CN112595174B - Multi-unmanned aerial vehicle tactical decision method and device in dynamic environment - Google Patents
Multi-unmanned aerial vehicle tactical decision method and device in dynamic environment Download PDFInfo
- Publication number
- CN112595174B CN112595174B CN202011356317.0A CN202011356317A CN112595174B CN 112595174 B CN112595174 B CN 112595174B CN 202011356317 A CN202011356317 A CN 202011356317A CN 112595174 B CN112595174 B CN 112595174B
- Authority
- CN
- China
- Prior art keywords
- weapon
- unmanned aerial
- aerial vehicle
- enemy
- probability
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F41—WEAPONS
- F41G—WEAPON SIGHTS; AIMING
- F41G9/00—Systems for controlling missiles or projectiles, not provided for elsewhere
- F41G9/002—Systems for controlling missiles or projectiles, not provided for elsewhere for guiding a craft to a correct firing position
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/16—Matrix or vector computation, e.g. matrix-matrix or matrix-vector multiplication, matrix factorization
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N7/00—Computing arrangements based on specific mathematical models
- G06N7/01—Probabilistic graphical models, e.g. probabilistic networks
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Mathematical Physics (AREA)
- Mathematical Optimization (AREA)
- Pure & Applied Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Computational Mathematics (AREA)
- Mathematical Analysis (AREA)
- Data Mining & Analysis (AREA)
- Computing Systems (AREA)
- Algebra (AREA)
- Software Systems (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Probability & Statistics with Applications (AREA)
- Databases & Information Systems (AREA)
- Radar Systems Or Details Thereof (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides a multi-unmanned aerial vehicle tactical decision method and a multi-unmanned aerial vehicle tactical decision device in a dynamic environment, and relates to the technical field of multi-unmanned aerial vehicle countermeasure tactical decision. Based on the weapon quantity combination probability distribution, converting the unmanned aerial vehicle performance preference into a plurality of sub-optimization targets containing the weapon quantity combination probability, designing a payment function based on the sub-optimization targets, converting uncertain information of the weapon quantity into a plurality of optimization targets, effectively representing uncertainty, and then constructing a high-dimensional matrix to solve tactical decisions.
Description
Technical Field
The invention relates to the technical field of multi-unmanned aerial vehicle tactical decision making, in particular to a multi-unmanned aerial vehicle tactical decision making method and device in a dynamic environment.
Background
In the battle environment, drones have become one of the important members of modern air combat weaponry. Because the number and the performance of weapons and sensors carried by a single unmanned aerial vehicle are limited, the capacity of executing the air combat task is correspondingly limited, and a plurality of unmanned aerial vehicles can effectively cooperate to better complete the air combat task, so that the cooperation air combat decision technology of the plurality of unmanned aerial vehicles is paid more and more attention;
the number of the residual bombs, namely the number of the weapons, is one of the most important consideration factors in the air combat decision as important weapon firepower information, and the effective judgment of the number of the residual bombs of the enemy according to the acquired information is very critical in the air combat decision.
However, under the actual combat environment, the estimation of the weapon quantity of each unmanned aerial vehicle of the opposite party by both parties of the combat is uncertain, and under different weapon quantity combinations, the performance values of the unmanned aerial vehicles are different, so that the subsequent tactical decision is influenced.
Disclosure of Invention
Technical problem to be solved
Aiming at the defects of the prior art, the invention provides a multi-unmanned aerial vehicle tactical decision method and a multi-unmanned aerial vehicle tactical decision device in a dynamic environment, and solves the problem that the weapon quantity combination estimation of an enemy unmanned aerial vehicle is inaccurate in an actual combat environment.
(II) technical scheme
In order to achieve the purpose, the invention is realized by the following technical scheme:
in a first aspect, a multi-drone tactical decision method in a dynamic environment is provided, the method including:
t1, acquiring the total strategy space of the two confrontation parties;
t2, setting an optimization target based on the performance preference of the unmanned aerial vehicle;
t3, converting the optimization target into a plurality of sub-optimization targets based on the weapon quantity combination probability, and setting a corresponding payment function based on each sub-optimization target;
t4, respectively constructing high-dimensional matrixes of the two confrontation parties for evaluating the total strategy space based on the payment function;
and T5, solving based on the high-dimensional matrixes of the two countermeasures and outputting a Nash equilibrium solution.
Further, the T3 converts the optimization target into a plurality of sub-optimization targets based on the weapon quantity combination probability, and sets a corresponding payment function based on each sub-optimization target; the method comprises the following steps:
t301, calculating the combined probability of the weapon quantity;
t302, setting selectable values and corresponding weights of unmanned aerial vehicle performance based on the weapon quantity combination probability;
t303, constructing sub-optimization targets corresponding to the selectable value number of the unmanned aerial vehicle performance;
t304, respectively constructing unmanned aerial vehicle performance advantage matrixes of the two countermeasures corresponding to each sub-optimization target;
and T305, constructing a payment function of a sub-optimization target based on the unmanned aerial vehicle performance advantage matrix.
Further, the T301, calculating the weapon quantity combination probability; the method comprises the following steps:
s1, calculating the weapon emission probability of each enemy unmanned aerial vehicle under the information fusion of multiple unmanned aerial vehicles based on the weapon emission probability of each enemy unmanned aerial vehicle acquired by each unmanned aerial vehicle of our party;
s2, dividing the weapon quantity of each unmanned aerial vehicle of the enemy into a structure in which a plurality of layers of unmanned aerial vehicle weapon quantity combinations are nested based on the quantity of the unmanned aerial vehicles of the enemy;
s3, constructing a weapon quantity combination diagram corresponding to each layer of structure based on the maximum number of enemy single unmanned aerial vehicle weapons;
s4, obtaining all current weapon quantity combinations and the stages thereof based on the weapon quantity combination graph and the weapon emission quantity; and calculating the probability distribution of the weapon number combination based on the probability distribution function.
Further, the S1 is configured to calculate, based on the enemy unmanned aerial vehicle weapon emission probabilities acquired by each unmanned aerial vehicle of our party, the probability of each unmanned aerial vehicle weapon emission of the enemy under the information fusion of multiple unmanned aerial vehicles, and includes the following steps:
s11, acquiring enemy unmanned aerial vehicle weapon emission probability acquired by each unmanned aerial vehicle of our party;
s12, assigning a prior probability of the enemy unmanned aerial vehicle to launch weapons;
s13, calculating the probability of each unmanned aerial vehicle weapon emission of the enemy based on the Bayesian classifier;
wherein the Bayesian classifier is as follows:
wherein the content of the first and second substances,indicating that the sensor collected at my partyInfer the type of enemy-fired weapon drone under the circumstances ofThe conditional probability of (a);when the ith weapon is launched, the unmanned aerial vehicle of the enemy acquires the characteristic information of the unmanned aerial vehicle t of the enemy;representing an enemy drone t;representing the prior probability of an enemy drone t firing a weapon.
Further, S2, based on the number of enemy drones, splits the weapon number of each enemy drone into a structure in which a plurality of layers of two drone weapon number combinations are nested, including the steps of:
definitions (numB) 1 ,numB 2 ,...,numB t ,...,numB T-1 ,numB T ) Representing the weapon quantity combination condition corresponding to T unmanned aerial vehicles of the enemy;
s21, splitting the weapon quantity of each unmanned aerial vehicle according to the unmanned aerial vehicle number:
when T is odd, splitting into:
(numB 1 ,(numB 2 ,...,(numB (T+1)/2 ),...,numB T-1 ),numB T );
when T is an even number, splitting into:
(numB 1 ,(numB 2 ,...,(numB T/2 ,numB (T/2)+1 ),...,numB T-1 ),numB T );
s22, sequentially splitting the weapon quantity of each unmanned aerial vehicle into two-two combined parts according to the sequence from outside to inside { (numB) 1 ,numB T ),(numB 2 ,numB T-1 ) ,.., and all combinations of adjacent two layers, the next layer containing the previous layer, are possible.
Further, the step S3 of constructing a combined diagram of the weapon quantity corresponding to each layer structure based on the maximum number of weapons of the enemy single drone includes the steps of:
s31, constructing selectable values of the weapon quantity combination of two enemy unmanned aerial vehicles when different weapon emission quantities of each layer of structure are transmitted based on the maximum carrying quantity K of enemy unmanned aerial vehicle weapons, and using the selectable values as a weapon quantity combination diagram;
s32, recording the firing number of the weapons as a first stage when the firing number of the weapons is not more than K, and recording the firing number of the weapons as a second stage when the firing number of the weapons is more than K;
and S33, combining the weapon numbers introduced by the two arrows, marking the combined weapon numbers as the combined weapon number with fusion, and representing the result of probability superposition of the weapons of each unmanned aerial vehicle of the two enemies.
Further, the step S4, obtaining all current combinations of the weapon quantity and the corresponding stages based on the weapon quantity combination map and the weapon firing quantity; calculating the probability distribution of the weapon quantity combination based on the probability distribution function, comprising the following steps:
s41, obtaining selectable values of all current weapon quantity combinations from the corresponding weapon quantity combination diagram based on the weapon emission quantity, numbering from 0 in sequence, marking as {0, 1, … …, Nk, … …, Nk }, and determining the stages to which the weapon quantity combinations belong;
s42, calculating the probability of each weapon quantity combination by using a weapon quantity combination probability distribution function based on the probability distribution of the weapon quantity combination when the previous weapon is launched, wherein the probability marked as the existence of the fused weapon quantity combination is the sum of two probability values; in this layer, the weapon quantity of two unmanned aerial vehicles is:
numB1=K-i+nk-τ(K-i)
numB2=K-nk+τ(K-i)
nk=0,1,...,Nk
Nk=i+2τ(K-i)
wherein numB1 represents the weapon quantity of one of the drones in each layer structure, numB2 represents the weapon quantity of the other drone in each layer structure, Nk represents the number of the weapon quantity combination, Nk represents the number of the selectable values of the current weapon quantity combination, i represents the weapon firing quantity, K represents the maximum carrying quantity of enemy drone weapon, and τ is 0 in the first stage and τ is 1 in the second stage;
the weapon quantity combination probability distribution function is:
when i is 2, 3, … …, 2K:
representing the probability of the combination of the number of the nth weapon when the ith weapon is fired and the number of the nth weapon,indicating the launch by the enemy drone 1Probability of i weapons;and so on;
and S43, repeating the steps S41-S42, calculating the combined probability of the weapon quantity corresponding to each layer, combining the probabilities of the weapon quantity combinations of two adjacent layers again, and finally obtaining the probability of the weapon quantity combinations of all the unmanned aerial vehicles of the enemy.
Further, the number of the performance advantage matrix of the unmanned aerial vehicle is the combined number of the weapons of my party and the combined number of the weapons of the enemy party;
and the weight of the drone performance dominance matrix is the weight of the drone performance preference by the weapon number combined probability.
In a second aspect, a multi-drone tactics decision-making device in a dynamic environment is provided, which includes:
one or more processors;
a memory; and
one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, the programs comprising instructions for performing the method of:
t1, acquiring the total strategy space of the two confrontation parties;
t2, setting an optimization target based on the performance preference of the unmanned aerial vehicle;
t3, converting the optimization target into a plurality of sub-optimization targets based on the weapon quantity combination probability, and setting a corresponding payment function based on each sub-optimization target;
t4, respectively constructing high-dimensional matrixes of the two counterside parties for evaluating the total strategy space based on the payment function;
and T5, solving based on the high-dimensional matrixes of the two countermeasures and outputting a Nash equilibrium solution.
Further, the T3 converts the optimization target into a plurality of sub-optimization targets based on the weapon quantity combination probability, and sets a corresponding payment function based on each sub-optimization target; the method comprises the following steps:
t301, calculating the combined probability of the weapon quantity;
t302, setting selectable values and corresponding weights of unmanned aerial vehicle performance based on the weapon quantity combination probability;
t303, constructing sub-optimization targets corresponding to the selectable value number of the unmanned aerial vehicle performance;
t304, respectively constructing unmanned aerial vehicle performance advantage matrixes of the two countermeasures corresponding to each sub-optimization target;
and T305, constructing a payment function of a sub-optimization target based on the unmanned aerial vehicle performance advantage matrix.
Further, T301, calculating a weapon quantity combination probability; the method comprises the following steps:
s1, calculating the weapon emission probability of each enemy unmanned aerial vehicle under the information fusion of multiple unmanned aerial vehicles based on the weapon emission probability of each enemy unmanned aerial vehicle acquired by each unmanned aerial vehicle of our party;
s2, based on the number of the enemy unmanned aerial vehicles, dividing the weapon number of each enemy unmanned aerial vehicle into a structure in which a plurality of layers of weapon numbers of two unmanned aerial vehicles are nested;
s3, constructing a weapon quantity combination diagram corresponding to each layer of structure based on the maximum number of the enemy single unmanned aerial vehicle weapons;
s4, obtaining all current weapon quantity combinations and the stages thereof based on the weapon quantity combination graph and the weapon emission quantity; and calculating the probability distribution of the weapon number combination based on the probability distribution function.
Further, the S1 is configured to calculate, based on the enemy unmanned aerial vehicle weapon emission probabilities acquired by each unmanned aerial vehicle of our party, the probability of each unmanned aerial vehicle weapon emission of the enemy under the information fusion of multiple unmanned aerial vehicles, and includes the following steps:
s11, acquiring enemy unmanned aerial vehicle weapon emission probability acquired by each unmanned aerial vehicle of our party;
s12, assigning a prior probability of an enemy unmanned aerial vehicle launching weapon;
s13, calculating the probability of each unmanned aerial vehicle weapon emission of the enemy based on the Bayesian classifier;
wherein the Bayesian classifier is as follows:
wherein the content of the first and second substances,indicating that the sensor collected at my partyInfer the class of enemy-fired weapons droneThe conditional probability of (a);when the ith weapon is launched, the unmanned aerial vehicle s of the own party obtains the characteristic information of the unmanned aerial vehicle t of the enemy party;representing an enemy drone t;representing a prior probability of an enemy drone t firing a weapon.
Further, S2, based on the number of enemy drones, splits the weapon number of each enemy drone into a structure in which a plurality of layers of two drone weapon number combinations are nested, including the steps of:
definitions (numB) 1 ,numB 2 ,...,numB t ,...,numB T-1 ,numB T ) Representing the weapon quantity combination condition corresponding to T unmanned aerial vehicles of the enemy;
s21, splitting the weapon quantity of each unmanned aerial vehicle according to the unmanned aerial vehicle number:
when T is odd, splitting into:
(numB 1 ,(numB 2 ,...,(numB (T+1)/2 ),...,numB T-1 ),numB T );
when T is an even number, splitting into:
(numB 1 ,(numB 2 ,...,(numB T/2 ,numB (T/2)+1 ),...,numB T-1 ),numB T );
s22, sequentially dividing the weapon quantity of each unmanned aerial vehicle into two-two combination (numB) according to the sequence from outside to inside 1 ,numB T ),(numB 2 ,numB T-1 ) ,.., and the next layer of two adjacent layers contains all possible combinations of the previous layer.
Further, the step S3 of constructing a combined diagram of the weapon quantity corresponding to each layer structure based on the maximum number of weapons of the enemy single drone includes the steps of:
s31, constructing selectable values of the weapon quantity combination of two enemy unmanned aerial vehicles when different weapon emission quantities of each layer of structure are transmitted based on the maximum carrying quantity K of enemy unmanned aerial vehicle weapons, and using the selectable values as a weapon quantity combination diagram;
s32, recording the firing number of the weapons as a first stage when the firing number of the weapons is not more than K, and recording the firing number of the weapons as a second stage when the firing number of the weapons is more than K;
and S33, combining the weapon quantity introduced by the two arrows, marking the combination as the combination with fused weapon quantity, and representing the result of superposition of probabilities of the two enemy unmanned aerial vehicle weapons.
Further, S4, based on the combined diagram of the weapon quantity and the weapon firing quantity, obtaining all current weapon quantity combinations and the stages to which the combinations belong; calculating the probability distribution of the weapon number combination based on the probability distribution function, comprising the following steps:
s41, obtaining selectable values of all current weapon quantity combinations from the corresponding weapon quantity combination diagram based on the weapon emission quantity, numbering from 0 in sequence, marking as {0, 1, … …, Nk, … …, Nk }, and determining the stages to which the weapon quantity combinations belong;
s42, calculating the probability of each weapon quantity combination by using a weapon quantity combination probability distribution function based on the probability distribution of the weapon quantity combination when the previous weapon is launched, wherein the probability marked as the existence of the fused weapon quantity combination is the sum of two probability values; in this layer, the weapon quantity of two unmanned aerial vehicles is:
numB1=K-i+nk-τ(K-i)
numB2=K-nk+τ(K-i)
nk=0,1,...,Nk
Nk=i+2τ(K-i)
wherein numB1 represents the weapon quantity of one of the drones in each layer structure, numB2 represents the weapon quantity of the other drone in each layer structure, Nk represents the number of the weapon quantity combination, Nk represents the number of the selectable values of the current weapon quantity combination, i represents the weapon firing quantity, K represents the maximum carrying quantity of enemy drone weapon, and τ is 0 in the first stage and τ is 1 in the second stage;
the weapon quantity combination probability distribution function is:
when i is 2, 3, … …, 2K:
representing the probability of the combination of the number of the nth weapon when the ith weapon is fired and the number of the nth weapon,represents the probability of the ith weapon being fired by the enemy drone 1;and so on;
and S43, repeating the steps S41-S42, calculating the combined probability of the weapon quantity corresponding to each layer, combining the probabilities of the weapon quantity combinations of two adjacent layers again, and finally obtaining the probability of the weapon quantity combinations of all the unmanned aerial vehicles of the enemy.
Further, the number of the unmanned aerial vehicle performance advantage matrix is my weapon number combination number and enemy weapon number combination number;
and the weight of the drone performance dominance matrix is the weight of the drone performance preference as the weapon number combined probability.
(III) advantageous effects
The invention provides a tactical decision method and a tactical decision device for multiple unmanned aerial vehicles in a dynamic environment. Compared with the prior art, the method has the following beneficial effects:
the method is based on the weapon quantity combination probability distribution, the unmanned aerial vehicle performance preference is converted into a plurality of sub-optimization targets containing the weapon quantity combination probability, a payment function is designed based on the sub-optimization targets, uncertain information of the weapon quantity is converted into a plurality of optimization targets, the uncertainty is effectively represented, and then a high-dimensional matrix is constructed to solve tactical decisions.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
FIG. 1 is a flow chart of an embodiment of the present invention;
FIG. 2 is a flow chart of the present invention for constructing a payment function;
FIG. 3 is a flow chart of the present invention for calculating combined probability of weapon quantity;
FIG. 4 is a schematic diagram of a weapon quantity combination chart according to the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention are clearly and completely described, and it is obvious that the described embodiments are a part of the embodiments of the present invention, but not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The embodiment of the application provides a multi-unmanned aerial vehicle tactical decision method and device in a dynamic environment, and solves the problem that the weapon quantity combination estimation of an enemy unmanned aerial vehicle is inaccurate in an actual combat environment, so that a tactical decision can be obtained through solving.
In order to solve the technical problems, the general idea of the embodiment of the application is as follows: the uncertain information of the weapon quantity is converted into a plurality of optimization targets, the uncertainty is effectively represented, and subsequent tactical decision solving is facilitated.
In order to better understand the technical solution, the technical solution will be described in detail with reference to the drawings and the specific embodiments.
Example 1:
as shown in fig. 1, the present invention provides a multi-drone tactical decision method in a dynamic environment, which is executed by a computer, and comprises: T1-T5;
t1, acquiring the total strategy space of the two confrontation parties;
t2, setting an optimization target based on the performance preference of the unmanned aerial vehicle;
t3, converting the optimization target into a plurality of sub-optimization targets based on the weapon quantity combination probability, and setting a corresponding payment function based on each sub-optimization target;
t4, respectively constructing high-dimensional matrixes of the two confrontation parties for evaluating the total strategy space based on the payment function;
and T5, solving based on the high-dimensional matrixes of the two countermeasures and outputting a Nash equilibrium solution.
The beneficial effect of this embodiment does:
based on the weapon quantity combination probability distribution, converting the unmanned aerial vehicle performance preference into a plurality of sub-optimization targets containing the weapon quantity combination probability, designing a payment function based on the sub-optimization targets, converting uncertain information of the weapon quantity into a plurality of optimization targets, effectively representing uncertainty, and then constructing a high-dimensional matrix to solve tactical decisions.
The present embodiment is described in detail below:
t1, acquiring the total strategy space of the two confrontation parties;
the policy space of my party is X ═ X 1 ,...,x i ,...,x m The policy space of the enemy is marked as Y ═ Y 1 ,...,y j ,...,y n And f, recording the total strategy space of the two countermeasures as O ═ X × Y.
When the number of the selectable strategies and the number of the unmanned aerial vehicles of both countermeasures are smaller than a certain threshold, the target allocation scheme can be merged into the total strategy space, and the method specifically comprises the following steps:
acquiring optional strategies of the two confrontation parties, and acquiring an optional target distribution scheme based on the number of the unmanned aerial vehicles of the two confrontation parties;
calculating all optional strategy-optional target distribution scheme combinations of the two confrontation parties respectively, wherein each optional strategy-optional target distribution scheme combination is used as one strategy to obtain respective strategy spaces of the two confrontation parties; the policy space of my party is denoted as X ═ X 1 ,…,x i ,...,x m The policy space of the enemy is marked as Y ═ Y 1 ,...,y j ,...,y n }。
And acquiring the combination of all strategies of the two countermeasures based on the strategy spaces of the two countermeasures to construct a total strategy space.
For example, the following steps are carried out: and the red party is marked as R by my party, and the blue party is marked as B by the enemy party.
For example, if there are 5 policies that my party may select, such as attack type, attack and defense combined type, impersonation type, and escape type, and the number of drones is 1v2, and the target allocation scheme of my party is 2, then the policy space of my party may be represented as: x ═ X 1 ,x 2 ,...,x 10 -wherein the number m of policy-target allocation scheme combinations of my party is 10; there are 3 enemy policies, and the target allocation scheme is only 1, then the enemy policy space can be expressed as: y ═ Y 1 ,y 2 ,y 3 Where the number of policy-target allocation scheme combinations for the adversary n is 3. The total policy space can be expressed as O ═ X × Y, with a total of 30 policy pairs. Each policy pair is a combination of policies against both parties, which can be denoted as (x) i ,y j )。
T2, setting an optimization target based on the performance preference of the unmanned aerial vehicle;
the unmanned aerial vehicle performance calculation formula is as follows:
C=[ln B+ln(∑A 1 +1)+ln(∑A 2 )]ε 1 ε 2 ε 3 ε 4
wherein: c denotes the index of unmanned aerial vehicle performance, B denotes the mobility parameter, A 1 Denotes the parameter of fire, A 2 Representing a parameter of radar detection capability, epsilon 1 Represents the steering efficiency coefficient, ε 2 Denotes the coefficient of viability, ∈ 3 Representing the course coefficient, epsilon 4 Represents an electron-countermeasure capability coefficient;
take missile as an example, and the firepower parameter A 1 The method is determined by parameters of a maximum actual effective range Dmax, an allowable launching total height difference Hd, a single-shot killing probability Pk, a launching envelope total attack angle At, a missile maximum overload OLmax, a missile maximum tracking angular velocity Va, a total off-axis launching angle Az and the mounting number n of similar missiles. The specific calculation formula is as follows:
however, under an actual operation environment, the estimation of the weapon quantity (here, the carrying quantity of the similar missiles) of each unmanned aerial vehicle of the opposite party by both parties of the operation is uncertain, and under different missile quantity combinations, the performance values of the unmanned aerial vehicles are different, so that the accuracy of the performance of the unmanned aerial vehicles is influenced.
And T3, converting the optimization target into a plurality of sub-optimization targets based on the weapon quantity combination probability, and setting a corresponding payment function based on each sub-optimization target. The method specifically comprises the following steps as shown in figure 2: t301 to T305;
t301, calculating the combined probability of the weapon quantity;
as shown in fig. 3, including S1-S4;
s1, calculating the weapon emission probability of each enemy unmanned aerial vehicle under the information fusion of multiple unmanned aerial vehicles based on the enemy unmanned aerial vehicle weapon emission probability acquired by each unmanned aerial vehicle of the same party;
in the existing method, a weapon source is generally judged by adopting a sensor of a single unmanned aerial vehicle of one party, for example, the number of unmanned aerial vehicles of two confronters is 2v2, and characteristic information acquired by each unmanned aerial vehicle of one party is respectivelyHowever, in a scenario with multiple drones, the method for single drone weapon sources is not accurate enough and depends on the performance of the sensor. Therefore, information of multiple unmanned aerial vehicles needs to be fused to obtain the probability of weapon emission of each unmanned aerial vehicle of an enemy; the method comprises the following specific steps: S11-S13;
s11, acquiring enemy unmanned aerial vehicle weapon emission probability acquired by each unmanned aerial vehicle of our party;
s12, assigning a prior probability of an enemy unmanned aerial vehicle launching weapon;
and S13, calculating the probability of the weapon emission of each unmanned aerial vehicle of the enemy based on the Bayesian classifier.
Wherein the Bayesian classifier:
wherein the content of the first and second substances,indicating that the sensor collected at my partyInfer the class of enemy-fired weapons droneThe conditional probability of (a);when the ith weapon is launched, the unmanned aerial vehicle of the enemy acquires the characteristic information of the unmanned aerial vehicle t of the enemy;representing an enemy drone t;representing the prior probability of an enemy drone t firing a weapon.
The following describes the step S1 with the example of the number of opposing drones 2v 2:
the maximum weapon carrying capacity of the unmanned aerial vehicle is 4, and according to the weapon quantity combination diagram, after 3 weapons are fired, the weapon quantity combination situations of two enemy unmanned aerial vehicles can be 1+4, 2+3, 3+2 and 4+1, and the probability distribution is 16%, 41%, 34% and 9%.
Then at the time of firing the 4 th weapon:
the probability that the sensor of my drone 1 detects the firing of a weapon by the enemy drone 1 is
The probability that the sensor of my drone 2 detects the firing of a weapon by the enemy drone 1 is
The probability that the sensor of my drone 1 detects the firing of a weapon by the enemy drone 2 is
The probability that the sensor of my drone 2 detects the weapon being fired by the enemy drone 2 is
However, because the battlefield environment has the characteristic of uncertain depth, two unmanned aerial vehicles of the opposite side in air battle are difficult to obtain in a test or statistical mannerPrior probability to firing weaponIt is therefore desirable to assign a priori probabilities based on current battlefield conditions.
An expert experience based method is given below for assigning the prior probabilities:
the probability distribution of two unmanned aerial vehicle weapon combinations of enemy 1+4, 2+3, 3+2, 4+1 is 16%, 41%, 34%, 9%, it is obvious that enemy unmanned aerial vehicle 1 may possess the weapon quantity less than unmanned aerial vehicle 2, unmanned aerial vehicle 1 may only have 1 ~ 2 weapons, last 1 ~ 2 must be fired with care, so the prior probability that unmanned aerial vehicle 1 fires the weapon is less than the prior probability that unmanned aerial vehicle 2 fires the weapon, consequently can set for the prior probability respectively for the prior probability
After assignment, calculating posterior probability through a Bayesian classifier:
so far, the probability that the 4 th weapon is emitted by the enemy unmanned aerial vehicle 1 is obtainedThe probability of being transmitted by the enemy drone 2 is
S2, dividing the weapon quantity of each unmanned aerial vehicle of the enemy into a structure in which the weapon quantity of two unmanned aerial vehicles is combined and embedded in multiple layers based on the quantity of the unmanned aerial vehicles of the enemy.
The method specifically comprises the following steps: S21-S22;
definitions (numB) 1 ,numB 2 ,...,numB t ,...,numB T-1 ,numB T ) Representing the weapon quantity combination condition corresponding to T unmanned aerial vehicles of the enemy;
s21, splitting the weapon quantity of each unmanned aerial vehicle according to the unmanned aerial vehicle number:
when T is odd, splitting into:
(numB 1 ,(numB 2 ,...,(numB (T+1)/2 ),...,numB T-1 ),numB T );
when T is an even number, splitting into:
(numB 1 ,(numB 2 ,...,(numB T/2 ,numB (T/2)+1 ),...,numB T-1 ),numB T );
s22, sequentially dividing the weapon quantity of each unmanned aerial vehicle into two-two combination (numB) according to the sequence from outside to inside 1 ,numB T ),(numB 2 ,numB T-1 ) ,.., and the next layer of two adjacent layers contains all possible combinations of the previous layer.
The step of S2 will be described by taking 4 drones as an example:
the combined weapon quantity of 4 drones on the enemy can be expressed as (numB) 1 ,numB 2 ,numB 3 ,numB 4 );
T4 is an even number, so split is (numB) 1 ,(numB 2 ,numB 3 ),numB 4 );
The split structure is divided into two combinations as required, and is a first layer structure: (numB) 1 ,numB 4 ) And a second layer structure: (numB) 2 ,numB 3 ) And the first layer includes all possibilities of the second layer.
S3, constructing a weapon quantity combination diagram corresponding to each layer of structure based on the maximum number of enemy single unmanned aerial vehicle weapons, and comprising the following steps: S31-S33;
s31, constructing selectable values of the weapon quantity combination of two enemy unmanned aerial vehicles when different weapon emission quantities of each layer of structure are transmitted based on the maximum carrying quantity K of enemy unmanned aerial vehicle weapons, and using the selectable values as a weapon quantity combination diagram;
s32, recording the firing number of the weapons as a first stage when the firing number of the weapons is not more than K, and recording the firing number of the weapons as a second stage when the firing number of the weapons is more than K;
and S33, combining the weapon quantity introduced by the two arrows, marking the combination as the combination with fused weapon quantity, and representing the result of superposition of probabilities of the two enemy unmanned aerial vehicle weapons.
Next, the step S3 is explained as an example in S2:
assuming a single drone maximum weapon count of 4, for the first layer (numB) 1 ,numB 4 ) And constructing a combined diagram of the weapon quantity, as shown in FIG. 4; according to the condition that the enemy launches the weapons, the enemy recurs from top to bottom in sequence along the direction of the arrow on the right side, the possible types of weapon number combinations of the enemy tend to increase first and then decrease, and when the total number of the two unmanned aerial vehicles on the other side is 4, the maximum number of the weapon number combinations is 5. When the number i of the weapon shots is less than or equal to 4, the first stage is performed, and when the number i of the weapon shots is more than 4, the second stage is performed.
The box with two arrows indicates that the combination of the weapon numbers has a fusion. For example, an enemy only launches 1 weapon at present, the number combinations of the weapons of the enemy unmanned aerial vehicles 1 and 4 are respectively 3+4 and 4+3, the probabilities of the weapons are respectively 90% and 10%, the probability of launching the weapon of the enemy unmanned aerial vehicle 1 is comprehensively judged to be 80% according to sensor and information, and the distribution probabilities of the 2+4 combination and the 3+3 combination are 72% and 8% by utilizing rule reasoning; on the other hand, the probability of the enemy unmanned aerial vehicle 4 launching the weapon is 20%, the distribution probabilities of the 3+3 and 4+2 combinations are respectively 18% and 2% by inference, the combined result is comprehensively analyzed, the probabilities of the 3+3 combination conditions are fused, and the distribution probabilities of the weapon combinations 2+4, 3+3 and 4+2 are respectively 72%, 26% and 2%.
S4, obtaining all current weapon quantity combinations and the stages thereof based on the weapon quantity combination graph and the weapon emission quantity; calculating the probability distribution of the weapon number combination based on the probability distribution function, comprising the following steps: S41-S43;
s41, obtaining selectable values of all current weapon quantity combinations from the corresponding weapon quantity combination diagram based on the weapon emission quantity, numbering from 0 in sequence, marking as {0, 1, … …, Nk, … …, Nk }, and determining the stages to which the weapon quantity combinations belong;
s42, calculating the probability of each weapon quantity combination by using a weapon quantity combination probability distribution function based on the probability distribution of the weapon quantity combination when the previous weapon is launched, wherein the probability marked as the existence of the fused weapon quantity combination is the sum of two probability values;
the weapon counts for both drones are:
numB1=K-i+nk-τ(K-i)
numB2=K-nk+τ(K-i)
nk=0,1,...,Nk
Nk=i+2τ(K-i)
wherein numB1 represents the weapon quantity of one of the enemy drones in each layer structure, numB2 represents the weapon quantity of the other enemy drone, Nk represents the serial number of the weapon quantity combination, Nk represents the quantity of selectable values of the current weapon quantity combination, i represents the weapon emission quantity, K represents the maximum carrying quantity of the enemy drone weapon, and τ is 0 in the first stage and 1 in the second stage;
the weapon quantity combination probability distribution function is:
when i is 2, 3, … …, 2K:
indicating the combination of the number of the nth weapon when the ith weapon is firedThe probability of (a) of (b) being,representing the probability of the ith weapon being fired by the enemy drone 1;and so on.
And S43, repeating the steps of S41-S42, calculating the combined probability of the weapon quantity corresponding to each layer, and combining the probabilities of the weapon quantity combinations of two adjacent layers again to finally obtain the probability of the weapon quantity combinations of all the unmanned aerial vehicles of the enemy.
Next, the step S4 is explained as an example in S3:
the current weapon quantity combination of the estimated enemy of our party is 1+4, 2+3, 3+2 and 4+1, the probability distribution is 16%, 41%, 34% and 9%, 3 weapons are launched, and the probability of the weapon quantity combination is calculated beforeP 1 3 =41%,When the 4 th weapon is fired, the weapon number combination may be 0+4, 1+3, 2+2, 3+1, 4+0, and the weapon number combination is marked as 0, 1, 2, 3, 4 in sequence; in the first stage, τ is 0; through calculation of the weapon source by the Bayes classifier, the probability that the weapon is emitted by the enemy unmanned aerial vehicle 1 can be obtainedThe probability of being transmitted by the enemy drone 4 is
Thus, the weapon counts of two drones are respectively:
numB1=K-i+nk=4-4+nk=nk
numB2=K-nk=4-nk
Nk=i=4
selecting a corresponding weapon quantity combination probability distribution function as:
substituting into the formula, the probability of each weapon quantity combination can be calculated:
therefore, the probability distributions of 0+4, 1+3, 2+2, 3+1, 4+0 are, in order: 1.37%, 18.14%, 40.4%, 31.86% and 8.23%. This completes the calculation of the probability distribution of the combinations of the numbers of weapons of the first layer.
Same as the first layer calculation method, recalculate (numB) 2 ,numB 3 ) Probability distribution of corresponding combinations of weapon numbers.
Then (numB) 1 ,numB 4 ) And (numB) 2 ,numB 3 ) The results are recombined.
To illustrate, a handle (numB) 1 ,numB 4 ) Combined result of (1)And (numB) 2 ,numB 3 ) Combined result of (1)The combination is performed again.
The combination rule is as follows:
i(B 1 ,B 2 ,B 3 ,B 4 )=i(B 1 ,B 4 )+i(B 2 ,B 3 )
for example: when estimating the firing of the 4 th weapon, there may be several situations:
the first method comprises the following steps: b is 1 And B 4 Transmit 4 pieces in total, and B 2 And B 3 And (3) transmitting 0 pieces in total:
and the second method comprises the following steps: b is 1 And B 4 Transmit 3 pieces in total, and B 2 And B 3 Transmitting 1 piece in total:
and the third is that: b is 1 And B 4 Transmit 2 pieces in total, and B 2 And B 3 2 pieces of data are transmitted in total:
and fourthly: b is 1 And B 4 Transmit 1 bit in total, and B 2 And B 3 3 pieces of light are transmitted in total:
and a fifth mode: b 1 And B 4 Transmit 0 in total, and B 2 And B 3 Totally transmitting 4 pieces:
wherein i (B) 1 ,B 2 ,B 3 ,B 4 ) Representing the combination of the weapon numbers of 4 drones, i (B), when the ith weapon is fired 1 ,B 4 ) Is represented by B 1 And B 4 The number of weapons fired; i (B) 2 ,B 3 ) Is represented by B 2 And B 3 The number of weapons fired.
T302, setting selectable values and corresponding weights of unmanned aerial vehicle performance C based on the weapon quantity combination probability;
t303, constructing sub-optimization targets corresponding to the number of selectable values of the unmanned aerial vehicle performance value C;
t304, respectively constructing unmanned aerial vehicle performance advantage matrixes Ep of the two countersides corresponding to each sub-optimization target G,l G is the { R, B }, and comprises a performance advantage matrix Ep of the unmanned aerial vehicle of the party R,l And enemy unmanned aerial vehicle performance advantage matrix Ep B,l ;
The number of selectable values of the unmanned aerial vehicle performance value C is equal to the number of unmanned aerial vehicle performance advantage matrixes, i.e. the combined number of my weapon number and the combined number of enemy weapon number;
and the weight of the drone performance dominance matrix is the weight of the drone performance preference as the weapon number combined probability.
Taking the scene that the number of unmanned aerial vehicles of my party is 1 and the number of unmanned aerial vehicles of enemy party is 2 as an example, because two unmanned aerial vehicles of enemy parties need to be considered when my party attacks, the performance advantage matrix Ep of the unmanned aerial vehicle of my party corresponding to the ith sub-optimization target R,l Comprises the following steps:
wherein the content of the first and second substances,an unmanned aerial vehicle performance advantage matrix representing the relative unmanned aerial vehicle performance advantage matrix of the unmanned aerial vehicle 1 of the my party to the unmanned aerial vehicle 2 of the enemy party;the strategy representing the two confrontation parties is x i =p,y j When q, my drone 1 has a drone performance advantage matrix relative to the enemy drone 2.
Similarly, only 1 unmanned aerial vehicle on one party is considered during attack by the enemy, so that the performance advantage matrix Ep of the enemy unmanned aerial vehicle corresponding to the ith sub-optimization target B,l Comprises the following steps:
t305, constructing a payment function of each sub-optimization target based on the unmanned aerial vehicle performance advantage matrix;
the number of the payment functions is related to the number of the unmanned aerial vehicle performance advantage matrixes, and essentially is A 1 A number of selectable values of (d);
taking the scene that the number of unmanned aerial vehicles of the same party is 1 and the number of unmanned aerial vehicles of the enemy is 2 as an example, and taking the ith sub-optimization target of the same party as an example, two design modes of payment functions are given:
the first method comprises the following steps:
the construction method of the payment function can directly reflect the performance preference of the unmanned aerial vehicle, and is simple in calculation.
And the second method comprises the following steps:
the construction method of the payment function reflects the performance preference of the unmanned aerial vehicle by adopting the relative value of the performance advantages of the unmanned aerial vehicle, and is a result of the combined action of the performance advantages of the unmanned aerial vehicles of both parties.
T4, respectively constructing high-dimensional matrixes of the two counterside parties for evaluating the total strategy space based on the payment function;
the high-dimensional matrix of the two confrontation parties is:
wherein (x) i ,y j ) A policy pair, x, representing both parties of the countermeasure i Denotes my policy, y j To indicate the policy of the enemy,a payment function representing an optimization objective for the drone performance preference,a payment function corresponding to the first sub-optimization target of the optimization target corresponding to the performance preference of the unmanned aerial vehicle is represented; g denotes opposing parties, R denotes my party, and B denotes an enemy party.
And T5, solving based on the high-dimensional matrixes of the two countermeasures and outputting a Nash equilibrium solution.
The high-dimensional matrix can be solved by adopting the existing solving algorithm, for example, the multi-target mixed strategy Nash equilibrium solving algorithm is utilized, and the mixed strategy Nash equilibrium solution is output.
Example 2
A multi-drone tactical decision making apparatus in a dynamic environment, comprising:
one or more processors;
a memory; and
one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, the programs comprising instructions for performing the method of:
t1, acquiring the total strategy space of the two confrontation parties;
t2, setting an optimization target based on the performance preference of the unmanned aerial vehicle;
t3, converting the optimization target into a plurality of sub-optimization targets based on the weapon quantity combination probability, and setting a corresponding payment function based on each sub-optimization target;
t4, respectively constructing high-dimensional matrixes of the two confrontation parties for evaluating the total strategy space based on the payment function;
and T5, solving based on the high-dimensional matrixes of the two countermeasures and outputting a Nash equilibrium solution.
It can be understood that the multi-unmanned aerial vehicle tactical decision making apparatus in the dynamic environment provided by the embodiment of the present invention corresponds to the multi-unmanned aerial vehicle tactical decision making method in the dynamic environment, and the explanation, exemplification, beneficial effects and other parts of the relevant contents can refer to the corresponding contents in the multi-unmanned aerial vehicle collaborative decision making method for the uncertain events, and are not described herein again.
In summary, compared with the prior art, the invention has the following beneficial effects:
firstly, based on weapon quantity combination probability distribution, converting unmanned aerial vehicle performance preference into a plurality of sub-optimization targets containing weapon quantity combination probability, designing a payment function based on the sub-optimization targets, converting uncertain information of the weapon quantity into a plurality of optimization targets, effectively representing uncertainty, and then constructing a high-dimensional matrix to solve tactical decision.
It should be noted that, through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by software plus a necessary general hardware platform. With this understanding in mind, the above-described technical solutions may be embodied in the form of a software product, which can be stored in a computer-readable storage medium such as ROM/RAM, magnetic disk, optical disk, etc., and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the methods described in the embodiments or some parts of the embodiments. In this document, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.
The above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it should be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Claims (3)
1. A tactical decision method for multiple unmanned aerial vehicles in a dynamic environment is characterized by comprising the following steps:
t1, acquiring the total strategy space of the two confrontation parties;
t2, setting an optimization target based on the performance preference of the unmanned aerial vehicle;
t3, converting the optimization target into a plurality of sub-optimization targets based on the weapon quantity combination probability, and setting a corresponding payment function based on each sub-optimization target;
t4, respectively constructing high-dimensional matrixes of the two confrontation parties for evaluating the total strategy space based on the payment function;
t5, solving based on the high-dimensional matrixes of the two countermeasures, and outputting a Nash equilibrium solution;
the T3 converts the optimization target into a plurality of sub optimization targets based on the weapon quantity combination probability, and sets a corresponding payment function based on each sub optimization target; the method comprises the following steps:
t301, calculating the combined probability of the weapon quantity;
t302, setting selectable values and corresponding weights of unmanned aerial vehicle performance based on the weapon quantity combination probability;
t303, constructing sub-optimization targets corresponding to the selectable value number of the unmanned aerial vehicle performance;
t304, respectively constructing unmanned aerial vehicle performance advantage matrixes of the two countermeasures corresponding to each sub-optimization target;
t305, constructing a payment function of a sub-optimization target based on the unmanned aerial vehicle performance advantage matrix;
the T301, calculating the combined probability of the weapon quantity; the method comprises the following steps:
s1, calculating the weapon emission probability of each enemy unmanned aerial vehicle under the information fusion of multiple unmanned aerial vehicles based on the enemy unmanned aerial vehicle weapon emission probability acquired by each unmanned aerial vehicle of the same party;
s2, dividing the weapon quantity of each unmanned aerial vehicle of the enemy into a structure in which a plurality of layers of unmanned aerial vehicle weapon quantity combinations are nested based on the quantity of the unmanned aerial vehicles of the enemy;
s3, constructing a weapon quantity combination diagram corresponding to each layer of structure based on the maximum number of enemy single unmanned aerial vehicle weapons;
s4, obtaining all current weapon quantity combinations and the stages thereof based on the weapon quantity combination graph and the weapon emission quantity; calculating probability distribution of the weapon quantity combination based on the probability distribution function;
s1, calculating the probability of weapon emission of each enemy unmanned aerial vehicle under the information fusion of multiple unmanned aerial vehicles based on the enemy unmanned aerial vehicle weapon emission probability acquired by each unmanned aerial vehicle of our party, comprising the following steps:
s11, acquiring enemy unmanned aerial vehicle weapon emission probability acquired by each unmanned aerial vehicle of our party;
s12, assigning a prior probability of an enemy unmanned aerial vehicle launching weapon;
s13, calculating the probability of each unmanned aerial vehicle weapon emission of the enemy based on the Bayesian classifier;
wherein, the Bayesian classifier is as follows:
wherein the content of the first and second substances,indicating that the sensor collected at my partyInfer the class of enemy-fired weapons droneThe conditional probability of (a);when the ith weapon is launched, the unmanned aerial vehicle of the enemy acquires the characteristic information of the unmanned aerial vehicle t of the enemy;a category representing enemy-fired weapon drones;representing a prior probability of an enemy drone t firing a weapon;
s2, based on the number of enemy unmanned aerial vehicles, the method splits the weapon number of each enemy unmanned aerial vehicle into a structure in which the weapon numbers of two unmanned aerial vehicles are combined in a multi-layer embedded manner, and comprises the following steps:
definition (numB) 1 ,numB 2 ,...,numB t ,...,numB T-1 ,numB T ) Representing the weapon quantity combination condition corresponding to T unmanned aerial vehicles of the enemy;
s21, splitting the weapon quantity of each unmanned aerial vehicle according to the unmanned aerial vehicle number:
when T is odd, splitting into:
(numB 1 ,(numB 2 ,...,(numB (T+1)/2 ),...,numB T-1 ),numB T );
when T is an even number, splitting into:
(numB 1 ,(numB 2 ,...,(numB T/2 ,numB (T/2)+1 ),...,numB T-1 ),numB T );
s22, sequentially splitting the weapon quantity of each unmanned aerial vehicle into two-two combined parts according to the sequence from outside to inside { (numB) 1 ,numB T ),(numB 2 ,numB T-1 ) ,.., and of two adjacent layers, the next layer contains all possible combinations of the previous layer;
s3, constructing a weapon quantity combination diagram corresponding to each layer of structure based on the maximum number of enemy single unmanned aerial vehicle weapons, and including the following steps:
s31, constructing selectable values of the weapon quantity combination of two enemy unmanned aerial vehicles when different weapon emission quantities of each layer of structure are used as a weapon quantity combination diagram based on the maximum carrying quantity K of enemy single unmanned aerial vehicle weapons;
s32, recording the firing number of the weapons as a first stage when the firing number of the weapons is not more than K, and recording the firing number of the weapons as a second stage when the firing number of the weapons is more than K;
s33, combining the weapon quantity introduced by two arrows, marking the combination as the combination with fused weapon quantity, and representing the result of probability superposition of the two enemy unmanned aerial vehicle weapons;
s4, obtaining all current weapon quantity combinations and the stages thereof based on the weapon quantity combination graph and the weapon emission quantity; calculating the probability distribution of the weapon quantity combination based on the probability distribution function, comprising the following steps:
s41, obtaining selectable values of all current weapon quantity combinations from the corresponding weapon quantity combination diagram based on the weapon emission quantity, numbering from 0 in sequence, marking as {0, 1, … …, Nk, … …, Nk }, and determining the stages to which the weapon quantity combinations belong;
s42, calculating the probability of each weapon quantity combination by using a weapon quantity combination probability distribution function based on the probability distribution of the weapon quantity combination when the previous weapon is launched, wherein the probability marked as the existence of the fused weapon quantity combination is the sum of two probability values; in this layer, the weapon quantity of two unmanned aerial vehicles is:
numB1=K-i+nk-τ(K-i)
numB2=K-nk+τ(K-i)
nk=0,1,...,Nk
Nk=i+2τ(K-i)
wherein numB1 represents the weapon quantity of one of the drones in each layer structure, numB2 represents the weapon quantity of the other drone in each layer structure, Nk represents the serial number of the weapon quantity combination, Nk represents the quantity of selectable values of the current weapon quantity combination, i represents the weapon firing quantity, K represents the maximum carrying quantity of the enemy drone weapon, and τ is 0 in the first stage and 1 in the second stage;
the weapon quantity combination probability distribution function is:
when i is 2, 3, … …, 2K:
representing the probability of the combination of the number of the nth weapon when the ith weapon is fired and the number of the nth weapon,represents the probability of the ith weapon being fired by the enemy drone 1;and so on;
and S43, repeating the steps S41-S42, calculating the combined probability of the weapon quantity corresponding to each layer, combining the probabilities of the weapon quantity combinations of two adjacent layers again, and finally obtaining the probability of the weapon quantity combinations of all the unmanned aerial vehicles of the enemy.
2. The tactical decision making method for multiple drones in a dynamic environment of claim 1, wherein the number of the drones performance advantage matrix is my weapon number combined number and enemy weapon number combined number;
and the weight of the drone performance dominance matrix is the weight of the drone performance preference by the weapon number combined probability.
3. The utility model provides a many unmanned aerial vehicle tactics decision-making device under dynamic environment which characterized in that includes:
one or more processors;
a memory; and
one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, the programs comprising instructions for performing the method of any of claims 1-2.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011356317.0A CN112595174B (en) | 2020-11-27 | 2020-11-27 | Multi-unmanned aerial vehicle tactical decision method and device in dynamic environment |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011356317.0A CN112595174B (en) | 2020-11-27 | 2020-11-27 | Multi-unmanned aerial vehicle tactical decision method and device in dynamic environment |
Publications (2)
Publication Number | Publication Date |
---|---|
CN112595174A CN112595174A (en) | 2021-04-02 |
CN112595174B true CN112595174B (en) | 2022-09-13 |
Family
ID=75184383
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202011356317.0A Active CN112595174B (en) | 2020-11-27 | 2020-11-27 | Multi-unmanned aerial vehicle tactical decision method and device in dynamic environment |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN112595174B (en) |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105278542A (en) * | 2015-09-23 | 2016-01-27 | 沈阳航空航天大学 | Counter-attack countermeasure optimal strategy method for multi-unmanned plane cooperative strike task |
CN108549233A (en) * | 2018-05-04 | 2018-09-18 | 南京航空航天大学 | A kind of unmanned plane air combat maneuvering game method with intuitionistic fuzzy information |
CN110377052A (en) * | 2019-07-22 | 2019-10-25 | 合肥工业大学 | Unmanned plane, which is formed into columns, cooperates with the matrix games method and system of Target Assignment |
CN111666631A (en) * | 2020-06-03 | 2020-09-15 | 南京航空航天大学 | Unmanned aerial vehicle maneuvering decision method combining hesitation fuzzy and dynamic deep reinforcement learning |
Family Cites Families (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US10445442B2 (en) * | 2016-09-01 | 2019-10-15 | Energid Technologies Corporation | System and method for game theory-based design of robotic systems |
US20190354100A1 (en) * | 2018-05-21 | 2019-11-21 | Board Of Regents, The University Of Texas System | Bayesian control methodology for the solution of graphical games with incomplete information |
-
2020
- 2020-11-27 CN CN202011356317.0A patent/CN112595174B/en active Active
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105278542A (en) * | 2015-09-23 | 2016-01-27 | 沈阳航空航天大学 | Counter-attack countermeasure optimal strategy method for multi-unmanned plane cooperative strike task |
CN108549233A (en) * | 2018-05-04 | 2018-09-18 | 南京航空航天大学 | A kind of unmanned plane air combat maneuvering game method with intuitionistic fuzzy information |
CN110377052A (en) * | 2019-07-22 | 2019-10-25 | 合肥工业大学 | Unmanned plane, which is formed into columns, cooperates with the matrix games method and system of Target Assignment |
CN111666631A (en) * | 2020-06-03 | 2020-09-15 | 南京航空航天大学 | Unmanned aerial vehicle maneuvering decision method combining hesitation fuzzy and dynamic deep reinforcement learning |
Non-Patent Citations (3)
Title |
---|
Cooperative Occupancy Decision Making of Multi-UAV in Beyond-Visual-Range Air Combat: A Game Theory Approach;YI NGYI NG MA et al .;《IEEE》;20200117;11624-11634 * |
基于合作联盟的多无人机对地攻防对抗策略;陈侠等;《兵工自动化》;20140131;第33卷(第01期);49-55 * |
多无人机超视距空战博弈策略研究;赵明明等;《电光与控制》;20150430;第22卷(第04期);41-45 * |
Also Published As
Publication number | Publication date |
---|---|
CN112595174A (en) | 2021-04-02 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Kline et al. | The weapon-target assignment problem | |
US11669110B2 (en) | Control system based on multi-unmanned aerial vehicle cooperative strategic confrontation | |
CN107886184B (en) | Multi-type air defense weapon mixed-programming fire group target distribution optimization method | |
Leboucher et al. | Novel evolutionary game based multi-objective optimisation for dynamic weapon target assignment | |
Hu et al. | Improved Ant Colony Optimization for Weapon‐Target Assignment | |
CN112417710A (en) | Weapon equipment system contribution degree evaluation method based on combat ring | |
CN109408877B (en) | Intelligent shooting decision-making method for anti-tank missile teams | |
CN115759754A (en) | Beyond-visual-range air combat simulation target threat assessment method based on dynamic game variable weight | |
CN112612298B (en) | Multi-target game method and device for tactical decisions of multiple unmanned aerial vehicles in countermeasure environment | |
CN112595174B (en) | Multi-unmanned aerial vehicle tactical decision method and device in dynamic environment | |
CN112612206B (en) | Multi-agent collaborative decision-making method and system for uncertain events | |
Zhang et al. | Weapon–target assignment using a whale optimization algorithm | |
CN112612300B (en) | Multi-platform intelligent decision-making multi-target game method and device | |
CN110597199A (en) | Helicopter weapon scheduling method and system based on optimal model of shooting vector | |
CN116774721A (en) | Target allocation method and system for game countermeasure of multiple unmanned aerial vehicles | |
CN114565261B (en) | GMQN-based collaborative combat control method, system, equipment and medium | |
CN112818522B (en) | Ammunition consumption measuring and calculating method and device | |
Gallagher et al. | Probabilistic analysis of complex combat scenarios | |
Longyue et al. | Optimal index shooting policy for layered missile defense system | |
Jia et al. | An operational effectiveness evaluation method of the swarming UAVs air combat system | |
Masnica et al. | Using modeling of signal processing for optimizing the network architecture in the network oriented enviroment | |
Phua | An Operational Effectiveness Analysis on Manned Unmanned Teaming Using Weaponized Unmanned Vehicles in Urban Terrain | |
CN114428999B (en) | Unmanned aerial vehicle ground attack and defense strategy selection method based on evolutionary game model | |
Virtanen et al. | An influence diagram approach to one-on-one air combat | |
CN109447398A (en) | A kind of intelligence shooting decision-making technique of artilleryman group |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |