Dynamic self-adaptive networking method, system and device for heterogeneous unmanned aerial vehicle cluster

Abstract

The application relates to a heterogeneous unmanned aerial vehicle cluster dynamic self-adaptive networking method, system and device, and the method comprises the following steps: constructing a communication network with scale-free characteristics of a heterogeneous unmanned aerial vehicle cluster under a static communication restricted condition; respectively updating a neighbor node set of each node and respectively calculating a node distance between each node and a node in the connected node set according to position coordinates of each node in the current communication network; judging a node in the connected node set with a node distance exceeding a communication distance as a failed node and eliminating the node from the connected node set; and based on a starting condition of an adaptive action of a MOLLY-REED criterion, performing dynamic self-adaptive networking on the nodes in the communication network according to a node connection probability function and a distance influence function. The dynamic self-adaptation of the unmanned aerial vehicle cluster network topology structure is efficiently realized, and the control performance of the unmanned aerial vehicle cluster is significantly improved.

Description

TECHNICAL FIELD

[0001] The present application belongs to the technical field of unmanned aerial vehicle cluster control, and relates to a heterogeneous unmanned aerial vehicle cluster dynamic self-adaptive networking method, system and device. BACKGROUND

[0002] Under the background of informatization and networked tasks, it has formed a wide consensus to abstract the task system as a complex network. In the field of unmanned task systems, previous research has focused on the distributed (centralized) task allocation of multiple unmanned platforms based on implicit (explicit) communication, and the system size is relatively small, often ignoring the geographical distance between task nodes and assuming that instant information transmission can be achieved between any nodes. However, for large-scale unmanned aerial vehicle clusters in real task space, this assumption has two problems: first, unmanned aerial vehicle clusters often use low-cost, consumable task units, and their task performance, including communication capabilities, is very limited due to communication distance limitations; second, when the number of unmanned aerial vehicles in the cluster reaches a certain scale, the coordination process between clusters is very complex, and the cost of this full-connection communication method based on Metcalfe's Law is huge and exceeds the node communication bandwidth limit.

[0003] Therefore, unmanned aerial vehicle clusters are based on a flat ad-hoc structure and use a multi-hop method for information transmission, simplifying the inter-aircraft communication topology to a subset of the cluster topology connection structure. Tran et al. modeled this system as a resilient unmanned aerial vehicle cluster C2 network, and scale-free networks and random networks are two typical unmanned aerial vehicle cluster network topology structures. In terms of information exchange efficiency, research shows that scale-free networks can form a hub structure with shorter average path length, which is of great significance to accelerate information transmission within the cluster.

[0004] In addition, in real task scenarios, unmanned aerial vehicle clusters exhibit strong dynamic characteristics, especially in the process of task execution involving frequent cross-domain collaborative scheduling and sudden node failure and edge failure, which causes the topology structure of the cluster network to change constantly, forming a dynamic unmanned aerial vehicle cluster ad-hoc network (FANETs, Flying Ad-hoc Networks), rather than maintaining a stable static topology structure. However, existing unmanned aerial vehicle cluster network control technologies cannot adapt to changes in the topology structure of the cluster network, and the control performance is poor. SUMMARY

[0005] To solve the problems in the above-mentioned traditional technologies, the present application proposes a heterogeneous unmanned aerial vehicle cluster dynamic self-adaptive networking method, a heterogeneous unmanned aerial vehicle cluster dynamic self-adaptive networking system and a computer device, which can efficiently realize the dynamic self-adaptation of the unmanned aerial vehicle cluster network topology structure and significantly improve the control performance of the unmanned aerial vehicle cluster.

[0006] To achieve the above object, the embodiment of the present application adopts the following technical solutions:

[0007] In one aspect, a dynamic self-adaptive networking method for a heterogeneous unmanned aerial vehicle cluster is provided, comprising the steps of:

[0008] constructing a communication network with scale-free characteristics for a heterogeneous unmanned aerial vehicle cluster under static communication restricted conditions;

[0009] updating the neighbor node set of each node and calculating the node distance between each node and the nodes in the connected node set according to the position coordinates of each node in the current communication network;

[0010] determining the nodes in the connected node set whose node distance exceeds the communication distance as failed nodes and removing them from the connected node set;

[0011] based on the start condition of the adaptive action according to the MOLLY-REED criterion, dynamically self-adapting the networking of the nodes in the communication network according to the node connection probability function and the distance influence function.

[0012] In one embodiment, based on the start condition of the adaptive action according to the MOLLY-REED criterion, the step of dynamically self-adapting the networking of the nodes in the communication network according to the node connection probability function and the distance influence function comprises:

[0013] determining whether there is a network giant in the communication network according to the MOLLY-REED criterion;

[0014] if there is a network giant, determining whether the start condition of the adaptive action is met for each node in the communication network;

[0015] if the start condition of the adaptive action is met, establishing new connections between each node and the nodes in the corresponding neighbor node set of the node according to the connection probability function and the distance influence function until the start condition of the adaptive action is not met or full connection with the corresponding neighbor node set is achieved.

[0016] In one embodiment, the start condition of the adaptive action is:

[0017]

[0018] wherein κ i is the estimated value of the degree κ of node i for the entire network, C i is the connected node set of node i, is the connected node of node i, δ is the margin coefficient, k i is the degree of freedom of node i, k max is the upper limit of the degree of a single node.

[0019] In one embodiment, the connection probability function is P i→j (i, G t ):

[0020]

[0021] where k j is the degree of node j, N t is the number of nodes in the current communication network, G t is the current formed communication network, ε is a bias factor, and F(d i→j ) is a distance influence function.

[0022] The distance influence function is F(d i→j ):

[0023]

[0024] where r c is the communication radius of a single node, d i→j is the geographical distance between nodes, and η is a distance adjustment coefficient.

[0025] In one embodiment, the task execution state of the unmanned aerial vehicle in the heterogeneous unmanned aerial vehicle cluster includes no target traction, target traction, and fixed target selection, and the motion state of the unmanned aerial vehicle includes snake maneuvering, flight along the track, waiting around, synchronous attack, and node failure.

[0026] In another aspect, a dynamic adaptive networking system for a heterogeneous unmanned aerial vehicle cluster is also provided, comprising:

[0027] A static construction module for constructing a communication network with scale-free characteristics of a heterogeneous unmanned aerial vehicle cluster under static communication restricted conditions;

[0028] A node update module for updating the neighbor node set of each node and calculating the node distance between each node and the nodes in the connected node set according to the position coordinates of each node in the current communication network;

[0029] A failure elimination module for determining the connected nodes in the connected node set whose node distance exceeds the communication distance as failed nodes and eliminating them from the connected node set;

[0030] An adaptive module for dynamically adaptive networking of nodes in the communication network based on the starting condition of adaptive action of the MOLLY-REED criterion according to the node connection probability function and the distance influence function.

[0031] In one embodiment, the adaptive module comprises:

[0032] The giant component judging submodule is configured to judge whether a network giant component exists in the communication network according to the MOLLY-REED criterion.

[0033] The start judging submodule is configured to judge whether a start condition of an adaptive action is met for each node in the communication network when the network giant component exists.

[0034] The ad hoc network submodule is configured to establish a new connection between each node and a node in a corresponding neighbor node set of the node according to a connection probability function and a distance influence function when the start condition of the adaptive action is met, until the start condition of the adaptive action is not met or full connection with the corresponding neighbor node set is achieved.

[0035] In one of the embodiments, the start condition of the adaptive action is:

[0036]

[0037] wherein κ i is an estimated value of a degree κ of the node i in the whole network, C i is a connected node set of the node i, is a connected node of the node i, δ is a margin coefficient, k i is a degree of freedom of the node i, k max is an upper limit of the degree of a single node.

[0038] In yet another aspect, a computer device is provided, which includes a memory and a processor, the memory stores a computer program, and the processor implements the steps of the above-mentioned dynamic adaptive networking method for a heterogeneous UAV cluster when executing the computer program.

[0039] In still another aspect, a computer readable storage medium is provided, which stores a computer program, and the computer program implements the steps of the above-mentioned dynamic adaptive networking method for a heterogeneous UAV cluster when executed by a processor.

[0040] One of the above technical solutions has the following advantages and beneficial effects:

[0041] The isomerous unmanned aerial vehicle cluster dynamic self-adaptive networking method, system and device abstract the unmanned aerial vehicle cluster as a complex network model at the network level as the basis of the information interaction process, adaptively design the network topology structure according to the dynamic characteristics of the unmanned aerial vehicle cluster in the working environment, consider the dynamic evolution of the cluster network in the real working environment and realize the dynamic self-adaptive adjustment of the edges between nodes. In the adaptive stage, each node can first judge whether the node meets the starting condition of the adaptive action based on the MOLLY-REED criterion from the perspective of maintaining network robustness, and then add one or more new edges to the network according to the node connection probability function and the distance influence function, thereby efficiently realizing the dynamic self-adaptation of the unmanned aerial vehicle cluster network topology structure and significantly improving the control performance of the unmanned aerial vehicle cluster. BRIEF DESCRIPTION OF DRAWINGS

[0042] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the drawings needed to be used in the embodiments or the prior art description will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0043] Figure 1 A flowchart of the dynamic self-adaptive networking method of the isomerous unmanned aerial vehicle cluster in an embodiment;

[0044] Figure 2 A flowchart of the execution of the dynamic self-adaptive networking in an embodiment;

[0045] Figure 3 A schematic diagram of the motion state transition of the unmanned aerial vehicle in an embodiment;

[0046] Figure 4 A module structure schematic diagram of the dynamic self-adaptive networking system of the isomerous unmanned aerial vehicle cluster in an embodiment. DETAILED DESCRIPTION

[0047] In order to make the purpose, technical solutions and advantages of the present application more clear, the present application will be further described in detail below in combination with the drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not intended to limit the present application.

[0048] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used in the specification of the present application is only for the purpose of describing specific embodiments and is not intended to limit the present application.

[0049] It is noted that reference herein to "embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment can be included in at least one embodiment of the application. The appearances of the phrase in various places in the specification are not necessarily all referring to the same embodiment, nor are they necessarily mutually exclusive of one another.

[0050] It will be appreciated by persons skilled in the art that embodiments described herein can be combined with other embodiments. The term "and / or" as used herein refers to and encompasses any and all possible combinations of one or more of the associated listed items, and vice versa.

[0051] In one embodiment, as shown in Figure 1 , a heterogeneous UAV cluster dynamic adaptive networking method is provided, comprising steps S12 to S18:

[0052] S12, a communication network of scale-free characteristics of a heterogeneous UAV cluster under static communication limited conditions is constructed.

[0053] It can be understood that first, a communication network of scale-free characteristics of a UAV cluster under static communication limited conditions is constructed by using a traditional method, and the network growth process thereof is similar to the traditional BA structure. The size of the initial communication network G0 is set to m0, and the nodes are fully connected.

[0054] Further, the new node i adds m (m≤m0) new connection edges to the existing network, and the connection probability of the new node i with any node j in the network can be further determined by using the following connection probability function P i→j (i,G t ):

[0055]

[0056] where k j is the degree of freedom of node j, N t is the number of nodes in the current communication network, G t is the current formed communication network, ε is a bias factor, and F(d i→j ) is a distance influence function.

[0057] Further, the distance influence function is F(d i→j ):

[0058]

[0059] where r c is the communication radius of a single node, and d i→jLet be the geographical distance between nodes, and η be the distance adjustment coefficient. The final result is a communication network G = {n} of a heterogeneous UAV swarm with scale-free characteristics under static communication constraints of size N. i}(i=1,2,...,N); Record node information n i ={x i ,y i ,k i}, where (x i ,y i ) and k i Let be the position coordinates and degree of node i, respectively.

[0060] Use the connected cluster of each node. Characterizes the connectivity of the network, where Let i be the connected nodes of node i; let i be the neighbor list of nodes within the communication range of each node. Characterizes the relative positional distribution of nodes, where For the distance to node i to be less than r c The node.

[0061] Considering the dynamic evolution of the communication network of a drone swarm in a real-world operating environment, subsequent steps will be used to achieve dynamic adaptive adjustment of the connections between nodes.

[0062] S14. Based on the location coordinates of each node in the current communication network, update the neighbor node set of each node and calculate the node distance between each node and the nodes in the connected node set.

[0063] S16, determine the nodes in the set of connected nodes whose distance exceeds the communication distance as failed nodes and remove them from the set of connected nodes.

[0064] This is understandable; first, based on the position coordinates (x, y) of each node i in the current communication network... i ,y i Update the neighbor node set NL i And calculate its connection to the set of connected nodes C. i Nodes in The distance, if that distance exceeds the communication distance r c Then the node The node is determined to be invalid and is connected to node i from the set of connected nodes C. i Remove from the middle, correspondingly, node i and node The connection is lost at this point. Subsequently, each node can dynamically adapt to the network based on local information within its communication range (such as location coordinates and node degree).

[0065] S18, the starting condition of adaptive action based on MOLLY-REED criterion, dynamically and adaptively groups the nodes in the communication network according to the node connection probability function and the distance influence function.

[0066] It can be understood that in the previous research, in order to maintain the stable connection of the network, the home node of the failed edge can also add a new edge to the network according to formula (1) and formula (2), so as to maintain the stable connection of the network and the relatively fixed total number of edges. But the adaptive effect of dynamic unmanned aerial vehicle cluster self-organizing network FANETs is strongly related to the node self-organizing movement mode, and the existing research mostly drives the self-organizing movement of network nodes in the background of homogeneous unmanned aerial vehicle cluster executing reconnaissance tasks. During the task execution process, the reconnaissance aircraft maintains a relatively uniform distribution in the task space, so that the cluster network topology changes relatively stably. For heterogeneous clusters, the task execution process is characterized by global dispersion and regional aggregation of heterogeneous resources, and the network topology structure fluctuates strongly, and the network is prone to percolation transition of giant component decomposition, which will greatly affect the network performance.

[0067] Therefore, in the adaptive stage, each node can first judge whether the network giant component exists according to the existing MOLLY-REED criterion from the perspective of maintaining network robustness, and then add one or more new edges to the network according to the above formula (1) and formula (2).

[0068] Specifically, the MOLLY-REED criterion indicates that if the network giant component exists, then there must be more than two communication links between a node in the giant component and any node in the network on average. According to the probability model, the equivalent mathematical expression is:

[0069]

[0070] wherein, <k>is the average node degree of the whole network. It can be seen that the decision of MOLLY-REED criterion needs to know the degree distribution of the whole network, which means that each node needs to broadcast its node degree in the network every time the network adapts. To simplify the decision process, each node can use the average consensus method known in the art to estimate the average node degree of the whole network according to the local information of the nodes connected within one hop range of itself <k>and <k 2 Estimation is made as shown in equation (4):

[0071]

[0072] where <k * > i is the average node degree of the network nodes for node i <k>or <k 2 >Estimated value; |C i | represents the size of the set of nodes connected to node i.

[0073] In some implementations, further, such as Figure 2 As shown, step S18 above may specifically include the following processing steps S182 to S186:

[0074] S182, Determine whether there are network giants in the communication network according to the MOLLY-REED criterion;

[0075] S184, if a network block exists, then determine whether each node in the communication network meets the activation conditions for the adaptive action.

[0076] S186. If the activation condition of the adaptive action is met, then according to the connection probability function and the distance influence function, establish new connections between each node and the nodes in the corresponding neighbor node set, until the activation condition of the adaptive action is no longer met or a full connection is achieved with the corresponding neighbor node set.

[0077] It is understandable that, since the research object of this application is heterogeneous swarm networks, although the existence of giant swarms can maintain a relatively large degree of connectivity at the network structure level, it cannot strictly guarantee the effective connection of heterogeneous resources. Given the task context of constructing heterogeneous UAV swarm networks, it is impossible to stably form a closed operational chain. Therefore, considering both estimation errors and swarm heterogeneity, this application sets a certain margin for the critical threshold of κ, the specific value of which depends on the distribution density of the swarm in the task space and the ratio of swarm heterogeneity. Simultaneously, to avoid information blockage caused by the unlimited growth of the node degree of a few "hub" nodes during the adaptation process, the upper limit of the node degree of a single node is set to k. max The final activation condition for the adaptive action of node i is:

[0078]

[0079] Among them, κ i Let be the estimated degree of node i to the entire network node k. Furthermore, when |C i When |=0, node i is directly determined to be κ. i =0; δ is the margin coefficient, k i Let be the degrees of freedom of node i. Node i can initiate adaptive actions as long as it satisfies the conditions for such actions, i.e., equation (5), and then interact with its neighbor set NL according to equations (1) and (2) above. i Nodes in Establish new connections until the adaptive action initiation condition is no longer met or the neighbor node set NL is reached. i Full connectivity has been achieved.

[0080] It should be noted that for the case of judging that there is no network giant piece, each node can perform network dynamic self-adaptation according to local information within the communication range of the node. For the case of judging that the starting condition of the self-adaptation action is not met, no processing can be performed.

[0081] The above heterogeneous unmanned aerial vehicle cluster dynamic self-adaptation networking method abstracts the unmanned aerial vehicle cluster as a complex network model at the network level as the basis for the information interaction process, performs adaptive design of the network topology structure for the dynamic characteristics of the unmanned aerial vehicle cluster in the working environment, considers the dynamic evolution of the cluster network in the real working environment and realizes dynamic self-adaptation adjustment of the edges between nodes. In the adaptive stage, each node can first judge whether the node meets the starting condition of the self-adaptation action based on the MOLLY-REED criterion from the perspective of maintaining network robustness, and then add one or more new edges to the network according to the node connection probability function and the distance influence function, thereby efficiently realizing dynamic self-adaptation of the unmanned aerial vehicle cluster network topology structure and significantly improving the control performance of the unmanned aerial vehicle cluster.

[0082] In one embodiment, the task execution state of the unmanned aerial vehicle in the heterogeneous unmanned aerial vehicle cluster includes no target traction, target traction and fixed target selection, and the motion state of the unmanned aerial vehicle includes snake maneuvering, flight along a track, waiting in a circle, synchronous attack and node failure.

[0083] It can be understood that it is mentioned above that the unmanned aerial vehicle cluster network in the working environment relies on the self-organizing behavior of each node to drive the dynamic evolution effect. This process involves nonlinear and emergent behavior generated by interaction between the task unit group and the environment when mapped from the cyber space to the physical space.

[0084] Therefore, from the perspective of task entities participating in the task process, the unmanned aerial vehicle cluster can be classified as a complex adaptive system (CAS). Traditional complex system modeling methods based on differential equations, such as the Lanchester equation, often stay at the macro level for information feedback between task units, lacking description of dynamic properties at the micro level of task entities. For example, the simulation method based on discrete events performs top-down coarse-grained decomposition of the task process, which is difficult to fully consider the heterogeneous characteristics and action details of the task units.

[0085] And the Agent-based modeling method (ABM) has a natural advantage in describing complex systems with heterogeneity, nonlinearity, emergence and large-scale self-organization and self-adaptation. In summary, the ABM (i.e. agent-based modeling) method can set the functional attributes of a single task unit, greatly simplify the description of the interaction process between task units by designing the "if-then" action set and distributed decision-making process, and effectively combine the micro actions of the Agent and the macro emergence of the swarm intelligence.

[0086] At present, the Agent-based modeling method is widely used in the field of multi-agent task planning, and the core modules of its model establishment mainly include: situation awareness module, information processing module, decision-making module and behavior driving module. The present application mainly models the behavior driving module directly related to the self-organizing operation of the UAV swarm.

[0087] Specifically, the behavior driving module can be divided into state driving mode and trigger condition, i.e. the precondition and subsequent action of the "if-then" rule. For ease of description, the ABM modeling process is introduced into the real task scene. For example, the task background can be set as follows: the human-machine platform is used as a high-value, multi-functional monolithic task unit to carry the unmanned bee swarm dispenser, which reaches the safe task area outside the opponent's defense zone under the support of the preliminary reconnaissance information and releases a large-scale low-value, modular functional Mosaic task platform to form a heterogeneous UAV swarm close to the opponent's position. The task target of the UAV swarm is to build an information interaction network within the swarm, realize distributed situation awareness and information sharing, form a loose temporary task alliance for multiple task targets, aggregate the task functions dispersed on multiple platforms into a dynamic adaptive execution network, and finally complete the task according to the preset cooperative attack task pattern. Under the action of the behavior driving module in the present embodiment, the various motion states and transition rules of the UAV are as shown in the following table. Figure 3

[0088] The task execution state es of the UAV in the task execution process is divided into three types, namely uncommitted, committed and sticky. The motion state ms is divided into five types, namely snake maneuver, flight along the track, wait around, synchronous attack and node failure.

[0089] ​Where no target attraction means that the UAV is currently not responding to any target's demand, and is in a random walk state in the mission space, in a snake-like maneuver. Target attraction means that the UAV is currently responding to a target's demand, and is in a flight path state. In the process of going to the task execution location, the UAV can find a target with higher benefit and switch to the flight path to the target's task execution location. In addition, the UAV can find that there is a UAV that has already gone to execute the task, and then it is considered to have failed in the "bidding" for the task, and switches back to the snake-like maneuver state.

[0090] Fixed target selection means that the UAV is "sticky" to the currently selected target task and does not switch tasks until it reaches a specific task execution location around the target, enters a waiting state, and waits for the formation of a temporary task alliance with the remaining heterogeneous UAVs for the target. When the alliance is formed, the heterogeneous UAVs in the alliance will launch a simultaneous attack on the target, and after the attack is completed, the alliance will be dissolved and each UAV will return to the snake-like maneuver state. In some cases, the UAV in the waiting state may be stuck for a long time without new UAVs joining the alliance, and thus be stuck. At this time, the UAV can actively break out of this state (such as setting a waiting countdown) and re-enter the snake-like maneuver state to respond to the demand of the remaining targets. In addition, under dynamic confrontation conditions, the UAV can be attacked by the opponent at any time during the entire task execution process and enter a node failure state (dead).

[0091] It should be understood that, although Figures 1 to 3 The steps in the flowchart are shown in sequence according to the arrows, but these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order limitation for the execution of these steps, and these steps can be executed in other orders. Moreover Figures 1 to 3 At least a part of the steps of the flowchart can include multiple sub-steps or multiple stages, which are not necessarily executed at the same time, but can be executed at different times, and the execution order of these sub-steps or stages is not necessarily sequential, but can be executed in rotation or alternation with other steps or sub-steps or stages of other steps.

[0092] Please refer to Figure 4 In one embodiment, a heterogeneous unmanned aerial vehicle cluster dynamic adaptive networking system 100 is also provided, comprising a static construction module 11, a node update module 13, a failure elimination module 15, and an adaptive module 17. The static construction module 11 is configured to construct a communication network with scale-free characteristics of a heterogeneous unmanned aerial vehicle cluster under static communication restricted conditions. The node update module 13 is configured to update a neighbor node set of each node and calculate a node distance between each node and a node in the neighbor node set according to a position coordinate of each node in the current communication network. The failure elimination module 15 is configured to determine a node in the neighbor node set whose node distance exceeds a communication distance as a failure node and eliminate the node from the neighbor node set. The adaptive module 17 is configured to perform dynamic adaptive networking of nodes in the communication network according to a node connection probability function and a distance influence function based on a starting condition of an adaptive action of the MOLLY-REED criterion.

[0093] The heterogeneous unmanned aerial vehicle cluster dynamic adaptive networking system 100 described above abstracts the unmanned aerial vehicle cluster as a complex network model at the network level as a basis for an information interaction process, performs adaptive design of a network topology structure for dynamic characteristics of the unmanned aerial vehicle cluster in a working environment, considers dynamic evolution of the cluster network in a real working environment, and realizes dynamic adaptive adjustment of edges between nodes. In the adaptive stage, each node can determine whether the node meets the starting condition of the adaptive action of the MOLLY-REED criterion from the perspective of maintaining network robustness, and then add one or more new edges to the network according to the node connection probability function and the distance influence function, thereby efficiently realizing dynamic adaptation of the unmanned aerial vehicle cluster network topology structure and significantly improving the control performance of the unmanned aerial vehicle cluster.

[0094] In one embodiment, the adaptive module 17 described above can specifically include a giant component judgment sub-module, a starting judgment sub-module, and an ad hoc network sub-module. The giant component judgment sub-module is configured to determine whether there is a network giant component in the communication network according to the MOLLY-REED criterion. The starting judgment sub-module is configured to determine whether each node in the communication network meets the starting condition of the adaptive action when there is a network giant component. The ad hoc network sub-module is configured to establish a new connection between each node and a node in a corresponding neighbor node set of the node according to the connection probability function and the distance influence function when the starting condition of the adaptive action is met, until the starting condition of the adaptive action is not met or full connection with the corresponding neighbor node set is achieved.

[0095] In one embodiment, the starting condition of the adaptive action is:

[0096]

[0097] wherein κ i is an estimated value of the node i for the degree κ of the entire network, C i is the set of connected nodes of node i, is the connected node of node i, and δ is the margin coefficient, k i is the degree of freedom of node i, k max is the set upper limit of the degree of a single node.

[0098] In one embodiment, the connection probability function is P i→j (i, G t ):

[0099]

[0100] wherein k j is the degree of freedom of node j, N t is the number of nodes in the current communication network, G t is the current formed communication network, ε is the bias factor, and F(d i→j ) is the distance influence function.

[0101] The distance influence function is F(d i→j ):

[0102]

[0103] wherein r c is the communication radius of a single node, d i→j is the geographical distance between nodes, and η is the distance adjustment coefficient.

[0104] In one embodiment, the task execution state of the unmanned aerial vehicle in the heterogeneous unmanned aerial vehicle cluster includes no target traction, target traction, and fixed target selection, and the motion state of the unmanned aerial vehicle includes snake maneuvering, flight along the track, waiting in a circle, synchronous attack, and node failure.

[0105] For specific limitations of the heterogeneous unmanned aerial vehicle cluster dynamic adaptive networking system 100, please refer to the corresponding limitations of the heterogeneous unmanned aerial vehicle cluster dynamic adaptive networking method in the above, which will not be repeated here. Each module in the above heterogeneous unmanned aerial vehicle cluster dynamic adaptive networking system 100 can be realized by software, hardware, and combinations thereof, in whole or in part. The above modules can be embedded in or independent of the device with specific data processing functions in hardware form, or can be stored in the memory of the aforementioned device in software form, so that the processor can call and execute the operations corresponding to each module. The aforementioned device can be, but is not limited to, various types of portable, vehicle-mounted or ship-mounted unmanned aerial vehicle control devices in the art.

[0106] In one embodiment, a computer device is also provided, comprising a memory and a processor, the memory storing a computer program, and the processor implementing the following processing steps when executing the computer program: constructing a communication network of scale-free characteristics of a heterogeneous unmanned aerial vehicle cluster under static communication limited conditions; updating a neighbor node set of each node and calculating a node distance between each node and a node in the connected node set of each node according to a position coordinate of each node in the current communication network; determining a node in the connected node set whose node distance exceeds a communication distance as a failed node and removing the node from the connected node set; and performing dynamic adaptive networking of nodes in the communication network according to a node connection probability function and a distance influence function based on a starting condition of adaptive action of the MOLLY-REED criterion.

[0107] It can be understood that, in addition to the memory and the processor described above, the computer device described above further comprises other software and hardware components not listed in the specification, which can be determined according to the specific data processing and control device model in different application scenarios, and the specification will not be listed in detail.

[0108] In one embodiment, the processor, when executing the computer program, can also implement the steps or sub-steps added in each embodiment of the heterogeneous unmanned aerial vehicle cluster dynamic adaptive networking method.

[0109] In one embodiment, a computer readable storage medium is also provided, which stores a computer program, and the computer program, when executed by a processor, implements the following processing steps: constructing a communication network of scale-free characteristics of a heterogeneous unmanned aerial vehicle cluster under static communication limited conditions; updating a neighbor node set of each node and calculating a node distance between each node and a node in the connected node set of each node according to a position coordinate of each node in the current communication network; determining a node in the connected node set whose node distance exceeds a communication distance as a failed node and removing the node from the connected node set; and performing dynamic adaptive networking of nodes in the communication network according to a node connection probability function and a distance influence function based on a starting condition of adaptive action of the MOLLY-REED criterion.

[0110] In one embodiment, the computer program, when executed by the processor, can also implement the steps or sub-steps added in each embodiment of the heterogeneous unmanned aerial vehicle cluster dynamic adaptive networking method.

[0111] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a non-volatile computer readable storage medium, and when the computer program is executed, the processes of the above-mentioned embodiments of the methods can be included. Any reference to memory, storage, database or other medium used in the embodiments provided in the present application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration but not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus dynamic random access memory (Rambus DRAM, RDRAM for short) and interface dynamic random access memory (DRDRAM).

[0112] Any combination of the technical features of the above embodiments can be made. In order to make the description simple, all possible combinations of the technical features in the above embodiments are not described, however, as long as the combination of the technical features does not exist, it should be considered as the scope of the present application.

[0113] The above embodiments only express several implementation manners of the present application, and the description is more specific and detailed, but it should not be understood as a limitation on the scope of the patent. It should be pointed out that for ordinary skilled in the art, without departing from the concept of the present application, some modifications and improvements can be made, which all belong to the protection scope of the present application. Therefore, the protection scope of the patent of the present application should be subject to the appended claims.< / k> < / k> < / k>

Claims

1. A method for dynamic adaptive networking of heterogeneous unmanned aerial vehicle (UAV) swarms, characterized in that, Including the following steps: Constructing a scale-free communication network for heterogeneous UAV swarms under static communication constraints; Based on the location coordinates of each node in the current communication network, update the neighbor node set of each node and calculate the node distance between each node and the nodes in the connected node set. Nodes in the set of connected nodes whose distance exceeds the communication distance are identified as invalid nodes and removed from the set of connected nodes; The activation conditions for adaptive actions based on the MOLLY-REED criterion are used to dynamically and adaptively network the nodes in the communication network according to the node connection probability function and the distance influence function. These include: Determine whether a network giant exists in the communication network based on the MOLLY-REED criterion; If a network giant exists, then each node in the communication network is checked to determine whether it meets the activation conditions of the adaptive action; If the activation condition of the adaptive action is met, then according to the connection probability function and the distance influence function, new connections are established between each node and the nodes in the corresponding set of neighboring nodes, until the activation condition of the adaptive action is no longer met or a full connection is achieved with the corresponding set of neighboring nodes. The activation condition for the adaptive action is: in, For nodes i Degree of all network nodes The estimated value, For nodes i The set of connected nodes, For nodes i Connected nodes, This is the margin coefficient. For nodes i degrees of freedom This sets the maximum degree of a single node.

2. The heterogeneous UAV swarm dynamic adaptive networking method according to claim 1, characterized in that, The connection probability function is: : in, For nodes j degrees of freedom This represents the number of nodes in the current communication network. For the current communication network, It is a positive factor. The distance influence function; The distance influence function is: : in, This refers to the communication radius of a single node. The geographical distance between nodes. This is the distance adjustment factor.

3. The heterogeneous UAV swarm dynamic adaptive networking method according to claim 1, characterized in that, The mission execution states of the drones in the heterogeneous drone swarm include targetless traction, target traction, and fixed target selection. The movement states of the drones include serpentine maneuvers, trajectory flight, circling and waiting, synchronous attack, and node failure.

4. A heterogeneous unmanned aerial vehicle (UAV) swarm dynamic adaptive networking system, characterized in that, include: The static building module is used to build a scale-free communication network for heterogeneous UAV swarms under static communication constraints. The node update module is used to update the neighbor node set of each node according to the current location coordinates of each node in the communication network, and to calculate the node distance between each node and the nodes in the connected node set. The failure removal module is used to determine the nodes in the set of connected nodes whose distance exceeds the communication distance as failure nodes and remove them from the set of connected nodes; An adaptive module is used to initiate adaptive actions based on the MOLLY-REED criterion, and to dynamically and adaptively network the nodes in the communication network according to the node connection probability function and the distance influence function. The adaptive module includes: The giant network detection submodule is used to determine whether there are network giants in the communication network according to the MOLLY-REED criterion. The startup judgment submodule is used to determine whether each node in the communication network meets the startup conditions for adaptive action when a network block exists. The self-organizing network submodule is used to establish new connections between each node and the nodes in the corresponding set of neighboring nodes according to the connection probability function and the distance influence function when the activation condition of the adaptive action is met, until the activation condition of the adaptive action is no longer met or full connection is achieved with the corresponding set of neighboring nodes. The activation condition for the adaptive action is: in, For nodes i Degree of all network nodes The estimated value, For nodes i The set of connected nodes, For nodes i Connected nodes, This is the margin coefficient. For nodes i degrees of freedom This sets the maximum degree of a single node.

5. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the heterogeneous unmanned aerial vehicle (UAV) swarm dynamic adaptive networking method according to any one of claims 1 to 3.

6. A 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 steps of the heterogeneous unmanned aerial vehicle (UAV) swarm dynamic adaptive networking method according to any one of claims 1 to 3.

Images