CN113627082A - Unmanned intelligent cluster confrontation control method based on wolf hunting behavior bionics - Google Patents
Unmanned intelligent cluster confrontation control method based on wolf hunting behavior bionics Download PDFInfo
- Publication number
- CN113627082A CN113627082A CN202110883725.XA CN202110883725A CN113627082A CN 113627082 A CN113627082 A CN 113627082A CN 202110883725 A CN202110883725 A CN 202110883725A CN 113627082 A CN113627082 A CN 113627082A
- Authority
- CN
- China
- Prior art keywords
- enemy
- beta
- gamma
- intelligent
- cluster
- 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
- 238000000034 method Methods 0.000 title claims abstract description 40
- 241000282461 Canis lupus Species 0.000 title claims abstract description 23
- 235000001968 nicotinic acid Nutrition 0.000 title claims description 5
- 230000000903 blocking effect Effects 0.000 claims abstract description 17
- 230000008901 benefit Effects 0.000 claims abstract description 12
- 230000002776 aggregation Effects 0.000 claims abstract description 11
- 238000004220 aggregation Methods 0.000 claims abstract description 11
- 238000004891 communication Methods 0.000 claims abstract description 6
- 239000011664 nicotinic acid Substances 0.000 claims description 15
- 238000013459 approach Methods 0.000 claims description 6
- 230000015572 biosynthetic process Effects 0.000 claims description 6
- 230000002431 foraging effect Effects 0.000 claims description 3
- 238000013178 mathematical model Methods 0.000 claims description 3
- 230000008447 perception Effects 0.000 claims 2
- 230000006399 behavior Effects 0.000 abstract description 17
- 238000011160 research Methods 0.000 abstract description 4
- 230000003042 antagnostic effect Effects 0.000 abstract description 2
- 230000008485 antagonism Effects 0.000 abstract 1
- 239000002360 explosive Substances 0.000 abstract 1
- 238000004088 simulation Methods 0.000 abstract 1
- 239000003795 chemical substances by application Substances 0.000 description 23
- 230000009471 action Effects 0.000 description 18
- 239000013598 vector Substances 0.000 description 13
- 230000000007 visual effect Effects 0.000 description 7
- 230000000875 corresponding effect Effects 0.000 description 5
- 241000282421 Canidae Species 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 230000007123 defense Effects 0.000 description 3
- 238000013461 design Methods 0.000 description 3
- 230000001737 promoting effect Effects 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 230000006378 damage Effects 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000004069 differentiation Effects 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 230000009182 swimming Effects 0.000 description 2
- 239000006185 dispersion Substances 0.000 description 1
- 238000005265 energy consumption Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 244000144992 flock Species 0.000 description 1
- 230000009916 joint effect Effects 0.000 description 1
- 230000005012 migration Effects 0.000 description 1
- 238000013508 migration Methods 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 230000004083 survival effect Effects 0.000 description 1
- 238000012549 training Methods 0.000 description 1
- 230000001960 triggered effect Effects 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/004—Artificial life, i.e. computing arrangements simulating life
- G06N3/006—Artificial life, i.e. computing arrangements simulating life based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2111/00—Details relating to CAD techniques
- G06F2111/08—Probabilistic or stochastic CAD
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Software Systems (AREA)
- General Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Biophysics (AREA)
- Computer Hardware Design (AREA)
- Medical Informatics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Life Sciences & Earth Sciences (AREA)
- Biomedical Technology (AREA)
- Geometry (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)
- Catching Or Destruction (AREA)
Abstract
The invention discloses an unmanned intelligent cluster countermeasure control method based on simulation of wolf hunting behaviors, which combines the research on the wolf hunting behaviors, mainly uses an unmanned intelligent cluster with mediocre individual hitting performance as a main body, and develops countermeasures to enemies with high hitting performance through scale advantages and maneuvering performance advantages under the limitations of low communication performance among clusters and effective individual real-time vision. The control method fully simplifies the complex roles of the wolf colony society into two roles which have different functions and are matched with each other, namely a beta body with relatively strong durability and a gamma body with relatively strong explosive power, and continuously divides the antagonistic behaviors of each role into different stages, namely three stages of the beta body of wandering enemy seeking, starting-circulation aggregation and movement blocking and two stages of the gamma body of group seeking enemy and enemy attacking and attacking, thereby constructing the antagonistic control method which has a simple structure and is assisted by mass winning, decentralization and interference.
Description
Technical Field
The invention relates to an unmanned intelligent cluster countermeasure control method, in particular to a cluster countermeasure control method of a simple intelligent agent with high maneuverability and low durability.
Background
With the rapid development of the fields of automatic control, computer technology and the like, intelligent combat has become a major key point of the development of modern battlefields. The sophisticated intelligent agent with excellent individual striking performance can provide good advantages for users, but the configuration breadth of the intelligent agent is limited by the large requirements on cost and energy consumption; in contrast, a general agent, although not dominant in individual striking performance, has relative advantages in maneuvering performance, and can achieve more demands through a larger-scale clustering strategy, thereby being suitable for a wider application range. Meanwhile, the current cluster research mainly focuses on formation, communication and the like, the exploration on the decentralized countermeasure control aspect is still relatively thin, and direct discussion on the intelligent countermeasure strategy level is still less.
Compared with other existing unmanned cluster confrontation control methods, the bionic-based control method well considers the balance among different indexes such as interpretability, training difficulty and strategy flexibility. The hunting characteristics of the wolf pack further meet the core requirements of the unmanned cluster on excellence strength, decentralization, interference assistance and the like, and provide a high-quality template for a corresponding bionic control method. In particular, hunting strategies of wolf flocks can often defeat targets larger than their own size through quantitative advantages and special strategies; the hunting process does not depend on complicated communication among teams too much, and more, independent analysis of situation under unified combat guidelines is relied on by individuals to construct global cooperation; the hunting action is also in the process of quick and efficient fighting, and strong interference to real-time decision of an enemy is often attached.
The concept of the 'wolf pack war' is applied to the sea warfare in the European war field of the second war at the earliest, but the basic operational concept of 'converting cost advantage and maneuverability advantage into scale advantage to make up the peaceful of own individual strength' is only adopted, and the concept is not embodied as a real confrontation command model. Later wolves bionic research mostly focuses on optimization algorithms, but the design is rare in the aspect of cluster confrontation, the existing design is also over constrained to the recurrence of the complete social level of the wolves, and the implementation cost of the scheme is improved due to the complex role setting. The invention abstracts and researches the wolf hunting behaviors from the actual characteristics of the confrontation problem, summarizes the confrontation thought into more flexible role design and more specific confrontation steps, and establishes a simple and effective mathematical model, thereby providing a control method which is more suitable for a special main body of an unmanned cluster.
Disclosure of Invention
The invention provides a bionic control method based on wolf hunting behaviors and an implementation method thereof, aiming at solving the problem of cluster confrontation of low-ammunition-quantity and low-armored intelligent bodies. The control method can be applied to military occasions such as timely defense according to points, enemy target destruction and the like, and has certain advantages in aspects of blocking enemy actions and dividing enemy battle forms. Meanwhile, after local enemy force is eliminated, the control method can enable the intelligent cluster to continue to actively resist other enemy force organizations.
The unmanned intelligent cluster confrontation control method based on wolf hunting behavior bionics is a bionic control method with strategic stage differentiation and more importance on role division.
In the aspect of role division, the control method simply divides the cluster into a beta body and a gamma body without losing effectiveness:
the beta body carries more ammunition but has slower action speed, and is responsible for constructing a defense line and blocking enemy corresponding to the 'strong wolf' in the wolf group; the gamma body is agile in action, but carries less ammunition, and is responsible for fully striking and disturbing enemy corresponding to 'weak wolves' in wolves; the beta body has the potential of promoting into alpha body, and the promoted alpha body corresponds to the head wolf in the wolf group and is responsible for sending out a specific signal and gathering the our colony to the exact position where the enemy appears. Considering the possibility of many enemy paths, too long queues, complex lineups, etc., the control method allows coexistence of multiple alphabodies.
In the aspect of strategic stage division, the beta body has three stages of wandering and enemy seeking, starting-circulation gathering and movement blocking, and the gamma body has two stages of wandering along with a group and adversary attack. Although each agent makes independent phase switching according to the respective visual field information, the consistency of the battlefield situation can still generally generalize the control method into three cluster phases:
the first phase corresponds to the wandering phase after the start of the challenge, and no alpha bodies are yet present. The beta body is positioned at the stage of swimming to find enemy, keeps the distance between clusters and approaches to the approximate direction of an enemy target; the gamma body is in the group walk phase, following the nearby beta body.
The second phase corresponds to the staging phase triggered by the presence of an enemy object in a certain beta field of view. Promoting beta body meeting enemy to alpha body, sending out aggregation signal in the stage of starting aggregation; the beta body receiving the signal is in a cycle aggregation stage, and the beta body is selected to continuously swim to find enemies according to a certain probability and promote to the alpha body by itself or quickly move to the closest alpha body; the gamma body is still in the phase of group migration and rapidly approaches to the nearest alpha body along with the beta body.
The third phase then corresponds to the attack phase that my agent has entered by arriving at the collection. The alpha body enters a movement enemy resistance stage while keeping the starting aggregation, and starts movement resistance on enemy targets; when the beta body reaches the gathering position, the stage of moving and enemy blocking is carried out to assist the alpha body in blocking the enemy target; when the gamma body reaches the gathering position, the gamma body directly enters the stage of meeting enemy paradox, a rapid paradox is launched to an enemy target, a large amount of ammunition is rapidly put in, and large-scale striking is formed.
The invention is characterized in that:
(1) the intelligent agent clusters are differentiated by means of roles, a confrontation pattern with the cooperation of target concentration, alternate shielding and impact resistance is formed, the overall survival rate of the intelligent clusters is better improved, the action range of enemies is limited, the cluster confrontation efficiency is optimized, and the safety of the local base is guaranteed;
(2) the intelligent agent cluster depends on role differentiation, so that the intelligent agent can be manufactured according to role characteristics, only highlights the advantages of certain aspects and reduces the standards of other aspects, and the overall cost investment is effectively reduced.
(3) The intelligent agent behaviors ensure decentralization and low interaction rate, and meanwhile, the overall cooperativity of the individual behaviors is ensured by means of the same rule constraint, so that an overall strategy with certain interpretability is presented.
Drawings
FIG. 1 is a flow chart of an unmanned intelligent cluster countermeasure control method based on wolf hunting behavior bionics
Detailed Description
The present invention provides a bionic unmanned intelligent cluster countermeasure control method based on wolf hunting behaviors and its implementation, which will be described in detail with reference to the accompanying drawings.
The invention provides a wolf pack control method based on bionic wolf pack hunting behaviors. According to the objective performance difference existing in the intelligent agent of our party, the control method divides the unmanned cluster into beta bodies with more ammunition and weak maneuverability and gamma bodies with less ammunition and strong maneuverability. On the functional level, the beta body is responsible for constructing a defense line and blocking enemy by means of a large amount of ammunition; the gamma body is responsible for fully striking and disturbing enemy troops by virtue of excellent maneuvering performance. In addition, the beta body has the potential of promoting to the alpha body, and the promoted alpha body can send out a specific signal which is responsible for marking the exact position where the enemy appears by the group of the our parties and guiding other intelligent bodies to build up to the position.
Different agents have different confrontation stage selections in confrontation, and the different agents correspond to different confrontation behavior modes; each agent can independently switch the confrontation stage according to the respective visual field information and the embedded control logic and calculate the action decision corresponding to the stage. The overall control method flow is shown in fig. 1.
The following describes in detail the mathematical models of the two types of fighting characters and their multi-stage antagonistic actions involved in the present control method with reference to fig. 1.
1. Countermeasure model of beta body wandering foraging, starting-circulating gathering and motion blocking stage
The beta body of the bionic unmanned intelligent cluster confrontation control method has three-stage behavior modes, namely a wandering enemy seeking stage, a starting-cycle aggregation stage and a motion blocking stage.
(1) Stage of wandering to find enemy
The beta body wandering enemy seeking stage of the bionic unmanned intelligent cluster confrontation control method mainly corresponds to the initial stage of confrontation starting and the clearance of multiple confrontations. At this stage, the my intelligent agent still has a long distance from the enemy target, and the position of the enemy target can be roughly estimated only by timing information provided by a communication satellite and other systems, so that the main targets of the enemy can be divided into two types in order to more effectively contact the enemy target: the intelligent clusters remain dispersed within the clusters, located approximately close to the enemy target to increase the probability of contact.
According to the two action purposes, the control method obtains two corresponding action vectors uto_ene(i, t) and ufr_gar(i, t) are the action vectors of the approach of the body i to the enemy group and the dispersion of the group at time t. The unit action vectors obtained by normalizing the two are respectively recorded as
And
the calculation method is as follows:
in the formula, Dg(i, t) is the set of my agents (beta and gamma) in the field of view of my agent i (here beta) at time t, GeFor the set of data adversary targets in the satellite's latest interaction, rand (G, 5) is an operation of randomly picking up a maximum of 5 objects (without repetition) in set G, Xe(e, t) is a two-dimensional coordinate of the enemy target e at the time t; xβAnd (g, t) is a two-dimensional coordinate of the beta body g at the time t.
The target priority of the approaching enemy is higher than the cluster spread, and the distance (R) represented by two motion vectorstoAnd Rfr) The proportion of the two is influenced, and the final warfare of the intelligent agent i at the moment t can be balanced through the characteristicThe vector is acted upon slightly. The calculation method is as follows:
if my agent does not already exist in the field of view, the strategic action vector is directly equivalent to the action vector of the proximate enemy group, and the calculation method is as follows:
(2) starting-cycle order assembling stage
The beta body starting-cycle starting stage of the bionic unmanned intelligent cluster confrontation control method mainly corresponds to a starting stage when an enemy target appears behind a certain beta body visual field, and starting is directed to a beta body which is promoted to an alpha body, and cycle starting is directed to the beta body. At this stage, the beta body meeting enemy will advance to alpha body and send out aggregate command, and other beta bodies will have maximum stable speed v0(i) The approach to the closest α -body, the velocity and strategic action vector are calculated as follows:
v＝v0(i)
in the formula, Dα(i, t) is a set of alpha bodies that can be received by my agent i (here, beta body or alpha body) at time t, and R (k, i, t) is the distance from my agent i (here, beta body or alpha body) to a specified object k at time t.
If the beta body finds an enemy target at other places in the approaching process and the nearby alpha body can not be sensed through the received aggregation signal, whether the approaching is stopped or not is selected according to a certain probability, and the beta body is promoted to a new alpha body locally and a new aggregation is organized. If the sudden mass command disappears, the beta body resumes the wandering-away enemy-seeking phase. The holding time of the phase depends on the position of each agent, and is likely to be very short, even the alpha body keeps the starting posture to directly enter the motion blocking phase.
(3) Stage of motion blocking
The beta body movement blocking stage of the bionic unmanned intelligent cluster confrontation control method is promoted to be the joint action of the beta body of the alpha body and the beta body which acts around the alpha body. The beta body (including alpha body) immediately starts motion blocking upon encountering an enemy target. The purpose of the movement is to maintain a suitable distance within the enemy, the pair. Thus, the strategic action vector is defined as:
in the formula, Ratt(i) Is the radius of attack range of beta body i (or alpha body i), rand (a, b) is a random number between a and b,
is composed of
The strategic circular vector of the beta body i (or alpha body i) at the t moment obtained by 90 degrees is selected anticlockwise,
is a random unit vector.
The motion speed of the beta body i (or the alpha body i) is adjusted in real time according to the distance from an enemy target, and the calculation formula is as follows:
once no enemy target appears in the visual field, the beta body i (or the alpha body i) is converted into a state of wandering foraging or circulating congregation, and the specific selection is realized according to a certain probability.
2. Countermeasure model of gamma body in stages of walking with group and encountering enemy
The gamma body of the bionic unmanned intelligent cluster confrontation control method has two stages of behavior modes, namely a group walking stage and an enemy attack stage.
(1) Phase of swimming with the group
The bionic unmanned intelligent cluster confrontation control method is characterized in that the gamma body following the cluster walking stage mainly corresponds to the initial stage of confrontation starting, the clearance of multiple confrontations and the aggregation process of approaching to the alpha body according to signals. Given the limited gamma defence and ammunition count, it is required to act with the population to exert and shield the beta from each other.
The behavior strategy of the gamma body in the phase is basically the same as that of the beta body circulation aggregation phase. Therefore, the velocity and strategic action vector of γ body i at time t are calculated as follows:
v＝v0(i)
in the formula, XγAnd (g, t) is a two-dimensional coordinate of the gamma body g at the time t.
The only difference is that if the gamma body still can sense the existence of the beta body (including the beta body promoted to the alpha body) through direct sensing in the visual field, aggregate signal receiving, satellite timing information analysis and the like, the gamma body cannot be promoted to the alpha body. Thus, in general, when an enemy target enters the gamma field of view, the gamma will directly select an enemy strike. At this time, because of the previous grouping strategy, the gamma body acts near the beta body, and the rushing behavior can cover the beta body to form a blocking battle line and can also cause quick and practical disturbance and damage to the enemy, thereby meeting the fighting habit originally exhibited by the wolf colony.
(2) Attack stage in enemy
The gamma body attack enemy water stage in the bionic unmanned intelligent cluster confrontation control method mainly corresponds to the condition that enemy targets are sensed in a gamma body field. At this stage, the action target of the gamma body is to pay attention to the force of attack against the enemy and ignore the self-abandonment problem, so that the gamma body can launch half of the maximum volume of ammunition at most each time (if the target number of the enemy is not satisfied, the attack is carried out according to the target number of the enemy).
Considering that the deeper the gamma body is into the force of the enemy, the greater the disturbance and strike on the enemy. Thus, the gamma should move at the maximum steady speed towards the center of the enemy target in view, and the speed and strategic action vector are calculated as follows:
v＝v0(i)
at the same time, the gamma body should also fit the attack probability p according to the enemy situation in a comprehensive visual fielda(i, t) to measure whether a percussive action is currently initiated. The probability is calculated as follows:
in the formula, Ne(i, t) is the number of enemy objects in the gamma body i visual field range at the time t, NcThe number of enemy targets for recommending the hitting behavior of the intelligent agent.
If gamma ammunition is exhausted, the state of the charge should be maintained continuously to attract enemy firepower, disturb enemy formation and confuse enemy decisions. If the gamma body still survives after the assault, the assault is continuously started, the close alpha-beta body small cluster is returned, the action with the cluster is continuously carried out, and the assault is started opportunistically.
Claims (6)
1. Unmanned intelligent cluster confrontation control method based on wolf hunting behavior bionics, characterized by: the bionic unmanned intelligent cluster countermeasure control method enables each intelligent individual in the cluster to periodically broadcast the latest global battlefield information with low broadcasting frequency (20 minutes is taken as a reference unit) to the intelligent countermeasure cluster through the communication satellite system, and real-time countermeasure decisions are respectively made according to the unified countermeasure behavior mathematical model.
2. The intelligent countermeasure cluster of claim 1, characterized by: the subordinate intelligent confrontation cluster individuals comprise intelligent individuals with beta bodies and gamma bodies with different performance qualities; the number of the gamma bodies under the intelligent confrontation cluster is preferably about 5 times of that of the beta bodies; the total amount of the subordinate individuals of the intelligent confrontation cluster is not less than 6 times of the number of enemy targets to be struck.
3. The beta body according to claim 2, wherein: the beta body has the advantages of basic real-time local environment perception capability and relatively enemy maneuvering performance, and has no necessary limitation on other performance aspects; the beta body is embedded with the beta body basic algorithm logic of the wolf group tactics.
4. The gamma body of claim 2, wherein: the gamma body has no necessary limit on other performance aspects except the basic real-time local environment perception capability and the maneuvering performance advantage relative to the enemy; the gamma body is embedded with the gamma body basic algorithm logic of the wolf group tactics.
5. The beta basic algorithm logic of claim 3, wherein: the logic of the beta body basic algorithm is organically composed of three confrontation stages of wandering enemy seeking, starting-cyclic gathering and motion blocking, and an unmanned intelligent individual under the control of the algorithm is autonomously switched to a proper confrontation stage according to the situation of surrounding enemy and my power. In the stage of the wandering foraging, the beta body keeps a certain loose formation and approaches to the enemy according to the approximate global battlefield information timed by the communication satellite. In the starting-cycle stage, the beta body which is firstly contacted with the enemy is promoted to be alpha body, and an aggregation signal is sent to other intelligent individuals of our party, and meanwhile, the safe distance is kept between the beta body and the enemy target, and other beta cycle sets are waited; other beta bodies are quickly drawn to alpha at the starting position, if an enemy is met in the midway and no alpha body is started nearby, the approach is stopped, then the beta body is promoted to the alpha body per se, a set signal is initiated, and the beta body is continuously drawn to the original anchored alpha body position with small probability; in the motion blocking stage, a certain distance is kept between the issued alpha body and the beta body reaching the set position and an enemy target, and the motion type blocking is developed to block the enemy attack and interfere the enemy formation.
6. The gamma basic algorithm logic of claim 4, wherein: the gamma body basic algorithm logic is organically composed of two confrontation stages of walking along with a group and meeting enemy and front, and an unmanned intelligent individual under the control of the algorithm is autonomously switched to a proper confrontation stage according to the situation of surrounding enemy and my power. In the moving stage, the gamma body and the additional beta body always keep a certain distance range and move close to an enemy target along with the beta body; in the enemy attack stage, the gamma body quickly reaches the sending position of the alpha body, the attack is directly initiated by an enemy formation at the same speed, and a plurality of enemy targets are randomly selected to continuously and quickly strike while the attack is carried out, so that the enemy formation is destroyed, and the enemy strength is reduced.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110883725.XA CN113627082B (en) | 2021-08-03 | 2021-08-03 | Unmanned intelligent cluster countermeasure control method based on wolf group hunting behavior bionical |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110883725.XA CN113627082B (en) | 2021-08-03 | 2021-08-03 | Unmanned intelligent cluster countermeasure control method based on wolf group hunting behavior bionical |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113627082A true CN113627082A (en) | 2021-11-09 |
| CN113627082B CN113627082B (en) | 2024-02-13 |
Family
ID=78382340
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110883725.XA Active CN113627082B (en) | 2021-08-03 | 2021-08-03 | Unmanned intelligent cluster countermeasure control method based on wolf group hunting behavior bionical |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113627082B (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2018048854A1 (en) * | 2016-09-09 | 2018-03-15 | Wal-Mart Stores, Inc. | Apparatus and method for unmanned flight task optimization |
| CN110069076A (en) * | 2019-04-23 | 2019-07-30 | 北京航空航天大学 | A kind of unmanned plane cluster air battle method for surrounding and seize behavior based on violent wolf |
| CN112925345A (en) * | 2021-01-26 | 2021-06-08 | 北京航空航天大学 | Cluster enclosure control method of unmanned combat aircraft imitating wolf hunting behaviors |
-
2021
- 2021-08-03 CN CN202110883725.XA patent/CN113627082B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2018048854A1 (en) * | 2016-09-09 | 2018-03-15 | Wal-Mart Stores, Inc. | Apparatus and method for unmanned flight task optimization |
| CN110069076A (en) * | 2019-04-23 | 2019-07-30 | 北京航空航天大学 | A kind of unmanned plane cluster air battle method for surrounding and seize behavior based on violent wolf |
| CN112925345A (en) * | 2021-01-26 | 2021-06-08 | 北京航空航天大学 | Cluster enclosure control method of unmanned combat aircraft imitating wolf hunting behaviors |
Non-Patent Citations (2)
| Title |
|---|
| 张新明;涂强;康强;程金凤;: "强化狼群等级制度的灰狼优化算法", 数据采集与处理, no. 05 * |
| 郑国锋;于劲松;刘浩: "基于PXI总线的光学雷达自动测试系统研制", 计算机测量与控制, vol. 18, no. 05 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113627082B (en) | 2024-02-13 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108680063B (en) | A kind of decision-making technique for extensive unmanned plane cluster dynamic confrontation | |
| Johnson | Artificial intelligence: a threat to strategic stability | |
| Duan et al. | A predator-prey particle swarm optimization approach to multiple UCAV air combat modeled by dynamic game theory | |
| CN108318032A (en) | A kind of unmanned aerial vehicle flight path Intelligent planning method considering Attack Defence | |
| CN109709981B (en) | Competitive antagonism method for unmanned aerial vehicle group | |
| Liu et al. | A mechanism for recognizing and suppressing the emergent behavior of UAV swarm | |
| CN107562074A (en) | A kind of method for allocating tasks surrounded and seize towards MAUVS | |
| Arquilla | From blitzkrieg to bitskrieg: the military encounter with computers | |
| CN111624996A (en) | Multi-unmanned-boat incomplete information trapping method based on game theory | |
| Hanley | Creating the 1980s Maritime strategy and implications for today | |
| Betz | Redesigning Land Forces for Wars Amongst the People | |
| CN113627082A (en) | Unmanned intelligent cluster confrontation control method based on wolf hunting behavior bionics | |
| CN115061495B (en) | Unmanned aerial vehicle group countermeasure autonomous control method based on eagle pigeon game | |
| CN116661496A (en) | Multi-patrol-missile collaborative track planning method based on intelligent algorithm | |
| Spulak | A Theory of Special Operations. | |
| CN113703479B (en) | Weapon configuration method and system based on high-density value and large depth | |
| CN113627081B (en) | Unmanned intelligent cluster countermeasure control method based on eagle crowd hunting behavior bionical | |
| Gürcan et al. | The Gallipoli Campaign: The Turkish Perspective | |
| Simonjan et al. | Reinforcement Learning-based Countermeasures against Attacking UAV Swarms | |
| Hallinan | China's sea of conflict | |
| King et al. | Informal team assignment in a pursuit-evasion game | |
| Ross et al. | The Search for Tactical Success in Vietnam: An Analysis of Australian Task Force Combat Operations | |
| CN113325876B (en) | Unmanned aerial vehicle induced penetration strategy | |
| Mukayev | Historical aspects on the formation of the concepts" strategy"," tactics", principles of their application in modern organizations | |
| CN112578685B (en) | Unmanned aerial vehicle cluster countermeasure simulation method based on cascading failure |
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 |