Collaborative task allocation and path planning method for heterogeneous unmanned swarms based on emotion patterns

Abstract

The present invention discloses a method for collaborative task allocation and path planning for heterogeneous unmanned swarms based on emotional patterns, comprising: establishing a constraint model for heterogeneous unmanned swarms; constructing an objective function for the method based on emotional patterns, using this objective function as a measure of the effectiveness of the collaborative task allocation and path planning; establishing an optimization mathematical model for the collaborative task allocation and path planning for heterogeneous unmanned swarms based on emotional patterns, using the range, task requirements, track safety, and task payload of the heterogeneous unmanned swarms as constraints and maximizing the net benefit of the heterogeneous unmanned swarms as the optimization objective; and solving the optimization mathematical model for the collaborative task allocation and path planning for heterogeneous unmanned swarms based on emotional patterns using an ant colony algorithm, introducing a roulette wheel selection principle, and an elite strategy. The present invention performs a joint optimization design for the range, value benefit, and threat level of the heterogeneous unmanned swarms, demonstrating the effectiveness and superiority of the proposed method.

Description

Technical Field

[0001] The present invention relates to radar signal processing technology, and in particular to a method for collaborative task allocation and path planning of heterogeneous unmanned clusters based on emotion patterns. Background Art

[0002] Heterogeneous unmanned swarms are composed of various types of drones that can adapt to different environments and mission requirements. They use information interaction and feedback, incentives and responses to achieve behavioral coordination and complete more complex and efficient flight missions. Compared with homogeneous unmanned swarms, they can significantly improve system performance and reduce integration and maintenance costs.

[0003] The actual performance of UAV task allocation methods depends largely on the associated path planning process, but most existing research has not considered the coupling between task allocation and path planning. While this approach reduces the complexity of the problem, it also presents drawbacks in the face of increasingly challenging mission environments. Furthermore, to address the weak adaptability, low robustness, low flexibility, heavy communication load, and low resource utilization of unmanned clusters in complex multi-task scenarios, heterogeneous unmanned cluster networks established in a self-organizing manner can freely join and leave nodes, automatically adjust the topology, and flexibly utilize idle computing power or storage capacity without the need for central node management or intervention. In summary, the existing technology does not yet have a method for collaborative task allocation and path planning for heterogeneous unmanned clusters based on emotional patterns. Summary of the Invention

[0004] Purpose of the invention: The purpose of the present invention is to provide a method for collaborative task allocation and path planning of heterogeneous unmanned clusters based on emotional patterns, which realizes better collaborative task allocation and path planning of heterogeneous unmanned clusters and effectively improves the net benefit of heterogeneous unmanned clusters.

[0005] Technical solution: The present invention's method for collaborative task allocation and path planning for heterogeneous unmanned swarms based on emotional patterns includes the following steps:

[0006] (1) Establish a heterogeneous unmanned swarm constraint model, including range constraints, mission requirement constraints, trajectory safety constraints, and payload constraints;

[0007] (2) Construct an objective function for collaborative task allocation and path planning of heterogeneous unmanned swarms based on emotion patterns, and use it as a measure of the effectiveness of collaborative task allocation and path planning;

[0008] (3) Taking the range, mission requirements, trajectory safety, and mission payload of heterogeneous unmanned swarms as constraints and maximizing the net benefit of heterogeneous unmanned swarms as the optimization goal, a mathematical model for collaborative task allocation and path planning optimization of heterogeneous unmanned swarms based on emotional patterns is established;

[0009] (4) The ant colony algorithm is used to introduce the roulette wheel selection principle and elite strategy to solve the mathematical model of collaborative task allocation and path planning optimization of heterogeneous unmanned clusters based on emotional patterns.

[0010] Furthermore, the range constraint of the heterogeneous unmanned swarm is expressed as:

[0011]

[0012] in, Indicates drone U i From the starting point to task T i a distance; Indicates drone U i From T i a The predecessor task to task T i a Distance; L Max,i Indicates drone U i Range when fuel is exhausted; A represents the UAV i The total number of tasks assigned;

[0013] The task requirement constraints of heterogeneous unmanned swarm are expressed as:

[0014]

[0015] Among them, x ij represents the task decision variable; N represents the total number of drones in the heterogeneous unmanned swarm;

[0016] The safety constraints of the heterogeneous unmanned swarm trajectory are expressed as:

[0017] ① Threat probability for active threat areas such as radar:

[0018]

[0019] ② Threat probability for areas threatened by fixed obstacles such as high mountains:

[0020]

[0021] in, Indicates drone U i Threat Sources Threat probability; Indicates drone U i Threat Sources The distance between centers; D b Indicates the threat source Maximum threat radius; Indicates the threat source the degree of threat; Indicates drone U i The critical value of being destroyed;

[0022] The load constraint of heterogeneous unmanned cluster is expressed as:

[0023]

[0024] in, Indicates drone U i Execute Task T i a The load resources consumed; B Max,i Indicates drone U i Total mission payload resources carried.

[0025] Furthermore, the objective function of the heterogeneous unmanned swarm collaborative task allocation and path planning method based on emotion patterns is expressed as:

[0026] U u =μ1E u -μ2C u +D ij

[0027] Among them, U u represents the net benefit of the heterogeneous unmanned cluster; μ1 and μ2 are weight coefficients, and μ1+μ2=1; E u represents the ideal benefit of heterogeneous unmanned cluster; C u represents the cost of executing tasks by heterogeneous unmanned clusters; D ij Represents the UAV U in the heterogeneous unmanned swarm i Execute Task T j The profit adjustment function.

[0028] Furthermore, the ideal benefit E of heterogeneous unmanned clusters u The expression is:

[0029]

[0030] Where N represents the total number of drones in the heterogeneous unmanned cluster; E i Represents the UAV U in the heterogeneous unmanned swarm i The ideal benefit of mission attack is expressed as:

[0031]

[0032] Among them, A represents the drone U i Total number of tasks assigned; V_TARGET a Represents task T i a Value; P i aIndicates drone U i Destroy Mission T i a probability.

[0033] Furthermore, the cost C of heterogeneous unmanned clusters performing tasks u The expression is:

[0034]

[0035] Where N represents the total number of drones in the heterogeneous unmanned cluster; C i Represents the UAV U in the heterogeneous unmanned cluster i The task cost is expressed as:

[0036]

[0037] Among them, V_UAV i Indicates drone U i Self-worth; Represents task T i a Destroy the drone i probability; Represents task T i a UAV i The threat level of the drone U i The total number of tasks assigned.

[0038] Furthermore, the UAVs in heterogeneous unmanned clusters i Execute Task T j The income adjustment function D ij The expression is:

[0039]

[0040] Among them, E ij Indicates drone U i Execute Task T j The profit function; γ is the preference coefficient; E min represents the minimum ideal benefit of the drone, E max represents the maximum ideal benefit of the drone, E d =E max -E min .

[0041] Furthermore, the mathematical model of collaborative task allocation and path planning optimization for heterogeneous unmanned swarms based on emotional patterns is expressed as follows:

[0042]

[0043] Among them, U u represents the net benefit of heterogeneous unmanned cluster; μ1 and μ2 are weight coefficients; E u represents the ideal benefit of heterogeneous unmanned cluster; C u represents the cost of executing tasks by heterogeneous unmanned clusters; D ij Represents the UAV U in the heterogeneous unmanned cluster i Execute Task T j The income adjustment function of Indicates drone U i From the starting point to task T i a distance; Indicates drone U i From T i a The predecessor task to task T i a Distance; L Max,i Indicates drone U i Range until fuel is exhausted; x ij represents the task decision variable; Indicates drone U i Threat Sources Threat probability; Indicates drone U i The critical value of being destroyed; Indicates drone U i Execute Task T i a The load resources consumed; B Max,i Indicates drone U i The total mission payload resources carried; N represents the total number of drones in the heterogeneous unmanned swarm; A represents the number of drones U i The total number of tasks assigned.

[0044] Furthermore, in step (4), let the individual be represented by x i , i=1,2,...,ant, ant represents the size of the group, then its fitness value is f(x i ), the probability of each individual in the group being selected P(x i )for:

[0045]

[0046] From P(x1)+P(x2)+...+P(x ant )=1 to form a roulette wheel and calculate the cumulative probability q of each individual i :

[0047]

[0048] According to the cumulative probability, use rand() to generate a uniformly distributed pseudo-random number r in the interval [0,1]. If r falls in the probability interval q k-1 <r≤q k , then select individual x k .

[0049] Furthermore, the pheromone adjustment parameters in the elite strategy in step (4) are:

[0050]

[0051] in, represents the pheromone increment between nodes m and n caused by elite ants; T best represents the set of nodes that make up the optimal path; L best represents the path length of the optimal solution found so far; Q represents the pheromone enhancement coefficient; e represents the adjustment parameter, which is related to the length of the elite path.

[0052] The system corresponding to the above method includes:

[0053] The constraint model building unit is used to establish the constraint model of heterogeneous unmanned swarm, including the range constraint, mission requirement constraint, trajectory safety constraint and payload constraint of heterogeneous unmanned swarm;

[0054] The objective function construction unit is used to construct the objective function of the collaborative task allocation and path planning method of heterogeneous unmanned swarm based on emotion patterns, and use it as a measurement indicator of the collaborative task allocation and path planning effect;

[0055] The model building unit is used to establish a mathematical model for collaborative task allocation and path planning optimization of heterogeneous unmanned swarms based on emotional patterns, taking the range, mission requirements, trajectory safety, and mission payload of the heterogeneous unmanned swarm as constraints and maximizing the net benefit of the heterogeneous unmanned swarm as the optimization goal;

[0056] The model solving unit is used to adopt the ant colony algorithm, introduce the roulette wheel selection principle and the elite strategy to solve the mathematical model of collaborative task allocation and path planning optimization of heterogeneous unmanned swarm based on emotional patterns.

[0057] Beneficial effects: Compared with the existing technology, the advantages of the present invention are: (1) by jointly optimizing the parameters such as the range, value benefit and threat level of the heterogeneous unmanned cluster in the multi-task scenario, the emotions of the heterogeneous unmanned cluster are taken into consideration under the constraints of the range, mission requirements, track safety and mission payload, and the net benefit of the heterogeneous unmanned cluster is maximized; (2) a better collaborative task allocation and path planning of the heterogeneous unmanned cluster is achieved, which effectively improves the net benefit of the heterogeneous unmanned cluster. BRIEF DESCRIPTION OF THE DRAWINGS

[0058] Figure 1 Flowchart of the proposed method;

[0059] Figure 2 Simulation results of collaborative task allocation and path planning for heterogeneous unmanned swarms based on emotion patterns;

[0060] Figure 3 The net benefit curve of heterogeneous unmanned cluster under the emotional model;

[0061] Figure 4 This is the net benefit curve of the heterogeneous unmanned cluster under normal mode. DETAILED DESCRIPTION

[0062] The present invention will be described in detail below with reference to the accompanying drawings and specific embodiments.

[0063] Starting from a practical mission scenario, this paper assumes that several tasks are dispersed across a two-dimensional mission scenario, and a heterogeneous unmanned swarm performs reconnaissance and strikes on these tasks. This paper proposes a collaborative task allocation and path planning method for heterogeneous unmanned swarms based on emotional patterns. First, a constraint model for the heterogeneous unmanned swarm is established. Second, for this complex multi-task scenario, an objective function incorporating the emotions of the heterogeneous unmanned swarm is constructed as a metric for measuring the effectiveness of collaborative task allocation and path planning. Then, with the heterogeneous unmanned swarm's range, mission requirements, track safety, and mission payload as constraints, and maximizing the heterogeneous unmanned swarm's net benefit as the optimization objective, a collaborative task allocation and path planning model for the heterogeneous unmanned swarm based on emotional patterns is established. Finally, an ant colony algorithm with an elitist strategy is used to solve the model, obtaining the optimal solution while satisfying the constraints of the heterogeneous unmanned swarm's range, mission requirements, track safety, and mission payload. This method achieves a joint optimization design of the heterogeneous unmanned swarm's range, value benefit, and threat level, demonstrating the effectiveness and superiority of the proposed method.

[0064] like Figure 1 As shown in FIG, the method for collaborative task allocation and path planning of heterogeneous unmanned swarms based on emotion patterns includes the following steps:

[0065] (1) Establish a heterogeneous unmanned cluster constraint model;

[0066] Consider a two-dimensional mission scenario with N UAVs (U i , i=1,2,...,N) composed of a heterogeneous unmanned cluster with a total of M tasks (T j ,j=1,2,...,M) need to be allocated, there are F threat sources (Z f ,f=1,2,...,F). For a single UAV U i (i=1,2,3,...,N), let it be assigned to A tasks (T i a,a=1,2,...,A)(A≤M), encounter B threat sources on the way to the mission location

[0067] The range constraint of heterogeneous unmanned swarm is expressed as:

[0068]

[0069] in, Indicates drone U i Starting point to task T i a distance; Indicates drone U i From T i a The predecessor task to task T i a Distance; L Max,i Indicates drone U i Range until fuel runs out.

[0070] The task requirement constraints of heterogeneous unmanned swarm are expressed as:

[0071]

[0072] Among them, x ij represents the task decision variable.

[0073] The safety constraints of the heterogeneous unmanned swarm trajectory are expressed as:

[0074] ① Threat probability for active threat areas such as radar:

[0075]

[0076] ② Threat probability for areas threatened by fixed obstacles such as high mountains:

[0077]

[0078] in, Indicates drone U i Threat Sources Threat probability; Indicates drone U i Threat Sources The distance between centers; D b Indicates the threat source Maximum threat radius; Indicates the threat source the degree of threat; Indicates drone U i The critical value of being destroyed.

[0079] The load constraint of heterogeneous unmanned cluster is expressed as:

[0080]

[0081] in, Indicates drone U i Execute Task T i a The load resources consumed; B Max,i Indicates drone U i Total mission payload resources carried.

[0082] (2) Define the objective function of the heterogeneous unmanned swarm collaborative task allocation and path planning method based on emotion patterns:

[0083] U u =μ1E u -μ2C u +D ij (7)

[0084] Among them, U u represents the net benefit of the heterogeneous unmanned cluster; μ1 and μ2 are weight coefficients, and μ1+μ2=1.

[0085] In formula (7), E u The ideal benefit of a heterogeneous unmanned cluster is:

[0086]

[0087] Among them, E i Represents the UAV U in the heterogeneous unmanned cluster i Ideal benefits for mission strike:

[0088]

[0089] Among them, V_TARGET a Represents task T i a Value; P i a Indicates drone U i Destroy Mission T i a probability.

[0090] In formula (7), C u Represents the cost of executing tasks in a heterogeneous unmanned cluster:

[0091]

[0092] Among them, C i Represents the UAV U in the heterogeneous unmanned cluster i Mission cost:

[0093]

[0094] Among them, V_UAV i Indicates drone U i Self-worth; Represents task T i a Destroy the drone i probability; Represents task T i a UAV i The threat level; λ1, λ2, λ3 are weight coefficients, and λ1+λ2+λ3=1.

[0095] In formula (7), D ij Represents the UAV U in the heterogeneous unmanned cluster i Execute Task T j The profit adjustment function of :

[0096]

[0097] Among them, E ij Indicates drone U i Execute Task T j The profit function; γ is the preference coefficient, the value range is [0.1, 0.5]; E min represents the minimum ideal benefit of the drone, E max represents the maximum ideal benefit of the drone, E d =E max -E min .

[0098] (3) Establish a mathematical model for collaborative task allocation and path planning optimization of heterogeneous unmanned swarms based on emotional patterns.

[0099] By jointly optimizing the range, value benefits, and threat level of heterogeneous unmanned swarms, the resources of heterogeneous unmanned swarms can be fully utilized under the constraints of range, mission requirements, track safety, and mission payload, effectively improving the net benefits of heterogeneous unmanned swarms, as shown in the formula:

[0100]

[0101] In formula (13), the first constraint condition represents the value range of the flight distance of the heterogeneous unmanned cluster; the second constraint condition represents the mission requirement; the third constraint condition represents the value range of the probability of the heterogeneous unmanned cluster being threatened; and the fourth constraint condition represents the value range of the mission payload resources of the heterogeneous unmanned cluster.

[0102] (4) Roulette wheel selection and elite strategy are introduced into the ant colony algorithm to solve the optimization mathematical model (13).

[0103] Roulette wheel selection: also known as proportional selection method. In roulette, each option corresponds to a section on the wheel, and the size of each section is proportional to the probability of the option being selected. Specifically, each option is assigned an interval, and these intervals are arranged on the wheel according to the probability of the corresponding option. When making a choice, a pointer is rotated and stopped at a certain position on the wheel, thereby determining the selected option. The probability of selecting an option is proportional to the size of the interval it occupies on the wheel, so options with larger intervals are more likely to be selected. Let the individual be represented by x i (i=1,2,...,ant), ant represents the size of the group, then its fitness value is f(x i )(i=1,2,...,ant), the probability of selection of each individual in the population is P(x i )for:

[0104]

[0105] From P(x1)+P(x2)+...+P(x ant )=1 to form a roulette wheel and calculate the cumulative probability q of each individual i :

[0106]

[0107] According to the cumulative probability, use rand() to generate a uniformly distributed pseudo-random number r in the interval [0,1]. If r falls in the probability interval q k-1 <r≤q k , then select individual x k Introducing roulette wheel selection into the ant colony algorithm can increase the randomness of node selection and prevent the algorithm from falling into local optimality too early.

[0108] The basic idea of ​​the elite strategy is to extract the elite ant's solution at the end of each cycle and perform local pheromone adjustments on the elite ant's path to make the optimal solution found so far more attractive in the next cycle. The pheromone adjustment parameters are as follows:

[0109]

[0110] in, represents the pheromone increment between nodes m and n caused by elite ants; T best represents the set of nodes that make up the optimal path; L best= represents the path length of the optimal solution found so far; Q represents the pheromone enhancement coefficient; and e represents an adjustment parameter related to the length of the elite path. Introducing the elitist strategy into the ant colony algorithm allows for real-time updates of pheromone concentrations, increasing the algorithm's convergence speed.

[0111] The solution steps include:

[0112] (41) Initialize various parameters;

[0113] (42) Update pheromone concentration;

[0114] Use formula (16) to update the pheromone concentration on each path;

[0115] (43) Determine whether the ant has reached the task location;

[0116] If the ant reaches the task location, execute step (44); otherwise return to step (42).

[0117] (44) Determine whether all tasks have been executed.

[0118] If all tasks are executed, the algorithm ends and the optimal solution is recorded; otherwise, it returns to step (42).

[0119] Simulation results:

[0120] In a 100km×100km two-dimensional mission scenario map, when N=6 and M=6, the simulation results of heterogeneous unmanned swarm collaborative task allocation and path planning based on emotion patterns are as follows: Figure 2 As shown, from Figure 2 As can be seen from the figure, the task allocation results are: drone 1 → task 6, drone 2 → task 5, drone 3 → task 2, drone 4 → task 1, drone 5 → task 4, drone 6 → task 3. The net benefit curve of heterogeneous unmanned cluster under the emotional mode is as follows: Figure 3 As shown, from Figure 3 It can be seen that the net benefit value of the heterogeneous unmanned cluster is 5.895.

[0121] The net benefit curve of heterogeneous unmanned cluster in normal mode is as follows Figure 4 As shown, from Figure 4 It can be seen from the figure that the net benefit value of the heterogeneous unmanned cluster is 4.399, which is lower than the net benefit value of the heterogeneous unmanned cluster in the emotional mode, which verifies the superiority of the proposed method. It can also be seen that the task allocation of the heterogeneous unmanned cluster in the emotional mode is greatly affected by the task value, which shows the effectiveness of the proposed method.

[0122] The working principle and working process of the present invention:

[0123] This paper considers the emotions of heterogeneous unmanned aerial vehicle swarms in a two-dimensional mission scenario to conduct coordinated reconnaissance and strike operations on multiple spatially dispersed missions. First, a constraint model for the heterogeneous unmanned aerial vehicle swarm is established. Based on this model, an objective function incorporating the emotions of the heterogeneous unmanned aerial vehicle swarm is defined as a metric for measuring the effectiveness of collaborative task allocation and path planning. Then, a collaborative task allocation and path planning model for the heterogeneous unmanned aerial vehicle swarm based on the emotion model is established, with the swarm's range, mission requirements, trajectory safety, and mission payload as constraints and maximizing the swarm's net benefit as the optimization objective. Finally, an ant colony algorithm with an elitist strategy is employed to solve this optimization model, introducing the roulette wheel selection principle and an elitist strategy. A joint optimization design of the heterogeneous unmanned aerial vehicle swarm's range, value benefit, and threat level is performed to demonstrate the effectiveness and superiority of the proposed method. By solving this optimization model, the net benefit of the heterogeneous unmanned aerial vehicle swarm is maximized while satisfying the constraints of the swarm's range, mission requirements, trajectory safety, and mission payload.

Claims

1. A collaborative task allocation and path planning method for heterogeneous unmanned swarms based on emotional patterns, characterized by: The following steps are involved: (1) Establish a constraint model for heterogeneous unmanned swarms, including range constraints, mission requirement constraints, trajectory safety constraints, and payload constraints. The range constraints of heterogeneous unmanned swarms are expressed as: in, Indicates drone U i From the starting point to task T i a distance; Indicates drone U i From T i a The predecessor task to task T i a Distance; L Max,i Indicates drone U i Range when fuel is exhausted; A represents the UAV i The total number of tasks assigned; The task requirement constraints of heterogeneous unmanned swarm are expressed as: Among them, x ij represents the task decision variable; N represents the total number of drones in the heterogeneous unmanned swarm; The safety constraints of the heterogeneous unmanned swarm trajectory are expressed as: ① Threat probability for radar active threat area: ② Threat probability for high mountain fixed obstacle threat areas: in, Indicates drone U i Threat Sources Threat probability; Indicates drone U i Threat Sources The distance between centers; D b Indicates the threat source Maximum threat radius; Indicates the threat source the degree of threat; Indicates drone U i The critical value of being destroyed; The load constraint of heterogeneous unmanned cluster is expressed as: in, Indicates drone U i Execute Task T i a The load resources consumed; B Max,i Indicates drone U i Total mission payload resources carried; (2) Construct an objective function for collaborative task allocation and path planning of heterogeneous unmanned swarms based on emotion patterns, and use it as a measure of the effectiveness of collaborative task allocation and path planning; (3) Taking the range, mission requirements, trajectory safety, and mission payload of heterogeneous unmanned swarms as constraints and maximizing the net benefit of heterogeneous unmanned swarms as the optimization goal, a mathematical model for collaborative task allocation and path planning optimization of heterogeneous unmanned swarms based on emotional patterns is established; (4) The ant colony algorithm is used to introduce the roulette wheel selection principle and elite strategy to solve the mathematical model of collaborative task allocation and path planning optimization of heterogeneous unmanned clusters based on emotional patterns.

2. The method for collaborative task allocation and path planning for heterogeneous unmanned clusters based on emotional patterns according to claim 1 is characterized in that: The objective function of the collaborative task allocation and path planning method for heterogeneous unmanned swarms based on emotion patterns is expressed as: U u Zμ1E u -µ2C u +D ij Among them, U u represents the net benefit of the heterogeneous unmanned cluster; μ1 and μ2 are weight coefficients, and μ1+μ2=1; E u represents the ideal benefit of heterogeneous unmanned cluster; C u represents the cost of executing tasks by heterogeneous unmanned clusters; D ij Represents the UAV U in the heterogeneous unmanned swarm i Execute Task T j The profit adjustment function.

3. The method for collaborative task allocation and path planning for heterogeneous unmanned clusters based on emotion patterns according to claim 2 is characterized in that: The ideal benefit E of heterogeneous unmanned cluster u The expression is: Where N represents the total number of drones in the heterogeneous unmanned cluster; E i Represents the UAV U in the heterogeneous unmanned swarm i The ideal benefit of mission attack is expressed as: Among them, A represents the drone U i Total number of tasks assigned; V_TARGET a Represents task T i a Value; P i a Indicates drone U i Destroy Mission T i a probability.

4. The method for heterogeneous unmanned cluster collaborative task allocation and path planning based on emotion patterns according to claim 2 is characterized in that: The cost of executing tasks in a heterogeneous unmanned cluster C u The expression is: Where N represents the total number of drones in the heterogeneous unmanned cluster; C i Represents the UAV U in the heterogeneous unmanned swarm i The task cost is expressed as: Among them, V_UAV i Indicates drone U i Self-worth; Represents task T i a Destroy the drone i probability; Represents task T i a UAV i The threat level of the drone U i The total number of tasks assigned.

5. The method for collaborative task allocation and path planning for heterogeneous unmanned clusters based on emotional patterns according to claim 2 is characterized in that: UAVs in heterogeneous unmanned swarms i Execute Task T j The income adjustment function D ij The expression is: Among them, E ij Indicates drone U i Execute Task T j The profit function; γ is the preference coefficient; E min represents the minimum ideal benefit of the drone, E max represents the maximum ideal benefit of the drone, E d =E max -E min .

6. The method for collaborative task allocation and path planning for heterogeneous unmanned clusters based on emotional patterns according to claim 1 is characterized in that: The mathematical model of collaborative task allocation and path planning optimization for heterogeneous unmanned swarms based on emotional patterns is expressed as follows: Among them, U u represents the net benefit of heterogeneous unmanned cluster; μ1 and μ2 are weight coefficients; E u represents the ideal benefit of heterogeneous unmanned cluster; C u represents the cost of executing tasks by heterogeneous unmanned clusters; D ij Represents the UAV U in the heterogeneous unmanned swarm i Execute Task T j The income adjustment function of Indicates drone U i From the starting point to task T i a distance; Indicates drone U i From T i a The predecessor task to task T i a Distance; L Max,i Indicates drone U i Range until fuel is exhausted; x ij represents the task decision variable; Indicates drone U i Threat Sources Threat probability; Indicates drone U i The critical value of being destroyed; Indicates drone U i Execute Task T i a The load resources consumed; B Max,i Indicates drone U i The total mission payload resources carried; N represents the total number of drones in the heterogeneous unmanned swarm; A represents the number of drones U i The total number of tasks assigned.

7. The method for collaborative task allocation and path planning for heterogeneous unmanned clusters based on emotional patterns according to claim 1 is characterized in that: In step (4), let the individual be represented by x i , i=1,2,...,ant, ant represents the size of the group, then its fitness value is f(x i ), the probability of each individual in the group being selected P(x i )for: From P(x1)+P(x2)+...+P(x ant )=1 to form a roulette wheel and calculate the cumulative probability q of each individual i : According to the cumulative probability, use rand() to generate a uniformly distributed pseudo-random number r in the interval [0,1]. If r falls in the probability interval q k-1 <r≤q k , then select individual x k .

8. The method for collaborative task allocation and path planning for heterogeneous unmanned clusters based on emotional patterns according to claim 1 is characterized in that: The pheromone adjustment parameters in the elite strategy in step (4) are: in, represents the pheromone increment between nodes m and n caused by elite ants; T best represents the set of nodes that make up the optimal path; L best represents the path length of the optimal solution found so far; Q represents the pheromone enhancement coefficient; e represents the adjustment parameter, which is related to the length of the elite path.

9. Heterogeneous unmanned swarm collaborative task allocation and path planning system based on emotion patterns, characterized by: include: The constraint model building unit is used to establish the constraint model of heterogeneous unmanned swarm, including heterogeneous unmanned swarm range constraint, mission requirement constraint, trajectory safety constraint and payload constraint; the heterogeneous unmanned swarm range constraint is expressed as: in, Indicates drone U i From the starting point to task T i a distance; Indicates drone U i From T i a The predecessor task to task T i a Distance; L Max,i Indicates drone U i Range when fuel is exhausted; A represents the UAV i The total number of tasks assigned; The task requirement constraints of heterogeneous unmanned swarm are expressed as: Among them, x ij represents the task decision variable; N represents the total number of drones in the heterogeneous unmanned swarm; The safety constraints of the heterogeneous unmanned swarm trajectory are expressed as: ① Threat probability for radar active threat area: ② Threat probability for high mountain fixed obstacle threat areas: in, Indicates drone U i Threat Sources Threat probability; Indicates drone U i Threat Sources The distance between centers; D b Indicates the threat source Maximum threat radius; Indicates the threat source the degree of threat; Indicates drone U i The critical value of being destroyed; The load constraint of heterogeneous unmanned cluster is expressed as: in, Indicates drone U i Execute Task T i a The load resources consumed; B Max,i Indicates drone U i Total mission payload resources carried; The objective function construction unit is used to construct the objective function of the collaborative task allocation and path planning method of heterogeneous unmanned swarm based on emotion patterns, and use it as a measurement indicator of the collaborative task allocation and path planning effect; The model building unit is used to establish a mathematical model for collaborative task allocation and path planning optimization of heterogeneous unmanned swarms based on emotional patterns, taking the range, mission requirements, trajectory safety, and mission payload of the heterogeneous unmanned swarm as constraints and maximizing the net benefit of the heterogeneous unmanned swarm as the optimization goal; The model solving unit is used to adopt the ant colony algorithm, introduce the roulette wheel selection principle and the elite strategy to solve the mathematical model of collaborative task allocation and path planning optimization of heterogeneous unmanned swarm based on emotional patterns.

Images