Multi-target association identification method, system, device and medium for drone swarm

Abstract

The application provides a kind of unmanned aerial vehicle swarm multi-target association identification method, system, equipment and medium, it is related to unmanned aerial vehicle countermeasure technical field, the method comprises: first unmanned aerial vehicle receives each second unmanned aerial vehicle broadcast each second unmanned aerial vehicle real-time positioning information;Second unmanned aerial vehicle and first unmanned aerial vehicle exist cooperative relationship;According to real-time positioning information, the local multi-target detection information collected by the airborne detection component of first unmanned aerial vehicle is carried out detection information filtering, and first local detection information is obtained;According to first local detection information and each second unmanned aerial vehicle broadcast second local detection information, the target positioning information of each third unmanned aerial vehicle in global coordinate system is acquired;Third unmanned aerial vehicle and first unmanned aerial vehicle and second unmanned aerial vehicle exist counter cooperative relationship;According to target positioning information, the identity of each third unmanned aerial vehicle is acquired.The application realizes the efficient unity and alignment of enemy target identity in swarm, to improve the overall effectiveness of anti-swarm combat.

Description

Technical Field

[0001] This invention relates to the field of drone countermeasures technology, and in particular to a method, system, device and medium for multi-target association identification of drone swarms. Background Technology

[0002] With the rapid development of drone swarm warfare technology, swarm-to-swarm has become an important development direction in the field of Counter-Unmanned Aerial Systems (C-UAS). In such many-to-many interception scenarios, friendly interceptor swarms and enemy swarms often form a densely intertwined game situation in a very short time, which places extremely high demands on battlefield situational awareness and coordinated strike capabilities. In order to achieve efficient interception, friendly drone swarms need to grasp the precise distribution of enemy targets on the battlefield in real time and form a unified strike list within the swarm to avoid wasting firepower or missing targets.

[0003] In existing technologies, each UAV in a swarm assigns temporary numbers to the detected targets based on its own independent local coordinate system. This makes it difficult for the swarm to form a unified global battlefield situation map, and it is impossible to efficiently coordinate to carry out precise target allocation and interception mission planning, which greatly reduces the overall effectiveness of anti-swarm operations. Summary of the Invention

[0004] This invention provides a method, system, device, and medium for multi-target association identification of drone swarms, which solves the problem that in the prior art, different drones in a swarm temporarily number the detected targets based on their own independent local coordinate systems, resulting in poor overall effectiveness of anti-swarm operations. This invention achieves efficient unification and alignment of enemy target identities within the swarm, thereby improving the overall effectiveness of anti-swarm operations.

[0005] This invention provides a multi-target association identification method for a drone swarm, applied to a first drone in a target drone swarm, the method comprising:

[0006] Receive real-time location information of each of the second drones broadcast by each of the second drones; the second drones are drones in the target drone swarm that have a cooperative relationship with the first drone;

[0007] Based on the real-time positioning information, the local multi-target detection information collected by the airborne detection component of the first UAV is filtered to obtain the first local detection information; the first local detection information includes the local detection information of each third UAV that has an anti-cooperative relationship with the first UAV.

[0008] Based on the first local detection information and the second local detection information broadcast by each of the second UAVs, the target positioning information of each of the third UAVs in the global coordinate system is obtained; the second local detection information includes the local detection information of each of the third UAVs that have an anti-cooperative relationship with each of the second UAVs; the global coordinate system is the unified coordinate system used by the target UAV swarm for collaborative detection;

[0009] Based on the target positioning information, the identity identifiers of each of the third UAVs are obtained.

[0010] According to the present invention, a multi-target association identification method for a drone swarm includes obtaining target positioning information of each third drone in a global coordinate system based on the first local detection information and the second local detection information broadcast by each second drone.

[0011] Obtain the transformation matrix of the local coordinate system of the airborne detection component relative to the global coordinate system;

[0012] Based on the transformation matrix, the first local detection information is transformed to the global coordinate system to obtain the first global detection information;

[0013] Receive the second global detection information corresponding to the second local detection information broadcast by each of the second UAVs;

[0014] The first global detection information and the second global detection information are fused to obtain the target positioning information of each of the third UAVs.

[0015] According to the present invention, a multi-target association identification method for a drone swarm includes fusing the first global detection information and the second global detection information to obtain the target positioning information of each of the third drones, comprising:

[0016] Calculate the mutual distance between each first positioning information in the first global detection information and each second positioning information in the second global detection information;

[0017] Each set of first and second positioning information with a mutual distance of less than a preset overlap threshold is determined as an associated positioning information set for the same third UAV.

[0018] The target positioning information of each of the third UAVs is obtained by fusing the first positioning information and the second positioning information in the associated positioning information set.

[0019] According to the present invention, a multi-target association identification method for a drone swarm includes filtering the local multi-target detection information collected by the airborne detection component of the first drone based on the real-time positioning information to obtain first local detection information, comprising:

[0020] Obtain the transformation matrix of the local coordinate system of the airborne detection component relative to the global coordinate system;

[0021] Using the transformation matrix, the real-time positioning information is reversed and mapped to obtain the mapped positioning information of each of the second UAVs in the local coordinate system where the airborne detection component is located;

[0022] Calculate the spatial distance between the local detection information of each target in the local multi-target detection information and the mapping positioning information;

[0023] Based on the spatial distance, the local multi-target detection information is filtered to obtain the first local detection information.

[0024] According to the present invention, a multi-target association identification method for a drone swarm, wherein the step of filtering the local multi-target detection information based on the spatial distance to obtain the first local detection information includes:

[0025] The local detection information corresponding to the detection targets whose spatial distance is less than a preset error threshold is filtered out from the local multi-target detection information to obtain the first local detection information.

[0026] According to the present invention, a multi-target association identification method for a drone swarm includes obtaining the identity identifiers of each third drone based on the target positioning information, comprising:

[0027] Based on the target positioning information, the longitude, latitude, and elevation values ​​of each of the third UAVs are obtained;

[0028] The third UAVs are sorted according to the longitude, latitude, and elevation values.

[0029] Based on the sorting results, each of the third UAVs is assigned a unique digital code as its identity identifier.

[0030] According to the multi-target association identification method for a drone swarm provided by the present invention, the step of sorting each of the third drones according to the longitude value, the latitude value, and the elevation value includes:

[0031] Based on the combat mission of the target drone swarm, determine the comparison priority of each data dimension among the data dimensions corresponding to the longitude value, the data dimensions corresponding to the latitude value, and the data dimensions corresponding to the elevation value;

[0032] According to the comparison priority, the values ​​corresponding to each of the data dimensions are used as sorting keys to sort the third UAVs.

[0033] The present invention also provides a multi-target association identification system for a drone swarm, applied to a first drone in a target drone swarm, the system comprising:

[0034] The receiving module is used to receive the real-time location information of each of the second drones broadcast by each of the second drones; the second drones are drones in the target drone swarm that have a cooperative relationship with the first drone;

[0035] The filtering module is used to filter the local multi-target detection information collected by the airborne detection component of the first UAV based on the real-time positioning information to obtain the first local detection information; the first local detection information includes the local detection information of each third UAV that has an anti-cooperative relationship with the first UAV.

[0036] The positioning module is used to obtain the target positioning information of each of the third drones in a global coordinate system based on the first local detection information and the second local detection information broadcast by each of the second drones; the second local detection information includes the local detection information of each of the third drones that have an anti-cooperative relationship with each of the second drones; the global coordinate system is a unified coordinate system used by the target drone swarm for collaborative detection;

[0037] The identification module is used to obtain the identity identifier of each of the third UAVs based on the target positioning information.

[0038] The present invention also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the multi-target association identification method for drone swarms as described above.

[0039] The present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the multi-target association identification method for UAV swarms as described above.

[0040] The present invention also provides a computer program product, including a computer program that, when executed by a processor, implements the multi-target association identification method for UAV swarms as described above.

[0041] The present invention provides a method, system, device, and medium for multi-target association identification of UAV swarms. A first UAV receives real-time positioning information from second UAVs with cooperative relationships. Local multi-target detection information collected by the onboard detection components of the first UAV is filtered to accurately eliminate interference from friendly targets. The filtered first local detection information is then fused with the second local detection information broadcast by each second UAV in a unified global coordinate system to obtain the target positioning information of each third UAV. Finally, based on the unified global target positioning information, the identity identifier of each third UAV is directly obtained, thus completely eliminating ambiguity in cross-UAV target identification. This achieves efficient unification and alignment of enemy target identities within the swarm, effectively solving the problem of existing detection pods lacking identity recognition capabilities, which easily leads to friendly UAV collide attacks. It also eliminates the fragmentation of battlefield situational awareness caused by independent detection by a single UAV. Furthermore, it eliminates the need to exchange easily interfered or forged IDs; automatic alignment is achieved solely based on the spatial distribution characteristics of the targets. This greatly improves the intelligence and robustness of swarm-based collaborative countermeasures, enabling efficient collaborative and precise target allocation and interception mission planning, significantly enhancing the overall effectiveness of anti-swarm operations. Attached Figure Description

[0042] To more clearly illustrate the technical solutions in this invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0043] Figure 1 This is a flowchart illustrating the multi-target association identification method for drone swarms provided by the present invention.

[0044] Figure 2 This is a schematic diagram of target-related coordinate transformation between bee colonies provided by the present invention.

[0045] Figure 3 This is a schematic diagram of the structure of the multi-target association identification system for drone swarms provided by the present invention.

[0046] Figure 4 This is a schematic diagram of the structure of the electronic device provided by the present invention. Detailed Implementation

[0047] To make the objectives, technical solutions, and advantages of this invention clearer, the technical solutions of this invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this invention. All other embodiments obtained by those skilled in the art based on the embodiments of this invention without creative effort are within the scope of protection of this invention.

[0048] All actions involving the acquisition of signal information or data in this application are carried out in accordance with the relevant data protection laws and policies of the country where the application is located, and with the authorization granted by the owner of the relevant device.

[0049] In many-to-many interception scenarios involving swarms of drones, both sides' drones often engage in close-range combat in dense formations, posing a serious challenge to traditional friend-or-foe identification methods that rely on single-platform positioning and identification or pre-coded methods.

[0050] Specifically, in existing technologies, the detection pods carried by anti-drone interceptors generally focus on target tracking and locking. Their functional design is relatively simple; that is, many existing pod systems only have the ability to detect the direction of the target, but lack a precise mechanism for identifying the target's identity. This leads to a situation in swarm combat scenarios where, even if our swarm of drones can obtain its own precise positioning information through the Global Navigation Satellite System (GNSS), the pods cannot effectively use this position data to correlate and calculate with the detected target's location, making it difficult to filter out friendly targets. Consequently, effective friend-or-foe identification cannot be achieved. Since individual drones in the interceptor swarm need to coordinate to attack enemy swarm targets, the inability to quickly distinguish friend from foe can easily lead to friendly fire incidents or redundant firepower distribution. Meanwhile, because each interceptor operates independently, the enemy target location information it detects is based on temporary numbers assigned to the enemy target by its own sensors when detecting the target independently. This information cannot be effectively shared, merged, or deduplicated within the swarm, resulting in different UAVs generating different local numbers for the same enemy target. This cross-aircraft target number mismatch causes cross-aircraft target identification information to become disordered, making it difficult for the swarm to form a unified battlefield situation map and hindering efficient coordination for precise fire allocation and interception mission planning. This significantly reduces the overall effectiveness of anti-swarm operations. Therefore, how to achieve efficient friend-or-foe identification within the swarm and complete the unified alignment of enemy target identities across aircraft in low-bandwidth, high-dynamic combat environments has become a key bottleneck in improving the effectiveness of swarm-to-anti-swarm interception.

[0051] To address this issue, this application provides a multi-target association and identification method for UAV swarms. This method is applicable to multi-UAV anti-game-free adversarial tasks under dense formation conditions. Its core lies in utilizing the shared global positioning information among individual UAVs and the target location information detected by the payload. Through spatial position alignment calculations, it achieves unified identification of friend or foe and the identification of enemy targets, providing a unified enemy target identification for more complex multi-UAV adversarial tasks. In terms of technical features: First, this method only requires exchanging the coordinate information of the UAVs and the targets they detect, resulting in small communication data volume and low bandwidth requirements, making it very suitable for swarm networks with limited wireless communication resources. Second, the core algorithm relies on efficient matrix operations, resulting in low computational complexity and easy real-time operation on embedded platforms with limited computing resources, ensuring the system's rapid response capability. Of particular note is that this method employs a mechanism for exchanging identity information without identification. It assigns numbers to enemy targets uniformly based solely on the spatial distribution characteristics of the targets, fundamentally avoiding the security risks associated with exchanging easily interfered or forged identity information. This achieves secure, efficient, and automatic cross-aircraft target identity alignment without prior negotiation, greatly enhancing the intelligence and robustness of swarm-based collaborative countermeasures, and thus significantly improving the overall effectiveness of anti-swarm operations.

[0052] Figure 1 This is a flowchart illustrating the multi-target association identification method for drone swarms provided by the present invention. Figure 2 This is a schematic diagram of target-related coordinate transformation between bee colonies provided by the present invention.

[0053] It should be noted that the multi-target association identification method for UAV swarms provided in this application is applicable to multi-UAV anti-game-free adversarial tasks under dense formation conditions, and is particularly suitable for scenarios where UAVs within a swarm conduct cooperative detection and target identification through a wireless communication network. This method is executed by the first UAV in the target UAV swarm, which shares its location information with other cooperating second UAVs to achieve accurate identification and unified numbering of the enemy (i.e., the third UAV).

[0054] The target drone swarm is the drone swarm that needs to perform friend-or-foe identification and cross-drone enemy target identity alignment, also known as the friendly drone swarm. It includes multiple friendly drones that cooperate with each other, and the first drone can be any friendly drone in the target drone swarm.

[0055] like Figure 1 As shown, the method includes:

[0056] Step 110: Receive the real-time location information of each of the second drones broadcast by each of the second drones; the second drones are drones in the target drone swarm that have a cooperative relationship with the first drone.

[0057] The second drone here refers to other friendly drones in the target drone swarm that cooperate with the first drone, in addition to the first drone. Specifically, this includes the communication connection, tactical coordination, and information sharing relationships between the first drone and each of the second drones.

[0058] Optionally, the individual drones in the swarm (i.e., the first drone and each of the second drones) establish a connection via a wireless communication link. In order to achieve efficient collaboration in a swarm network with limited communication bandwidth, each drone can exchange its own real-time location information to maintain a small amount of communication data.

[0059] Specifically, the first UAV can receive real-time positioning information broadcast by each of the second UAVs. This real-time positioning information can be obtained by real-time acquisition of the spatial coordinates of the second UAV's body using a positioning sensor, such as GNSS, deployed within it. Similarly, the real-time positioning information of the first UAV can also be obtained by real-time acquisition of the spatial coordinates of the first UAV's body using a positioning sensor, such as GNSS, deployed within it.

[0060] For example, such as Figure 2 As shown, assume a typical swarm vs. swarm scenario, where the friendly drone swarm has two friendly drones, denoted as drone A1 and drone A2; and the enemy drone swarm has two enemy drones, also known as two third drones, denoted as drone E1 and drone E2.

[0061] Among them, the first UAV is UAV A1, and the second UAV is UAV A2. The local coordinate system of the airborne detection component carried by UAV A1 is X'Y'Z', and the local coordinate system of the airborne detection component carried by UAV A2 is X"Y"Z. The global coordinate system (such as the GNSS positioning coordinate system) of the individual UAVs in the swarm (i.e., the target UAV swarm) is XYZ. Simultaneously, the transformation matrix from the local coordinate system X'Y'Z' of the airborne detection component carried by UAV A1 to the global coordinate system is: The transformation matrix from the local coordinate system X”Y”Z” of the airborne detection component carried by the UAV A2 to the global coordinate system is: .

[0062] The real-time positioning information (such as GNSS coordinate information) of UAV A1 is: The real-time positioning information (such as GNSS coordinate information) of the A2 UAV is The A1 drone can It is broadcast to drone A2, and similarly, drone A2 can... The information is broadcast to drone A1 so that drones in the swarm can exchange their real-time location information.

[0063] Step 120: Based on the real-time positioning information, filter the local multi-target detection information collected by the airborne detection component of the first UAV to obtain the first local detection information.

[0064] Optionally, while receiving real-time positioning information broadcast by each of the second UAVs, the first UAV can also acquire local multi-target detection information collected by its onboard detection components. Here, the onboard detection components of the first UAV refer to sensor devices installed on the first UAV's fuselage for acquiring information about external environmental targets. Specifically, these can be payloads with azimuth or position detection capabilities, such as electro-optical pods, infrared detectors, lidar, or millimeter-wave radar. The local multi-target detection information collected by the first UAV's onboard detection components refers to the detection data of all targets within the field of view collected by the first UAV through these components in the local coordinate system where the onboard detection components are located. It should be noted that before identification and filtering, this local multi-target detection information contains third UAVs (i.e., enemy UAVs, or simply enemy aircraft) that have a counter-cooperative relationship with the first UAV within the target UAV swarm, as well as second UAVs (i.e., friendly UAVs, or simply friendly aircraft) that may enter the detection field of view and have a cooperative relationship with the first UAV.

[0065] After acquiring real-time positioning information from each of the second UAVs and local multi-target detection information collected by the first UAV's onboard detection components, the first UAV can filter the local multi-target detection information collected by its onboard detection components based on the real-time positioning information of each of the second UAVs. This filters out the detection information of friendly UAVs (i.e., the second UAVs) from the local multi-target detection information collected by the first UAV's onboard detection components, retaining only the detection information of enemy UAVs (i.e., the third UAVs). In this process, the first UAV can combine the received real-time positioning information of each of the second UAVs and, through spatial geometric relationship matching calculations, determine whether each detection target in the local multi-target detection information coincides with or matches the spatial position of a certain second UAV. If the coincidence or matching is successful, the detection target is identified as a friendly UAV, and its corresponding detection data is filtered out from the local multi-target detection information.

[0066] The information obtained after the above filtering process is the first local detection information. This first local detection information mainly includes the local detection information of each third UAV that has an anti-cooperative relationship with the first UAV, that is, the local detection information of each enemy UAV in the enemy UAV swarm, thereby realizing the elimination of friendly UAVs and the preliminary screening of enemy UAVs at the single-aircraft level.

[0067] For example, such as Figure 2 As shown, the enemy drone swarm includes two enemy drones (i.e., the third drone), namely drone E1 and drone E2.

[0068] Assume the first drone is drone A1. Drone A1 detects two enemy drones, namely drone E1 and drone E2, through a pod. The positions (i.e., local detection information) of the two enemy drones in drone A1's local coordinate system X'Y'Z' are respectively... and Furthermore, drone A1 received the real-time location information broadcast by drone A2. Then, drone A1 can receive real-time location information shared by drone A2. Rather than detecting local detection information of UAV E1 Local detection information from the E2 drone Spatial location matching was performed, and the matching revealed local detection information. and local detection information With real-time location information If none of them match, it indicates that there is no local detection information of friendly UAVs in the local multi-target detection information obtained. The detection targets corresponding to all local detection information in the local multi-target detection information can be identified as enemy UAVs, and all the corresponding detection information is the first local detection information.

[0069] Similarly, each second UAV can also acquire the second local detection information in the same way. For details, please refer to the steps for acquiring the first local detection information, which will not be repeated here.

[0070] For example, suppose the second drone is drone A2. Drone A2 detects two enemy drones and one friendly drone via a pod, namely drones E1, E2, and A1. The local detection information (also known as the orientation) of these three drones in drone A2's local coordinate system are as follows: , and At this point, based on the real-time positioning information (such as GNSS coordinate information) shared between UAVs A1 and A2, it can be further determined whether the aerial target detected by the pod is enemy or friendly. Specifically, UAV A2 uses the real-time positioning information shared by UAV A1... and the local detection information it detected , and Spatial location matching was performed, and the matching revealed local detection information. With real-time location information Matching indicates that the local multi-target detection information obtained from the detection includes local detection information of friendly UAVs. It can extract local detection information from local multi-target detection information. Delete it. At this point, the remaining local detection information is determined to be the local detection information of the enemy drone, that is, the second local detection information.

[0071] Step 130: Based on the first local detection information and the second local detection information broadcast by each of the second UAVs, obtain the target positioning information of each of the third UAVs in the global coordinate system.

[0072] Optionally, to achieve swarm-level collaborative detection, not only does the first UAV need to process its own detection data, but each second UAV also synchronously performs similar detection and filtering operations. The second local detection information here refers to the local multi-target detection information acquired by each second UAV using its onboard detection components, and the detection information retained after filtering by friendly UAVs based on their shared real-time positioning information. The specific implementation steps are detailed in steps 110 and 120, and will not be repeated here. Each second UAV broadcasts this second local detection information via a wireless communication link.

[0073] In addition, the first UAV needs to acquire a global coordinate system, which is a unified coordinate system used by the target UAV swarm for collaborative detection, such as the coordinate system used by GNSS, which can be labeled as XYZ. Here, establishing a unified global coordinate system is to eliminate the differences in observation perspectives caused by the different positions and attitudes of different UAVs, so that multi-source detection data can be compared and fused.

[0074] Subsequently, the first UAV needs to map or transform its acquired local detection information and the received local detection information from each of the second UAVs into the global coordinate system. Since multiple UAVs in the swarm (the first and second UAVs) may simultaneously detect the same enemy UAV (i.e., the third UAV), there may be multiple detection data points targeting the same enemy UAV in the global coordinate system. The first UAV needs to fuse this multi-source data, for example, through spatial distance clustering analysis or deduplication, merging multiple detection points pointing to the same physical entity (the third UAV) into a single, defined location coordinate. This ultimately yields a precise location description of each third UAV in the global coordinate system, i.e., target positioning information. This achieves spatial location sharing and unification of enemy target information throughout the swarm, eliminating the limitations and blind spots of single-UAV detection and constructing a complete spatial distribution map of enemy targets.

[0075] For example, such as Figure 2 As shown, the first UAV A1 transforms the enemy target it detects (first local detection information) into the global coordinate system, and also receives the enemy target detected by the second UAV A2 (second local detection information). A1 compares these two sets of data in the global coordinate system. If it finds that the location of a target detected by A1 overlaps with the location of a target detected by A2 in space, it merges them to obtain the target location information of the same third UAV.

[0076] Step 140: Obtain the identity identifier of each of the third UAVs based on the target positioning information.

[0077] Optionally, after obtaining unified, global target location information for all third UAVs, the first UAV can process this target location information according to a pre-defined unified rule within the target UAV swarm to obtain the identity (ID) of each third UAV. This identity is used to uniquely mark and distinguish each third UAV within the target UAV swarm's combat system, facilitating unified fire allocation, mission tracking, or situational awareness display.

[0078] For example, the first UAV can logically sort the third UAVs based on the spatial geometric features in the target positioning information of each third UAV, such as the size relationship of coordinate values ​​and the spatial distribution order. According to the sorting order, a unique digital code or character code is assigned to each third UAV as the identity identifier.

[0079] Since the target positioning information (i.e. after fusion and deduplication) used by all drones in the swarm is consistent and the sorting rules are also uniform, for the same drone, the identity identifier calculated by the first drone and the identity identifier calculated by the second drone will necessarily point to the same third drone. Thus, automatic alignment of enemy target identities across drones is achieved without the need to exchange specific identity identifier information.

[0080] In summary, the method provided in this application has the following advantages:

[0081] First, this application combines real-time positioning information shared within the swarm with detection information from airborne detection components, and achieves efficient friend-or-foe identification through spatial position matching calculation, effectively solving the problem that existing detection pods lack identification functions and are prone to accidentally damaging friendly aircraft.

[0082] Secondly, this application establishes a target positioning information fusion mechanism under a global coordinate system, enabling UAVs from different perspectives to reach a consensus on the position of the same enemy target (i.e., enemy UAV), thus eliminating the fragmentation problem of battlefield situational awareness caused by independent detection by a single UAV.

[0083] Finally, this application adopts an identity generation strategy based on unified target location information. It eliminates the need to transmit enemy target IDs that are easily interfered with or forged in the communication network. It can achieve enemy target ID alignment across the entire swarm range based solely on objective spatial location characteristics. This not only greatly reduces the occupation of wireless communication bandwidth and adapts to the low bandwidth environment of dense swarms, but also improves the system's anti-interference capability and security, providing a solid data foundation for swarm-to-swarm collaborative operations.

[0084] The method provided in this embodiment involves a first UAV receiving real-time positioning information from a second UAV with a cooperative relationship. This information is then filtered through the local multi-target detection information collected by the first UAV's onboard detection components to accurately eliminate interference from friendly targets. The filtered first local detection information is then fused with the second local detection information broadcast by each second UAV in a unified global coordinate system to obtain the target positioning information of each third UAV. Finally, based on the unified global target positioning information, the identity identifier of each third UAV is directly obtained, thus completely eliminating ambiguity in cross-UAV target identification. This achieves efficient unification and alignment of enemy target identities within the swarm, effectively solving the problem of existing detection pods lacking identity recognition capabilities, which easily leads to friendly aircraft being accidentally damaged. It also eliminates the fragmentation of battlefield situational awareness caused by independent detection by a single UAV. Furthermore, it eliminates the need to exchange easily interfered or forged IDs; automatic alignment is achieved solely based on the spatial distribution characteristics of the targets. This greatly improves the intelligence and robustness of swarm-based collaborative countermeasures, enabling efficient collaborative and precise target allocation and interception mission planning, significantly enhancing the overall effectiveness of anti-swarm operations.

[0085] In some embodiments, step 130 specifically includes:

[0086] Obtain the transformation matrix of the local coordinate system of the airborne detection component relative to the global coordinate system;

[0087] Based on the transformation matrix, the first local detection information is transformed to the global coordinate system to obtain the first global detection information;

[0088] Receive the second global detection information corresponding to the second local detection information broadcast by each of the second UAVs;

[0089] The first global detection information and the second global detection information are fused to obtain the target positioning information of each of the third UAVs.

[0090] Optionally, in densely packed multi-drone combat scenarios, in order to eliminate the positional deviations caused by the different observation angles and attitudes of each drone, it is necessary to unify the multi-source detection data to the same spatial reference for fusion, so as to obtain unified global target positioning information for each third drone. The specific implementation steps are as follows:

[0091] First, the first UAV obtains the transformation matrix of its local coordinate system relative to the global coordinate system, where its onboard detection components reside. This transformation matrix typically describes the rotation and translation relationship between the local coordinate system of the first UAV's onboard detection components and the global coordinate system (such as the GNSS coordinate system) used by the target UAV swarm. For example, the transformation matrix from the local coordinate system X'Y'Z' of the first UAV A1's onboard detection components (such as the pod) to the global coordinate system (such as the coordinate system corresponding to GNSS) is: .

[0092] Similarly, each second UAV can also obtain the transformation matrix of its own onboard detection components' local coordinate system relative to the global coordinate system. For example, the transformation matrix of the local coordinate system X"Y"Z" of the onboard detection components (such as the pod) of the second UAV A2 from the global coordinate system (such as the coordinate system corresponding to GNSS) is: .

[0093] Subsequently, the first UAV can use its corresponding transformation matrix to perform coordinate transformation on the first local detection information retained after filtering out friendly UAVs in step 120. Specifically, the transformation matrix can be multiplied by each local detection information (i.e., positioning information) in the first local detection information to obtain the first global detection information.

[0094] Furthermore, after each second UAV (such as UAV A2) completes the filtering of friendly aircraft locally, it also uses its own transformation matrix to convert the second local detection information it detected into coordinates in the global coordinate system, forming second global detection information. For details, please refer to the acquisition of the first global detection information, which will not be repeated here. Then, each second UAV broadcasts its own second global detection information through a wireless communication link.

[0095] Since multiple friendly drones may simultaneously detect the same enemy drone, multiple coordinate points from different observation sources will exist for the same target in global space. To eliminate redundancy and improve positioning accuracy, after acquiring global detection information of the enemy drones it detected and the global detection information of the enemy drones shared by all friendly drones, the first drone can fuse the global detection information of the same enemy drone detected by multiple parties to deduplicate the global detection information of the enemy drones, thereby forming a set of enemy drone positioning information without duplication, that is, a set of target positioning information.

[0096] The fusion here can be achieved by combining the similarity or distance between each first positioning information in the first global detection information and each second positioning information in the second global detection information.

[0097] In one possible implementation, the first global detection information and the second global detection information are fused to obtain the target positioning information of each of the third UAVs, specifically including:

[0098] Calculate the mutual distance between each first positioning information in the first global detection information and each second positioning information in the second global detection information;

[0099] Each set of first and second positioning information with a mutual distance of less than a preset overlap threshold is determined as an associated positioning information set for the same third UAV.

[0100] The target positioning information of each of the third UAVs is obtained by fusing the first positioning information and the second positioning information in the associated positioning information set.

[0101] Optionally, the first UAV traverses each coordinate point (first positioning information) in the first global detection information and calculates the mutual distance between it and each coordinate point (second positioning information) in the received second global detection information, such as Euclidean distance.

[0102] In addition, the first UAV acquires a preset overlap threshold, which is a spatial distance threshold set based on the detection error range of the airborne detection component and the minimum spacing of the swarm targets, for example, 2 meters or 5 meters.

[0103] If the distance between the first positioning information of target A detected by the first UAV and the second positioning information of target B detected by the second UAV is less than the preset overlap threshold, then target A and target B are determined to be the same third UAV, and these two coordinate positions are assigned to the same associated coordinate position set.

[0104] For each set of associated coordinate locations, the first UAV uses a data fusion algorithm to calculate its precise location. Optionally, this fusion calculation can use the arithmetic mean method, that is, calculate the average value of all coordinates in the same set of associated coordinate locations as the final target positioning information; or it can use the weighted average method, specifically assigning weights based on the confidence level detected by each UAV or the distance from a target.

[0105] Similarly, for the second UAV, the same steps can be used to obtain the global coordinate set of the corresponding enemy aircraft, that is, the target positioning information of each UAV, which will not be elaborated here.

[0106] For example, if the first UAV is UAV A1 and the second UAV is UAV A2, the local coordinates of the remaining enemy aircraft after filtering are transformed into the global coordinate system by both UAV A1 and UAV A2. This yields the global coordinate set of the enemy aircraft corresponding to UAV A1 (i.e., the first global detection information), which is marked as... This global coordinate set is broadcast and received by A2; it can also obtain the global coordinate set of the enemy aircraft corresponding to UAV A2 (i.e., the second detection information), marked as The global coordinate set is broadcast and then received by A1.

[0107] After receiving the second detection information shared by a friendly drone, namely drone A2, drone A1 can fuse it with its own first global detection information to traverse and identify overlapping enemy targets (i.e., third drones or enemy drones), forming a unique global location set of enemy targets, that is, a set including the target location information of all third drones. Specifically, drone A1 calculates the global coordinate set of the enemy aircraft it has detected. With the global coordinate set of enemy aircraft shared from the A2 UAV. The mutual distance between them is used, and the payload detection error distance (e.g., 2 meters) is used as a threshold to find the positions of enemy targets with overlapping spatial locations, thus discovering... and Overlapping positions and The locations overlap, and by merging them, a deduplicated global location set of enemy targets is obtained. .

[0108] The method provided in this embodiment effectively solves the problems of field-of-view stitching and target deduplication in multi-machine collaborative detection by transforming local observations to the global coordinate system and fusing them based on a distance threshold, thus ensuring the uniqueness and accuracy of the swarm's perception of the number and location of enemy targets.

[0109] In some embodiments, step 120 specifically includes:

[0110] Obtain the transformation matrix of the local coordinate system of the airborne detection component relative to the global coordinate system;

[0111] Using the transformation matrix, the real-time positioning information is reversed and mapped to obtain the mapped positioning information of each of the second UAVs in the local coordinate system where the airborne detection component is located;

[0112] Calculate the spatial distance between the local detection information of each target in the local multi-target detection information and the mapping positioning information;

[0113] Based on the spatial distance, the local multi-target detection information is filtered to obtain the first local detection information.

[0114] Optionally, the first UAV obtains the transformation matrix of its local coordinate system relative to the global coordinate system, where its onboard detection components are located.

[0115] Subsequently, the first UAV uses the inverse transformation of the transformation matrix (e.g., the inverse of the transformation matrix) to map the received real-time positioning information (global coordinates) of the second UAV back to the local coordinate system where the onboard detection component of the first UAV is located.

[0116] After obtaining the mapping and positioning information corresponding to each second UAV, the first UAV can compare the actual position of each detected target detected by its own airborne detection component (i.e., local detection information) with the calculated theoretical position of the friendly UAV (i.e., mapping and positioning information) and calculate the distance between the two.

[0117] The local detection information of friendly aircraft is filtered out from the local detection information of each target actually detected by the onboard detection components of the first UAV based on the distance, so as to obtain the first local detection information containing only the local detection information of enemy aircraft.

[0118] For example, the specific steps for filtering the local multi-target detection information based on the spatial distance to obtain the first local detection information include:

[0119] The local detection information corresponding to the detection targets whose spatial distance is less than a preset error threshold is filtered out from the local multi-target detection information to obtain the first local detection information.

[0120] The preset error threshold here is used to accommodate positioning and detection errors, for example, 2 meters.

[0121] Optionally, if the distance between the local detection information and the mapped positioning information of a certain target detected by the first UAV is less than the threshold, it indicates that the location of the target coincides with the location of a friendly UAV. Therefore, the target is determined to be a friendly UAV, and the local detection information of the friendly UAV is deleted from the local multi-target detection information detected by the first UAV. After traversing all detection targets, the remaining unfiltered local detection information is the set of local detection information for the third UAV, which is the first local detection information.

[0122] Similarly, each second UAV can also obtain the second local detection information through the above filtering method. The specific filtering method of the first local detection information can be referred to, and will not be repeated here.

[0123] For example, the real-time location information of drone A2 Mapping and positioning information in the local coordinate system of UAV A1 The specific mathematical expression is as follows:

[0124] ;

[0125] in, This is the transformation matrix corresponding to UAV A1; It is the inverse of the transformation matrix corresponding to UAV A1.

[0126] Similarly, the real-time location information of the drone A1 Mapping and positioning information in the local coordinate system of UAV A2 The specific mathematical expression is as follows:

[0127] ;

[0128] in, This is the transformation matrix corresponding to UAV A2; It is the inverse of the transformation matrix corresponding to UAV A2.

[0129] UAVs A1 and A2 can use the received and converted mapped positioning information from friendly UAVs to match it with the local multi-target detection information acquired by the current payload (i.e., the onboard detection components). This allows them to identify and filter out local detection information of friendly UAVs among the detected targets, ensuring that the remaining local detection information is all from enemy UAVs. Specifically, for UAV A2, it uses the real-time positioning information of UAV A1... The converted mapping and positioning information is The local multi-target detection information obtained by its payload detection is , The mapping and positioning information is calculated. and The set of spatial distances between them is , The target calculated by the A2 drone Spatial distance; To detect the target The coordinate difference components between the local detection information and the mapped positioning information. Then, using a typical distance error (e.g., 2 meters) as an error threshold, the matching local detection information is found, such as... Therefore, it is determined The corresponding detection target is UAV A1, which is also a friendly UAV, thus... After filtering, local detection information of enemy drones corresponding to UAV A2 is obtained.

[0130] The method provided in this embodiment achieves low-cost and highly reliable identification of friend or foe by using existing positioning and detection data without relying on dedicated hardware such as identification interrogation machines, through inverse coordinate mapping and spatial distance comparison. It effectively prevents friendly aircraft from being accidentally damaged, and the computational load is small, making it suitable for real-time processing on the airborne end.

[0131] In some embodiments, step 140 specifically includes:

[0132] Based on the target positioning information, the longitude, latitude, and elevation values ​​of each of the third UAVs are obtained;

[0133] The third UAVs are sorted according to the longitude, latitude, and elevation values.

[0134] Based on the sorting results, each of the third UAVs is assigned a unique digital code as its identity identifier.

[0135] Optionally, once each drone in the swarm has a unified list of third-party drone target location information after fusion and deduplication, it is necessary to assign a unified ID to these targets. Specific implementation steps include:

[0136] Since target positioning information typically exists in three-dimensional coordinates within a global coordinate system, specifically including longitude, latitude, and elevation values, the first UAV can parse and obtain the longitude, latitude, and elevation values ​​of each third UAV from the target positioning information of each third UAV.

[0137] Subsequently, to ensure that all friendly drones in the target drone swarm have the same identification number for the same enemy drone, a unified sorting rule needs to be adopted across the entire swarm. This rule applies the longitude, latitude, and altitude values ​​of each third drone to sort them. This sorting rule is used to define the comparison priority of each data dimension among the longitude, latitude, and altitude values. The specific sorting rule can be set according to actual needs or dynamically associated based on the combat mission of the target drone swarm; this embodiment does not impose specific limitations on this.

[0138] For example, in some embodiments, sorting the third UAVs according to the longitude value, the latitude value, and the elevation value includes:

[0139] Based on the combat mission of the target drone swarm, determine the comparison priority of each data dimension among the data dimensions corresponding to the longitude value, the data dimensions corresponding to the latitude value, and the data dimensions corresponding to the elevation value;

[0140] According to the comparison priority, the values ​​corresponding to each of the data dimensions are used as sorting keys to sort the third UAVs.

[0141] Optionally, the comparison priority of each data dimension among the data dimensions corresponding to longitude, latitude, and elevation values ​​can be dynamically determined by the association mapping relationship between the combat mission of the target drone swarm and the setting rules for the comparison priority of different data dimensions.

[0142] The comparison priority here determines which data dimension is prioritized for classification in multidimensional coordinate data. Assuming a drone swarm is engaged in wide-area search or horizontal advance missions, where the distinction of horizontal orientation is crucial, the comparison priority of each data item can be set as follows: data items corresponding to longitude values ​​have the highest priority, followed by data items corresponding to latitude values, and data items corresponding to elevation values ​​have the lowest priority.

[0143] Subsequently, based on the comparison priority, the values ​​corresponding to each data dimension are used as sorting keys to sort each third UAV, thus obtaining the arrangement order of each third UAV.

[0144] For example, when the data item corresponding to the longitude value has the highest priority, the data item corresponding to the latitude value has the second highest priority, and the data item corresponding to the elevation value has the lowest priority, the first UAV first compares the longitude values ​​of each third UAV and places the third UAV with the smaller longitude value at the front of the sequence; secondly, if at least two third UAVs have the same longitude value (or are considered the same within a preset small error range), the first UAV further compares the latitude values ​​of these third UAVs and places the third UAV with the smaller latitude value at the front of the sequence; finally, if at least two third UAVs have the same longitude and latitude values, the first UAV compares the elevation values ​​of these third UAVs and places the third UAV with the smaller elevation value at the front of the sequence.

[0145] Since all our drones are sorted based on the same fused location data and the same priority rules, the sorting results are strictly consistent.

[0146] After sorting, the first drone can assign identity tags to each of the third drones in sequence.

[0147] Similarly, each second drone can also use this coding method to assign an identity identifier to each third drone, which will not be elaborated here.

[0148] The method provided in this embodiment, through a sorting and numbering method based on unified spatial geometric features, eliminates the need for cumbersome ID assignment information exchange in the communication network for UAV swarms, and also eliminates the need to establish a central node for ID distribution. This globally unified ID alignment method greatly reduces communication overhead, eliminates the risk of ID conflicts caused by communication packet loss, and because it does not rely on explicit ID transmission, even if the enemy conducts communication interference or forges ID signals, it cannot disrupt the ID consistency based on physical location within the swarm. This achieves efficient unification and alignment of enemy target identities within the swarm, greatly improving the intelligence level and robustness of swarm collaborative countermeasures. Consequently, it enables efficient collaborative and precise target allocation and interception mission planning, significantly enhancing the overall effectiveness of anti-swarm operations.

[0149] The following describes the multi-target association recognition system for drone swarms provided by the present invention. The multi-target association recognition system for drone swarms described below can be referred to in correspondence with the multi-target association recognition method for drone swarms described above.

[0150] Figure 3 This is a schematic diagram of the structure of the multi-target association identification system for drone swarms provided by the present invention; as shown below. Figure 3 As shown, the system includes:

[0151] The receiving module 310 is used to receive the real-time location information of each of the second drones broadcast by each of the second drones; the second drones are drones in the target drone swarm that have a cooperative relationship with the first drone;

[0152] The filtering module 320 is used to filter the local multi-target detection information collected by the airborne detection component of the first UAV based on the real-time positioning information to obtain the first local detection information; the first local detection information includes the local detection information of each third UAV that has an anti-cooperative relationship with the first UAV.

[0153] The positioning module 330 is used to obtain the target positioning information of each of the third drones in the global coordinate system based on the first local detection information and the second local detection information broadcast by each of the second drones; the second local detection information includes the local detection information of each of the third drones that have an anti-cooperative relationship with each of the second drones; the global coordinate system is the unified coordinate system used by the target drone swarm for collaborative detection;

[0154] The identification module 340 is used to obtain the identity identifier of each of the third UAVs based on the target positioning information.

[0155] The system provided in this embodiment receives real-time positioning information from a second UAV with a cooperative relationship from a first UAV. It filters the local multi-target detection information collected by the onboard detection components of the first UAV to accurately eliminate interference from friendly targets. Then, it fuses the filtered first local detection information with the second local detection information broadcast by each second UAV in a unified global coordinate system to obtain the target positioning information of each third UAV. Finally, it directly obtains the identity of each third UAV based on the unified global target positioning information, thereby completely eliminating the ambiguity of cross-aircraft target identification. It achieves efficient unification and alignment of enemy target identities within the swarm, effectively solving the problem that existing detection pods lack identity recognition functions, which can easily lead to friendly aircraft being accidentally damaged. It also eliminates the fragmentation of battlefield situational awareness caused by independent detection by a single UAV. Moreover, it does not require exchanging IDs that are easily interfered with or forged; it can automatically align based solely on the spatial distribution characteristics of the target. This greatly improves the intelligence level and robustness of swarm cooperative countermeasures, and enables efficient collaborative and precise target allocation and interception mission planning, significantly improving the overall effectiveness of anti-swarm operations.

[0156] The system provided by this invention is used to execute the above-described method embodiments. For specific processes and details, please refer to the above embodiments, which will not be repeated here.

[0157] Figure 4 An example is a schematic diagram of the physical structure of an electronic device, such as... Figure 4As shown, the electronic device may include: a processor 410, a communications interface 420, a memory 430, and a communications bus 440, wherein the processor 410, the communications interface 420, and the memory 430 communicate with each other through the communications bus 440. The processor 410 can call logical instructions in the memory 430 to execute a multi-target association identification method for a drone swarm. This method includes: receiving real-time positioning information broadcast by each second drone; the second drones being drones in the target drone swarm that have a cooperative relationship with the first drone; filtering the local multi-target detection information collected by the onboard detection components of the first drone based on the real-time positioning information to obtain first local detection information; the first local detection information including local detection information of each third drone that has a negative cooperative relationship with the first drone; obtaining target positioning information of each third drone in a global coordinate system based on the first local detection information and the second local detection information broadcast by each second drone; the second local detection information including local detection information of each third drone that has a negative cooperative relationship with each of the second drones; the global coordinate system being a unified coordinate system used by the target drone swarm for collaborative detection; and obtaining the identity identifier of each third drone based on the target positioning information.

[0158] Furthermore, the logical instructions in the aforementioned memory 430 can be implemented as software functional units and, when sold or used as independent products, can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0159] On the other hand, the present invention also provides a computer program product, which includes a computer program that can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the multi-target association identification method for UAV swarms provided by the above methods. The method includes: receiving real-time positioning information of each second UAV broadcast by each second UAV; the second UAV is a UAV in the target UAV swarm that has a cooperative relationship with the first UAV; filtering the local multi-target detection information collected by the airborne detection component of the first UAV according to the real-time positioning information to obtain first local detection information; the first local detection information includes local detection information of each third UAV that has a negative cooperative relationship with the first UAV; obtaining target positioning information of each third UAV in a global coordinate system according to the first local detection information and the second local detection information broadcast by each second UAV; the second local detection information includes local detection information of each third UAV that has a negative cooperative relationship with each of the second UAVs; the global coordinate system is a unified coordinate system used by the target UAV swarm for collaborative detection; and obtaining the identity identifier of each third UAV according to the target positioning information.

[0160] In another aspect, the present invention also provides a non-transitory computer-readable storage medium storing a computer program thereon. When executed by a processor, the computer program implements a multi-target association identification method for UAV swarms provided by the methods described above. This method includes: receiving real-time positioning information of each second UAV broadcast by each second UAV; the second UAV being a UAV in the target UAV swarm that has a cooperative relationship with the first UAV; filtering local multi-target detection information collected by the airborne detection component of the first UAV based on the real-time positioning information to obtain first local detection information; the first local detection information includes local detection information of each third UAV that has a negative cooperative relationship with the first UAV; obtaining target positioning information of each third UAV in a global coordinate system based on the first local detection information and the second local detection information broadcast by each second UAV; the second local detection information includes local detection information of each third UAV that has a negative cooperative relationship with each of the second UAVs; the global coordinate system is a unified coordinate system used by the target UAV swarm for collaborative detection; and obtaining the identity identifier of each third UAV based on the target positioning information.

[0161] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.

[0162] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.

[0163] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for multi-target association and identification in a drone swarm, characterized in that, The method, applied to a first drone in a target drone swarm, includes: Receive real-time location information of each of the second drones broadcast by each of the second drones; the second drones are drones in the target drone swarm that have a cooperative relationship with the first drone; Based on the real-time positioning information, the local multi-target detection information collected by the airborne detection component of the first UAV is filtered to obtain the first local detection information; the first local detection information includes the local detection information of each third UAV that has an anti-cooperative relationship with the first UAV. Based on the first local detection information and the second local detection information broadcast by each of the second UAVs, the target positioning information of each of the third UAVs in the global coordinate system is obtained; the second local detection information includes the local detection information of each of the third UAVs that have an anti-cooperative relationship with each of the second UAVs; the global coordinate system is the unified coordinate system used by the target UAV swarm for collaborative detection; Based on the target positioning information, the identity identifiers of each of the third UAVs are obtained.

2. The multi-target association identification method for UAV swarms according to claim 1, characterized in that, The step of obtaining the target positioning information of each of the third UAVs in the global coordinate system based on the first local detection information and the second local detection information broadcast by each of the second UAVs includes: Obtain the transformation matrix of the local coordinate system of the airborne detection component relative to the global coordinate system; Based on the transformation matrix, the first local detection information is transformed to the global coordinate system to obtain the first global detection information; Receive the second global detection information corresponding to the second local detection information broadcast by each of the second UAVs; The first global detection information and the second global detection information are fused to obtain the target positioning information of each of the third UAVs.

3. The multi-target association identification method for UAV swarms according to claim 2, characterized in that, The process of fusing the first global detection information and the second global detection information to obtain the target positioning information of each of the third UAVs includes: Calculate the mutual distance between each first positioning information in the first global detection information and each second positioning information in the second global detection information; Each set of first and second positioning information with a mutual distance of less than a preset overlap threshold is determined as an associated positioning information set for the same third UAV. The target positioning information of each of the third UAVs is obtained by fusing the first positioning information and the second positioning information in the associated positioning information set.

4. The multi-target association identification method for UAV swarms according to any one of claims 1-3, characterized in that, The step of filtering the local multi-target detection information collected by the airborne detection component of the first UAV based on the real-time positioning information to obtain the first local detection information includes: Obtain the transformation matrix of the local coordinate system of the airborne detection component relative to the global coordinate system; Using the transformation matrix, the real-time positioning information is reversed and mapped to obtain the mapped positioning information of each of the second UAVs in the local coordinate system where the airborne detection component is located; Calculate the spatial distance between the local detection information of each target in the local multi-target detection information and the mapping positioning information; Based on the spatial distance, the local multi-target detection information is filtered to obtain the first local detection information.

5. The multi-target association identification method for UAV swarms according to claim 4, characterized in that, The step of filtering the local multi-target detection information based on the spatial distance to obtain the first local detection information includes: The local detection information corresponding to the detection targets whose spatial distance is less than a preset error threshold is filtered out from the local multi-target detection information to obtain the first local detection information.

6. The multi-target association identification method for UAV swarms according to any one of claims 1-3, characterized in that, The step of obtaining the identity identifiers of each of the third UAVs based on the target positioning information includes: Based on the target positioning information, the longitude, latitude, and elevation values ​​of each of the third UAVs are obtained; The third UAVs are sorted according to the longitude, latitude, and elevation values. Based on the sorting results, each of the third UAVs is assigned a unique digital code as its identity identifier.

7. The multi-target association identification method for UAV swarms according to claim 6, characterized in that, The process of sorting the third UAVs according to the longitude, latitude, and elevation values ​​includes: Based on the combat mission of the target drone swarm, determine the comparison priority of each data dimension among the data dimensions corresponding to the longitude value, the data dimensions corresponding to the latitude value, and the data dimensions corresponding to the elevation value; According to the comparison priority, the values ​​corresponding to each of the data dimensions are used as sorting keys to sort the third UAVs.

8. A multi-target association identification system for unmanned aerial vehicle (UAV) swarms, characterized in that, A first drone used in a target drone swarm, the system comprising: The receiving module is used to receive the real-time location information of each of the second drones broadcast by each of the second drones; the second drones are drones in the target drone swarm that have a cooperative relationship with the first drone; The filtering module is used to filter the local multi-target detection information collected by the airborne detection component of the first UAV based on the real-time positioning information to obtain the first local detection information; the first local detection information includes the local detection information of each third UAV that has an anti-cooperative relationship with the first UAV. The positioning module is used to obtain the target positioning information of each of the third drones in a global coordinate system based on the first local detection information and the second local detection information broadcast by each of the second drones; the second local detection information includes the local detection information of each of the third drones that have an anti-cooperative relationship with each of the second drones; the global coordinate system is a unified coordinate system used by the target drone swarm for collaborative detection; The identification module is used to obtain the identity identifier of each of the third UAVs based on the target positioning information.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that, When the processor executes the computer program, it implements the multi-target association identification method for drone swarms as described in any one of claims 1 to 7.

10. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the multi-target association identification method for drone swarms as described in any one of claims 1 to 7.

Images