Heterogeneous unmanned aerial vehicle cluster target search method and device, unmanned aerial vehicle and storage medium

By dividing grids, predicting state and action sequences in heterogeneous drone clusters, sharing information, and using fixed-wing drones as communication relays, communication constraints and collision avoidance problems in heterogeneous drone clusters are solved, and the problem of communication constraints and collision avoidance in heterogeneous drone clusters is improved. Search efficiency and performance are suitable for complex dynamic task environments.

CN119089714AInactive Publication Date: 2024-12-06ZHUOYI ZHINENG
View PDF 0 Cites 2 Cited by

Patent Information

Application Number
CN202411583605.8
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-11-07
Publication Date
2024-12-06
Estimated Expiration
Not applicable · inactive patent

AI Technical Summary

Technical Problem

The prior art fails to effectively utilize individual height and speed differences in heterogeneous drone clusters, resulting in communication constraint problems, and insufficient collision avoidance and threat avoidance functions in large-scale clusters, making it difficult to meet the search needs of complex dynamic task environments.

Method used

By dividing the search target area into multiple discrete grids, using the drone state and pose at the current moment to determine the state formula and action formula, predict future state and action sequences, and share information in the data link, and determine based on the optimization algorithm model. The optimal action sequence uses a fixed-wing drone as a communication relay node to improve information transmission efficiency and search performance.

Benefits of technology

It significantly improves the efficiency of collaborative search of heterogeneous drones, can quickly reconnaise mission areas and discover targets, and is suitable for fields such as emergency rescue and environmental reconnaissance.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119089714A_ABST
    Figure CN119089714A_ABST
Patent Text Reader

Abstract

The invention discloses a heterogeneous unmanned aerial vehicle cluster target search method and device, unmanned aerial vehicles and a storage medium, and the method comprises the steps: dividing a search target region into a plurality of discrete grids, so as to carry out the discrete processing of the motion of each unmanned aerial vehicle in a cluster in a rasterized map; determining a state formula and an action formula of each unmanned aerial vehicle by taking the grid and the attitude of the unmanned aerial vehicle at the current moment as a reference; estimating the state of each unmanned aerial vehicle at the next moment according to the state formula and the action formula of each unmanned aerial vehicle at the current moment; repeating the previous step to obtain an action sequence and a state sequence of the unmanned aerial vehicle in the plurality of prediction steps; each unmanned aerial vehicle in the cluster shares the action sequence, the state sequence and the search result into a data link; and in each decision period, each unmanned aerial vehicle determines an optimal solution from an action sequence of the unmanned aerial vehicle based on an optimization algorithm model according to the information in the data chain. According to the scheme, the collaborative search efficiency can be remarkably improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of unmanned aerial vehicle positioning and navigation technology, and in particular to a heterogeneous unmanned aerial vehicle cluster target search method, device, unmanned aerial vehicle and storage medium. Background Art

[0002] Collaborative search technology has important application value in both civil and military fields, and can be used for tasks such as field rescue, environmental monitoring, and target reconnaissance. The core function of this technology is to help drone clusters make online search direction decisions in wide-area unknown environments, so that drones can quickly find targets. In collaborative search tasks in three-dimensional space and multi-media, existing technologies use a variety of different individuals such as rotors, fixed wings, cars, and ships to form heterogeneous clusters. In order to improve search efficiency, clusters need to share search information during the search process so that individuals in the cluster avoid repeated searches of the same area. In terms of considering communication constraints, existing technologies use methods such as minimum spanning trees to ensure the connectivity of information transmission by controlling the topological shape of the cluster and the distance between nodes, and by designing search information fusion methods, clusters have ideal search decision efficiency under conditions such as communication interruptions and data loss.

[0003] In the existing technology targeting homogeneous clusters, there is no consideration of how to use the differences in height and speed of individuals in heterogeneous clusters to solve the communication constraint problem; in the existing technology targeting heterogeneous clusters, there is no consideration of the collision avoidance and threat avoidance functions of large-scale clusters, and the trajectory planning results cannot simultaneously meet multiple search requirements such as target probability and environmental uncertainty, and are not suitable for use in complex and dynamic mission environments.

[0004] Therefore, a new search scheme needs to be proposed to overcome the above problems. Summary of the invention

[0005] In view of the above problems, the present invention is proposed to provide a heterogeneous UAV cluster target search method, device, UAV and storage medium that overcome the above problems or at least partially solve the above problems.

[0006] According to one aspect of the present invention, a heterogeneous UAV cluster target search method is provided, the method comprising: The search target area is divided into multiple discrete grids to discretize the movement of each drone in the cluster in the rasterized map; Based on the grid and posture of the drone at the current moment, determine the state formula and action formula of each drone at the current moment; According to the state formula and action formula of each drone at the current moment, estimate the state of each drone at the next moment; Repeat the previous step to obtain the action sequence and state sequence of the drone in multiple prediction steps; Each drone in the cluster shares its own action sequence, state sequence and search results to the data link; In each decision cycle, each drone determines the optimal solution from its own action sequence based on the optimization algorithm model according to its own information in the data link and the information obtained from other drones in the cluster.

[0007] In some embodiments, the state formula and action formula of each drone at the current moment are determined based on the grid and posture of the drone at the current moment, including: Determine the state of the drone based on the drone's perception of its own state, environment, target or threat, wherein the state includes heading angle, flight speed or position; The action of the drone is determined according to the flight direction of the drone, where the flight directions include: straight flight, left yaw, and right yaw.

[0008] In some implementations, estimating the state of each drone at the next moment according to the state formula and action formula of each drone at the current moment includes: Determine the state of the next moment based on the action and state of the drone at the current moment and the mapping relationship from the current moment to the state of the next moment; Repeating the previous step to obtain the action sequence and state sequence of the drone in multiple prediction steps includes: According to the current state of the drone and the action sequence within the predicted number of steps, the state sequence of the drone is obtained.

[0009] In some embodiments, in each decision cycle, each drone determines the optimal solution from its own action sequence based on the optimization algorithm model according to its own information in the data link and the information of other drones in the cluster, including: Within the range of the possible state set and the permissible action set of the drone, based on the sequence actions, sequence states and search results of each drone in the cluster, the optimization algorithm model is used to determine the optimal action sequence from the self-action sequence.

[0010] In some embodiments, the cluster of drones includes rotary-wing drones and fixed-wing drones, and each drone in the cluster shares its own action sequence, state sequence, and search results to the data link, including: The fixed-wing UAV is used as a communication relay node, and the action sequence, state sequence and search result of each UAV in the cluster are obtained and updated through the fixed-wing UAV.

[0011] In some embodiments, each drone in the cluster shares its own action sequence, state sequence and search results to the data link further comprising: Constructing an information structure of a data link, wherein the information structure includes a drone state information matrix and a target information matrix, wherein the drone state information matrix stores the position and heading information of the drone and the corresponding timestamp, and the target information matrix stores the position information of the target and the corresponding timestamp, and the drone state information matrix and the target information matrix are sequentially arranged to form a data link; When different UAVs communicate, each UAV updates its own data link based on the data link of other UAVs.

[0012] In some embodiments, when different drones are communicating, each drone updates its own data link based on the data link of other drones, including: After receiving the data link of another drone, the drone obtains the timestamps of other drones in the drone state information matrix in the data link. If the timestamp is closer to the current moment than the timestamp of the corresponding drone stored in the drone, the drone updates its own data link, otherwise it does not update; and / or, After receiving the data link from another drone, the drone obtains the timestamp of each target in the target information matrix in the data link. If the timestamp is closer to the current moment than the timestamp of the corresponding target stored in itself, it updates its own data link, otherwise it does not update.

[0013] According to another aspect of the present invention, a heterogeneous UAV cluster target search device is provided, the device comprising: The area division module is suitable for dividing the search target area into multiple discrete grids so as to discretize the movement of each drone in the cluster in the rasterized map; A state determination module is adapted to determine the state formula and action formula of each drone at the current moment based on the grid and posture of the drone at the current moment; The state estimation module is suitable for estimating the state of each drone at the next moment according to the state formula and action formula of each drone at the current moment; A sequence determination module is adapted to repeat the previous step to obtain the action sequence and state sequence of the drone in multiple prediction steps; The data sharing module is suitable for each drone in the cluster to share its own action sequence, state sequence and search results into the data link; The optimal solution determination module is suitable for each UAV to determine the optimal solution from its own action sequence based on the optimization algorithm model in each decision cycle according to its own information in the data link and the information obtained from other UAVs in the cluster.

[0014] According to another aspect of the present invention, a drone is provided, comprising: a processor and a memory arranged to store computer executable instructions, wherein when the executable instructions are executed, the processor executes the heterogeneous drone cluster target search method according to any one of the above-mentioned embodiments.

[0015] According to another aspect of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores one or more programs, and when the one or more programs are executed by a processor, the heterogeneous drone cluster target search method according to any one of the above-mentioned methods is implemented.

[0016] As can be seen from the above, according to the heterogeneous drone cluster target search method disclosed by the present invention, the efficiency of heterogeneous drone collaborative search is significantly improved compared with homogeneous drone clusters, and the mission area can be quickly scouted and the target can be found. The above search method has important application value in the fields of emergency rescue, environmental reconnaissance, etc.

[0017] The above description is only an overview of the technical solution of the present invention. In order to more clearly understand the technical means of the present invention, it can be implemented according to the contents of the specification. In order to make the above and other purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Various other advantages and benefits will become apparent to those of ordinary skill in the art by reading the detailed description of the preferred embodiments below. The accompanying drawings are only for the purpose of illustrating the preferred embodiments and are not to be considered as limiting the present invention. Moreover, the same reference symbols are used throughout the accompanying drawings to represent the same components. In the accompanying drawings: Figure 1 A schematic diagram of a process flow of a heterogeneous UAV cluster target search method according to some embodiments of the present invention is shown; Figure 2 A schematic diagram showing a predicted state sequence of a drone on a grid according to some embodiments of the present invention; Figure 3 A schematic diagram of a communication strategy of a heterogeneous drone cluster according to some embodiments of the present invention is shown; Figure 4 A schematic diagram showing information transmission between drones according to some embodiments of the present invention is shown; Figure 5 A schematic diagram of a process for updating local information of a drone according to some embodiments of the present invention is shown; Figure 6 A schematic diagram showing collaborative search of heterogeneous drone clusters according to some embodiments of the present invention is shown; Figure 7A schematic diagram of the structure of a heterogeneous UAV cluster target search device according to some embodiments of the present invention is shown; Figure 8 A schematic structural diagram of a drone according to an embodiment of the present invention is shown. DETAILED DESCRIPTION

[0019] The exemplary embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. Although the exemplary embodiments of the present invention are shown in the accompanying drawings, it should be understood that the present invention can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided in order to enable a more thorough understanding of the present invention and to enable the scope of the present invention to be fully communicated to those skilled in the art.

[0020] The main idea of ​​the embodiment of the present invention is: based on a distributed decision-making framework, the embodiment of the present invention proposes a collaborative search method for heterogeneous UAV clusters suitable for complex environments: using rotorcraft UAVs to perform low-altitude search tasks, and using fixed-wing UAVs as communication relay nodes to hover at high altitudes to promote information flow within the cluster; by designing information transmission content and update methods, the amount of information transmission between UAVs in the cluster is reduced, so that the heterogeneous cluster has ideal communication efficiency and efficient search performance under the constraints of communication bandwidth and distance.

[0021] Figure 1 The following is a flow chart of a method for searching a target in a cluster of heterogeneous UAVs according to an embodiment of the present invention. The method can be implemented by a program in a flight control system of the UAV. The method includes the following steps: Step S110, dividing the search target area into a plurality of discrete grids, so as to discretize the movement of each UAV in the cluster in the rasterized map; Step S120, determining the state formula and action formula of each drone at the current moment based on the grid and posture of the drone at the current moment; Step S130, estimating the state of each drone at the next moment according to the state formula and action formula of each drone at the current moment; Step S140, repeat the previous step to obtain the action sequence and state sequence of the drone in multiple prediction steps; Step S150, each drone in the cluster shares its own action sequence, state sequence and search results in the data link; Step S160, in each decision cycle, each UAV determines the optimal solution from its own action sequence based on the optimization algorithm model according to its own information in the data link and the information obtained from other UAVs in the cluster.

[0022] According to the heterogeneous drone cluster target search method disclosed in the above embodiment of the present invention, the collaborative search efficiency of heterogeneous drones is significantly improved compared with that of homogeneous drone clusters, and the mission area can be scouted and targets can be discovered quickly.

[0023] In some embodiments, in step S120, based on the grid and posture of the drone at the current moment, the state formula and action formula of each drone at the current moment are determined, including: Determine the state of the drone based on the drone's perception of its own state, environment, target or threat, wherein the state includes heading angle, flight speed or position; The action of the drone is determined according to the flight direction of the drone, where the flight directions include: straight flight, left yaw, and right yaw.

[0024] In some embodiments, in step S130, based on the state formula and action formula of each drone at the current moment, estimating the state of each drone at the next moment includes: Determine the state of the next moment based on the action and state of the drone at the current moment and the mapping relationship from the current moment to the state of the next moment; In step S140, the previous step is repeated to obtain the action sequence and state sequence of the drone in multiple prediction steps, including: According to the current state of the drone and the action sequence within the predicted number of steps, the state sequence of the drone is obtained.

[0025] In some embodiments, in step S160, in each decision cycle, each drone determines the optimal solution from its own action sequence based on the optimization algorithm model according to its own information in the data link and the information of other drones in the cluster, including: Within the range of the possible state set and the permissible action set of the drone, based on the sequence actions, sequence states and search results of each drone in the cluster, the optimization algorithm model is used to determine the optimal action sequence from the self-action sequence.

[0026] Optionally, the optimization algorithm model can be a genetic algorithm, an improved ant colony algorithm, a particle swarm optimization algorithm, etc. In addition, when designing the objective function, the following can be considered: environmental reconnaissance benefit as J, that is, the UAV can detect unknown areas with higher uncertainty as much as possible. The environmental reconnaissance benefit is determined by the sum of the uncertainties in the track grid path points on the search path. Generally speaking, the target prediction position has the highest uncertainty, and the area that has been searched has the lowest uncertainty; the mission execution cost, that is, the UAV is allowed to keep flying straight as much as possible and reduce the number of turns, that is, the sum of the changes in the yaw angle on the search path.

[0027] Specifically, according to the above embodiment of the present invention, the UAV is regarded as a particle in space in the collaborative search decision, and only the planar motion of the UAV is considered. discrete grids, each grid is marked ,and , The movement of the UAV is discretized in the rasterized map. In order to make the UAV collaborative search decision more forward-looking, the model predictive control technology is used to plan the search points in the future m time intervals based on the current UAV position and situation information. At time t, the state and action of UAV i can be expressed as:

[0028] In formula (1), It means the speed direction remains unchanged and the flight is in a straight line. represents a yaw to the left. represents a right yaw. and , the state of drone i at time k+1 can be calculated as: In formula (2), function f represents the mapping relationship between the current action and state to the next state. Assume that the number of prediction steps in the discrete time domain is m, and the current state and action sequences , ,..., You can get the predicted state sequence in sequence , ,..., Taking the example of moving one grid at a time, when m=3, the predicted state sequence of the drone is as follows: Figure 2 shown.

[0029] Figure 2 Nodes with different line depths represent states at different times, each connected broken line represents a predicted state sequence, and the branch options of each node represent the actions at the current moment. The state and action sequence of a search track of drone i in the prediction time domain at time k can be expressed as: The drone swarm adopts distributed autonomous decision-making, and each drone shares its own status, actions, and search results in the data link. In each decision cycle, the drone searches for the optimal solution in all predicted action sequences based on the situation information it can obtain. The collaborative search decision model for the i-th drone can be expressed as: In formula (4), is the shared information of other UAVs except UAV i at time k, The optimal action sequence solved for the optimization problem, and They represent the possible state set and permissible action set of the UAV when making decisions, represents the number of drones in the cluster. According to formula (4), in the search decision, drone i is Compute the objective function for the cell. If known, each Corresponding to the only .

[0030] In some embodiments, the drone cluster includes rotary-wing drones and fixed-wing drones, and each drone in the cluster shares its own action sequence, state sequence and search results to the data link in step S150, including: The fixed-wing UAV is used as a communication relay node, and the action sequence, state sequence and search result of each UAV in the cluster are obtained and updated through the fixed-wing UAV.

[0031] In distributed collaborative search, drones obtain search information from other drones through data links to avoid repeated searches of the target area by drone clusters. In practical applications, external interference and factors such as data link communication bandwidth and communication range limitations can cause information transmission interruptions. Although the drone cluster can continue to work in this case, the lack of communication between individuals will reduce the efficiency of cluster search. In order to solve the problem of cluster communication interruption, a heterogeneous drone cluster communication strategy under communication constraints is designed. Figure 3 This strategy uses fixed-wing UAVs as communication relay nodes, giving full play to the advantages of fixed-wing UAVs' fast flight speed and wide communication range. Through the centralized transmission of search information and the state reproduction function, it effectively promotes the information flow between the rotor UAVs in the cluster and greatly improves the communication efficiency of the UAV cluster.

[0032] Specifically, within a certain range, the rotor UAVs can communicate with each other. If the range is exceeded, communication between the rotor UAVs may be difficult. At this time, a fixed-wing UAV with a faster flight speed and a larger range is introduced. The data of each rotor UAV can be updated through the long-distance and large-range flight of the fixed-wing UAV.

[0033] In some embodiments, in step S150, each drone in the cluster shares its own action sequence, state sequence and search results to the data link further including: Constructing an information structure of a data link, wherein the information structure includes a drone state information matrix and a target information matrix, wherein the drone state information matrix stores the position and heading information of the drone and the corresponding timestamp, and the target information matrix stores the position information of the target and the corresponding timestamp, and the drone state information matrix and the target information matrix are sequentially arranged to form a data link; When different UAVs communicate, each UAV updates its own data link based on the data link of other UAVs.

[0034] In the above formula (4), it is necessary to obtain the shared information of other drones If the data link is interrupted or the communication conditions are not ideal, it will cause the individual objective function of the drone to The calculation is inaccurate, thus affecting the overall search performance.

[0035] Under the condition that drone i knows the detection area of ​​other drones, By only including the search position, heading angle and target discovery status of other drones, the drone can reproduce the search information of other drones locally and update its own search information synchronously, thereby calculating the objective function Through this form of The design method can greatly reduce the data link communication content. In addition, historical search information can be transmitted when the data link bandwidth allows, so that after the drone re-establishes the link, it can quickly obtain the historical search information of other drones during the communication interruption and update the search information locally.

[0036] The design of information transmission content and local information storage method between drones is as follows Figure 4 As shown in the figure, each drone locally stores The UAV state information matrix and the target information matrix are stored in the UAV state information matrix. The UAV position, heading information and corresponding timestamp are stored in the target information matrix. The target position information and corresponding timestamp are stored in the target information matrix. During the UAV communication process, the UAV state information and target information are encoded and stored in the information structure in turn to realize information sending and receiving.

[0037] For example, there are 5 drones in the cluster, each drone stores 10 target information and centrally transmits the search information of the past 100 steps. Figure 4 As shown in the figure, there are 400 elements in the drone state information matrix and 30 elements in the target information matrix. Each drone stores 5 state information matrices and 1 target information matrix. All elements are stored in float (4bit) format. The amount of information transmitted by each drone communication is (400´5+30)´4=8.12kb.

[0038] In some embodiments, when different drones communicate in step S150, each drone updates its own data link according to the data link of other drones, including: After receiving the data link of another drone, the drone obtains the timestamps of other drones in the drone state information matrix in the data link. If the timestamp is closer to the current moment than the timestamp of the corresponding drone stored in the drone, the drone updates its own data link, otherwise it does not update; and / or, After receiving the data link from another drone, the drone obtains the timestamp of each target in the target information matrix in the data link. If the timestamp is closer to the current moment than the timestamp of the corresponding target stored in itself, it updates its own data link, otherwise it does not update.

[0039] Specifically, since the communication ranges of different drones in a heterogeneous drone cluster are different, when drone i enters the communication range of drone j, drone i will receive the communication message sent by drone j. The message contains all drone status information and target status information stored by drone j itself. After receiving the message, drone j first reads the last updated timestamp of each drone status information. , , Represents the number of drones in the cluster. Compare the drone status information timestamp with the status information timestamp stored locally by drone i. If , the information of drone c in the message is used to replace the information of drone c stored in drone i. Similarly, the timestamp is also used , , Represents the number of targets and determines whether to update the target information stored in the drone. The drone local information update process is as follows: Figure 5 shown.

[0040] After the information transmission is completed, the search information is updated according to the detection range and target discovery of drone c pre-stored in the drone. Finally, the objective function value of drone i in the current state is calculated based on the other drone information obtained by drone i.

[0041] It should be noted that, according to the embodiments of the present invention, the following can be obtained: Figure 6 Schematic diagram of collaborative search among heterogeneous drone clusters shown.

[0042] The above embodiments of the present invention can achieve the following technical effects: (1) Use fixed-wing UAVs as communication nodes, giving full play to the advantages of fixed-wing UAVs in high flight altitude, high speed and wide communication range, and greatly improving the flow of information between rotary-wing UAVs; (2) Using specially designed information transmission content and information update methods, drones can share historical search information with small communication bandwidth requirements and reproduce the search status of other drones locally based on the acquired information, greatly improving the information transmission efficiency of drone clusters under communication constraints.

[0043] (3) Under communication constraints, the collaborative search efficiency of heterogeneous clusters using this method is significantly improved compared to homogeneous clusters, and can quickly scout the mission area and discover targets. This technology has important application value in emergency rescue, environmental reconnaissance and other fields.

[0044] Combination Figure 7 As shown, the present invention also protects a heterogeneous UAV cluster target search device 700, and the heterogeneous UAV cluster target search device 700 includes: The area division module 710 is adapted to divide the search target area into a plurality of discrete grids so as to discretize the motion of each UAV in the cluster in the rasterized map; The state determination module 720 is adapted to determine the state formula and action formula of each drone at the current moment based on the grid and posture of the drone at the current moment; The state estimation module 730 is adapted to estimate the state of each drone at the next moment according to the state formula and action formula of each drone at the current moment; A sequence determination module 740 is adapted to repeat the previous step to obtain the action sequence and state sequence of the drone in multiple prediction steps; Data sharing module 750, adapted for each drone in the cluster to share its own action sequence, state sequence and search results into the data link; The optimal solution determination module 760 is suitable for each drone to determine the optimal solution from its own action sequence based on the optimization algorithm model in each decision cycle according to its own information in the data link and the information obtained from other drones in the cluster.

[0045] According to the heterogeneous drone cluster target search device disclosed in this embodiment, the efficiency of collaborative search of heterogeneous drones is significantly improved compared with that of homogeneous drone clusters, and the mission area can be scouted and targets can be discovered quickly.

[0046] In some embodiments, the state determination module 720 is adapted to: Determine the state of the drone based on the drone's perception of its own state, environment, target or threat, wherein the state includes heading angle, flight speed or position; The action of the drone is determined according to the flight direction of the drone, where the flight directions include: straight flight, left yaw, and right yaw.

[0047] In some embodiments, the state estimation module 730 is adapted to: Determine the state of the next moment based on the action and state of the drone at the current moment and the mapping relationship from the current moment to the state of the next moment; The sequence determination module 740 is adapted to: According to the current state of the drone and the action sequence within the predicted number of steps, the state sequence of the drone is obtained.

[0048] In some embodiments, the optimal solution determination module 760 is adapted to: Within the range of the possible state set and the permissible action set of the drone, based on the sequence actions, sequence states and search results of each drone in the cluster, the optimization algorithm model is used to determine the optimal action sequence from the self-action sequence.

[0049] In some embodiments, the data sharing module 750 is adapted to: The fixed-wing UAV is used as a communication relay node, and the action sequence, state sequence and search result of each UAV in the cluster are obtained and updated through the fixed-wing UAV.

[0050] In some embodiments, the data sharing module 750 is further adapted to: Constructing an information structure of a data link, wherein the information structure includes a drone state information matrix and a target information matrix, wherein the drone state information matrix stores the position and heading information of the drone and the corresponding timestamp, and the target information matrix stores the position information of the target and the corresponding timestamp, and the drone state information matrix and the target information matrix are sequentially arranged to form a data link; When different UAVs communicate, each UAV updates its own data link based on the data link of other UAVs.

[0051] In some embodiments, when different drones are communicating, each drone updates its own data link based on the data link of other drones, including: After receiving the data link of another drone, the drone obtains the timestamps of other drones in the drone state information matrix in the data link. If the timestamp is closer to the current moment than the timestamp of the corresponding drone stored in the drone, the drone updates its own data link, otherwise it does not update; and / or, After receiving the data link from another drone, the drone obtains the timestamp of each target in the target information matrix in the data link. If the timestamp is closer to the current moment than the timestamp of the corresponding target stored in itself, it updates its own data link, otherwise it does not update.

[0052] It should be noted that: The algorithm and display provided herein are not inherently related to any particular computer, virtual device or other equipment. Various general-purpose devices can also be used together with the teachings based on this. According to the above description, it is obvious to construct the structure required for this type of device. In addition, the present invention is not directed to any specific programming language either. It should be understood that various programming languages ​​can be utilized to realize the content of the present invention described herein, and the description of the above specific language is for the purpose of disclosing the best mode of the present invention.

[0053] In the description provided herein, a large number of specific details are described. However, it is understood that embodiments of the present invention can be practiced without these specific details. In some instances, well-known methods, structures and techniques are not shown in detail so as not to obscure the understanding of this description.

[0054] Similarly, it should be understood that in order to streamline the present invention and aid in understanding one or more of the various inventive aspects, in the above description of exemplary embodiments of the present invention, various features of the present invention are sometimes grouped together into a single embodiment, figure, or description thereof. However, this method of disclosure should not be interpreted as reflecting an intention that the claimed invention requires more features than are expressly recited in each claim.

[0055] Those skilled in the art will appreciate that the modules in the devices in the embodiments may be adaptively changed and arranged in one or more devices different from the embodiments. The modules or units or components in the embodiments may be combined into one module or unit or component, and further may be divided into a plurality of submodules or subunits or subcomponents. All features disclosed in this specification (including the accompanying claims, abstracts and drawings) and all processes or units of any method or device so disclosed may be combined in any combination, except that at least some of such features and / or processes or units are mutually exclusive. Unless otherwise expressly stated, each feature disclosed in this specification (including the accompanying claims, abstracts and drawings) may be replaced by an alternative feature that provides the same, equivalent or similar purpose.

[0056] Furthermore, those skilled in the art will appreciate that although some embodiments described herein include certain features included in other embodiments but not other features, the combination of features from different embodiments is meant to be within the scope of the present invention and to form different embodiments.

[0057] The various component embodiments of the present invention may be implemented in hardware, or in software modules running on one or more processors, or in a combination thereof. Those skilled in the art should understand that a microprocessor or a digital signal processor (DSP) may be used in practice to implement some or all of the functions of some or all of the components in the heterogeneous UAV cluster target search device according to an embodiment of the present invention. The present invention may also be implemented as a device or apparatus program (e.g., a computer program and a computer program product) for executing part or all of the methods described herein. Such a program for implementing the present invention may be stored on a computer-readable medium, or may be in the form of one or more signals. Such a signal may be downloaded from an Internet website, or provided on a carrier signal, or provided in any other form.

[0058] An embodiment of the present invention provides a non-volatile computer storage medium, which stores at least one executable instruction, and the computer executable instruction can execute the above-mentioned heterogeneous drone cluster target search method in any of the above-mentioned method embodiments.

[0059] Figure 8 A schematic diagram of the structure of an embodiment of a drone of the present invention is shown, and the specific embodiment of the present invention does not limit the specific structure of the drone.

[0060] like Figure 8 As shown, the UAV (including the flight control system) may include: a processor (processor) 802 , a communications interface (Communications Interface) 804 , a memory (memory) 806 , and a communication bus 808 .

[0061] Wherein: the processor 802, the communication interface 804, and the memory 806 communicate with each other through the communication bus 808. The communication interface 804 is used to communicate with other devices such as a client or other server network elements. The processor 802 is used to execute the program 810, which can specifically execute the relevant steps in the above-mentioned heterogeneous drone cluster target search method embodiment for drones.

[0062] Specifically, the program 810 may include program codes, which include computer operation instructions.

[0063] The processor 802 may be a central processing unit (CPU), or an application-specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of the present invention. The one or more processors included in the drone may be processors of the same type, such as one or more CPUs; or processors of different types, such as one or more CPUs and one or more ASICs.

[0064] The memory 806 is used to store the program 810. The memory 806 may include a high-speed RAM memory, and may also include a non-volatile memory (non-volatile memory), such as at least one disk memory.

[0065] Program 810 can be specifically used to enable processor 802 to perform operations corresponding to the above-mentioned heterogeneous drone cluster target search method embodiment.

[0066] It should be noted that the above embodiments illustrate the present invention rather than limit it, and that those skilled in the art may devise alternative embodiments without departing from the scope of the appended claims. In the claims, any reference symbol between brackets shall not be construed as a limitation on the claims. The word "comprising" does not exclude the presence of elements or steps not listed in the claims. The word "one" or "an" preceding an element does not exclude the presence of a plurality of such elements. The present invention may be implemented by means of hardware comprising a number of different elements and by means of a suitably programmed computer. In a unit claim enumerating a number of devices, several of these devices may be embodied by the same hardware item. The use of the words first, second, and third, etc., does not indicate any order. These words may be interpreted as names.

Claims

1. A heterogeneous UAV cluster target search method, characterized in that: The method comprises: The search target area is divided into multiple discrete grids to discretize the movement of each drone in the cluster in the rasterized map; Based on the grid and posture of the drone at the current moment, determine the state formula and action formula of each drone at the current moment; According to the state formula and action formula of each drone at the current moment, estimate the state of each drone at the next moment; Repeat the previous step to obtain the action sequence and state sequence of the drone in multiple prediction steps; Each drone in the cluster shares its own action sequence, state sequence and search results to the data link; In each decision cycle, each drone determines the optimal solution from its own action sequence based on the optimization algorithm model according to its own information in the data link and the information obtained from other drones in the cluster.

2. The method according to claim 1, characterized in that The state formula and action formula of each drone at the current moment are determined based on the grid and posture of the drone at the current moment, including: Determine the state of the drone based on the drone's perception of its own state, environment, target or threat, wherein the state includes heading angle, flight speed or position; The action of the drone is determined according to the flight direction of the drone, where the flight directions include: straight flight, left yaw, and right yaw.

3. The method according to claim 2, characterized in that The estimation of the state of each drone at the next moment based on the state formula and action formula of each drone at the current moment includes: Determine the state of the next moment based on the action and state of the drone at the current moment and the mapping relationship from the current moment to the state of the next moment; Repeating the previous step to obtain the action sequence and state sequence of the drone in multiple prediction steps includes: According to the current state of the drone and the action sequence within the predicted number of steps, the state sequence of the drone is obtained.

4. The method according to claim 1, characterized in that: In each decision cycle, each drone determines the optimal solution from its own action sequence based on the optimization algorithm model according to its own information in the data link and the information of other drones in the cluster, including: Within the range of the possible state set and the permissible action set of the drone, based on the sequence actions, sequence states and search results of each drone in the cluster, the optimal action sequence is determined from the self-action sequence using the optimization algorithm model.

5. The method according to any one of claims 1 to 4, characterized in that The drone cluster includes rotary-wing drones and fixed-wing drones, and each drone in the cluster shares its own action sequence, state sequence and search results to the data link, including: The fixed-wing UAV is used as a communication relay node, and the action sequence, state sequence and search result of each UAV in the cluster are obtained and updated through the fixed-wing UAV.

6. The method according to claim 1, characterized in that Each drone in the cluster shares its own action sequence, state sequence and search results to the data link, further including: Constructing an information structure of a data link, wherein the information structure includes a drone state information matrix and a target information matrix, wherein the drone state information matrix stores the position and heading information of the drone and the corresponding timestamp, and the target information matrix stores the position information of the target and the corresponding timestamp, and the drone state information matrix and the target information matrix are sequentially arranged to form a data link; When different UAVs communicate, each UAV updates its own data link based on the data link of other UAVs.

7. The method according to claim 6, characterized in that When different drones communicate, each drone updates its own data link based on the data link of other drones, including: After receiving the data link of another drone, the drone obtains the timestamps of other drones in the drone state information matrix in the data link. If the timestamp is closer to the current moment than the timestamp of the corresponding drone stored in the drone, the drone updates its own data link, otherwise it does not update; and / or, After receiving the data link from another drone, the drone obtains the timestamp of each target in the target information matrix in the data link. If the timestamp is closer to the current moment than the timestamp of the corresponding target stored in itself, it updates its own data link, otherwise it does not update.

8. A heterogeneous UAV cluster target search device, characterized in that: The device comprises: The area division module is suitable for dividing the search target area into multiple discrete grids so as to discretize the movement of each drone in the cluster in the rasterized map; A state determination module is adapted to determine the state formula and action formula of each drone at the current moment based on the grid and posture of the drone at the current moment; The state estimation module is suitable for estimating the state of each drone at the next moment according to the state formula and action formula of each drone at the current moment; A sequence determination module is adapted to repeat the previous step to obtain the action sequence and state sequence of the drone in multiple prediction steps; The data sharing module is suitable for each drone in the cluster to share its own action sequence, state sequence and search results into the data link; The optimal solution determination module is suitable for each UAV to determine the optimal solution from its own action sequence based on the optimization algorithm model in each decision cycle according to its own information in the data link and the information obtained from other UAVs in the cluster.

9. A drone, characterized in that: It comprises a processor and a memory arranged to store computer executable instructions, wherein when the executable instructions are executed, the processor executes the heterogeneous UAV cluster target search method according to any one of claims 1-7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores one or more programs, which, when executed by a processor, implement the heterogeneous UAV cluster target search method according to any one of claims 1-7.

Citation Information

Cited By

  • Cluster unmanned aerial vehicle region traversal search method

    CN119292313A

  • Unmanned aerial vehicle cluster collaborative search method and system based on multi-agent reinforcement learning

    CN121742524A