehicle and generating a navigation map; using the LCALR algorithm based on the launch point and the target point of the unmanned aerial vehicle 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, and obtaining the usefulness cost of the first trajectory and the second trajectory; substituting the launch point and the target point into the preset planning model, using a preset algorithm based on the LCALR algorithm and a constrained Lagrangian relaxation algorithm combined with the usefulness cost to solve the preset planning model, and obtaining a wandering loop of the unmanned aerial vehicle from the launch point to the target point; and constructing the wandering trajectory of the unmanned aerial vehicle based on the first trajectory, the second trajectory and the wandering loop.

Description

Technical Field

[0001] The present invention relates to the technical field of track planning, and in particular to a wandering track planning method for an unmanned aerial vehicle and related equipment. Background Art

[0002] As a typical representative of unmanned aerial vehicles, cruise drones, with the support of satellite communication data links and "man-in-the-loop" guidance technology, have the ability to perform multiple support tasks, change strike targets, target reconnaissance and damage assessment. The new capabilities of controllable unmanned aerial vehicles determine that the flight track of unmanned aerial vehicles includes not only the track from the launch point to the target point, but also the loitering track for tactical loitering flight, and the evaluation indicators of the track are not only required to be flight distance and safety.

[0003] The existing flight trajectory planning method for unmanned aerial vehicles only considers the flight distance and safety of the unmanned aerial vehicles, which is far from meeting the needs of unmanned aerial vehicles performing multiple support tasks, changing strike targets, and target reconnaissance tasks. Therefore, it requires a large number of professional background control and lacks sufficient intelligence. Summary of the invention

[0004] In view of this, the present invention provides a loitering trajectory planning method and related equipment for an unmanned aerial vehicle, which is used to solve the problem that the trajectory planning method in the prior art cannot meet the needs of more and more types of tasks. In order to achieve one or part or all of the above purposes or other purposes, the present invention proposes a loitering trajectory planning method for an unmanned aerial vehicle, including: obtaining target area data of the unmanned aerial vehicle operation and generating a navigation map, wherein the navigation map includes a threat area and a flexible target emergence area;

[0005] Based on the launch point and the target point of the unmanned aerial vehicle, a first track from the launch point to each node in the navigation map and a second track from each node in the navigation map to the target point are planned using an LCALR algorithm, and the usefulness costs of the first track and the second track are obtained according to the threat area and the flexible target emergence area;

[0006] Substituting the launch point and the target point into the preset planning model, solving the preset planning model by using a preset algorithm based on the LCALR algorithm and a Lagrangian relaxation algorithm with constraints combined with the usefulness cost, and obtaining a wandering loop of the unmanned aerial vehicle from the launch point to the target point;

[0007] A wandering track of the unmanned aerial vehicle is constructed based on the first track, the second track and the wandering loop.

[0008] Optionally, the step of planning a first track from the launch point to each node in the navigation map and a second track from each node in the navigation map to the target point using an LCALR algorithm based on the launch point and the target point of the unmanned aerial vehicle, and obtaining the usefulness cost of the first track and the second track according to the threat area and the flexible target emergence area includes:

[0009] Using the LCALR algorithm to plan a minimum risk trajectory from the launch point to the target point;

[0010] Determine a first track from the launch point to each node in the navigation map and a second track from each node in the navigation map to the target point based on the minimum risk track;

[0011] Obtaining distance cost values ​​between the first track and the second track;

[0012] The usefulness costs of the first track and the second track are obtained according to the distance cost value and the emergence probability of the flexible target in the threat area and / or the flexible target emergence area.

[0013] Optionally, the step of substituting the launch point and the target point into the preset planning model, solving the preset planning model using a preset algorithm based on the LCALR algorithm and a Lagrangian relaxation algorithm with constraints in combination with the usefulness cost, and obtaining a wandering loop of the unmanned aerial vehicle from the launch point to the target point includes:

[0014] Substituting the launch point and the target point into the preset planning model, the preset algorithm based on the LCALR algorithm in the preset planning model is combined with the usefulness cost to calculate the target wandering track;

[0015] Determine the upper and lower bounds of the Lagrangian relaxation coefficient based on the constraint conditions, obtain the constrained Lagrangian relaxation algorithm, and screen the target feasible solution of the unmanned aerial vehicle from the launch point to the target point in the target wandering track according to the constrained Lagrangian relaxation algorithm;

[0016] The target feasible solution is taken as a wandering loop of the UAV from the launch point to the target point.

[0017] Optionally, the step of calculating the target wandering track by combining the preset algorithm based on the LCALR algorithm in the preset planning model with the usefulness cost includes:

[0018] Select a target node in the navigation graph, set a target cost label from a launch point to the target node to an infinite real number, set the parent node of the launch point to the launch point itself, and initialize the target cost label of the launch point;

[0019] Check whether the first-in-first-out node linked list is empty, and if the first-in-first-out node linked list is not empty, remove the first node in the first-in-first-out node linked list;

[0020] Obtain all adjacent track segments corresponding to the first node that satisfy the maximum turning angle constraint of the unmanned aerial vehicle;

[0021] A target wandering track is obtained based on the adjacent track segments and the usefulness cost.

[0022] Optionally, the step of obtaining the target wandering track based on the adjacent track segments and the usefulness cost includes:

[0023] The track segment from the target node to the first node is used as the target track segment. When the target cost from the launch point to the target node is greater than the sum of the target cost from the launch point to the first node and the target cost of the target track segment, the target cost of the target node, the distance cost of the minimum cost track and the risk cost of the minimum cost track are updated, and the parent node of the target node is updated to the first node to obtain an initial wandering track;

[0024] It is determined whether the initial wandering track has a directed negative cycle, and if the initial wandering track has a directed negative cycle, the initial wandering track is used as the target wandering track.

[0025] Optionally, before the step of determining whether the initial wandering track has a directed negative cycle, the method further includes:

[0026] Obtaining a parent node set in a minimum cost trajectory from the launch point to the target node;

[0027] Determine whether the first node exists in the parent node set;

[0028] If the first node exists in the parent node set, the initial wandering track is used as the target wandering track;

[0029] If the first node does not exist in the parent node set, it is determined whether there is a directed negative cycle in the initial wandering track.

[0030] Optionally, the step of determining the upper and lower bounds of the Lagrangian relaxation coefficient based on the constraint conditions to obtain the Lagrangian relaxation algorithm with constraints, and screening the target feasible solution of the unmanned aerial vehicle from the launch point to the target point in the target wandering track according to the Lagrangian relaxation algorithm with constraints includes:

[0031] When there is a directed negative cycle in the target wandering track, a target wandering track where a negative cycle corresponding to the ratio of usefulness cost to distance cost is located is selected in the target wandering track to obtain a target feasible solution for the unmanned aerial vehicle from the launch point to the target point;

[0032] When there is no directed negative cycle in the target wandering track, a feasible track with the highest usefulness cost is selected in the target wandering track to obtain a target feasible solution for the unmanned aerial vehicle from the launch point to the target point.

[0033] On the other hand, an embodiment of the present application further provides a loitering trajectory planning device for an unmanned aerial vehicle, the planning device comprising:

[0034] A data receiving module is used to obtain target area data of the unmanned aerial vehicle and generate a navigation map, wherein the navigation map includes a threat area and a flexible target emergence area;

[0035] A usefulness cost calculation module, configured to plan a first track from the launch point to each node in the navigation map and a second track from each node in the navigation map to the target point using an LCALR algorithm based on the launch point and the target point of the unmanned aerial vehicle, and obtain usefulness costs of the first track and the second track according to the threat area and the flexible target emergence area;

[0036] A wandering loop solving module, used for substituting the launch point and the target point into the preset planning model, using a preset algorithm based on the LCALR algorithm and a Lagrangian relaxation algorithm with constraints and combining the usefulness cost to solve the preset planning model, and obtaining a wandering loop of the unmanned aerial vehicle from the launch point to the target point;

[0037] A planning module is used to construct a wandering track of the unmanned aerial vehicle based on the first track, the second track and the wandering ring.

[0038] In a third aspect, an embodiment of the present application provides an electronic device, comprising: a processor, a memory and a bus, wherein the memory stores machine-readable instructions executable by the processor, and when the electronic device is running, the processor and the memory communicate through the bus, and when the machine-readable instructions are executed by the processor, the steps of the wandering trajectory planning method for an unmanned aerial vehicle as described above are performed.

[0039] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the above-mentioned method for planning the wandering trajectory of an unmanned aerial vehicle are executed.

[0040] Implementing the embodiments of the present invention will have the following beneficial effects:

[0041] The target area data of the unmanned aerial vehicle is obtained, and a navigation map is generated, wherein the navigation map includes a threat area and a flexible target emergence area; based on the launch point and the target point of the unmanned aerial vehicle, a first track from the launch point to each node in the navigation map and a second track from each node in the navigation map to the target point are planned using the LCALR algorithm, and the usefulness cost of the first track and the second track is obtained according to the threat area and the flexible target emergence area; the launch point and the target point are substituted into the preset planning model, and the preset algorithm based on the LCALR algorithm and the constrained Lagrangian relaxation algorithm are used in combination with the usefulness cost to solve the preset planning model, so as to obtain a wandering loop of the unmanned aerial vehicle from the launch point to the target point; and the wandering track of the unmanned aerial vehicle is constructed based on the first track, the second track and the wandering loop. The introduction of the arc's usefulness cost of wandering realizes the automatic planning and generation of wandering loops in the trajectory, and realizes the three-dimensional planning capability; the preset algorithm based on the LCALR algorithm and the constrained Lagrangian relaxation algorithm are adopted to ensure the feasibility of the planned trajectory, so that when the cost value is not all non-negative, a controllable unmanned aerial vehicle flight trajectory containing wandering loops can be planned, meeting the requirements of more and more types of tasks for the wandering cruise of unmanned aerial vehicles. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0043] in:

[0044] Figure 1 is a flow chart of a loitering trajectory planning method for an unmanned aerial vehicle provided in an embodiment of the present application;

[0045] Figure 2 This is a flow chart of another method for planning a loitering trajectory of an unmanned aerial vehicle provided in an embodiment of the present application;

[0046] Figure 3 It is a negative cycle schematic diagram of another method for planning a loitering trajectory of an unmanned aerial vehicle provided in an embodiment of the present application;

[0047] Figure 4 It is a structural schematic diagram of a wandering trajectory planning device for an unmanned aerial vehicle provided in an embodiment of the present application;

[0048] Figure 5It is a structural schematic diagram of an electronic device provided in an embodiment of the present application;

[0049] Figure 6 It is a structural schematic diagram of a storage medium provided in an embodiment of the present application. DETAILED DESCRIPTION

[0050] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0051] like Figure 1 As shown, the embodiment of the present application provides a loitering trajectory planning method for an unmanned aerial vehicle, comprising:

[0052] S101, acquiring target area data of the unmanned aerial vehicle and generating a navigation map, wherein the navigation map includes a threat area and a flexible target emergence area;

[0053] For example, according to the battlefield environment, a directed graph with information required for trajectory planning is generated. , set up threat zones and flexible target emergence areas;

[0054] S102, planning a first track from the launch point to each node in the navigation map and a second track from each node in the navigation map to the target point using an LCALR algorithm based on the launch point and the target point of the unmanned aerial vehicle, and obtaining the usefulness cost of the first track and the second track according to the threat area and the flexible target emergence area;

[0055] For example, LCALR is used to plan a minimum risk trajectory from the launch point to the target point, and a navigation map is stored. The distance cost and parent node pointer chain list from the launch point to each node are used to calculate the distance cost value that can be used for unmanned hovering flight. , which is equivalent to the maximum fuel value that can be used for unmanned hovering flight; similarly, the navigation map is calculated and stored The distance cost from the target point to each node and the parent node pointer list;

[0056] S103, substituting the launch point and the target point into the preset planning model, using a preset algorithm based on the LCALR algorithm and a Lagrangian relaxation algorithm with constraints and combining the usefulness cost to solve the preset planning model, and obtaining a wandering loop of the unmanned aerial vehicle from the launch point to the target point;

[0057] Exemplarily, the launch point and the target point are substituted into the preset planning model, and the preset planning model is:

[0058]

[0059] Target cost It represents other cost values ​​besides distance, such as the probability of the drone being destroyed. For controllable drones, their trajectory planning also needs to add a maximum range constraint, namely: ,in For unmanned aerial vehicles in arc The Lagrange relaxation method can be used to solve the constrained trajectory planning problem, that is, first relax the auxiliary constraints, and then add the auxiliary constraints to the objective function of the original problem. The objective function value is:

[0060]

[0061] S104: construct a wandering track of the unmanned aerial vehicle based on the first track, the second track and the wandering loop.

[0062] Exemplarily, a track from a starting point to a target point with a wandering loop is constructed based on the first track, the second track and the wandering loop.

[0063] The target area data of the unmanned aerial vehicle is obtained, and a navigation map is generated, wherein the navigation map includes a threat area and a flexible target emergence area; based on the launch point and the target point of the unmanned aerial vehicle, a first track from the launch point to each node in the navigation map and a second track from each node in the navigation map to the target point are planned using the LCALR algorithm, and the usefulness cost of the first track and the second track is obtained according to the threat area and the flexible target emergence area; the launch point and the target point are substituted into the preset planning model, and the preset algorithm based on the LCALR algorithm and the constrained Lagrangian relaxation algorithm are used in combination with the usefulness cost to solve the preset planning model, so as to obtain a wandering loop of the unmanned aerial vehicle from the launch point to the target point; and the wandering track of the unmanned aerial vehicle is constructed based on the first track, the second track and the wandering loop. The introduction of the arc's usefulness cost of wandering realizes the automatic planning and generation of wandering loops in the trajectory, and realizes the three-dimensional planning capability; the preset algorithm based on the LCALR algorithm and the constrained Lagrangian relaxation algorithm are adopted to ensure the feasibility of the planned trajectory, so that when the cost value is not all non-negative, a controllable unmanned aerial vehicle flight trajectory containing wandering loops can be planned, meeting the requirements of more and more types of tasks for the wandering cruise of unmanned aerial vehicles.

[0064] In a possible implementation, the step of planning a first track from the launch point to each node in the navigation map and a second track from each node in the navigation map to the target point using the LCALR algorithm based on the launch point and the target point of the unmanned aerial vehicle, and obtaining the usefulness cost of the first track and the second track according to the threat area and the flexible target emergence area includes:

[0065] Using the LCALR algorithm to plan a minimum risk trajectory from the launch point to the target point;

[0066] Determine a first track from the launch point to each node in the navigation map and a second track from each node in the navigation map to the target point based on the minimum risk track;

[0067] Obtaining distance cost values ​​between the first track and the second track;

[0068] The usefulness costs of the first track and the second track are obtained according to the distance cost value and the emergence probability of the flexible target in the threat area and / or the flexible target emergence area.

[0069] Exemplary, usefulness cost It is used to measure the possibility of the UAV changing its attack target and reaching the specified emergent target within the specified time after receiving effective information instructions to change the attack target during flight. If the cost values ​​of all track segments are positive, that is, , then the above trajectory planning model will not be able to obtain a trajectory containing a loop, and The directed loops in will not be paid attention to. Therefore, in order to obtain a wandering trajectory with a loop, this paper designs the wandering usefulness cost to be a negative cost value. When planning a wandering trajectory, using a trajectory segment with a negative wandering usefulness cost value will help improve the target cost value of the wandering trajectory planning; if the usefulness cost value of the trajectory segment is zero, it means that there is no effect; and using a positive usefulness cost value means that the target value is damaged. For the trajectory segment within the threat range, if the unmanned vehicle will be destroyed if it flies in this trajectory segment, then there is no point in the unmanned vehicle performing tactical wandering flight in the area containing such trajectory segments. Therefore, any trajectory segment with an important threat risk must be assigned a large positive cost value to ensure that the wandering trajectory does not contain these trajectory segments.

[0070] For the sake of convenience, the following definitions are used to measure the cost of wandering usefulness: : Number of emergent flexible targets

[0071] : Emergent Flexible Targets The coordinate value of

[0072] : Indicates the position coordinates of the emergent flexible target Possibility of occurrence

[0073] : Effective time threshold for unmanned vehicles to strike emerging flexible targets

[0074] : From the connection node and nodes The expected time from the track segment to the default target

[0075] : From the launch point to the node The distance cost corresponding to the minimum risk track

[0076] : From the target point to the node The distance cost corresponding to the minimum risk track

[0077] in, From the track segment The distance from the midpoint of the vehicle to the flexible target is divided by the theoretical speed of the unmanned vehicle.

[0078] In the following discussion, the following assumptions are made:

[0079] They are evenly distributed in the target emergent area ETA (Emergent Target Area);

[0080] It follows an exponential distribution;

[0081] The expected position of the unmanned vehicle receiving the command to change the attack target is the track segment Central location.

[0082] No. The probability of a flexible target being selected is uniformly distributed, then .

[0083] Assume that the UAV passes through the track segment Flexible Target has been selected, and let represents the probability that the robot reaches the target in time, The calculation method is shown in the formula:

[0084]

[0085] When the UAV passes through the track segment If the attack target is changed at the same time, the probability of the unmanned vehicle successfully attacking the emergent flexible target is:

[0086]

[0087] From launch point to node And slave nodes The minimum risk track distance to the target point may be greater than the minimum risk track distance from the launch point to the target point. In this case, assuming that the UAV can change the attack target while being able to perform tactical loitering flight, The probability of reaching the flexible target will be reduced for all the track segments that begin with the launch point, because the UAV cannot spend the same amount of time loitering on these track segments as it would on the minimum risk track from the launch point to the target point. The corresponding wandering usefulness can be calculated according to the following formula:

[0088]

[0089] In a possible implementation, the step of substituting the launch point and the target point into the preset planning model, using a preset algorithm based on the LCALR algorithm and a Lagrangian relaxation algorithm with constraints and combining the usefulness cost to solve the preset planning model to obtain a wandering loop of the unmanned aerial vehicle from the launch point to the target point includes:

[0090] Substituting the launch point and the target point into the preset planning model, the preset algorithm based on the LCALR algorithm in the preset planning model is combined with the usefulness cost to calculate the target wandering track;

[0091] Determine the upper and lower bounds of the Lagrangian relaxation coefficient based on the constraint conditions, obtain the constrained Lagrangian relaxation algorithm, and screen the target feasible solution of the unmanned aerial vehicle from the launch point to the target point in the target wandering track according to the constrained Lagrangian relaxation algorithm;

[0092] The target feasible solution is taken as a wandering loop of the UAV from the launch point to the target point.

[0093] Exemplarily, the pseudo code corresponding to the process of solving the preset planning model based on the preset algorithm of the LCALR algorithm and the constrained Lagrangian relaxation algorithm can be described as:

[0094] Initialize the upper and lower bounds of the Lagrangian relaxation coefficients to be and ;

[0095] While ( )

[0096] {

[0097] ;

[0098] Using the target cost function , using the preset algorithm based on the LCALR algorithm to solve the optimal hovering usefulness cost trajectory;

[0099] Determine whether the planned trajectory has a directed negative cycle;

[0100] If (there is a negative cycle) then

[0101] { , store the negative cycle with the best ratio of wandering usefulness cost to distance cost found so far;

[0102] }

[0103] Else { , store the currently found feasible track with the best hovering usefulness cost}

[0104] }

[0105] Among them, the initial upper and lower bounds of the Lagrangian relaxation coefficient used for iterative calculation are shown as follows:

[0106] ,

[0107] In the formula, is the distance cost corresponding to the width of a grid unit of the UAV flight, and the maximum hovering usefulness cost value of any track segment is -1, such as Figure 3 As shown, the shortest directed negative cycle consists of four unit edges and four unit hypotenuses, so the ratio of its maximum possible wandering usefulness cost to distance cost is: ; The lower bound of the probability of the unmanned vehicle successfully attacking an emergent flexible target is obtained when the navigation map When there is no threat risk, Medium track segment Corresponding hovering usefulness cost The absolute value of is the probability of successfully attacking an emergent flexible target, so when hour, ; As defined above.

[0108] In a possible implementation, the step of calculating the target wandering track by combining the preset algorithm based on the LCALR algorithm in the preset planning model with the usefulness cost includes:

[0109] Select a target node in the navigation graph, set a target cost label from a launch point to the target node to an infinite real number, set the parent node of the launch point to the launch point itself, and initialize the target cost label of the launch point;

[0110] Check whether the first-in-first-out node linked list is empty, and if the first-in-first-out node linked list is not empty, remove the first node in the first-in-first-out node linked list;

[0111] Obtain all adjacent track segments corresponding to the first node that satisfy the maximum turning angle constraint of the unmanned aerial vehicle;

[0112] A target wandering track is obtained based on the adjacent track segments and the usefulness cost.

[0113] In a possible implementation, the step of obtaining the target wandering track based on the adjacent track segments and the usefulness cost includes:

[0114] The track segment from the target node to the first node is used as the target track segment. When the target cost from the launch point to the target node is greater than the sum of the target cost from the launch point to the first node and the target cost of the target track segment, the target cost of the target node, the distance cost of the minimum cost track and the risk cost of the minimum cost track are updated, and the parent node of the target node is updated to the first node to obtain an initial wandering track;

[0115] It is determined whether the initial wandering track has a directed negative cycle, and if the initial wandering track has a directed negative cycle, the initial wandering track is used as the target wandering track.

[0116] For example, for FIG. The target node in ,initialization is an infinite real number, the emission point Initialize to ; ; .

[0117] examine Is it empty? If it is empty, the algorithm stops;

[0118] Will The first data in the queue---the first node Remove and Delete the first node ;

[0119] For the first node The corresponding maximum turning angle of the unmanned vehicle All adjacent track segments constrained ;

[0120] If the node exist

[0121] {Update various label data: , , ;

[0122] { Check whether there is a directed negative cycle. If there is a directed negative cycle, output the directed negative cycle and stop the calculation;

[0123] }

[0124] The node The parent node of ,Right now: .

[0125] Check Node Is it in If not, add node j to middle.

[0126] }

[0127] in, Track segment The target cost, Track segment The distance cost, Track segment The risk cost, From the launch point To Node The target cost label, From the launch point To Node The distance cost of the minimum cost track, Indicates starting point To Node The risk cost of the minimum cost trajectory; It is a first-in-first-out node linked list. Is the target node From the launch point To the target node The parent node in the minimum cost trajectory of .

[0128] In a possible implementation manner, before the step of determining whether the initial wandering track has a directed negative cycle, the method further includes:

[0129] Obtaining a parent node set in a minimum cost trajectory from the launch point to the target node;

[0130] Determine whether the first node exists in the parent node set;

[0131] If the first node exists in the parent node set, the initial wandering track is used as the target wandering track;

[0132] If the first node does not exist in the parent node set, it is determined whether there is a directed negative cycle in the initial wandering track.

[0133] For example, in the past Before adding node j to the table, check whether node j is in Inside, if the node is already in If there is a negative cycle in it, the algorithm terminates and returns the pointer to this node and the negative cycle. However, if all arc costs are positive, or if the navigation graph is acyclic, this is not necessary; the worst-case running time of this algorithm can be arrive Among them is the number of nodes, is the number of arcs.

[0134] In a possible implementation, the step of determining the upper and lower bounds of the Lagrangian relaxation coefficient based on the constraint conditions to obtain a Lagrangian relaxation algorithm with constraints, and screening and obtaining a target feasible solution for the unmanned aerial vehicle from the launch point to the target point in the target wandering track according to the Lagrangian relaxation algorithm with constraints includes:

[0135] When there is a directed negative cycle in the target wandering track, a target wandering track where a negative cycle corresponding to the ratio of usefulness cost to distance cost is located is selected in the target wandering track to obtain a target feasible solution for the unmanned aerial vehicle from the launch point to the target point;

[0136] When there is no directed negative cycle in the target wandering track, a feasible track with the highest usefulness cost is selected in the target wandering track to obtain a target feasible solution for the unmanned aerial vehicle from the launch point to the target point.

[0137] For example, if the directed graph G contains a directed negative cycle, the target cost value corresponding to the node series connecting the cycle will be reduced indefinitely. If the cycle calculation is performed, the algorithm will not stop. The main methods for detecting directed negative cycles are:

[0138] First, if any node in the track has been checked times, then there is a directed negative cycle;

[0139] Second, when , if for the target node exist , then it is proved that there is a directed negative cycle;

[0140] Third, for the first node , periodically tracking nodes through their parent node pointers to the starting point. If the node also appears in its own backtracking queue, then there is a directed negative cycle.

[0141] When a node is updated, the first and second methods require a separate comparison of the cost labels each time, but this does not affect the range of the worst search time, but only adds a little cost to the algorithm search time. When a node cost label is updated, the third method requires a The worst case is If only directed negative cycles are checked, the first and second methods have low computational complexity and good practical application effects. When not only directed negative cycles need to be detected but also directed negative cycles need to be tracked, the third method is more accurate and meets the task requirements of tracking directed negative cycles.

[0142] In a possible implementation, Figure 2 As shown, the embodiment of the present application also provides a method for loitering trajectory planning of an unmanned aerial vehicle, comprising: step 1, generating a directed graph marked with information required for trajectory planning according to the battlefield environment , set up threat zones and flexible target emergence areas;

[0143] Step 2: Use LCALR to plan the minimum risk trajectory from the launch point to the target point and store the navigation map The distance cost and parent node pointer chain list from the launch point to each node are used to calculate the distance cost value that can be used for unmanned hovering flight. (equivalent to the maximum fuel value available for unmanned hovering flight);

[0144] Step 3: Use the same method to calculate and store the directed graph The distance cost from the target point to each node and the parent node pointer list;

[0145] Step 4: Based on the calculated distance cost value and the probability of emergence of flexible targets, calculate the directed graph The usefulness cost of hovering for each track segment;

[0146] Step 5: Combining the planning model and the hovering usefulness cost, a preset algorithm based on the LCALR algorithm and a constrained Lagrangian relaxation algorithm are used to obtain the hovering trajectory from the launch point to the target point;

[0147] Step 6: If a directed cycle is obtained in step 5, according to the parent node pointer of the minimum cost track calculated in steps 2 and 3, backtrack to obtain the track from the launch point to the wandering ring and the track from the wandering ring to the target point, so as to construct a wandering track with a wandering ring;

[0148] Step 7: If there is no directed cycle in the result of step 5, according to the directed graph The usefulness cost of wandering in each track segment is calculated, and the track from the launch point to the wandering ring is traced back to obtain the wandering track. The vertical track is smoothed and the planning is completed.

[0149] In a possible implementation, Figure 4 As shown, the embodiment of the present application also provides a wandering trajectory planning device for an unmanned aerial vehicle, the planning device comprising:

[0150] The data receiving module 201 is used to obtain the target area data of the UAV operation and generate a navigation map, wherein the navigation map includes a threat area and a flexible target emergence area;

[0151] A usefulness cost calculation module 202 is used to plan a first track from the launch point to each node in the navigation map and a second track from each node in the navigation map to the target point using an LCALR algorithm based on the launch point and the target point of the unmanned aerial vehicle, and obtain the usefulness costs of the first track and the second track according to the threat area and the flexible target emergence area;

[0152] A wandering loop solving module 203 is used to substitute the launch point and the target point into the preset planning model, adopt a preset algorithm based on the LCALR algorithm and a Lagrangian relaxation algorithm with constraints and combine the usefulness cost to solve the preset planning model, and obtain a wandering loop of the unmanned aerial vehicle from the launch point to the target point;

[0153] The planning module 204 is configured to construct a wandering track of the UAV based on the first track, the second track and the wandering loop.

[0154] In a possible implementation, Figure 5As shown, an embodiment of the present application 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, the following steps are implemented: obtaining target area data of the operation of the unmanned aerial vehicle and generating a navigation map, wherein the navigation map includes a threat area and a flexible target emergence area; using the LCALR algorithm to plan a first track from the launch point to each node in the navigation map and a second track from each node in the navigation map to the target point based on the launch point and the target point of the unmanned aerial vehicle, and obtaining the usefulness cost of the first track and the second track according to the threat area and the flexible target emergence area; substituting the launch point and the target point into the preset planning model, using a preset algorithm based on the LCALR algorithm and a constrained Lagrangian relaxation algorithm combined with the usefulness cost to solve the preset planning model, and obtaining a wandering loop of the unmanned aerial vehicle from the launch point to the target point; and constructing a wandering track of the unmanned aerial vehicle based on the first track, the second track and the wandering loop.

[0155] In a possible implementation, Figure 6 As shown, an embodiment of the present application 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: obtaining target area data for the operation of an unmanned aerial vehicle and generating a navigation map, wherein the navigation map includes a threat area and a flexible target emergence area; using the LCALR algorithm based on the launch point and the target point of the unmanned aerial vehicle to plan a first track from the launch point to each node in the navigation map and a second track from each node in the navigation map to the target point, and obtaining the usefulness cost of the first track and the second track according to the threat area and the flexible target emergence area; substituting the launch point and the target point into the preset planning model, using a preset algorithm based on the LCALR algorithm and a constrained Lagrangian relaxation algorithm combined with the usefulness cost to solve the preset planning model, and obtaining a wandering loop of the unmanned aerial vehicle from the launch point to the target point; and constructing a wandering track of the unmanned aerial vehicle based on the first track, the second track and the wandering loop.

[0156] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, which carry computer-readable program code. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer-readable signal media may also be any computer-readable medium other than a computer-readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0157] The program code embodied on the computer readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

[0158] Computer program code for performing the operation of the present invention may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0159] It should be understood by those skilled in the art that the modules or steps of the present invention described above can be implemented by a general-purpose computing device, they can be concentrated on a single computing device, or distributed on a network composed of multiple computing devices, optionally, they can be implemented by a program code executable by a computer device, so that they can be stored in a storage device and executed by the computing device, or they can be made into individual integrated circuit modules, or multiple modules or steps therein can be made into a single integrated circuit module for implementation. Thus, the present invention is not limited to any specific combination of hardware and software.

[0160] Note that the above are only preferred embodiments of the present invention and the technical principles used. Those skilled in the art will understand that the present invention is not limited to the specific embodiments described above, and that various obvious changes, readjustments and substitutions can be made by those skilled in the art without departing from the scope of protection of the present invention. Therefore, although the present invention has been described in more detail through the above embodiments, the present invention is not limited to the above embodiments, and may include more other equivalent embodiments without departing from the concept of the present invention, and the scope of the present invention is determined by the scope of the appended claims.

[0161] The above disclosure is only the preferred embodiment of the present invention, which certainly cannot be used to limit the scope of the present invention. Therefore, equivalent changes made according to the claims of the present invention are still within the scope of the present invention.

Claims

1. A loitering trajectory planning method for an unmanned aerial vehicle, characterized in that: include: Acquiring target area data of the unmanned aerial vehicle and generating a navigation map, wherein the navigation map includes a threat area and a flexible target emergence area; Based on the launch point and the target point of the unmanned aerial vehicle, a first track from the launch point to each node in the navigation map and a second track from each node in the navigation map to the target point are planned using an LCALR algorithm, and the usefulness costs of the first track and the second track are obtained according to the threat area and the flexible target emergence area; Substituting the launch point and the target point into a preset planning model, solving the preset planning model using a preset algorithm based on the LCALR algorithm and a Lagrangian relaxation algorithm with constraints combined with the usefulness cost, and obtaining a wandering loop of the unmanned aerial vehicle from the launch point to the target point; A wandering track of the unmanned aerial vehicle is constructed based on the first track, the second track and the wandering loop.

2. The loitering trajectory planning method of an unmanned aerial vehicle as claimed in claim 1, characterized in that: The step of planning a first track from the launch point to each node in the navigation map and a second track from each node in the navigation map to the target point using the LCALR algorithm based on the launch point and the target point of the unmanned aerial vehicle, and obtaining the usefulness cost of the first track and the second track according to the threat area and the flexible target emergence area includes: Using the LCALR algorithm to plan a minimum risk trajectory from the launch point to the target point; Determine a first track from the launch point to each node in the navigation map and a second track from each node in the navigation map to the target point based on the minimum risk track; Obtaining distance cost values ​​between the first track and the second track; The usefulness costs of the first track and the second track are obtained according to the distance cost value and the emergence probability of the flexible target in the threat area and / or the flexible target emergence area.

3. The loitering trajectory planning method of an unmanned aerial vehicle as claimed in claim 1, characterized in that: The step of substituting the launch point and the target point into the preset planning model, solving the preset planning model using a preset algorithm based on the LCALR algorithm and a Lagrangian relaxation algorithm with constraints in combination with the usefulness cost, and obtaining a wandering loop of the unmanned aerial vehicle from the launch point to the target point includes: Substituting the launch point and the target point into the preset planning model, the preset algorithm based on the LCALR algorithm in the preset planning model is combined with the usefulness cost to calculate the target wandering track; Determine the upper and lower bounds of the Lagrangian relaxation coefficient based on the constraint conditions, obtain the constrained Lagrangian relaxation algorithm, and screen the target feasible solution of the unmanned aerial vehicle from the launch point to the target point in the target wandering track according to the constrained Lagrangian relaxation algorithm; The target feasible solution is taken as a wandering loop of the UAV from the launch point to the target point.

4. The loitering trajectory planning method of an unmanned aerial vehicle as claimed in claim 3, characterized in that: The step of calculating the target wandering track by combining the preset algorithm based on the LCALR algorithm in the preset planning model with the usefulness cost includes: Select a target node in the navigation graph, set a target cost label from a launch point to the target node to an infinite real number, set the parent node of the launch point to the launch point itself, and initialize the target cost label of the launch point; Check whether the first-in-first-out node linked list is empty, and if the first-in-first-out node linked list is not empty, remove the first node in the first-in-first-out node linked list; Obtain all adjacent track segments corresponding to the first node that satisfy the maximum turning angle constraint of the unmanned aerial vehicle; A target wandering track is obtained based on the adjacent track segments and the usefulness cost.

5. The loitering trajectory planning method of an unmanned aerial vehicle as claimed in claim 4, characterized in that: The step of obtaining the target wandering track based on the adjacent track segments and the usefulness cost comprises: The track segment from the target node to the first node is used as the target track segment. When the target cost from the launch point to the target node is greater than the sum of the target cost from the launch point to the first node and the target cost of the target track segment, the target cost of the target node, the distance cost of the minimum cost track and the risk cost of the minimum cost track are updated, and the parent node of the target node is updated to the first node to obtain an initial wandering track; It is determined whether the initial wandering track has a directed negative cycle, and if the initial wandering track has a directed negative cycle, the initial wandering track is used as the target wandering track.

6. The loitering trajectory planning method of an unmanned aerial vehicle as claimed in claim 5, characterized in that: Before the step of determining whether the initial wandering track has a directed negative cycle, the method further includes: Obtaining a parent node set in a minimum cost trajectory from the launch point to the target node; Determine whether the first node exists in the parent node set; If the first node exists in the parent node set, the initial wandering track is used as the target wandering track; If the first node does not exist in the parent node set, it is determined whether there is a directed negative cycle in the initial wandering track.

7. The loitering trajectory planning method for an unmanned aerial vehicle as claimed in claim 3, characterized in that: The step of determining the upper and lower bounds of the Lagrangian relaxation coefficient based on the constraint conditions, obtaining the Lagrangian relaxation algorithm with constraints, and screening the target feasible solution of the unmanned aerial vehicle from the launch point to the target point in the target wandering track according to the Lagrangian relaxation algorithm with constraints includes: When there is a directed negative cycle in the target wandering track, a target wandering track where a negative cycle corresponding to the ratio of usefulness cost to distance cost is located is selected in the target wandering track to obtain a target feasible solution for the unmanned aerial vehicle from the launch point to the target point; When there is no directed negative cycle in the target wandering track, a feasible track with the highest usefulness cost is selected in the target wandering track to obtain a target feasible solution for the unmanned aerial vehicle from the launch point to the target point.

8. A loitering trajectory planning device for an unmanned aerial vehicle, characterized in that: The planning device comprises: A data receiving module is used to obtain target area data of the unmanned aerial vehicle and generate a navigation map, wherein the navigation map includes a threat area and a flexible target emergence area; A usefulness cost calculation module, configured to plan a first track from the launch point to each node in the navigation map and a second track from each node in the navigation map to the target point using an LCALR algorithm based on the launch point and the target point of the unmanned aerial vehicle, and obtain usefulness costs of the first track and the second track according to the threat area and the flexible target emergence area; A wandering loop solving module, used for substituting the launch point and the target point into a preset planning model, using a preset algorithm based on the LCALR algorithm and a Lagrangian relaxation algorithm with constraints and combining the usefulness cost to solve the preset planning model, and obtaining a wandering loop of the unmanned aerial vehicle from the launch point to the target point; A planning module is used to construct a wandering track of the unmanned aerial vehicle based on the first track, the second track and the wandering loop.

9. An electronic device, comprising: A processor, a memory and a bus, wherein the memory stores machine-readable instructions executable by the processor, and when the electronic device is running, the processor and the memory communicate through the bus, and when the machine-readable instructions are executed by the processor, the steps of the wandering 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, and when the computer program is executed by a processor, the steps of the wandering trajectory planning method for an unmanned aerial vehicle as claimed in any one of claims 1 to 7 are executed.

Images