CN112305913A - Multi-UUV collaborative dynamic maneuver decision method based on intuitive fuzzy game - Google Patents

Multi-UUV collaborative dynamic maneuver decision method based on intuitive fuzzy game Download PDF

Info

Publication number
CN112305913A
CN112305913A CN202011150929.4A CN202011150929A CN112305913A CN 112305913 A CN112305913 A CN 112305913A CN 202011150929 A CN202011150929 A CN 202011150929A CN 112305913 A CN112305913 A CN 112305913A
Authority
CN
China
Prior art keywords
strategy
uuv
fuzzy
optimal
party
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.)
Withdrawn
Application number
CN202011150929.4A
Other languages
Chinese (zh)
Inventor
刘禄
张立川
白春梅
张硕
任染臻
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Northwestern Polytechnical University
Original Assignee
Northwestern Polytechnical University
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Northwestern Polytechnical University filed Critical Northwestern Polytechnical University
Priority to CN202011150929.4A priority Critical patent/CN112305913A/en
Publication of CN112305913A publication Critical patent/CN112305913A/en
Withdrawn legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
    • G05B13/00—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion
    • G05B13/02—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric
    • G05B13/04—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric involving the use of models or simulators
    • G05B13/042—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric involving the use of models or simulators in which a parameter or coefficient is automatically adjusted to optimise the performance

Abstract

The invention relates to a multi-UUV collaborative dynamic maneuver decision method based on an intuitive fuzzy game, and belongs to the field of collaborative confrontation of multi-underwater robots. Firstly, intuitive fuzzy multi-attribute evaluation is carried out on the UUV maneuvering optional scheme, and an intuitive fuzzy payment matrix of the cooperative dynamic maneuvering game is obtained. Then, Nash equilibrium conditions meeting the intuition fuzzy full-sequence relation are provided, and a Nash equilibrium maneuvering decision model under the dynamic underwater environment is established. The method solves the problem that the modeling difficulty is influenced by weak connectivity, uncertainty and variability of the underwater environment.

Description

Multi-UUV collaborative dynamic maneuver decision method based on intuitive fuzzy game
Technical Field
The invention belongs to the field of multi-underwater robot cooperative confrontation, and particularly relates to a multi-UUV cooperative confrontation method based on an intuitive fuzzy game decision algorithm.
Background
The unmanned underwater vehicle has the characteristics of small volume, good maneuverability, low cost, good invisibility and the like. It can be operated autonomously or under the control of a person. The multi-UUV control algorithm attracts wide attention, but research on cooperative countermeasures of the multi-UUV is limited. The multi-UUV cooperative countermeasure can be applied to marine scientific research and military countermeasure, including underwater multi-target tracking, monitoring and detection, the underwater combat radius is effectively enlarged, and the loss of underwater equipment and the casualties of personnel are reduced.
The maneuver decision is the key of the multi-UUV cooperative countermeasure, and is the basic action of each countermeasure step. There is also much research on unilateral strategy optimization, but little research on bilateral game theory. Therefore, by introducing the cooperative game theory into the maneuvering decision of the unmanned aerial vehicle system cluster, a more scientific and more accurate real-time countermeasure strategy can be made.
Disclosure of Invention
Technical problem to be solved
The complexity and uncertainty of the underwater environment are not considered sufficiently by the existing method, so that the reliability of the obtained decision model is not high, the original decision algorithm is easy to fall into the local optimal dilemma, the final decision scheme is difficult to convince, and the decision scheme cannot be applied to the real sea area environment. The invention aims to provide a method for combining intuitionistic fuzzy theory and game theory aiming at the defects of the existing method, which is characterized in that an intuitionistic fuzzy set is utilized to fully consider various uncertain underwater environments, and then an improved particle swarm algorithm is utilized to effectively make a decision on the confrontation of a plurality of UUV clusters.
Technical scheme
A multi-UUV collaborative dynamic maneuver decision method based on an intuitive fuzzy game is characterized by comprising the following steps:
step 1: evaluating the maneuvering attributes of the UUV according to the situation information of the opposite party and the opposite party, and establishing a fuzzy payment matrix;
(1) maneuver attribute set M will consider four attributes:
m ═ D, V, E, F, where D is the distance factor, V is the velocity factor, E is the yaw angle, and F is the pitch angle;
attribute m of my partypThe fuzzy evaluation matrix of (a) is expressed as p 1.
Figure BDA0002741228400000021
UUV has sevenBasic flight actions, i.e. keeping the flight as intended, accelerating, decelerating, turning left, turning right, climbing and diving, the maneuver strategy of the A side is an N 1, 7, the adversary selects the maneuver strategy dqQ 1.., 7, set of intuitive ambiguities fnq＝(unq,vnq) Obtained from the following table:
TABLE 1 fuzzy language and intuitive fuzzy number correspondence
Figure BDA0002741228400000022
(2) The fuzzy payment matrix is:
Figure BDA0002741228400000023
wherein Fnq＝(Unq,Vnq)，
Figure BDA0002741228400000024
Figure BDA0002741228400000025
lijIs attribute miRelative attribute mjIs obtained from the following table:
TABLE 2 Attribute importance Scale
Figure BDA0002741228400000026
Step 2: obtaining an intuitionistic fuzzy payment matrix according to the attribute evaluation, and further establishing a planning model;
the mixed policy space of my and enemy is represented as:
Figure BDA0002741228400000031
xi，yjrepresents: the probability of my choosing the ith strategy and the probability of the enemy choosing the jth strategy;
the expected revenue for my participants is:
Figure BDA0002741228400000032
according to the maximum and minimum theorem of game theory, the optimal countermeasure strategy is found here using a non-linear programming model:
max(ρ,σ)
Figure BDA0002741228400000033
where max (ρ, σ) is the maximum expected profit for my party, min (ζ, γ) is the minimum loss for the enemy,
Figure BDA0002741228400000034
take epsilon for an enemyjThe profit of my party when making a policy,
Figure BDA0002741228400000035
means that I takes epsilonjLoss of locality in policy;
and step 3: solving the model in the step 2 to obtain the maximum x of our partiAnd xiCorresponding strategy epsilonjMeaning that when two parties are working against, i take epsilonjThe strategy is the optimal strategy of the party, so that the income of the party
Figure BDA0002741228400000036
Maximum;
by the optimal parameter x in the optimal solutioniAnd the probability of adopting the optimal strategy at the moment is obtained, and the AUV executes the action of the optimal strategy pair.
The technical scheme of the invention is further that: the optimal countermeasure strategy in step 2 may be equivalent to
Figure BDA0002741228400000037
The technical scheme of the invention is further that: in the step 3, an optimal maneuvering strategy of the multi-UUV underwater strategy is realized by adopting an improved particle swarm optimization algorithm; the improved particle swarm optimization algorithm comprises the following steps:
Vid(t+1)＝αVid(t)+c1(βBestid(t)-Pid(t))*rand1
+c2(δBestid(t)-Pid(t)*rand2)
+c3(R(t)-Pid(t)*rand3
wherein the added detection vector R (t) -Pid(t) the radius r (t) can be detected by the adaptive variable to help the particles cover a wider range of solutions with greater probability,
Figure BDA0002741228400000041
μ∈[0,1]is a random number that is a function of the number,
Figure BDA0002741228400000042
is the upper and lower bounds of the problem, λ is a variable parameter, and t represents the iteration time.
Advantageous effects
The invention provides a multi-UUV collaborative dynamic maneuver decision method based on an intuitive fuzzy game, which has the following beneficial effects:
(1) the influence of weak connectivity, uncertainty and variability of an underwater environment on the modeling difficulty is solved, the established model is more convincing, and the model is more reliable in application of an actual water area. The intuitionistic fuzzy set can represent underwater environment characteristics including various uncertainties, and the established model is high in reliability and more persuasive.
(2) The problem that the decision algorithm falls into the local optimal situation is solved, the optimal solution is searched in the whole algorithm, and the obtained result is more accurate and credible. The MPSO is used in each step of the dynamic countermeasure process to obtain the optimal maneuver strategy, the obtained optimal solution is the global optimal solution, and the obtained decision scheme is more scientific.
Drawings
FIG. 1: overall diagram of maneuver decision process
FIG. 2: MPSO algorithm with learning capability
FIG. 3: profit value
FIG. 4: and (3) multi-UUV collaborative dynamic maneuver decision: first stage
FIG. 5: and (3) multi-UUV collaborative dynamic maneuver decision: second stage
FIG. 6: and (3) multi-UUV collaborative dynamic maneuver decision: the third stage
FIG. 7: and (3) multi-UUV collaborative dynamic maneuver decision: fourth stage
FIG. 8: and (3) multi-UUV collaborative dynamic maneuver decision: the fifth stage
Detailed Description
The invention will now be further described with reference to the following examples and drawings:
the technical scheme of the invention is as follows: by means of the intuitionistic fuzzy set, the underwater environment with weak connectivity, underwater noise and dynamic uncertainty is fully considered, and one of the main problems in the underwater decision making process is solved. And then, performing intuitive fuzzy multi-attribute evaluation on the UUV maneuvering optional scheme to obtain an intuitive fuzzy payment matrix of the cooperative dynamic maneuvering game. Then, Nash equilibrium conditions meeting the intuition fuzzy full-sequence relation are provided, and a Nash equilibrium maneuvering decision model under the dynamic underwater environment is established. Meanwhile, an improved particle swarm algorithm is provided, the existing problems are solved, and an optimal strategy is found. The method comprises the following steps:
step 1: in order to establish the fuzzy payment matrix, the maneuvering attributes of the UUV are evaluated according to the situation information of the opposite parties. The competing trajectories of UUVs can be viewed as a combination of each maneuver. The UUV has seven basic flight actions, i.e., maintain the intended flight, accelerate, decelerate, turn left, turn right, climb and dive. It should also be noted that these action limitations are considered in terms of the characteristics of the UUV. These two pairs of antibodies were designated "a" and "D", respectively.
Maneuver attribute set M will consider four attributes:
m ═ D, V, E, F, where D is the distance factor, V is the velocity factor, E is the yaw angle, and F is the pitch angle.
The multi-UUV countermeasure model generally includes two forms: one is a pure policy model and the other is a hybrid policy model. When the probability of a hybrid strategy is 1, it will becomeA pure policy model. In actual countermeasure, the two parties need to determine a strategy according to dynamic information in the countermeasure process, and then obtain revenue matrixes of the two parties. If the maneuver strategy of "A" is an(n ═ 1.., 7.) and "D" select maneuver strategy Dq(q 1.., 7), an intuitive blur set f can be obtained from table 1nq＝(unq,vnq) To quantitatively evaluate the selected strategy, wherein unqAnd vnqRespectively, degree of membership and degree of non-membership. Attribute m of "ApThe blur evaluation matrix under (p ═ 1.., 4) is expressed as:
Figure BDA0002741228400000061
the UUV has seven basic flight actions, namely, keeping the original flight, accelerating, decelerating, turning left, turning right, climbing and diving, and the maneuvering strategy of 'A' is an(n ═ 1.., 7), "D" selects maneuver strategy Dq(q ═ 1.., 7.), set of intuitive ambiguities fnq＝(unq,vnq) From table 1, we obtain:
the main difference between the multi-UUV counter-action and the other autonomous robot counter-actions is the transmission mode of the information. Due to the influence of the submarine environment, information in the multi-UUV countermeasure process is mainly received through underwater acoustics. The shallow sea acoustic channel is a channel with space-time frequency variations. It has the characteristics of strong multipath interference, high environmental noise, larger transmission loss and serious Doppler shift effect. Therefore, there is a great uncertainty about the information provided by the UUVs during the countermeasure. It is difficult to accurately quantify the threat level of both parties in the decision making process. Thus, the present invention uses an intuitive fuzzy language to classify each attribute into seven levels. In actual confrontation, the fuzzy language may be converted into a specific set to participate in the decision-making process. The fuzzy language herein is converted into an intuitive fuzzy set because the intuitive fuzzy set can measure the fuzzy degree of the original information more comprehensively. The relationship between fuzzy language and fuzzy sets is shown in table 1:
TABLE 1 fuzzy language and intuitive fuzzy number correspondence
Figure BDA0002741228400000062
In actual confrontation, the real-time change of the confrontation condition information makes it difficult for both parties to acquire the information of the mutual policy in advance, and therefore it is difficult to make an optimal policy. The main feature of game theory is that the schemes of action taken by the participants are interdependent and the benefits depend on the strategies taken by the participants and others. It can also find the optimal solution in case the adversary information is incomplete. Therefore, there is a clear advantage to solving such problems with relevant knowledge of game theory.
(2) The invention discusses a maneuvering game under uncertain underwater environment, which belongs to the category of zero sum countermeasures of two persons in essence. During the course of a contest, each contestant is considered a participant. Due to the uncertainty and poor interconnectivity of the underwater environment, participant judgment of the situation is often ambiguous and uncertain. The benefit value is expressed by using the double-scale intuitive fuzzy set, and an effective way is provided for solving the problems.
Fuzzy payment matrix is
Figure BDA0002741228400000071
Wherein Fnq＝(Unq,Vnq)，
Figure BDA0002741228400000072
Figure BDA0002741228400000073
lijIs attribute mi relative to attribute mjIs obtained from the following table:
TABLE 2 Attribute importance Scale
Figure BDA0002741228400000074
Step 2: obtaining an intuitionistic fuzzy payment matrix according to the attribute evaluation, and further establishing a planning model;
"A" square and "D"The hybrid strategy space of the party is represented as:
Figure BDA0002741228400000075
xi，yjrepresents: the probability of "A" selecting the ith policy and "D" selecting the jth policy.
The expected revenue for participant "a" was:
Figure BDA0002741228400000076
according to the maximum and minimum theorem of game theory, the optimal countermeasure strategy is found here using a non-linear programming model:
max(ρ,σ)
Figure BDA0002741228400000077
or is equivalent to
min(ζ,γ)
Figure BDA0002741228400000081
max (ρ, σ) is the maximum expected profit for my party, min (ζ, γ) is the minimum loss for the enemy,
Figure BDA0002741228400000082
take epsilon for an enemyjThe profit of my party when making a policy,
Figure BDA0002741228400000083
means that I takes epsilonjLoss of adversaries in the strategy.
And step 3: and the optimal maneuvering strategy of the multi-UUV underwater strategy is realized by improving a particle swarm optimization algorithm.
The optimal strategy is that when two parties carry out a battle, the most appropriate action is taken in each step, including 7 actions of keeping the original flight, accelerating, decelerating, turning left, turning right, climbing and diving, so that the party has the maximum income, and the enemy has the minimum loss.
As shown in fig. 2: in practice, the fitness function should be multi-modal, which requires that when a particle is trapped in a local optimum, the proposed parametric optimization algorithm should be able to change its original trajectory to adaptively explore the new solution space. For this purpose, a learning strategy is applied to the proposed MPSO method. There are two points to emphasize. First, in order to improve the dynamic performance of the PSO, a new speed update equation is designed. Then, a backward learning strategy based on self-adaptive Gaussian distribution is provided to overcome the blindness in random evolution search and enable the particles to be separated from local optimization. It should be noted that the proposed MPSO algorithm with learning capability does not increase the temporal complexity compared to the original PSO algorithm.
In recent years, many studies have shown that if particles converge too fast, they will shrink locally optimally within generations. This phenomenon will lead to similar search behavior between individuals and to a loss of diversity. If particles get trapped in local areas, they will hardly jump out of local optima due to their similar search behavior and lack of adaptive detection capability. To improve the performance of the PSO algorithm, the particles should be able to adaptively change the original trajectory and explore a new space. The problem is how to guide the particles to move to different areas that are desired to be global optimal and to explore the solution space more extensively. Therefore, in the present invention, an improved method with adaptive detection vector is proposed, which is:
Vid(t+1)＝αVid(t)+c1(βBestid(t)-Pid(t))*rand1
+c2(δBestid(t)-Pid(t)*rand2)
+c3(R(t)-Pid(t)*rand3
added detection vector R (t) -Pid(t) the radius r (t) can be detected by the adaptive variable to help the particles cover a wider range of solutions with greater probability.
Figure BDA0002741228400000091
Wherein μ ∈ [0,1 ]]Is a random number that is a function of the number,
Figure BDA0002741228400000092
is the upper and lower bounds of the problem, λ is a variable parameter, and t represents the iteration time. The speed update equation of the algorithm shows that team members can explore the unvisited area with a higher probability in the solution space. The larger detection radius helps to enhance the exploration behavior of the particle, move the particle away from the current region, and facilitate the particle searching for other regions. The smaller detection radius enhances the development of the particle optimal solution by searching for a small region near the optimal solution. Thus, by updating the equations using the velocity of the adaptive variable detection vectors, the entire feasible solution space can be covered and explored as much as possible.
Example (c): assume that "a" and "D" are involved in the 2V2 confrontation of UUV. The initial positions of "A1", "A2" are (-400m, 100m, 800m), (-400m, 100m, 800m), "D1", and "D2" are (400m, 100m, 800m), (400m, -100m, 800 m). The speeds, deflection angles and pitch angles of A1 and A2 are 23m/s, -60 degrees, 5 degrees and 23m/s, 60 degrees and-5 degrees respectively; the velocities, yaw angles and pitch angles of "D1" and "D2" were 25m/s, 128 °, 3 ° and 25m/s, -128 °, and-3 °, respectively. Both parties have the same control capability and the time interval of the countermeasure step is 5 s. It is clear that "D" has advantages from the outset. It should also be noted that the maximum maneuver step should be decided based on the validity of the UUV used in the countermeasure.
To compare the challenge performance, "a" uses the collaborative dynamic maneuver decision algorithm proposed by the present invention and "D" uses the max-min decision algorithm in the multi-UUV challenge process. A three-dimensional challenge process with 5 main steps is shown in fig. 4 to 7. "+" shows the initial position and "Δ" shows the current position. The countermeasure ends when the return value of one party reaches absolute advantage.
The calculation part in the invention is as follows:
Figure BDA0002741228400000101
ω1＝0.3391，ω2＝0.3137，ω3＝0.1736，ω4＝0.1736，α＝1，c1＝1.5，c2＝2，
Figure BDA0002741228400000102
as shown in fig. 3: there are 40 steps in the countermeasure process, which are returned in the figure.
As shown in fig. 4: the return value obtained indicates that the nash equilibrium condition of the intuitive fuzzy game is satisfied. For step 1 in FIG. 4, "D" holds the dominance, where "D1" tries to attack "A1" and "D2" steps toward "A2".
At step 2 in fig. 5, "D1" and "D2" attempt to attack "a 2" and "a 1" attempt to turn around to escape.
At step 3 in fig. 6, "D1" and "D2" still try to attack "a 2", but "a 2" turns away and "a 1" turns back to the confrontation state.
At step 4 of fig. 7, "a 2" continuously rotated and successfully escaped, "a 1" also rotated and attempted to turn "a 2" back to "D1" and "D2", "D1" and "D2". The situation changes, and "A" takes the dominant position. This can also be verified in fig. 3, where the return value changes from negative to positive.
At step 5 of fig. 8, finally, "a 1" and "a 2" both occupy the primary positions, so "a" gains absolute advantage and ends the challenge.
The invention introduces an intuitionistic fuzzy set into a game theory and researches a cooperative dynamic maneuver decision algorithm of a plurality of UUV. The intuitive fuzzy sets represent features of the underwater environment including various uncertainties. And (3) establishing a maneuvering game model with intuitionistic fuzzy information and giving conditions of a Nash equilibrium strategy. In conjunction with background and model features, MPSO is used in each step of the dynamic countermeasure process to obtain the optimal maneuver strategy. Furthermore, a multi-UUV dynamic confrontation example with multiple maneuver decision steps is given to show the superiority and effectiveness of the proposed maneuver decision algorithm.

Claims (3)

1. A multi-UUV collaborative dynamic maneuver decision method based on an intuitive fuzzy game is characterized by comprising the following steps:
step 1: evaluating the maneuvering attributes of the UUV according to the situation information of the opposite party and the opposite party, and establishing a fuzzy payment matrix;
(1) maneuver attribute set M will consider four attributes:
m ═ D, V, E, F, where D is the distance factor, V is the velocity factor, E is the yaw angle, and F is the pitch angle;
attribute m of my partypThe fuzzy evaluation matrix of (a) is expressed as p 1.
Figure FDA0002741228390000011
The UUV has seven basic flight actions, namely, keeping the original flight, accelerating, decelerating, turning left, turning right, climbing and diving, and the maneuvering strategy of the A side is anN 1, 7, the adversary selects the maneuver strategy dqQ 1.., 7, set of intuitive ambiguities fnq＝(unq,vnq) Obtained from the following table:
TABLE 1 fuzzy language and intuitive fuzzy number correspondence
Figure FDA0002741228390000012
(2) The fuzzy payment matrix is:
Figure FDA0002741228390000013
wherein Fnq＝(Unq,Vnq)，
Figure FDA0002741228390000014
Figure FDA0002741228390000015
lijIs attribute miRelative attribute mjIs heavyTo scale, obtained from the following table:
TABLE 2 Attribute importance Scale
Figure FDA0002741228390000016
Step 2: obtaining an intuitionistic fuzzy payment matrix according to the attribute evaluation, and further establishing a planning model;
the mixed policy space of my and enemy is represented as:
Figure FDA0002741228390000021
xi，yjrepresents: the probability of my choosing the ith strategy and the probability of the enemy choosing the jth strategy;
the expected revenue for my participants is:
Figure FDA0002741228390000022
according to the maximum and minimum theorem of game theory, the optimal countermeasure strategy is found here using a non-linear programming model:
max(ρ,σ)
Figure FDA0002741228390000023
where max (ρ, σ) is the maximum expected profit for my party, min (ζ, γ) is the minimum loss for the enemy,
Figure FDA0002741228390000024
take epsilon for an enemyjThe profit of my party when making a policy,
Figure FDA0002741228390000025
means that I takes epsilonjLoss of locality in policy;
and step 3: solving the model in the step 2 to obtain the maximum x of our partiAnd xiCorresponding strategy epsilonjMeaning that when two parties are working against, i take epsilonjThe strategy is the optimal strategy of the party, so that the income of the party
Figure FDA0002741228390000026
Maximum;
by the optimal parameter x in the optimal solutioniAnd the probability of adopting the optimal strategy at the moment is obtained, and the AUV executes the action of the optimal strategy pair.
2. The multi-UUV collaborative dynamic maneuver decision method based on intuitive fuzzy game as claimed in claim 1, wherein the best countermeasure strategy in step 2 can be equivalent to
min(ζ,γ)
Figure FDA0002741228390000027
3. The cooperative multi-UUV dynamic maneuver decision method based on the intuitive fuzzy game as claimed in claim 1, wherein the optimal maneuver strategy of the multi-UUV underwater strategy is realized by adopting an improved particle swarm optimization algorithm in the step 3; the improved particle swarm optimization algorithm comprises the following steps:
Vid(t+1)＝αVid(t)+c1(βBestid(t)-Pid(t))*rand1+c2(δBestid(t)-Pid(t)*rand2)+c3(R(t)-Pid(t)*rand3
wherein the added detection vector R (t) -Pid(t) the radius r (t) can be detected by the adaptive variable to help the particles cover a wider range of solutions with greater probability,
Figure FDA0002741228390000031
μ∈[0,1]is a random number that is a function of the number,
Figure FDA0002741228390000032
is the upper and lower bounds of the problem, λ is a variable parameter, and t represents the iteration time.
CN202011150929.4A 2020-10-24 2020-10-24 Multi-UUV collaborative dynamic maneuver decision method based on intuitive fuzzy game Withdrawn CN112305913A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202011150929.4A CN112305913A (en) 2020-10-24 2020-10-24 Multi-UUV collaborative dynamic maneuver decision method based on intuitive fuzzy game

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202011150929.4A CN112305913A (en) 2020-10-24 2020-10-24 Multi-UUV collaborative dynamic maneuver decision method based on intuitive fuzzy game

Publications (1)

Publication Number Publication Date
CN112305913A true CN112305913A (en) 2021-02-02

Family

ID=74327298

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202011150929.4A Withdrawn CN112305913A (en) 2020-10-24 2020-10-24 Multi-UUV collaborative dynamic maneuver decision method based on intuitive fuzzy game

Country Status (1)

Country Link
CN (1) CN112305913A (en)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113033107A (en) * 2021-04-16 2021-06-25 西北工业大学 Multi-AUV cluster game countermeasure model construction method based on central intelligence set theory
CN114326822A (en) * 2022-03-09 2022-04-12 中国人民解放军66136部队 Unmanned aerial vehicle cluster information sharing method based on evolutionary game
CN114675660A (en) * 2022-03-02 2022-06-28 西北工业大学 Multi-UUV collaborative search method based on PSO-LSHADE-CLM

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
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
CN110188461A (en) * 2019-05-29 2019-08-30 哈尔滨工程大学 A kind of red blue party AHP intimidation estimating method of more UUV towards base attacking and defending task

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
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
CN110188461A (en) * 2019-05-29 2019-08-30 哈尔滨工程大学 A kind of red blue party AHP intimidation estimating method of more UUV towards base attacking and defending task

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
LU LIU 等: "Multi-UUV Cooperative Dynamic Maneuver Decision-Making Algorithm Using Intuitionistic Fuzzy Game Theory", 《COMPLEXITY》 *

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113033107A (en) * 2021-04-16 2021-06-25 西北工业大学 Multi-AUV cluster game countermeasure model construction method based on central intelligence set theory
CN114675660A (en) * 2022-03-02 2022-06-28 西北工业大学 Multi-UUV collaborative search method based on PSO-LSHADE-CLM
CN114675660B (en) * 2022-03-02 2024-05-07 西北工业大学 PSO-LSHADE-CLM-based multi-UUV collaborative search method
CN114326822A (en) * 2022-03-09 2022-04-12 中国人民解放军66136部队 Unmanned aerial vehicle cluster information sharing method based on evolutionary game

Similar Documents

Publication Publication Date Title
CN112305913A (en) Multi-UUV collaborative dynamic maneuver decision method based on intuitive fuzzy game
CN109539886B (en) Submarine stealth aid decision-making system and submarine stealth aid decision-making method
CN108444481B (en) A kind of underwater hiding-machine paths planning method based on aid decision-making system
CN107063255A (en) A kind of three-dimensional Route planner based on improvement drosophila optimized algorithm
CN112306070A (en) Multi-AUV dynamic maneuver decision method based on interval information game
Liu et al. Multi-UUV cooperative dynamic maneuver decision-making algorithm using intuitionistic fuzzy game theory
CN113052289B (en) Method for selecting cluster hitting position of unmanned ship based on game theory
Analikwu et al. Multi-agent learning in the game of guarding a territory
Li et al. Search-evasion path planning for submarines using the artificial bee colony algorithm
CN116225049A (en) Multi-unmanned plane wolf-crowd collaborative combat attack and defense decision algorithm
CN115951709A (en) Multi-unmanned aerial vehicle air combat strategy generation method based on TD3
Yuan et al. Research on UCAV maneuvering decision method based on heuristic reinforcement learning
Nantogma et al. Behavior-based genetic fuzzy control system for multiple USVs cooperative target protection
CN116185059A (en) Unmanned aerial vehicle air combat autonomous evasion maneuver decision-making method based on deep reinforcement learning
CN114638339A (en) Intelligent agent task allocation method based on deep reinforcement learning
CN116680509A (en) Dynamic matching method for multi-spacecraft escape-tracking game task
CN115993835A (en) Target maneuver intention prediction-based short-distance air combat maneuver decision method and system
Yan et al. A novel path planning for AUV based on objects’ motion parameters predication
Xia et al. Research on collision avoidance algorithm of unmanned surface vehicle based on deep reinforcement learning
CN113159266B (en) Air combat maneuver decision method based on sparrow searching neural network
Zhang et al. Intelligent vector field histogram based collision avoidance method for auv
CN117270528A (en) Unmanned ship escape game control method and controller
CN116774712A (en) Real-time dynamic obstacle avoidance method in underactuated AUV three-dimensional environment
CN114911269B (en) Networking radar interference strategy generation method based on unmanned aerial vehicle group
CN116225065A (en) Unmanned plane collaborative pursuit method of multi-degree-of-freedom model for multi-agent reinforcement learning

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
WW01 Invention patent application withdrawn after publication

Application publication date: 20210202

WW01 Invention patent application withdrawn after publication