CN115016526A - Cluster self-organizing control method for double-layer defense - Google Patents
Cluster self-organizing control method for double-layer defense Download PDFInfo
- Publication number
- CN115016526A CN115016526A CN202210476976.0A CN202210476976A CN115016526A CN 115016526 A CN115016526 A CN 115016526A CN 202210476976 A CN202210476976 A CN 202210476976A CN 115016526 A CN115016526 A CN 115016526A
- Authority
- CN
- China
- Prior art keywords
- item
- cluster
- individual
- defense
- intrusion
- 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.)
- Granted
Links
- 230000007123 defense Effects 0.000 title claims abstract description 75
- 238000000034 method Methods 0.000 title claims abstract description 23
- 239000013598 vector Substances 0.000 claims description 32
- 230000008447 perception Effects 0.000 claims description 15
- 230000009545 invasion Effects 0.000 claims description 9
- 230000008859 change Effects 0.000 claims description 3
- 239000000126 substance Substances 0.000 claims description 3
- 238000004590 computer program Methods 0.000 claims description 2
- 230000003993 interaction Effects 0.000 abstract description 11
- 230000000694 effects Effects 0.000 abstract description 7
- 230000002195 synergetic effect Effects 0.000 abstract 4
- 238000004088 simulation Methods 0.000 description 9
- 230000033001 locomotion Effects 0.000 description 8
- 230000006399 behavior Effects 0.000 description 5
- 238000010586 diagram Methods 0.000 description 5
- 230000001133 acceleration Effects 0.000 description 4
- 230000007246 mechanism Effects 0.000 description 4
- 230000002265 prevention Effects 0.000 description 3
- 238000004422 calculation algorithm Methods 0.000 description 2
- 238000009826 distribution Methods 0.000 description 2
- 241000251468 Actinopterygii Species 0.000 description 1
- 241000022852 Letis Species 0.000 description 1
- 238000009825 accumulation Methods 0.000 description 1
- 230000002776 aggregation Effects 0.000 description 1
- 238000004220 aggregation Methods 0.000 description 1
- 230000001740 anti-invasion Effects 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 238000004138 cluster model Methods 0.000 description 1
- 230000010485 coping Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000005290 field theory Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000009827 uniform distribution Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
- G05D1/10—Simultaneous control of position or course in three dimensions
- G05D1/101—Simultaneous control of position or course in three dimensions specially adapted for aircraft
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/02—Total factory control, e.g. smart factories, flexible manufacturing systems [FMS] or integrated manufacturing systems [IMS]
Landscapes
- Engineering & Computer Science (AREA)
- Aviation & Aerospace Engineering (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Burglar Alarm Systems (AREA)
Abstract
The invention relates to a cluster self-organizing control method for double-layer defense, wherein a defense cluster and an intrusion cluster respectively have different individual attributes and interaction strategies, wherein for the defense cluster, a defense potential field force is formed by constructing a defense potential field to realize a double-layer defense effect, and a position synergistic item, a speed synergistic item, a self-driving item, an anti-intrusion item and a random noise item are also present, and the position synergistic item, the speed synergistic item, the self-driving item, the anti-intrusion item and the random noise item are set to cope with the intrusion of an intruder by setting different weight coefficients; for an intrusion cluster, a certain difference exists between a cooperative rule and a defense cluster, and main cooperative items include: the position collaborative item, the self-driven item, the individual intrusion item, the back-driven item-by-item and the random noise item are set through the collaborative item weight coefficient to complete the intrusion task. And making a rule for the cooperation rule and the interaction strategy of the two-party cluster, further determining a defense cluster parameter according to the defense effect, and finally realizing the successful cluster defense.
Description
Technical Field
The invention relates to the technical field of cluster intelligence, in particular to a self-organization control method for cluster defense and confrontation by utilizing a double-layer defense potential field.
Background
The phenomenon of cluster motion is widely found in nature, and suggests that the fish from whirling to migrating of the bird colony and the ant colony from cooperating to forming of the flora. The individual ability of the group is limited and does not have complex intelligent thinking, and the group formed by the individuals finally can show a complex, ordered and diverse intelligent clustering phenomenon, which is also called cluster self-organizing emerging behavior. The core of cluster movement is the basic rule followed by individuals in a cluster, and the abundant phenomenon finally emerges at the cluster level through the individuals following the rule. By referring to the natural clustering rules, people construct various artificial cluster systems, which are embodied in military use and civil use. If the system is applied to the unmanned aerial vehicle cluster, complex environment exploration, forest fire prevention and control, personnel search and rescue under disasters can be completed by the unmanned aerial vehicle cluster, and even cross-domain cooperation can be realized by the cluster technology. Meanwhile, various cluster models such as a social force model, a Viscek model, a Couzin model and the like are also provided on a theoretical level by realizing actual artificial clustering.
While the most basic model for defending against intrusion is called: target-intruder-defender confrontation model (TAD game). This basic countermeasure model contains three participants, a target, an intruder and a defender. The intruder aims to catch the target while avoiding attack by the defender. Defenders attempt to protect the target while also capturing the intruder as much as possible. The target has no defense capability for the intruder, and can only avoid the attack of the intruder in an escape mode. Solutions for TAD models are mainly divided into two categories: and dividing the leading area according to the initial position, selecting an optimal strategy and constructing a dynamic update state of a differential equation. The TAD problem is directed to the problem of intrusion prevention for a single individual, and when the TAD problem is directed to intrusion prevention among a plurality of individuals (groups), a target matching is generally performed between an defender and an intruder by using a distribution algorithm, and a conventional TAD solution is used after one-to-one matching is completed. That is, the current idea for the inter-group defense intrusion problem is to decompose the inter-group defense into two steps: individual matching and individual defense. The method simply considers the group as the accumulation sum of a plurality of individuals, changes the group defense into a plurality of individual defenses which are carried out simultaneously, and does not fully highlight the group advantages.
Therefore, how to arouse population dominance is a core problem for the current population defense. The use of a cluster self-organization approach to defend against intrusion is an option, and how to design cluster individual rules to enable the emergence of defense behavior is a problem worthy of intensive study.
Disclosure of Invention
Technical problem to be solved
In order to avoid the defects of the prior art, the invention provides a cluster defense self-organizing control method, which updates the motion state of an individual by the design of an individual interaction mechanism in a cluster and an individual interaction mechanism among clusters and combining a social force model, and finally realizes the self-organizing control of the cluster defense.
Technical scheme
A cluster self-organizing control method of double-layer defense is characterized in that: setting a cooperative rule of an individual in the defense cluster and an individual in the intrusion cluster;
1) the expression of the cooperative rule of the individuals in the defense cluster is as follows:
wherein, the first and the second end of the pipe are connected with each other,in order to be a self-driving item,in the case of a location-collaborative item,in order to be a speed-coordinated term,in order to protect the terms of the potential field,as anti-invasive term, η xi i Is random noise;
Where α represents the maximum value of defensive clustering speed, | | v i (t) | | represents the magnitude of defensive clustering speed;
Represents a gravitational-repulsive force equilibrium position adjustment parameter, representing repulsive force when the individual pitch is smaller than the value, and attractive force when it is larger than the value;represents the subgroup spacing, the repulsive force between subgroups reaches a maximum when the individual spacing equals this value;representing neighbor individuals to individuals D i In the direction ofA unit vector of quantities;
N i as set of perceptual neighbors:
N i ={k|d ik <R sen ,k∈{1,...,N D },k≠i}
wherein d is ik Representing the distance, R, between individuals within a defensive cluster sen The perception radius of the defense cluster is more than 0;
Wherein d is ip Indicating the distance of the defending individual to the protected object,representing an individual D i A unit vector to a location vector of the protected object;respectively corresponding to potential field boundary distances around the protected object;
T i Set of perceived intruders:
T i ={k|d ik <R sen ,k∈{1,...,N I }}
wherein d is ik Representing protection of an individual against an intruder T within the perception domain i At a distance of (2), hereRepresenting an individual D i To the intruder T in the perception domain i A unit vector of the position vector of (a);
the random noise eta xi i Representing random noise with intensity of eta > 0, letIs in the range of [ -0.5,0.5 [)] 2 Random vectors satisfying uniform distribution;
2) the expression of the cooperative rule of the individual in the intrusion cluster is as follows:
wherein the self-driving forceAnd random noise η ξ j The expression is consistent with that of a defender, only the parameters of the self-driving force of the invading individual, namely the speed maximum value beta is different from the self-driving force parameter alpha of the defending individual, and the beta is more than alpha; the remaining items including location coordination itemsIndividual intrusion itemAnti-evictionItem(s)The specific expression is as follows:
Wherein beta represents the maximum value of the invasion cluster speed, and beta is more than alpha and | v j (t) | | represents the size of the intrusion cluster speed;
Wherein the content of the first and second substances,representing neighbor individuals to individuals I j A unit vector of the position vector of (a);
N j the set of perceived neighbors is:
N j ={k|d jk <r sen ,k∈{1,...,N I },k≠j}
wherein d is jk Represents the distance, r, between individuals within an intrusion cluster sen The sensing radius of the intrusion cluster is more than 0;
T j The set of imperceptible defenders is:
T j ={k|d jk <r sen ,k∈{1,...,N D }}
N D representing a defensive cluster;
the random noise eta xi j Random noise with intensity eta > 0, orderIs in the range of [ -0.5,0.5 [)] 2 Uniformly distributed random vectors.
A computer system, comprising: one or more processors, a computer readable storage medium, for storing one or more programs, which when executed by the one or more processors, cause the one or more processors to implement the above-described method.
A computer-readable storage medium having stored thereon computer-executable instructions for performing the above-described method when executed.
A computer program comprising computer executable instructions which when executed perform the method described above.
Advantageous effects
The cluster self-organizing control method for double-layer defense provided by the invention solves the problem of defense intrusion countermeasures by utilizing the cluster self-organizing control method. Through the design of individual interaction mechanisms in the groups and the individual interaction mechanisms among the groups, the motion state of the individual is updated by combining the social force model, and finally the self-organization control of the cluster defense is realized. The defense cluster and the intrusion cluster respectively have different individual attributes and interaction strategies, wherein for the defense cluster, a defense potential field force is formed by constructing a defense potential field so as to realize a double-layer defense effect, and in addition, a position coordination item, a speed coordination item, a self-driving item, an anti-intrusion item and a random noise item are also present, and the position coordination item, the speed coordination item, the self-driving item, the anti-intrusion item and the random noise item are used for coping with the intrusion of an intruder by setting different weight coefficients; for an intrusion cluster, a certain difference exists between a cooperative rule and a defense cluster, and main cooperative items include: the method comprises the steps of setting a position cooperative item, a self-driven item, an individual invasion item, a back-drive item by item and a random noise item, and completing an invasion task by setting a cooperative item weight coefficient. And making a rule for the cooperative rules and the interaction strategies of the two-party clusters, further determining the defense cluster parameters according to the defense effect, and finally realizing the successful cluster defense.
Drawings
The drawings are only for purposes of illustrating particular embodiments and are not to be construed as limiting the invention, wherein like reference numerals are used to designate like parts throughout.
FIG. 1 is a schematic diagram of a potential field design of a double-layer defense ring.
FIG. 2 is a diagram of a simulation interface in the method of the present invention.
FIG. 3 is a simulation of the formation of a double layer defense circle by a subgroup of defense in the method of the present invention.
FIG. 4 is a simulation diagram of the radius of capture of an intruder entering defender in the method of the present invention.
FIG. 5 is a simulation diagram of the inner and outer defense subgroups surrounding an intruder in the method of the present invention.
FIG. 6 is a simulation diagram of successful defense of the defense cluster in the method of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention will be described in further detail below with reference to the accompanying drawings and examples. It should be understood that the specific embodiments described herein are merely illustrative of the invention and do not limit the invention. In addition, the technical features involved in the embodiments of the present invention described below may be combined with each other as long as they do not conflict with each other.
The invention provides a cluster defense model capable of realizing defense intrusion confrontation between two clusters, which ensures that a cluster can emerge cooperative defense behaviors in the motion process and finally realizes an effective self-organizing defense effect. The cluster defense system has the following characteristics:
1. the individuals in the group are isomorphic and consistent in rule. That is, the individual attributes in the same group are consistent, and the individual behavior rules are also the same. Wherein the individual attributes comprise kinematics (maximum speed, maximum acceleration, etc.), perception capabilities, capturing capabilities, etc.
2. The individuals in the groups are heterogeneous and have different rules. That is, there is a difference in individual attributes between groups of different camps, such as a difference between a defender and an intruder in the maximum speed and the maximum acceleration, and also a difference in the perception level, and the specific parameters are shown in table one.
3. The individuals within all groups are identical. Namely, the identity of the individual cannot be identified through the external or signal, all the individuals are consistent in expression in the cluster, and no specificity exists.
4. Individual decision making is performed autonomously, and centralized distribution is not available. All individuals in the group are autonomously sensed, the individual states are autonomously updated according to the cluster rule, autonomous decision is made, and upper and lower levels among the individuals or following dependence do not exist.
5. The fight between clusters is embodied in a captured form. The defender intercepts the invader to catch the invader until the invader enters the capturing radius of the defender, the defender and the invader share the same meaning to represent the confrontation of the defender to the invader, and the invader escapes from the defender to catch the protected object until the protected object enters the capturing radius of the invader, which represents the successful confrontation of the invader.
The defense cluster and the invasion cluster are constructed according to the five-point characteristics, wherein the defense cluster is named as D and comprises N D (ii) individuals; the intrusion cluster is named I, whichIn which contains N I (ii) individuals; the protected object is named P. Wherein the individual D i (i=1,...,N D ),I j (j=1,...,N I ) A position vector ofThe velocity vector isRegardless of the individual shape characteristics, the individual mass is assumed to be m 1. The individual satisfies Newton's law of mechanics, where individual synergies are divided into intra-cluster synergies and inter-cluster synergies. The defense individual position speed updating formula is as follows:
wherein u is i (t) denotes defensive individuals D i Since the mass is 1, the resultant force and the acceleration are equivalent, where u is i (t) denotes a defensive individual D i Of the acceleration of (2). The intrusion individual position speed updating formula is the same as the defense cluster updating formula, and the cooperative items of the individuals in the two clusters are different, as follows:
first is the cooperative rule that defends individuals within a cluster, as follows:
defending against clustered individual collaborative items including self-driven itemsLocation collaborative itemsVelocity synergy termPotential field protection termAnti-intrusion entryAnd random noise eta xi i . The specific rule settings are as follows:
(1) self-driving item
Where α represents the maximum value of the velocity, | | v i (t) | | represents the velocity magnitude.
(2) Sports synergy item
Individual interaction is based on the motion state of a neighbor partner, and it is assumed that an individual can sense the motion state information (position and speed) of a neighbor in a certain neighborhood in real time. Wherein the perceived radius of the defensive cluster is R sen > 0, the set of perceptual neighbors is:
N i ={k|d ik <R sen ,k∈{1,...,N D },k≠i} (4)
wherein d is ik Representing the distance between individuals within a defensive cluster.
The position coordination term formula is shown above, and the model is short-distance repulsion-long-distance attraction-medium-distance repulsion.Indicates the attractive force-repulsive forceAn equilibrium position adjustment parameter that exhibits repulsion when the individual spacing is less than the value and attraction when greater than the value;indicating the subgroup spacing, the repulsion between the subgroups reaches a maximum when the individual spacing equals this value.Representing neighbor individuals to individuals D i The unit vector of the position vector of (2).
The speed cooperative item adopts a non-average rule, and selects a neighbor individual with the largest angle change from the neighborsAnd to refer to its velocity bearing.
(3) Potential field protection term
And (3) constructing a double-layer defense potential field by combining artificial potential field theory, as shown in figure 1. The defense power is expressed as follows:
where the defending individual is globally aware of the protected object, d ip Indicating the distance of the defending individual to the protected object,representing an individual D i A unit vector to a location vector of the protected object. When the defending individual is in different potential fields and is subjected to potential field forces in different directions, the positive and negative of the potential field protection force correspond to two actions of approaching to a protected object and departing from the protected object. WhereinRespectively correspond to the circumferenceThe potential field boundary distance around the protected object, as shown in figure 1. The defense clusters thus finally form a double-layered defense circle around the protected object.
(4) Anti-intrusion entry
This is an inter-group interaction term, i.e. defending an individual from interacting with an invading individual. The defense individual can locally sense the invading individual, and the sensing radius of the defending individual to the invading individual is also R sen If > 0, the set of perceived intruders is:
T i ={k|d ik <R sen ,k∈{1,...,N I }} (8)
the anti-intrusion force is the resultant force direction of each intruder in the approaching perception range, and the distance from the intruder to the defender influences the corresponding weight, and the specific form is as follows:
wherein d is ik Representing protection of an individual against an intruder T within the perception domain i At a distance of (2), hereRepresenting an individual D i Perception of an intra-domain intruder T i The unit vector of the position vector of (2).
(5) Random noise
ηξ i Random noise with intensity eta > 0, orderIs in the range of [ -0.5,0.5 [)] 2 The upper satisfies a uniformly distributed random vector.
Then, the cooperative rule of the individual in the intrusion cluster is expressed as follows:
wherein the self-driving forceAnd random noise η ξ j The expression is consistent with that of defenders, only the parameters of the self-driving force of the invading individual, namely the speed maximum value beta is different from the self-driving force parameter alpha of the defending individual, and the general value is beta>α. The remaining items including location coordination itemsIndividual invasion itemBack drive item by itemThe specific expression is as follows:
(1) location coordination items
There is also a local perception of intruders, where the perception radius of the intrusion cluster is r sen > 0, the set of perceptual neighbors is:
N j ={k|d jk <r sen ,k∈{1,...,N I },k≠j} (11)
the positions of the invading individuals and the neighbors in the perception domain thereof cooperatively follow the principle of 'exclusive only', namely, the individuals are only in collision avoidance, and aggregation does not exist, and the specific expression is as follows:
(2) individual intrusion item
The invading individual has an invading trend and an individual invading force to the protected object, which are specifically expressed as follows:
(3) back drive item by item
The item is an inter-group interaction item of the invading individual, namely, the invading individual interacts with the defending individual. The invading individual can locally sense the defending individual and defendThe perception radius of the individual is also r sen If the ratio is more than 0, the set of the sensible defenders is as follows:
T j ={k|d jk <r sen ,k∈{1,...,N D }} (14)
the back-driving gradual force is the resultant force direction of each defender far away from the sensing range, and the distance from the defender to the invader influences the corresponding weight, and the specific form is as follows:
simulation result
The above algorithm is simulated, the simulation object is composed of three parts of a defense cluster, an intrusion cluster and a protection object, and the simulation interface is shown in fig. 2. According to the cooperative rules, the speed and position information of the individuals in the cluster are updated in real time, and the simulation result finally shows that the defense cluster can spontaneously emerge various defense behaviors in the cluster defense confrontation, for example, the defense subgroups form a double-layer defense ring, the inner and outer defense subgroups surround an attack invader, the outer ring directly attacks and captures the invader, and finally the cluster self-organization defense is successfully realized, the specific effect is shown in fig. 3-6, and the double-layer defense ring is formed again to cope with the next invasion after the defense cluster defense succeeds.
Table-cluster parameter
While the invention has been described with reference to specific embodiments, the invention is not limited thereto, and various equivalent modifications or substitutions can be easily made by those skilled in the art within the technical scope of the present disclosure.
Claims (4)
1. A cluster self-organizing control method of double-layer defense is characterized in that: setting a cooperative rule of an individual in the defense cluster and an individual in the intrusion cluster;
1) the expression of the cooperative rule of the individuals in the defense cluster is as follows:
wherein the content of the first and second substances,in order to be a self-driving item,in the case of a location-collaborative item,in order to be a speed-coordinated term,in order to protect the terms of the potential field,eta xi, an anti-intrusive term i Is random noise;
Where α represents the maximum value of defensive clustering speed, | | v i (t) | | represents the magnitude of the defensive clustering speed;
Expressing a gravitational-repulsive force equilibrium position adjustment parameter, expressing a repulsive force when the individual pitch is smaller than the value, and expressing a gravitational force when it is larger than the value;represents the subgroup spacing, the repulsive force between subgroups reaches a maximum when the individual spacing equals this value;representing neighbor individuals to individuals D i A unit vector of the position vector of (a);
N i as a set of perceptual neighbors:
N i ={k|d ik <R sen ,k∈{1,...,N D },k≠i}
wherein d is ik Representing the distance, R, between individuals within a defensive cluster sen The perception radius of the defense cluster is more than 0;
Wherein d is ip Indicating the distance of the defending individual to the protected object,representing an individual D i A unit vector to a location vector of the protected object;respectively corresponding to potential field boundary distances around the protected object;
T i Set of perceived intruders:
T i ={k|d ik <R sen ,k∈{1,...,N I }}
wherein d is ik Representing protection of an individual against an intruder T within the perception domain i At a distance of (2), hereRepresenting an individual D i Perception of an intra-domain intruder T i A unit vector of the position vector of (a);
the random noise eta xi i Random noise with intensity eta > 0, orderIs in the range of [ -0.5,0.5 [)] 2 Random vectors which are uniformly distributed are satisfied;
2) the expression of the cooperative rule of the individual in the intrusion cluster is as follows:
wherein the self-driving forceAnd random noise eta xi j The expression is consistent with that of a defender, only the parameters of the self-driving force of the invading individual, namely the speed maximum value beta is different from the self-driving force parameter alpha of the defending individual, and the beta is more than alpha; the remaining items including location coordination itemsIndividual intrusion itemBack drive item by itemThe specific expression is as follows:
Wherein beta represents the maximum value of the invasion cluster speed, and beta is more than alpha and | v | j (t) | | represents the size of the intrusion cluster speed;
Wherein the content of the first and second substances,representing neighbor individuals to individuals I j A unit vector of the position vector of (a);
N j the set of perceived neighbors is:
N j ={k|d jk <r sen ,k∈{1,...,N I },k≠j}
wherein d is jk Represents the distance, r, between individuals within an intruding cluster sen The sensing radius of the invading cluster is more than 0;
T j The set of imperceptible defenders is:
T j ={k|d jk <r sen ,k∈{1,...,N D }}
N D representing a defensive cluster;
2. A computer system, comprising: one or more processors, a computer readable storage medium, for storing one or more programs, wherein the one or more programs, when executed by the one or more processors, cause the one or more processors to implement the method of claim 1.
3. A computer-readable storage medium having stored thereon computer-executable instructions for, when executed, implementing the method of claim 1.
4. A computer program comprising computer executable instructions which when executed perform the method of claim 1.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210476976.0A CN115016526B (en) | 2022-05-01 | 2022-05-01 | Cluster self-organizing control method for double-layer defense |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210476976.0A CN115016526B (en) | 2022-05-01 | 2022-05-01 | Cluster self-organizing control method for double-layer defense |
Publications (2)
Publication Number | Publication Date |
---|---|
CN115016526A true CN115016526A (en) | 2022-09-06 |
CN115016526B CN115016526B (en) | 2024-04-30 |
Family
ID=83066843
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202210476976.0A Active CN115016526B (en) | 2022-05-01 | 2022-05-01 | Cluster self-organizing control method for double-layer defense |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN115016526B (en) |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108680063A (en) * | 2018-05-23 | 2018-10-19 | 南京航空航天大学 | A kind of decision-making technique for the dynamic confrontation of extensive unmanned plane cluster |
CN112000070A (en) * | 2020-07-28 | 2020-11-27 | 西北工业大学 | Heterogeneous cluster cooperative motion planning method |
WO2021036833A1 (en) * | 2019-08-28 | 2021-03-04 | 中国人民解放军国防科技大学 | Method for generating unmanned aerial vehicle cluster escort behavior based on improved virtual force field |
WO2021174765A1 (en) * | 2020-03-03 | 2021-09-10 | 中国科学院自动化研究所 | Control system based on multi-unmanned-aerial-vehicle collaborative game confrontation |
-
2022
- 2022-05-01 CN CN202210476976.0A patent/CN115016526B/en active Active
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108680063A (en) * | 2018-05-23 | 2018-10-19 | 南京航空航天大学 | A kind of decision-making technique for the dynamic confrontation of extensive unmanned plane cluster |
WO2021036833A1 (en) * | 2019-08-28 | 2021-03-04 | 中国人民解放军国防科技大学 | Method for generating unmanned aerial vehicle cluster escort behavior based on improved virtual force field |
WO2021174765A1 (en) * | 2020-03-03 | 2021-09-10 | 中国科学院自动化研究所 | Control system based on multi-unmanned-aerial-vehicle collaborative game confrontation |
CN112000070A (en) * | 2020-07-28 | 2020-11-27 | 西北工业大学 | Heterogeneous cluster cooperative motion planning method |
Non-Patent Citations (1)
Title |
---|
梁晓龙;孙强;尹忠海;王亚利;刘苹妮;: "大规模无人系统集群智能控制方法综述", 计算机应用研究, no. 01, pages 17 - 22 * |
Also Published As
Publication number | Publication date |
---|---|
CN115016526B (en) | 2024-04-30 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110929394B (en) | Combined combat system modeling method based on super network theory and storage medium | |
CN111260031A (en) | Unmanned aerial vehicle cluster target defense method based on deep reinforcement learning | |
CN110554709A (en) | Distributed bionic multi-agent autonomous cluster control method | |
CN112269396A (en) | Unmanned aerial vehicle cluster cooperative confrontation control method for eagle pigeon-imitated intelligent game | |
CN101901012A (en) | Distributed type multi-robot synchronous swarming control method | |
Liu et al. | A mechanism for recognizing and suppressing the emergent behavior of UAV swarm | |
La et al. | Cooperative flocking and learning in multi-robot systems for predator avoidance | |
Hahn et al. | Emergent escape-based flocking behavior using multi-agent reinforcement learning | |
CN109104737A (en) | A kind of cluster antagonism appraisal procedure based on time-varying network | |
Toghiani-Rizi et al. | Evaluating deep reinforcement learning for computer generated forces in ground combat simulation | |
CN112000070B (en) | Heterogeneous cluster cooperative motion planning method | |
CN114692397A (en) | Cluster distributed capture method based on multi-mechanism combination strategy | |
CN115016526A (en) | Cluster self-organizing control method for double-layer defense | |
Bouarara et al. | New swarm intelligence technique of artificial social cockroaches for suspicious person detection using N-gram pixel with visual result mining | |
Tang et al. | Research on an infectious disease transmission by flocking birds | |
Sun et al. | The study on intelligent advanced fighter air combat decision support system | |
Kaewkamnerdpong et al. | Perceptive particle swarm optimisation | |
Meng et al. | Research on multi-npc marine game ai system based on q-learning algorithm | |
Menne et al. | Alive in the Net | |
CN113283124B (en) | Multi-agent-based autonomous USoS participation model construction method and system | |
Sur et al. | Coalition formation for multi-agent coordination for surveillance and capture of foreign intruder using bacteria foraging algorithm | |
Zou et al. | A Self-organizing Dual-Layer Defense Algorithm for Multi-agent Systems | |
Das et al. | Prediction of behavior of a noncommunicative robot based on observations of its movement | |
CN116501036A (en) | Cluster system risk avoiding method based on partial interaction | |
Leigh et al. | Finding attack strategies for predator swarms using genetic algorithms |
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 |