Heterogeneous UAV Cluster Cooperative Search Optimization Method and System Based on Multi-Situation Map Fusion

Abstract

The present invention relates to the technical field of trajectory planning, and particularly to a heterogeneous UAV cluster collaborative search optimization method and system based on multi-situation map fusion. By constructing a target probability map for reflecting the probability of a UAV detecting a target in an environmental grid, a digital pheromone map for reflecting the search time interval of the UAV cluster for the environmental grid in the mission area, and an environmental search map for reflecting the search coverage of the UAV cluster for the environmental grid; according to a preset weight value and by combining the benefits of the target probability map, the digital pheromone map, and the environmental search, an optimization objective function for the collaborative search of the UAV cluster is generated, so as to use the optimization objective function for the collaborative search of the UAV cluster to obtain the optimal decision of the UAV cluster under the constraint conditions. The present invention improves the objective function in the collaborative search process of the heterogeneous UAV cluster, facilitating better obtaining of the optimal decision that maximizes the overall performance index under the predetermined constraint conditions, so as to improve the collaborative efficiency and task execution efficiency of the UAV cluster.

Description

Technical Field

[0001] The present invention relates to the technical field of trajectory planning, and particularly relates to a heterogeneous UAV cluster collaborative search optimization method and system based on multi-situation map fusion. Background Art

[0002] Unmanned aerial vehicles (UAVs) have been increasingly used to expand the capabilities of manned aircraft in modern air combat. Efficient collaboration among multiple UAVs can effectively improve the task execution efficiency of the UAV cluster. A heterogeneous UAV cluster can adapt to changing task requirements during the execution of collaborative tasks. Compared with a homogeneous UAV cluster, it can significantly improve system performance and reduce integration and maintenance costs. Therefore, heterogeneous UAV cluster collaboration technology has been widely studied.

[0003] The multi-UAV cluster collaborative mission planning problem (MCMPP) is a quite complex and challenging NP-H optimization problem. The mission planning optimization algorithm optimizes the flight paths of the UAV cluster under the constraints of the mission environment to improve the collaborative efficiency and task execution efficiency of the UAV cluster. The collaborative search problem of heterogeneous UAV clusters for dynamic targets is an important application research in the field of MCMPP. To solve this problem, environmental situation map models such as the target probability map (TPM), digital pheromone map (DPM), and environmental detection map are widely used to help the UAV cluster collaboratively perceive the surrounding environment. Therefore, the model establishment and numerical update of each environmental situation map are important links in the UAV cluster collaboration method. However, there are problems in the existing algorithms such as unreasonable numerical update methods and inapplicability to heterogeneous UAV clusters, making it difficult to meet the actual application requirements. Summary of the Invention

[0004] Therefore, the present invention provides a heterogeneous UAV cluster collaborative search optimization method and system based on multi-situation map fusion to solve the collaborative search problem of heterogeneous UAV clusters for dynamic targets.

[0005] According to the design scheme provided by the present invention, a heterogeneous UAV cluster collaborative search optimization method based on multi-situation map fusion is provided, including:

[0006] Constructing a target probability map for reflecting the probability of a UAV detecting a target in an environmental grid, a digital pheromone map for reflecting the search time interval of the UAV cluster for the environmental grid in the mission area, and an environmental search map for reflecting the search coverage of the UAV cluster for the environmental grid;

[0007] Generating a UAV cluster collaborative search optimization objective function based on a preset weight value and jointly combining the benefits of the target probability map, digital pheromone map, and environmental search, so as to use the UAV cluster collaborative search optimization objective function to obtain the optimal decision of the UAV cluster under the constraint conditions.

[0008] As the heterogeneous UAV cluster collaborative search optimization method based on multi-situation map fusion of the present invention, further, a target probability map is constructed to reflect the probability of a UAV detecting a target in an environmental grid, including:

[0009] First, divide the types of targets to be searched into unknown static targets, unknown dynamic targets, and dynamic targets with partial prior information.

[0010] Next, use the uniform distribution function to construct the first target probability distribution of unknown static targets and unknown dynamic targets, and use the two-dimensional normal distribution function to construct the second target probability distribution of dynamic targets with partial prior information.

[0011] Then, obtain the prior target probability distribution by summing the first target probability distribution and the second target probability distribution, and generate the target probability map based on the prior target probability distribution, the UAV target detection performance parameters, and the distance from the position of the dynamic target with partial prior information.

[0012] As the heterogeneous UAV cluster collaborative search optimization method based on multi-situation map fusion of the present invention, further, the expression of the target probability map is: where n represents the UAV number, p n (x,y) represents the probability that UAV n detects a target at the position (x,y), represents the distance between the position (x,y) where the UAV is located and the position (x * ,y * ) of the dynamic target with partial prior information, α n represents the target detection performance parameter of UAV n, and tpm(x * ,y * ) represents the prior target probability distribution at the position (x * ,y * ).

[0013] As the heterogeneous UAV cluster collaborative search optimization method based on multi-situation map fusion of the present invention, further, a digital pheromone map is constructed to reflect the search time interval of the UAV cluster for the environmental grid of the mission area, including:

[0014] First, use the digital pheromone concentration in the digital pheromone map to describe the degree of attraction of the environmental network to the UAV cluster, and set the digital pheromone map update rule for regional search coordination between UAVs. Among them, the digital pheromone map update rule includes: the digital pheromone volatilization rule set according to the digital pheromone concentration at the position and the digital pheromone enrichment rule set according to the time of the last volatilized pheromone at the position.

[0015] Then, initialize the digital pheromone map as a matrix of all 1s, and update the concentration values of each digital pheromone in the digital pheromone map during the search optimization process using the digital pheromone map update rule.

[0016] As the heterogeneous UAV swarm collaborative search optimization method based on multi-situation map fusion of the present invention, further, the digital pheromone evaporation rule is expressed as: where a x,y (k) represents the digital pheromone concentration at the position (x, y) at time k, d n represents the distance from UAV n to the position (x, y), and R n represents the maximum detection distance of UAV n.

[0017] As the heterogeneous UAV swarm collaborative search optimization method based on multi-situation map fusion of the present invention, further, the digital pheromone enrichment rule is expressed as: where k last represents the time when the pheromone at the position (x, y) was last evaporated, φ(τ) is the normal distribution function, λ is a constant parameter, and k max is the maximum execution time of the task.

[0018] As the heterogeneous UAV swarm collaborative search optimization method based on multi-situation map fusion of the present invention, further, construct an environmental search map for reflecting the search coverage of the UAV swarm for the environmental grid, including:

[0019] First, use the environmental search value in the environmental search map to describe the detection coverage of the environmental grid by the UAVs at a preset time, and set the environmental search map update rule;

[0020] Then, initialize the environmental search map as a matrix of all 0s, and update the environmental search values in the environmental search map during the search optimization process using the environmental search map update rule.

[0021] As the heterogeneous UAV swarm collaborative search optimization method based on multi-situation map fusion of the present invention, further, the environmental search map update rule is expressed as: where e x,y (k) represents the environmental search value at the position (x, y) at time k, and k x,y represents the time when the position (x, y) was searched by the UAV swarm. When any UAV n detects the position (x, y) at time k x,y , e x,y (k) is assigned a value of 1 and remains at that value until k max .

[0022] As a heterogeneous UAV swarm collaborative search optimization method based on multi-situation map fusion in the present invention, further, the collaborative search optimization objective function of the UAV swarm is expressed as: where J(k) represents the overall performance index of the UAV swarm N at time k, ω a and ω s are both weight parameters, p n (x,y) is the target existence probability gain in the target probability map, J A (k) n is the digital pheromone gain in the digital pheromone map, J S (k) n is the environmental search gain in the environmental search map.

[0023] Further, the present invention also provides a heterogeneous UAV swarm collaborative search optimization system based on multi-situation map fusion, including: a situation map construction module and a situation map fusion module, where,

[0024] The situation map construction module is used to construct a target probability map for reflecting the probability of detecting a target by UAVs in the environmental grid, a digital pheromone map for reflecting the search time interval of the UAV swarm for the environmental grid in the mission area, and an environmental search map for reflecting the search coverage of the UAV swarm for the environmental grid;

[0025] The situation map fusion module is used to generate a collaborative search optimization objective function of the UAV swarm according to the preset weight value and by combining the gains of the target probability map, the digital pheromone map, and the environmental search, so as to use the collaborative search optimization objective function of the UAV swarm to obtain the optimal decision of the UAV swarm under the constraint conditions.

[0026] Advantages of the present invention:

[0027] The present invention improves the search optimization function by constructing an improved multi-situation map and fusing the multi-situation map gain function. By improving the construction algorithm of the multi-situation map, a target detection probability map applicable to heterogeneous UAV swarms and a digital pheromone map with an adjustable enrichment rate can be generated, which helps to improve the perception degree of heterogeneous UAV swarms for the environment of the mission area. Using the improved search optimization function as the objective function in the collaborative search process of heterogeneous UAV swarms, through the optimization of the objective function, it is convenient to better obtain the optimal decision that maximizes the overall performance index under the predetermined constraint conditions, and the flight path of the UAV swarm can be optimized under the constraints of the mission environment to improve the collaborative efficiency and mission execution efficiency of the UAV swarm. Description of the drawings

[0028] Figure 1 It is a schematic diagram of the heterogeneous UAV swarm collaborative search optimization process based on multi-situation map fusion in the embodiment;

[0029] Figure 2 Schematic illustration of the search optimization algorithm principle in the embodiment. Specific implementation manner

[0030] To make the objectives, technical solutions and advantages of the present invention clearer and more understandable, the present invention will be further described in detail below with reference to the accompanying drawings and technical solutions.

[0031] In the embodiment of the present invention, refer to Figure 1 As shown, a heterogeneous UAV cluster collaborative search optimization method based on multi-situation map fusion is provided, including:

[0032] S101. Construct a target probability map for reflecting the probability of a UAV detecting a target in an environmental grid, a digital pheromone map for reflecting the search time interval of the UAV cluster for the environmental grid in the mission area, and an environmental search map for reflecting the search coverage of the UAV cluster for the environmental grid.

[0033] The task of the UAV swarm is to collaboratively search for a moving target in an unknown environment through an effective decision-making method based on limited prior information. Taking a two-dimensional space as an example, the mission area can be discretized into several environmental grid maps, and the target and the optional paths and possible position points at the next moment under the UAV maneuver constraints are displayed in the environmental grid map. The optimal path of the UAV during the mission execution under the maneuver constraints is obtained through search optimization.

[0034] Furthermore, in the embodiment of this case, when constructing a target probability map for reflecting the probability of a UAV detecting a target in an environmental grid, first, the target types to be searched are classified into unknown static targets, unknown dynamic targets, and dynamic targets with known partial prior information; then, a first target probability distribution of the unknown static targets and unknown dynamic targets is constructed using a uniform distribution function, and a second target probability distribution of the known partial prior information is constructed using a two-dimensional normal distribution function; then, the prior target probability distribution is obtained by summing the first target probability distribution and the second target probability distribution, and a target probability map is generated based on the prior target probability distribution, the UAV target detection performance parameters, and the distance from the position of the dynamic target with known partial prior information.

[0035] For the target prior information, it needs to be converted into a prior target probability map model through target type classification, prior information processing, and two-dimensional normal distribution algorithm calculation. Three target types are defined. Type I a targets refer to unknown static targets, and type I b targets refer to unknown dynamic targets. The characteristics of these two types of targets are that there is no prior information; type I c targets refer to dynamic targets with known partial prior information.

[0036] For type I a and type Ib Two types of targets, a target probability map model is established using a uniform distribution function, and constructed according to the following expression

[0037]

[0038] where and respectively represent the target distribution probabilities of two types of targets I a and I b at the position (x, y), and Lx×Ly is the size of the task area.

[0039] For the I c type of target, a target probability map model is established using a two-dimensional normal distribution function, and constructed according to the following expression

[0040]

[0041] where represents the prior information coordinate data, E represents the number of prior information data, and δ0≥0 represents the variance of the two-dimensional normal distribution function.

[0042] After summation, the prior target probability map model is obtained and constructed according to the following expression

[0043]

[0044] where tpm(x, y) represents the target distribution probability at the position (x, y).

[0045] The processed target prior information, based on the target detection model of heterogeneous UAV clusters, calculates the heterogeneous target detection probability map model and constructs it according to the following expression

[0046]

[0047] where n represents the UAV number, p n (x, y) represents the probability that UAV n detects a target at the position (x, y), represents the distance between (x, y) and (x * , y * )), and α n represents the target detection performance parameter of UAV n.

[0048] Further, in the digital pheromone map constructed in the embodiments of this case to reflect the time interval of the UAV swarm's grid search for the task area environment, the digital pheromone concentration can be first used in the digital pheromone map to describe the degree of attraction of the environmental network to the UAV swarm, and a digital pheromone map update rule for regional search coordination among UAVs can be set. Among them, the digital pheromone map update rule includes: a digital pheromone volatilization rule set according to the digital pheromone concentration at the position and a digital pheromone enrichment rule set according to the time of the last volatilized pheromone at the position; then, the digital pheromone map is initialized as an all-1 matrix, and the digital pheromone map update rule is used to update each digital pheromone concentration value in the digital pheromone map during the search optimization process.

[0049] In the digital pheromone map, the digital pheromone concentrations of different grids can be used to reflect the degree of attraction of the grid to the UAV swarm N. The higher the digital pheromone concentration, the more inclined the UAV is to transfer to the grid. Therefore, the UAVs can reasonably update the pheromone structure according to the search situation and can achieve group task coordination. To avoid over-searching a certain area by the swarm, a coordination mechanism can be established among the UAVs, such as the digital pheromone map update rule, to ensure regional search coordination among the UAVs. After UAV n completes one-step detection of the surrounding environment at (x n , y n ), it will volatilize a certain amount of pheromone in the surrounding grids to reduce the pheromone concentration of the searched grid and prevent the UAV swarm from repeatedly searching a certain area.

[0050] The degree of pheromone volatilization of UAV n should depend on the radar detection system it carries. Therefore, based on the radar detection model carried by UAV n, the projection of the detection range of the UAV on the task area plane has a radius assumed to be R n . Considering that the UAV swarm carries a certain radar detection system, it can image within the detection range at a detection interval of Τ and judge whether there is a target in the field of view according to the image. Usually, the closer the UAV is to the target and the more times it takes pictures, the greater the probability of detecting the target.

[0051] The digital pheromone volatilization principle can be expressed as:

[0052]

[0053] where a x,y (k) represents the digital pheromone concentration at the position (x, y) at time k, d n represents the distance from UAV n to the position (x, y), and R n represents the maximum detection distance of UAV n.

[0054] A new target may appear in the searched area, which increases uncertainty and the attractiveness to the UAVs. Therefore, it is necessary to increase the pheromone concentration of each grid accordingly. Moreover, the longer the time interval between UAV clusters for grid search, the faster the pheromone concentration on the grid should increase. The digital pheromone enrichment principle can be expressed as:

[0055]

[0056]

[0057] where k last represents the moment when pheromone was last volatilized at the (x, y) position, φ(τ) is the normal distribution function, λ is a constant parameter, and k max is the maximum execution time of the task.

[0058] Furthermore, in the environmental search graph constructed in the embodiments of this case to reflect the coverage of the UAV cluster for environmental grid search, the environmental grid detection coverage at a preset moment of the UAV can be first described using the environmental search value in the environmental search graph, and the environmental search graph update rule can be set; then, the environmental search graph is initialized as a matrix of all 0s, and each environmental search value in the environmental search graph is updated using the environmental search graph update rule during the search optimization process.

[0059] The environmental search graph update rule can be expressed as:

[0060]

[0061] where e x,y (k) represents the environmental search value at the (x, y) position at time k, and k x,y represents the moment when the (x, y) position is searched by the UAV cluster.

[0062] When any UAV n detects the position (x, y) at time k x,y , e x,y (k) is assigned a value of 1 and maintains this value until k max .

[0063] S102. Generate the collaborative search optimization objective function of the UAV cluster based on the preset weight value and by combining the benefits of the target probability map, the digital pheromone map, and the environmental search, so as to obtain the optimal decision of the UAV cluster under the constraint conditions using the collaborative search optimization objective function of the UAV cluster.

[0064] Refer to Figure 2 In the shown algorithm, the search optimization function includes three sub-functions, namely the environmental search benefit J S (k) n , the digital pheromone benefit JA (k) n and the target presence probability gain p n (x, y). By fusing three environmental situation maps, a search optimization function is obtained, which will be used as the objective function of the optimization algorithm. The collaborative search optimization objective function of the UAV swarm is expressed as: where J(k) represents the overall performance index of the UAV swarm N at time k, ω a and ω s are both weight parameters, p n (x, y) is the target presence probability gain in the target probability map, J A (k) n is the digital pheromone gain in the digital pheromone map, and J S (k) n is the environmental search gain in the environmental search map.

[0065] The environmental search gain J S (k) n can be expressed as: where J S (k) n represents the environmental search gain of UAV n at time k.

[0066] The digital pheromone gain J A (k) n can be expressed as where J A (k) n represents the digital pheromone gain of UAV n at time k.

[0067] The goal of the collaborative search task of the UAV swarm is to obtain decision inputs to maximize the overall performance index under certain constraints. By optimizing and solving the objective function, the UAV swarm N can consider longer path optimization to jump out of the local optimum and improve the overall search task performance.

[0068] Furthermore, based on the above method, an embodiment of the present invention also provides a heterogeneous UAV swarm collaborative search optimization system based on multi-situation map fusion, including: a situation map construction module and a situation map fusion module, where

[0069] The situation map construction module is used to construct a target probability map for reflecting the probability of detecting a target by UAVs in the environmental grid, a digital pheromone map for reflecting the search time interval of the UAV swarm for the environmental grid in the task area, and an environmental search map for reflecting the search coverage of the UAV swarm for the environmental grid;

[0070] The situation map fusion module is used to generate an optimal objective function for cooperative search of an unmanned aerial vehicle (UAV) cluster based on a preset weight value and by combining the benefits of the target probability map, the digital pheromone map, and environmental search, so as to use the optimal objective function for cooperative search of the UAV cluster to obtain the optimal decision of the UAV cluster under constraint conditions.

[0071] Unless otherwise specifically stated, the relative steps, numerical expressions, and values of the components and steps set forth in these embodiments do not limit the scope of the present invention.

[0072] Each embodiment in this specification is described in a progressive manner. The key point of each embodiment is to illustrate the differences from other embodiments. The same or similar parts among the embodiments can be referred to each other. For the system disclosed in the embodiments, since it corresponds to the method disclosed in the embodiments, the description is relatively simple. For the relevant parts, reference can be made to the description in the method part.

[0073] The units and method steps of each example described in combination with the embodiments disclosed in this document can be implemented by electronic hardware, computer software, or a combination of the two. To clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described according to functions in the above description. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. Those of ordinary skill in the art can use different methods to implement the described functions for each specific application, but such implementation is not considered to exceed the scope of the present invention.

[0074] Those of ordinary skill in the art can understand that all or part of the steps in the above method can be completed by instructing relevant hardware through a program. The program can be stored in a computer-readable storage medium, such as a read-only memory, a magnetic disk, or an optical disc, etc. Optionally, all or part of the steps in the above embodiments can also be implemented using one or more integrated circuits. Correspondingly, each module / unit in the above embodiments can be implemented in the form of hardware or in the form of a software functional module. The present invention is not limited to any specific form of the combination of hardware and software.

[0075] Finally, it should be noted that the above-described embodiments are only specific embodiments of the present invention, which are used to illustrate the technical solutions of the present invention, rather than to limit it. The protection scope of the present invention is not limited thereto. Although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that any technician familiar with the technical field of the present invention can still modify the technical solutions recorded in the foregoing embodiments or easily conceive of changes, or make equivalent replacements for some of the technical features; and these modifications, changes or replacements 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, and should all be covered by the protection scope of the present invention. Therefore, the protection scope of the present invention should be subject to the protection scope of the claims.

Claims

1. A collaborative search optimization method for heterogeneous UAV clusters based on multi-situation map fusion, characterized in that, Including: Construct a target probability map for reflecting the probability of a drone detecting a target in an environmental grid, a digital pheromone map for reflecting the search time interval of a drone swarm for the environmental grid in a mission area, and an environmental search map for reflecting the search coverage of a drone swarm for the environmental grid; Generate an optimized objective function for the collaborative search of the UAV swarm by combining the preset weight values with the benefits of the target probability map, the digital pheromone map, and the environmental search, so as to use the optimized objective function for the collaborative search of the UAV swarm to obtain the optimal decision of the UAV swarm under the constraint conditions. Among them, the optimized objective function for the collaborative search of the UAV swarm is expressed as: J(k) represents the overall performance index of the UAV swarm N at time k, ω a and ω s are both weight parameters, p n (x, y) is the target presence probability benefit in the target probability map, J A (k) n is the digital pheromone benefit in the digital pheromone map, J S (k) n is the environmental search benefit in the environmental search map.

2. The heterogeneous UAV cluster collaborative search optimization method based on multi-situation map fusion according to claim 1, wherein Construct a target probability map for reflecting the probability of a drone detecting a target in an environmental grid, including: First, divide the types of searched targets into unknown static targets, unknown dynamic targets, and dynamic targets with partial prior information; Next, use the uniform distribution function to construct the first target probability distribution of unknown static targets and unknown dynamic targets, and use the two-dimensional normal distribution function to construct the second target probability distribution of dynamic targets with partial prior information; Then, obtain the prior target probability distribution by summing the first target probability distribution and the second target probability distribution, and generate the target probability map based on the prior target probability distribution, the drone target detection performance parameters, and the distance from the position of the dynamic target with partial prior information.

3. The heterogeneous UAV cluster collaborative search optimization method based on multi-situation map fusion according to claim 2, wherein, The target probability map expression is represented as: where n represents the UAV number, p n (x,y) represents the probability that the UAV n detects a target at the position (x,y), represents the distance between the position (x,y) where the UAV is located and the dynamic target position (x * ,y * ) of the known partial prior information, α n represents the target detection performance parameter of the UAV n, tpm(x * ,y * ) represents the prior target probability distribution at the position (x * ,y * ).

4. The heterogeneous UAV cluster collaborative search optimization method based on multi-situation map fusion according to claim 1, characterized in that, Construct a digital pheromone map for reflecting the search time interval of a drone swarm for the environmental grid in a mission area, including: First, use the digital pheromone concentration in the digital pheromone map to describe the degree of attraction of the environmental network to the drone swarm, and set the digital pheromone map update rule for regional search coordination among drones, where the digital pheromone map update rule includes: the digital pheromone evaporation rule set according to the digital pheromone concentration at the position and the digital pheromone enrichment rule set according to the time of the last evaporation of pheromone at the position; Then, initialize the digital pheromone map as a matrix of all 1s, and update each digital pheromone concentration value in the digital pheromone map during the search optimization process using the digital pheromone map update rule.

5. The collaborative search optimization method for heterogeneous UAV clusters based on multi-situation map fusion according to claim 4, characterized in that The digital pheromone volatilization rule is expressed as: where a x,y (k) represents the digital pheromone concentration at the position (x, y) at time k, d n represents the distance from UAV n to the position (x, y), R n represents the maximum detection distance of UAV n, and α n represents the target detection performance parameter of UAV n.

6. The method for optimizing the collaborative search of heterogeneous UAV clusters based on multi-situation map fusion according to claim 5, wherein The digital pheromone enrichment rule is expressed as: where k last represents the moment when the pheromone was last volatilized at the (x, y) position, φ(τ) is the normal distribution function, λ is a constant parameter, and k max is the maximum execution time of the task.

7. The heterogeneous UAV cluster cooperative search optimization method based on multi-situation map fusion according to claim 1, wherein Construct an environmental search map for reflecting the search coverage of a drone swarm for the environmental grid, including: First, use the environmental search value in the environmental search map to describe the detection coverage of a drone for the environmental grid at a preset moment, and set the environmental search map update rule; Then, initialize the environmental search map as a matrix of all 0s, and update each environmental search value in the environmental search map during the search optimization process using the environmental search map update rule.

8. The heterogeneous UAV cluster collaborative search optimization method based on multi-situation map fusion according to claim 7, characterized in that The environmental search map update rule is expressed as: Among them, e x,y (k) represents the environmental search value at the position (x, y) at time k, and k x,y represents the time when the position (x, y) is searched by the UAV swarm. When any UAV n detects the position (x, y) at time k x,y after that, e x,y (k) is assigned the value 1 and maintains this value until k max .

9. A heterogeneous UAV cluster collaborative search optimization system based on multi-situation map fusion, characterized in that, Including: a situation map construction module and a situation map fusion module, where The situation map construction module is used to construct a target probability map for reflecting the probability of a drone detecting a target in an environmental grid, a digital pheromone map for reflecting the search time interval of a drone swarm for the environmental grid in a mission area, and an environmental search map for reflecting the search coverage of a drone swarm for the environmental grid; The situation map fusion module is used to generate an optimal decision-making function for the UAV swarm collaborative search under constraints by using the UAV swarm collaborative search optimization objective function, which is generated based on preset weight values and combines the benefits of the target probability map, the digital pheromone map, and the environmental search. The UAV swarm collaborative search optimization objective function is expressed as: J(k) represents the overall performance index of the UAV swarm N at time k, ω a and ω s are both weight parameters, p n (x,y) is the target existence probability benefit in the target probability map, J A (k) n is the digital pheromone benefit in the digital pheromone map, J S (k) n is the environmental search benefit in the environmental search map.

Images