CN114492058B - Multi-agent confrontation scene oriented defense situation assessment method and device - Google Patents
Multi-agent confrontation scene oriented defense situation assessment method and device Download PDFInfo
- Publication number
- CN114492058B CN114492058B CN202210115950.3A CN202210115950A CN114492058B CN 114492058 B CN114492058 B CN 114492058B CN 202210115950 A CN202210115950 A CN 202210115950A CN 114492058 B CN114492058 B CN 114492058B
- Authority
- CN
- China
- Prior art keywords
- agent
- safety energy
- energy
- safety
- protection
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
- G06F2119/02—Reliability analysis or reliability optimisation; Failure analysis, e.g. worst case scenario performance, failure mode and effects analysis [FMEA]
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Software Systems (AREA)
- Computational Mathematics (AREA)
- Pure & Applied Mathematics (AREA)
- Databases & Information Systems (AREA)
- Mathematical Optimization (AREA)
- Mathematical Analysis (AREA)
- Algebra (AREA)
- Computer Hardware Design (AREA)
- Evolutionary Computation (AREA)
- Geometry (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The application discloses a multi-agent confrontation scene oriented defense situation assessment method and device, wherein the method comprises the following steps: and under the multi-agent confrontation scene, judging whether the multi-agent confrontation starts or not, if the multi-agent confrontation starts, calculating protection safety energy in the confrontation environment by using a preset safety energy field hierarchical model, updating a safety energy field situation map according to the protection safety energy, and updating the safety energy field situation at the current moment until the multi-agent confrontation ends to obtain a defense situation evaluation result of the multi-agent confrontation scene. Therefore, the problems that the concrete behaviors of the intelligent agent on the microscopic level are ignored, the modeling of objective physical laws is lacked, the interpretability is low, the intelligent degree is low, the real-time performance is poor, the follow-up intelligent agent can not be subjected to decision service and the like in the related technology are solved.
Description
Technical Field
The application relates to the technical field of defense situation assessment, in particular to a multi-agent confrontation scene oriented defense situation assessment method and device.
Background
Under the modern informatization condition, the detectable range in the confrontation scene is increasingly expanded, the information sources are more and more extensive, the obtained information is large in quantity, complicated in meaning and quick in change, the information greatly exceeds the information comprehensive capability of the human brain, and the cognitive overload phenomenon of the finger control personnel is easily caused. Therefore, the understanding judgment of the situation of the multi-agent confrontation scene based on the multi-source information fusion has become one of the core technologies of the confrontation environment information system. However, the comprehensive situation assessment in the confrontation scene is difficult to realize in the related art, because there is no mature model to uniformly quantify and understand the multi-source information in the scene, it is difficult to make an accurate and quick judgment on the current situation.
There are two main types of related technologies:
the first method comprises the following steps: based on the confrontation environment information, the confrontation environment situation is classified into the capability situation, the efficiency situation, the comprehensive situation and the like. Although the method realizes unified carding of different 'potentials', the boundaries of various 'potentials' are fuzzy, and concrete quantification is difficult to realize;
and the second method comprises the following steps: based on the confrontation scene, aiming at a specific scene, a situation quantification model based on a rough set theory, information entropy, a dynamic Bayesian network and other methods is provided. Although the situation quantitative evaluation is realized by the method, the confrontation scene is endless, and the models cannot be unified.
In summary, most of the related technologies only propose some fuzzy overall situation awareness methods, and do not deeply explore the physical principles of the specific intelligent agent defense and attack behaviors.
Through analysis of the related technology, the current defense situation assessment method can be found to have the following main problems:
1) A situation assessment method based on the physical principle of the defense behaviors of the intelligent agent is not proposed;
2) Most research objects are macro scenes, and the specific behavior of the intelligent agent on the micro level is ignored;
3) Most research means are application of data statistical methods, but not modeling of objective physical laws, so that the method is not strong in universality and low in interpretability;
4) The situation assessment method lacks real-time performance and cannot serve the decision making of subsequent intelligent agents;
5) The method needs a large amount of data support and has low intelligent degree.
In summary, the defense situation assessment methods in the related art still need to be improved.
Disclosure of Invention
The application provides a defense situation assessment method and device for a multi-agent confrontation scene, and aims to solve the problems that the specific behaviors of agents on a microscopic level are ignored, modeling of objective physical laws is lacked, interpretability is low, intelligence degree is low, instantaneity is poor, decision service for subsequent agents cannot be achieved, and the like in the related art.
The embodiment of the first aspect of the application provides a defense situation assessment method facing a multi-agent confrontation scene, which comprises the following steps: under the multi-agent confrontation scene, judging whether the multi-agent confrontation starts or not; if the multi-agent confrontation starts, calculating protection safety energy in the confrontation environment by using a preset safety energy field hierarchical model; and updating a safety energy field situation map according to the protection safety energy, and updating the safety energy field situation at the current moment until the multi-agent confrontation is finished to obtain a defense situation evaluation result of the multi-agent confrontation scene.
Optionally, in an embodiment of the present application, the calculating the safeguard safety energy in the countermeasure environment by using the preset safety energy field hierarchical model includes: acquiring agent information of a plurality of agents; inputting the intelligent agent information and the current environment information into a passive protection safety layer model, a single motor safety layer model and/or a group cooperative safety layer model to obtain passive protection safety energy, single motor safety energy and/or group cooperative safety energy; obtaining the safeguard safety energy based on the passive safeguard safety energy, the individual mobile safety energy, and/or the population collaborative safety energy.
Optionally, in one embodiment of the present application, the agent information includes one or more of a type, a location, an orientation, a physical protection strength, and a mobility performance of the agent.
Optionally, in an embodiment of the present application, a calculation formula of the passive safety energy is:
wherein e is phy (x, y) is the defense security strength of the smart passive defense security contribution at the (x, y) point in the scene, FD bre The physical protection strength of the intelligent agent is defined as: energy of collision or impact per unit area, S, required to destroy a target agent mob Is the mobility range of the agent unit.
Optionally, in an embodiment of the present application, the calculation formula of the single body maneuver safety energy is:
wherein e is mob (x, y) is the defense security strength of the agent individual maneuver Security contribution at the (x, y) point in the scene, S dam Is the area of the damaged actor of the agent unit, e phy (x, y) is defense security strength of intelligent agent dynamic protection security contribution at (x, y) point in scene, S mob Is the mobility range of the agent unit.
Optionally, in an embodiment of the present application, a calculation formula of the group collaborative safety energy is:
wherein e is sog For the monomer comprehensive protection of safety energy, e saf And (x, y) is defense security strength of cooperative security contribution of the intelligent agent group at the point (x, y) in the scene, namely group comprehensive protection security energy.
Optionally, in an embodiment of the present application, the updating the safety energy field situation map according to the protection safety energy includes: based on the protection safety energy of any point in the countermeasure environment, the total protection safety energy in the countermeasure unit self-destruction amplitude transformer is obtained, and the expected safety energy field energy is determined, wherein the calculation formula of the expected safety energy field energy is as follows:
wherein E is saf For the resulting expected safe energy field energy, e saf (x, y) is defense security strength of cooperative security contribution of agent group at point (x, y) in scene, namely group comprehensive protection security energy, S dam Is the area of the damage spotter of the intelligent agent unit.
The embodiment of the second aspect of the present application provides a multi-agent confrontation scenario-oriented defense situation assessment device, including: the judging module is used for judging whether the multi-agent confrontation starts or not under the multi-agent confrontation scene; the computing module is used for computing protection safety energy in a confrontation environment by utilizing a preset safety energy field hierarchical model if the multi-agent confrontation is started; and the evaluation module is used for updating the safety energy field situation map according to the protection safety energy, updating the safety energy field situation at the current moment until the multi-agent confrontation is finished, and obtaining the defense situation evaluation result of the multi-agent confrontation scene.
Optionally, in an embodiment of the present application, the calculation module includes: an obtaining unit for obtaining agent information of a plurality of agents; the first computing unit is used for inputting the intelligent agent information and the current environment information into a passive protection safety layer model, a single motor safety layer model and/or a group cooperative safety layer model to obtain passive protection safety energy, single motor safety energy and/or group cooperative safety energy; a second computing unit, configured to obtain the safeguard safety energy based on the passive safeguard safety energy, the individual maneuver safety energy, and/or the group collaborative safety energy.
Optionally, in one embodiment of the present application, the agent information includes one or more of a type, a location, an orientation, a physical protection strength, and a mobility performance of the agent.
Optionally, in an embodiment of the present application, a calculation formula of the passive protection safety energy is:
wherein e is phy (x, y) is the defense security strength of the passive defense security contribution of the agent at the (x, y) point in the scene, FD bre The physical protection strength of the intelligent agent is defined as: energy of collision or impact per unit area, S, required to destroy a target agent mob Is the mobility range of the agent unit.
Optionally, in an embodiment of the present application, the calculation formula of the single body maneuvering safety energy is:
wherein e is mob (x, y) is defense security strength of agent monomer maneuvering security contribution at (x, y) point in scene, S dam Is the area of the damaged person of the agent unit, e phy (x, y) is defense security strength of intelligent agent dynamic protection security contribution at (x, y) point in scene, S mob Is the mobility range of the agent unit.
Optionally, in an embodiment of the present application, a calculation formula of the group collaborative safety energy is:
wherein e is sig For the monomer comprehensive protection of safety energy, e saf And (x, y) is defense security strength of cooperative security contribution of the intelligent agent group at the point (x, y) in the scene, namely group comprehensive protection security energy.
Optionally, in an embodiment of the present application, the evaluation module is further configured to: based on the protection safety energy of any point in the countermeasure environment, acquiring the total protection safety energy in the damage sponders of the countermeasure unit, and determining the expected safety energy field energy, wherein the calculation formula of the expected safety energy field energy is as follows:
wherein E is saf For the resulting expected safe energy field energy, e saf (x, y) is defense security strength of cooperative security contribution of intelligent agent groups at (x, y) point in scene, namely group comprehensive protection security energy, S dam Is the area of the damaged radiator of the intelligent body unit.
An embodiment of a third aspect of the present application provides an electronic device, including: the defense situation assessment method for the multi-agent confrontation scene comprises a memory, a processor and a computer program which is stored in the memory and can run on the processor, wherein the processor executes the program to realize the defense situation assessment method for the multi-agent confrontation scene according to the embodiment.
A fourth aspect of the present application provides a computer-readable storage medium, on which a computer program is stored, the program being executed by a processor for implementing the multi-agent confrontation scenario-oriented defense situation assessment method as claimed in any one of claims 1 to 7.
According to the embodiment of the application, the protection safety energy in the confrontation environment is calculated by establishing the safety energy field layered model, the safety energy field situation at the current moment is updated in real time, the defense situation evaluation result of the confrontation scene of the multi-agent is further obtained, the specific behavior of the agent on the microscopic level can be evaluated, the intelligent degree is high, the universality is high, the interpretability is high, the real-time performance is good, and the follow-up agent decision service can be provided. Therefore, the problems that the concrete behaviors of the intelligent agent on the microscopic level are ignored, the modeling of objective physical laws is lacked, the interpretability is low, the intelligent degree is low, the real-time performance is poor, the follow-up intelligent agent can not be subjected to decision service and the like in the related technology are solved.
Additional aspects and advantages of the present application will be set forth in part in the description which follows and, in part, will be obvious from the description, or may be learned by practice of the present application.
Drawings
The foregoing and/or additional aspects and advantages of the present application will become apparent and readily appreciated from the following description of the embodiments, taken in conjunction with the accompanying drawings of which:
FIG. 1 is a flowchart of a multi-agent confrontation scenario-oriented defense situation assessment method according to an embodiment of the present application;
FIG. 2 is a diagram of a collision range and maneuver range of a cross-hair unit provided in accordance with an embodiment of the present application;
FIG. 3 is a diagram of a range of hits on a boresight unit provided in accordance with one embodiment of the present application;
FIG. 4 is a group collaborative security graph provided in accordance with an embodiment of the present application;
FIG. 5 is a schematic diagram illustrating a multi-agent confrontation scenario oriented defense situation assessment method according to an embodiment of the present application;
FIG. 6 is an illustration of a safety energy field model test sample provided in accordance with an embodiment of the present application;
FIG. 7 is a diagram of a my party safe energy field situation provided in accordance with one embodiment of the present application;
fig. 8 is a situation diagram of a partner safety energy field provided according to an embodiment of the present application;
FIG. 9 is a schematic structural diagram of a multi-agent confrontation scenario-oriented defense situation assessment device according to an embodiment of the present application;
fig. 10 is a schematic structural diagram of an electronic device according to an embodiment of the present application.
Detailed Description
Reference will now be made in detail to embodiments of the present application, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to the same or similar elements or elements having the same or similar function throughout. The embodiments described below with reference to the drawings are exemplary and intended to be used for explaining the present application and should not be construed as limiting the present application.
The defense situation assessment method and device for the multi-agent confrontation scene according to the embodiment of the application are described below with reference to the accompanying drawings. In the method, by establishing a safety energy field layered model, protective safety energy in a confrontation environment is calculated, and the safety energy field situation at the current moment is updated in real time, so that a defense situation evaluation result of the confrontation scene of the multi-agent is obtained, the specific behavior of the agent on the microscopic level can be evaluated, the intelligent degree is high, the universality is strong, the interpretability is high, the real-time performance is good, and the subsequent agent decision service can be provided. Therefore, the problems that the concrete behaviors of the intelligent agent on the microscopic level are ignored, the modeling of objective physical laws is lacked, the interpretability is low, the intelligent degree is low, the real-time performance is poor, the follow-up intelligent agent can not be subjected to decision service and the like in the related technology are solved.
Specifically, fig. 1 is a schematic flowchart of a multi-agent confrontation scenario-oriented defense situation assessment method according to an embodiment of the present application.
As shown in FIG. 1, the defense situation assessment method facing the multi-agent confrontation scene comprises the following steps:
in step S101, in the multi-agent countermeasure scenario, it is determined whether multi-agent countermeasure is started.
In the actual execution process, when the agents of the two confrontation parties continuously move and take different actions, the embodiment of the application can monitor the surrounding environment condition in real time by using the sensor configured by the agent, and call sensor data such as an image sensor, a laser radar and a GPS (global positioning system), so as to provide data support for the subsequent steps.
In step S102, if the multi-agent countermeasure is started, the protection safety energy in the countermeasure environment is calculated using the preset safety energy field hierarchical model.
Specifically, after the multi-agent countermeasure is judged to be started, the protection safety energy in the countermeasure environment can be calculated by using a preset safety energy field layered model, wherein the establishment of the safety energy field layered model will be described in detail below. The embodiment of the application is based on the physical principle of defense behaviors of the intelligent agent, obtains the protection safety energy in the confrontation environment through the preset safety energy field layered model, can evaluate the specific behaviors of the intelligent agent on the microscopic level, and is high in intelligent degree, strong in universality and high in interpretability.
Optionally, in an embodiment of the present application, calculating a protection safety energy in the countermeasure environment using a preset safety energy field hierarchical model includes: acquiring agent information of a plurality of agents; inputting the intelligent agent information and the current environment information into a passive protection safety layer model, a single motor safety layer model and/or a group cooperative safety layer model to obtain passive protection safety energy, single motor safety energy and/or group cooperative safety energy; and acquiring protection safety energy based on the passive protection safety energy, the single motor safety energy and/or the group cooperative safety energy.
As a possible implementation manner, the embodiment of the present application may use a preset safety energy field hierarchical model to calculate the protection safety energy in the countermeasure environment, where the step of building the safety energy field hierarchical model includes: data extraction, passive protection safety layer model establishment, single motor safety layer model establishment, group cooperation safety layer model establishment and the like. According to the embodiment of the application, after the intelligent agent information of the multiple intelligent agents is obtained, the obtained intelligent agent information is input into the established model, and corresponding passive protection safety energy, single motor safety energy and/or group cooperation safety energy are obtained, so that protection safety energy is obtained. The embodiment of the application is based on the physical principle of defense behaviors of the intelligent agent, obtains the protection safety energy in the confrontation environment through the preset safety energy field layered model, can evaluate the specific behaviors of the intelligent agent on the microscopic level, and is high in intelligent degree, strong in universality and high in interpretability.
Optionally, in one embodiment of the present application, the agent information includes one or more of a type, location, orientation, physical protection strength, and mobility of the agent.
It can be understood that extracting agent information is an input module of a safety energy field, which has very important influence on efficiency and effect of defense situation assessment, and in a countermeasure environment, the embodiment of the application can obtain required agent information and environment information by two methods:
1. information acquisition based on a high-precision stereo fusion perception technology, such as: type, location and orientation of agent;
2. information acquisition relying on a comprehensive intelligent agent unit database, such as: physical protection strength of the agent, maneuvering characteristics (maximum speed, maximum acceleration, etc.).
In the embodiment of the present application, the information of the agent to be acquired includes, but is not limited to, one or more of the type, location, orientation, physical protection strength, and mobility of the agent, wherein the specific information acquisition type may be adjusted by a person skilled in the art according to the actual situation, and is not limited specifically here.
Optionally, in an embodiment of the present application, the calculation formula of the passive protection safety energy is:
wherein e is phy (x, y) is the defense security strength of the passive defense security contribution of the agent at the (x, y) point in the scene, FD bre The physical protection strength of the intelligent agent is defined as: energy of collision or impact per unit area, S, required to destroy a target agent mob Is the mobility range of the agent unit.
The establishment of the passive safeguard layer model is described in detail herein.
It can be understood that the action mechanism of the passive protection security layer is that the intelligent agent bears the threat through self armor, in the actual confrontation environment, because the intelligent agent unit has mobility, at any point in the self mobility range, the intelligent agent unit can provide protection for the intelligent agent unit or other intelligent agent units in the mobility range through the physical protection of the self armor, so the passive protection security energy is calculated as follows:
wherein e is phy (x, y) is defense security strength of the smart passive defense security contribution at (x, y) point in the scene, DD bre The physical protection strength of the intelligent agent is defined as: energy of collision or impact per unit area, S, required to destroy a target agent mob Is the mobility range of the agent unit.
In the actual implementation process, the radius R of the dynamic range of the intelligent agent is calculated mob In the process, assuming that the agent escapes with the maximum mobility, two situations need to be considered for calculation at this time:
1. the intelligent agent runs with the maximum acceleration which can be generated by the intelligent agent, and the intelligent agent can not reach the maximum speed of the intelligent agent within the maneuver escape time t, under the condition, the intelligent agent is in a uniform acceleration motion state within the time t, so the range radius R mob The maximum distance that the agent can travel within the time;
2. the intelligent body accelerates with the maximum acceleration that can be generated by the intelligent body, and within the escape time t of the movement, the intelligent body can reach the maximum speed of the intelligent body, under the condition, the intelligent body is firstly in a uniform acceleration movement state within the time t, and is in a uniform movement state after reaching the maximum speed, and the radius R of the range is at the moment mob Is the sum of the two movement distances.
That is, the radius T of the dynamic range of the agent mob The calculation may be as follows:
wherein v is 0 Is the current speed, v, of the agent unit max Is the maximum speed of the agent unit, a max The maximum acceleration which can be sent by the intelligent agent unit, and t is the maneuvering escape time of the intelligent agent unit. According to the embodiment of the application, the fact that the intelligent agent unit has strong steering capacity is considered, and therefore the influence of the current speed direction on the maneuvering range is ignored.
When the defense capacity of the intelligent agent unit is quantified, the maneuvering escape time t can be constant; in the embodiment of the application, when the defense function of the protection intelligent unit on the threat intelligent unit is specifically calculated, the maneuvering escape time t can be determined by the projectile emergence speed v of the threat intelligent unit and the distance d between the two parties, and the calculation formula is as follows:
optionally, in an embodiment of the present application, the calculation formula of the single body maneuver safety energy is:
wherein e is mob (x, y) is the defense security strength of the agent individual maneuver Security contribution at the (x, y) point in the scene, S dam Is the area of the damaged person of the agent unit, e phy (x, y) is defense security strength of intelligent agent dynamic protection security contribution at (x, y) point in scene, S mob Is the mobility range of the agent unit.
The construction of the model of the one-piece motorized security layer is explained in detail here.
It can be understood that the action mechanism of the single body maneuvering safety is that the intelligent body unit utilizes the self maneuverability, and when threatens the locking of the intelligent body unit by the other party, the intelligent body unit avoids the self by maneuvering, and the self physical protection function is played to the maximum extent. If the damage range of the intelligent unit of the opposite side is larger than the maneuvering range of the intelligent unit of the same side, the intelligent unit of the opposite side can be damaged as long as aiming at the current position of the intelligent unit of the same side to shoot, and the single maneuvering safety energy is the single passive protection safety energy at the moment. If the damage range of the intelligent unit of the opposite party is smaller than the maneuvering range of the intelligent unit of the opposite party, the intelligent unit of the opposite party can possibly avoid the threat behavior of the opposite party through the maneuverability of the intelligent unit of the opposite party, and equivalently, the defense capability of the intelligent unit of the opposite party is correspondingly enhanced in the damage scope of the intelligent unit of the opposite party.
Based on the above mechanism, when the single motor safety energy is calculated, the defense strength in the damage sponders needs to be strengthened. The embodiment of the application can use the ratio of the maneuvering range area of the intelligent body unit to the self damage width as the measurement standard of the defense reinforcing degree, and the field energy calculation mode is as follows:
wherein e is mob (x, y) is the defense security strength of the smart-body mobile security contribution, R, at the (x, y) point in the scene mob Is the mobile radius of the agent unit, S dam Is the area of the damage spotter of the intelligent agent unit.
In the above method for calculating the energy of the single maneuvering safety layer in the generalized safety energy field, during the specific field force calculation, since the object of attack and defense is already determined, a more detailed maneuvering safety energy calculation mode is required. The mode that the intelligent agent unit with the threat type of indirect aiming damages the target is regional explosion, so that the non-escape rate of the target intelligent agent unit is the ratio of the area of an explosion region to the area of a maneuvering range; for the intelligent unit with the threat type of direct aiming, the damage mode is linear shooting, so the non-escape rate of the target unit is the ratio of the shape of a maneuvering circle inscribed drum with the damage width man as half side length to the maneuvering range, namely:
1. inter-aiming intelligent body unit
If the detonation radius is smaller than the maneuver radius (as shown in FIG. 2), defense enhancement is performed within the offender of the agent unit based on the area ratio of the detonation range to the maneuver range; if the detonation radius is greater than or equal to the maneuver radius, no reinforcement is performed. The field energy is calculated as follows:
wherein R is exp For aiming between the explosion radius, R, of the agent unit mob To defend against the mobility radius of the agent unit.
2. Direct-aiming intelligent unit
The radius of the intelligent unit damage amplitude worker is considered as R dam If the flight path of the shot of the direct-aiming intelligent agent unit is the transverse line in the upper graph 3, the defense intelligent agent unit is determined to be damaged when the moving range of the mass center is in the dark blue rectangular frame in the maneuvering range, and otherwise, the defense intelligent agent unit is not damaged. Based on the evasive mechanism, the safety energy corresponding to the threat of the direct-view agent unit is calculated as follows:
wherein R is mob To protect the mobility radius of the agent unit, a is the area of the damaged area (i.e. the dark rectangle in fig. 3), and the calculation method is as follows:
after passive protection safety and monomer maneuvering safety are comprehensively considered, monomer comprehensive protection safety energy e sig The calculation is as follows:
when the intelligent agent unit monomer comprehensive protection safety energy is quantized,the embodiment of the application can regard the threat agent unit as an inter-aiming unit and has the radius R of the explosion range exp Taking a constant; when the protection safety energy of the intelligent agent unit to a specific threat unit is quantified, the monomer comprehensive protection safety energy can be obtained through the analysis and calculation.
Optionally, in an embodiment of the present application, a formula for calculating the group collaborative safety energy is:
wherein e is sig For the comprehensive protection of safety energy of the monomers, e saf And (x, y) is defense security strength of cooperative security contribution of the intelligent agent group at the point (x, y) in the scene, namely group comprehensive protection security energy.
The establishment of the group collaborative security layer model is described in detail herein.
It can be understood that in a real multi-agent confrontation environment, the importance levels of the agent units are different, and when the whole body is threatened greatly, the instructor is likely to need to make a trade-off between the agent units, even the agent unit with the lower importance level is needed to bear the threat to the agent unit with the higher importance level. The establishment of the safe energy field model also needs to take such a cooperative behavior into account, that is, the group cooperates with the safe energy. Through the steps, the monomer comprehensive protection safety energy e of each intelligent agent unit for resisting a certain point in the environment is obtained sig (x, y). At this time, if n our agent units are in the confrontation environment, the safety protection energy can be extended from the monomer protection to the cooperative protection. Fig. 4 shows the action principle of group cooperative protection, and the group cooperative protection safety energy can be directly superimposed by the individual safety energy of different agent units at a certain point, and is calculated as follows:
wherein e is saf And (x, y) is defense security strength of cooperative security contribution of the intelligent agent group at the point (x, y) in the scene, namely group comprehensive protection security energy.
In summary, the protection capability against a certain point in the environment consists of three protection behaviors: the self-physical protection, the self-mobility protection and the group cooperative protection respectively correspond to a passive protection safety, a monomer mobility safety and a group cooperative safety three-layer structure of a safety energy field.
In step S103, the safety energy field situation map is updated according to the protection safety energy, and the safety energy field situation at the current time is updated until the multi-agent confrontation is finished, so as to obtain a defense situation evaluation result of the multi-agent confrontation scene.
According to the embodiment of the application, the safety energy field situation map can be updated according to the protection energy obtained through calculation in the steps, the safety energy field situation at the current moment is updated until the multi-agent confrontation is finished, and then the defense situation evaluation result of the multi-agent confrontation scene is obtained. According to the embodiment of the application, the safety energy field model can be established based on the protection behaviors of the intelligent agents in the confrontation scene, and the evaluation of the defense situation in the confrontation environment is realized, so that the subsequent situation understanding and decision making are facilitated.
Optionally, in an embodiment of the present application, updating the safety energy field situation map according to the protection safety energy includes: based on the protection safety energy of any point in the countermeasure environment, the total protection safety energy in the damage amplitude transformer of the countermeasure unit is obtained, and the expected safety energy field energy is determined, wherein the calculation formula of the expected safety energy field energy is as follows:
wherein E is saf For the resulting expected safe energy field energy, e saf (x, y) is defense security strength of cooperative security contribution of agent group at point (x, y) in scene, namely group comprehensive protection security energy, S dam Is the area of the damage spotter of the intelligent agent unit.
In the actual implementation process, the embodiment of the application can obtain the comprehensive protection safety energy e of any point in the countermeasure environment through the analysis and calculation in the step S102 saf (x, y), the total protection safety energy in the damage amplitude personnel of the countermeasure unit is the obtained expected safety energy field energy E saf ：
The operation principle of the evaluation method according to the embodiment of the present application is described in detail with reference to fig. 2 to 8.
As shown in fig. 5, the evaluation method of the embodiment of the present application includes the following steps:
step S501: multi-agent confrontation begins. In the actual execution process, when the agents of the two confrontation parties continuously move and take different actions, the embodiment of the application can monitor the surrounding environment condition in real time by using the sensor configured by the agent, and call sensor data such as an image sensor, a laser radar and a GPS (global positioning system), so as to provide data support for subsequent steps.
Step S502: and establishing a safe energy field layered model according to the sensing result and the intelligent agent database. The embodiment of the application can use a preset safe energy field layered model to calculate the protection safe energy in the countermeasure environment, wherein the step of establishing the safe energy field layered model comprises the following steps: data extraction, passive protection safety layer model establishment, monomer maneuvering safety layer model establishment, group cooperation safety layer model establishment and the like. According to the embodiment of the application, after the intelligent agent information of the multiple intelligent agents is obtained, the obtained intelligent agent information is input into the established model, and corresponding passive protection safety energy, single motor safety energy and/or group cooperation safety energy are obtained, so that protection safety energy is obtained. The embodiment of the application is based on the physical principle of defense behaviors of the intelligent agent, obtains the protection safety energy in the confrontation environment through the preset safety energy field layered model, can evaluate the specific behaviors of the intelligent agent on the microscopic level, and is high in intelligent degree, strong in universality and high in interpretability.
The passive protection safety layer model establishment, the single motor safety layer model establishment and the group collaborative safety layer model establishment are respectively designed as follows:
and a, establishing a safety energy field model and extracting required data.
It can be understood that extracting agent information is an input module of a safety energy field, which has very important influence on efficiency and effect of defense situation assessment, and in a countermeasure environment, the embodiment of the application can obtain required agent information and environment information by two methods:
1. information acquisition based on a high-precision stereo fusion perception technology, such as: type, location and orientation of agent;
2. information acquisition relying on a comprehensive intelligent agent unit database, such as: physical protection strength, mobility (maximum speed, maximum acceleration, etc.) of the agent.
And b, establishing a passive protection safety layer model.
It can be understood that the passive protection safety layer has an action mechanism that an intelligent agent bears threats through self armors, and in an actual confrontation environment, because an intelligent agent unit has mobility, at any point in the mobility range of the intelligent agent unit, the intelligent agent unit can provide protection for the intelligent agent unit or other intelligent agent units in the mobility range through physical protection of the self armors, so that passive protection safety energy is calculated as follows:
wherein e is phy (x, y) is the defense security strength of the smart passive defense security contribution at the (x, y) point in the scene, FD bre Is the physical protection strength of the intelligent agent, and is defined as follows: energy of collision or impact per unit area, S, required to destroy a target agent mob Is the mobility range of the agent unit.
In the actual implementation process, the radius R of the dynamic range of the intelligent agent is calculated mob In time, assuming that the agent escapes with maximum mobility, the calculation needs to consider two situations:
1. the intelligent body is accelerated to run at the maximum acceleration which can be generated by the intelligent body, and the intelligent body cannot reach the maximum speed of the intelligent body within the running escape time t, under the condition, the intelligent body is in a uniform acceleration motion state within the time t, so the radius R of the range mob The maximum distance that the agent can travel within the time;
2. the intelligent body accelerates with the maximum acceleration that can be generated by the intelligent body, and within the escape time t of the movement, the intelligent body can reach the maximum speed of the intelligent body, under the condition, the intelligent body is firstly in a uniform acceleration movement state within the time t, and is in a uniform movement state after reaching the maximum speed, and the radius R of the range is at the moment mob Is the sum of the two movement distances.
Namely radius R of dynamic range of intelligent body mob The calculation is as follows:
wherein v is 0 Is the current speed, v, of the agent unit max Is the maximum speed of the agent unit, a max The maximum acceleration which can be sent by the intelligent agent unit, and t is the maneuvering escape time of the intelligent agent unit. According to the embodiment of the application, the fact that the intelligent agent unit has strong steering capacity is considered, and therefore the influence of the current speed direction on the maneuvering range is ignored.
When the defense capacity of the intelligent agent unit is quantified, the maneuvering escape time t can be constant; in the embodiment of the application, when the defense function of the protection intelligent unit on the threat intelligent unit is specifically calculated, the maneuvering escape time t can be determined by the projectile emergence speed v of the threat intelligent unit and the distance d between the two parties, and the calculation formula is as follows:
and c, establishing a monomer mobile safety layer model.
It can be understood that the action mechanism of the single body maneuvering safety is that the intelligent body unit utilizes the self maneuverability, and when threatens the locking of the intelligent body unit by the other party, the intelligent body unit avoids the self by maneuvering, and the self physical protection function is played to the maximum extent. If the damage range of the intelligent unit of the opposite side is larger than the maneuvering range of the intelligent unit of the same side, the intelligent unit of the opposite side can be damaged as long as aiming at the current position of the intelligent unit of the same side to shoot, and the single maneuvering safety energy is the single passive protection safety energy at the moment. If the damage range of the intelligent unit of the opposite party is smaller than the maneuvering range of the intelligent unit of the opposite party, the intelligent unit of the opposite party can possibly avoid the threat behavior of the opposite party through the maneuverability of the intelligent unit of the opposite party, and equivalently, the defense capability of the intelligent unit of the opposite party is correspondingly enhanced in the damage scope of the intelligent unit of the opposite party.
Based on the above mechanism, when the single motor safety energy is calculated, the defense strength in the damage sponders needs to be strengthened. The embodiment of the application can use the ratio of the maneuvering range area of the intelligent unit to the self-damaged amplitude transformer as the measurement standard of defense reinforcing degree, and the field energy calculation mode is as follows:
wherein e is mob (x, y) is the defense security strength of the smart-body mobile security contribution, R, at the (x, y) point in the scene mob Is the mobile radius of the agent unit, S dam Is the area of the damage spotter of the intelligent agent unit.
In the above method for calculating the energy of the single maneuvering safety layer in the generalized safety energy field, during the specific field force calculation, since the object of attack and defense is already determined, a more detailed maneuvering safety energy calculation mode is required. The mode that the intelligent agent unit with the threat type of indirect aiming damages the target is regional explosion, so that the non-escape rate of the target intelligent agent unit is the ratio of the area of an explosion region to the area of a maneuvering range; for the intelligent unit with the threat type of direct aiming, the damage mode is linear shooting, so the non-escape rate of the target unit is the ratio of the shape of a maneuvering circle inscribed drum with the damage width man as half side length to the maneuvering range, namely:
1. inter-aiming intelligent body unit
If the explosion radius is smaller than the maneuvering radius (as shown in fig. 2), defense enhancement is carried out in the damage spotters of the agent units based on the area ratio of the explosion range to the maneuvering range; if the detonation radius is greater than or equal to the maneuver radius, no reinforcement is performed. The field energy is calculated as follows:
wherein R is exp For aiming between the explosion radius, R, of the agent unit mob To defend against the mobility radius of the agent unit.
2. Direct-aiming intelligent unit
The radius of the intelligent unit damage amplitude worker is considered as R dam If the flying trajectory of the projectile of the direct-aiming intelligent body unit is the horizontal line in the upper graph 3, the defense intelligent body unit is determined to be damaged when the moving range of the center of mass of the defense intelligent body unit is in the dark blue rectangular frame in the moving range, otherwise, the defense intelligent body unit is not damaged. Based on the evasive mechanism, the safety energy corresponding to the threat of the direct-view agent unit is calculated as follows:
wherein R is mob To protect the mobility radius of the agent unit, a is the area of the damaged area (i.e. the dark rectangle in fig. 3), and the calculation method is as follows:
after passive protection safety and monomer maneuvering safety are comprehensively considered, monomer comprehensive protection safety energy e sig The calculation is as follows:
when the comprehensive protection safety energy of the intelligent agent unit monomer is quantified, the intelligent agent unit can be regarded as an inter-aiming unit, and the radius R of the explosion range exp Taking a constant; when the protection safety energy of the intelligent agent unit to a specific threat unit is quantified, the monomer comprehensive protection safety energy can be obtained through the analysis and calculation.
And d, establishing a group collaborative security layer model.
It will be appreciated that in a real multi-agent confrontation environment, the individual agent units will be of different importance, and that when the whole is threatened significantly, the director will likely need to make a trade-off between the agent units, or even the agent unit of lower importance, to sustain the threat to the agent unit of higher importance. The establishment of the safe energy field model also needs to consider the cooperative behavior, that is, the group cooperates with the safe energy. Through the steps, the comprehensive protection safety energy e of each intelligent agent unit for the monomer resisting a certain point in the environment is obtained sig (x, y). At this time, if n intelligent agent units of our party are in the confrontation environment, the safety protection energy can be extended from single protection to cooperative protection. Fig. 4 shows the action principle of group cooperative protection, and the group cooperative protection safety energy may be directly superimposed by the individual safety energy of different agent units at a certain point, and is calculated as follows:
wherein e is saf (x, y) is defense security strength of cooperative security contribution of the intelligent agent group at the (x, y) point in the scene, namely group comprehensive protection security energy.
In summary, the protection ability against a certain point in the environment consists of three protection behaviors: the self-physical protection, the self-mobility protection and the group cooperative protection respectively correspond to a passive protection safety, a monomer mobility safety and a group cooperative safety three-layer structure of a safety energy field.
Step S503: and updating the situation map of the safe energy field. According to the embodiment of the application, the comprehensive protection safety energy e of any point in the confrontation environment can be obtained through the analysis and calculation of the step S502 saf (x, y), the total protection safety energy in the damage amplitude of the countermeasure unit is the expected safety energy field energy E saf ：
A sample scenario for defense situation assessment using a safety energy field is given below, and is shown in fig. 6.
The sample graph is a 100m x 50m area, where blue is my agent unit and red is the counterpart agent unit. The 'D/D' represents a direct-aiming agent unit, the 'I/I' represents an intermediate-aiming agent unit, and the 'C/C' represents a command unit. The coordinate position of each unit is shown in table 1, and table 1 shows the coordinate position of each agent unit of the test sample.
TABLE 1
Sample parameters of the direct-aiming intelligent agent units (D1, D2, D1, D2), the intermediate-aiming intelligent agent units (I1, I2, I1, I2) and the command control units (C1, C1) are respectively shown in tables 2, 3 and 4. Wherein, table 2 is a direct-aiming intelligent agent unit sample parameter, table 3 is a indirect-aiming intelligent agent unit sample parameter, and table 4 is a command control unit sample parameter.
TABLE 2
TABLE 3
TABLE 4
The parameters are input into the safety energy field calculation model, and situation diagrams of the safety energy field of the current party and the safety energy field of the opposite party are obtained and are respectively shown as fig. 7 and fig. 8, wherein areas with brighter colors represent stronger defense safety situations.
According to the defense situation assessment method for the multi-agent confrontation scene, the protection safety energy in the confrontation environment is calculated by establishing the safety energy field layered model, the safety energy field situation at the current moment is updated in real time, and then the defense situation assessment result of the multi-agent confrontation scene is obtained. Therefore, the problems that the concrete behaviors of the intelligent agent on the microscopic level are ignored, the modeling of objective physical laws is lacked, the interpretability is low, the intelligent degree is low, the real-time performance is poor, the follow-up intelligent agent can not be subjected to decision service and the like in the related technology are solved.
Next, a multi-agent confrontation scenario-oriented defense situation assessment device according to an embodiment of the present application will be described with reference to the drawings.
Fig. 9 is a block diagram illustrating a defense situation assessment apparatus facing a multi-agent confrontation scenario according to an embodiment of the present application.
As shown in fig. 9, the multi-agent confrontation scenario-oriented defense situation assessment apparatus 10 includes: a judgment module 100, a calculation module 200 and an evaluation module 300.
Specifically, the determining module 100 is configured to determine whether the multi-agent confrontation starts in a multi-agent confrontation scenario.
A calculating module 200, configured to calculate, if the multi-agent countermeasure starts, protection safety energy in the countermeasure environment using a preset safety energy field hierarchical model.
And the evaluation module 300 is configured to update the safety energy field situation map according to the protection safety energy, and update the safety energy field situation at the current moment until the multi-agent confrontation is finished, so as to obtain a defense situation evaluation result of the multi-agent confrontation scene.
Optionally, in an embodiment of the present application, the computing module 200 includes: the device comprises an acquisition unit, a first calculation unit and a second calculation unit.
The acquiring unit is used for acquiring the agent information of the multi-agent.
The first computing unit is used for inputting the intelligent agent information and the current environment information into the passive protection safety layer model, the single motor safety layer model and/or the group cooperation safety layer model to obtain passive protection safety energy, single motor safety energy and/or group cooperation safety energy.
And the second computing unit is used for acquiring protection safety energy based on the passive protection safety energy, the single motor-driven safety energy and/or the group cooperative safety energy.
Optionally, in one embodiment of the present application, the agent information includes one or more of a type, location, orientation, physical protection strength, and mobility of the agent.
Optionally, in an embodiment of the present application, the calculation formula of the passive protection safety energy is:
wherein e is phy (x, y) is the defense security strength of the smart passive defense security contribution at the (x, y) point in the scene, FD bre Is the physical protection strength of the intelligent agent, and is defined as follows: energy of collision or impact per unit area, S, required to destroy a target agent mob Is the mobility range of the agent unit.
Optionally, in an embodiment of the present application, the calculation formula of the single body maneuvering safety energy is:
wherein e is mob (x, y) is the defense security strength of the agent individual maneuver Security contribution at the (x, y) point in the scene, S dam Is the area of the damaged actor of the agent unit, e phy (x, y) is defense security strength of intelligent agent dynamic protection security contribution at (x, y) point in scene, S mob Is the mobility range of the agent unit.
Optionally, in an embodiment of the present application, a formula for calculating the group collaborative safety energy is:
wherein e is sig For the monomer comprehensive protection of safety energy, e saf And (x, y) is defense security strength of cooperative security contribution of the intelligent agent group at the point (x, y) in the scene, namely group comprehensive protection security energy.
Optionally, in an embodiment of the present application, the evaluation module 300 is further configured to: based on the protection safety energy of any point in the countermeasure environment, the total protection safety energy in the damage amplitude transformer of the countermeasure unit is obtained, and the expected safety energy field energy is determined, wherein the calculation formula of the expected safety energy field energy is as follows:
wherein E is saf For the resulting expected safe energy field energy, e saf (x, y) is defense security strength of cooperative security contribution of agent group at point (x, y) in scene, namely group comprehensive protection security energy, S dam Is the area of the damage spotter of the intelligent agent unit.
It should be noted that the explanation of the embodiment of the method for evaluating a defense situation of a multi-agent confrontation scenario is also applicable to the apparatus for evaluating a defense situation of a multi-agent confrontation scenario of the embodiment, and details are not repeated herein.
According to the defense situation assessment device for the multi-agent confrontation scene, the protection safety energy in the confrontation environment is calculated by establishing the safety energy field layered model, the safety energy field situation at the current moment is updated in real time, and then the defense situation assessment result of the multi-agent confrontation scene is obtained. Therefore, the problems that the concrete behaviors of the intelligent agent on the microscopic level are ignored, the modeling of objective physical laws is lacked, the interpretability is low, the intelligent degree is low, the real-time performance is poor, the decision service for the follow-up intelligent agent cannot be realized and the like in the related technology are solved.
Fig. 10 is a schematic structural diagram of an electronic device according to an embodiment of the present application. The electronic device may include:
The processor 1002 executes the program to implement the multi-agent confrontation scenario-oriented defense situation assessment method provided in the above embodiment.
Further, the electronic device further includes:
a communication interface 1003 for communicating between the memory 1001 and the processor 1002.
A memory 1001 for storing computer programs that may be run on the processor 1002.
If the memory 1001, the processor 1002, and the communication interface 1003 are implemented independently, the communication interface 1003, the memory 1001, and the processor 1002 may be connected to each other through a bus and perform communication with each other. The bus may be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, an Extended ISA (EISA) bus, or the like. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of illustration, only one thick line is shown in FIG. 10, but this is not intended to represent only one bus or type of bus.
Optionally, in a specific implementation, if the memory 1001, the processor 1002 and the communication interface 1003 are integrated on one chip, the memory 1001, the processor 1002 and the communication interface 1003 may complete communication therebetween through an internal interface.
The processor 1002 may be a Central Processing Unit (CPU), an Application Specific Integrated Circuit (ASIC), or one or more Integrated circuits configured to implement embodiments of the present Application.
The present embodiment also provides a computer-readable storage medium, on which a computer program is stored, where the program, when executed by a processor, implements the multi-agent confrontation scenario-oriented defense situation assessment method as above.
In the description herein, reference to the description of the term "one embodiment," "some embodiments," "an example," "a specific example," or "some examples," etc., means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the application. In this specification, the schematic representations of the terms used above are not necessarily intended to refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or N embodiments or examples. Furthermore, various embodiments or examples and features of different embodiments or examples described in this specification can be combined and combined by one skilled in the art without contradiction.
Furthermore, the terms "first", "second" and "first" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one such feature. In the description of the present application, "N" means at least two, e.g., two, three, etc., unless specifically limited otherwise.
Any process or method descriptions in flow charts or otherwise described herein may be understood as representing modules, segments, or portions of code which include one or more N executable instructions for implementing steps of a custom logic function or process, and alternate implementations are included within the scope of the preferred embodiment of the present application in which functions may be executed out of order from that shown or discussed, including substantially concurrently or in reverse order, depending on the functionality involved, as would be understood by those reasonably skilled in the art of implementing the embodiments of the present application.
The logic and/or steps represented in the flowcharts or otherwise described herein, such as an ordered listing of executable instructions that can be considered to implement logical functions, can be embodied in any computer-readable medium for use by or in connection with an instruction execution system, apparatus, or device, such as a computer-based system, processor-containing system, or other system that can fetch the instructions from the instruction execution system, apparatus, or device and execute the instructions. For the purposes of this description, a "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of the computer-readable medium would include the following: an electrical connection (electronic device) having one or N wires, a portable computer diskette (magnetic device), a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disc read-only memory (CDROM). Additionally, the computer-readable medium could even be paper or another suitable medium upon which the program is printed, as the program can be electronically captured, via for instance optical scanning of the paper or other medium, then compiled, interpreted or otherwise processed in a suitable manner if necessary, and then stored in a computer memory.
It should be understood that portions of the present application may be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, the N steps or methods may be implemented in software or firmware stored in a memory and executed by a suitable instruction execution system. If implemented in hardware, as in another embodiment, any one or combination of the following techniques, which are known in the art, may be used: a discrete logic circuit having a logic gate circuit for implementing a logic function on a data signal, an application specific integrated circuit having an appropriate combinational logic gate circuit, a Programmable Gate Array (PGA), a Field Programmable Gate Array (FPGA), or the like.
It will be understood by those skilled in the art that all or part of the steps carried out in the method of implementing the above embodiments may be implemented by hardware related to instructions of a program, which may be stored in a computer readable storage medium, and the program, when executed, includes one or a combination of the steps of the method embodiments.
In addition, functional units in the embodiments of the present application may be integrated into one processing module, or each unit may exist alone physically, or two or more units are integrated into one module. The integrated module can be realized in a hardware mode, and can also be realized in a software functional module mode. The integrated module, if implemented in the form of a software functional module and sold or used as a separate product, may also be stored in a computer-readable storage medium.
The storage medium mentioned above may be a read-only memory, a magnetic or optical disk, etc. While embodiments of the present application have been shown and described above, it will be understood that the above embodiments are exemplary and should not be construed as limiting the present application and that changes, modifications, substitutions and alterations in the above embodiments may be made by those of ordinary skill in the art within the scope of the present application.
Claims (14)
1. A multi-agent confrontation scene oriented defense situation assessment method is characterized by comprising the following steps:
under the multi-agent confrontation scene, judging whether the multi-agent confrontation starts or not;
if the multi-agent confrontation starts, calculating protection safety energy in the confrontation environment by using a preset safety energy field layered model, wherein the step of establishing the preset safety energy field layered model comprises the steps of obtaining agent information of the multi-agent, inputting the agent information and current environment information into a passive protection safety layer model, a single mobile safety layer model and a group cooperative safety layer model to obtain passive protection safety energy, single mobile safety energy and group cooperative safety energy, and obtaining the protection safety energy based on the passive protection safety energy, the single mobile safety energy and the group cooperative safety energy; and
and updating a safety energy field situation map according to the protection safety energy, and updating the safety energy field situation at the current moment until the multi-agent confrontation is finished to obtain a defense situation evaluation result of the multi-agent confrontation scene.
2. The method of claim 1, wherein the agent information comprises one or more of agent type, location, orientation, physical defense strength, and mobility.
3. The method according to claim 1 or 2, wherein the passive safety energy is calculated by the formula:
wherein e is phy (x, y) is defense security strength of intelligent agent dynamic protection security contribution at (x, y) point in scene，FD bre The physical protection strength of the intelligent agent is defined as: energy of collision or impact per unit area, S, required to destroy a target agent mob Is the mobility range of the agent unit.
4. The method of claim 3, wherein the single body maneuver safety energy is calculated by the formula:
wherein e is mob (x, y) is the defense security strength of the agent individual maneuver Security contribution at the (x, y) point in the scene, S dam Is the area of the damage spotter of the intelligent agent unit.
5. The method of claim 4, wherein the formula for calculating the group collaborative safety energy is:
wherein e is sig For the monomer comprehensive protection of safety energy, e saf And (x, y) is defense security strength of cooperative security contribution of the intelligent agent group at the point (x, y) in the scene, namely group comprehensive protection security energy.
6. The method of claim 5, wherein updating the safety energy field situation map according to the safeguard safety energy comprises:
based on the protection safety energy of any point in the countermeasure environment, acquiring the total protection safety energy in the damage sponders of the countermeasure unit, and determining the expected safety energy field energy, wherein the calculation formula of the expected safety energy field energy is as follows:
wherein, E saf Is the expected safe energy field energy obtained.
7. A multi-agent confrontation scene-oriented defense situation assessment device is characterized by comprising:
the judging module is used for judging whether the multi-agent confrontation starts or not under the multi-agent confrontation scene;
the computing module is used for computing protection safety energy in a confrontation environment by using a preset safety energy field hierarchical model if the multi-agent confrontation is started, wherein the step of establishing the preset safety energy field hierarchical model comprises the steps of acquiring agent information of the multi-agent, inputting the agent information and current environment information into a passive protection safety layer model, a single mobile safety layer model and a group cooperation safety layer model to obtain passive protection safety energy, single mobile safety energy and group cooperation safety energy, and obtaining the protection safety energy based on the passive protection safety energy, the single mobile safety energy and the group cooperation safety energy; and
and the evaluation module is used for updating the safety energy field situation map according to the protection safety energy, updating the safety energy field situation at the current moment until the multi-agent confrontation is finished, and obtaining the defense situation evaluation result of the multi-agent confrontation scene.
8. The apparatus of claim 7, wherein the agent information comprises one or more of a type, location, orientation, physical defense strength, and mobility of an agent.
9. The apparatus of claim 7 or 8, wherein the passive safety energy is calculated by the formula:
wherein e is phy (x, y) is the defense security strength of the passive defense security contribution of the agent at the (x, y) point in the scene, FD bre Is the physical protection strength of the intelligent agent, and is defined as follows: energy of collision or impact per unit area, S, required to destroy a target agent mob Is the mobility range of the agent unit.
10. The apparatus of claim 9, wherein the calculation formula of the single body maneuver safety energy is:
wherein e is mob (x, y) is the defense security strength of the agent individual maneuver Security contribution at the (x, y) point in the scene, S dam Is the area of the damage spotter of the intelligent agent unit.
11. The apparatus of claim 9, wherein the formula for calculating the group coordination safety energy is:
wherein e is sig For the monomer comprehensive protection of safety energy, e saf And (x, y) is defense security strength of cooperative security contribution of the intelligent agent group at the point (x, y) in the scene, namely group comprehensive protection security energy.
12. The apparatus of claim 11, wherein the evaluation module is further configured to:
based on the protection safety energy of any point in the countermeasure environment, the total protection safety energy in the countermeasure unit self-destruction amplitude transformer is obtained, and the expected safety energy field energy is determined, wherein the calculation formula of the expected safety energy field energy is as follows:
wherein E is saf Is the expected safe energy field energy obtained.
13. An electronic device, comprising: a memory, a processor and a computer program stored on the memory and executable on the processor, the processor executing the program to implement the multi-agent confrontation scenario oriented defense situation assessment method as claimed in any of claims 1-6.
14. A computer-readable storage medium having stored thereon a computer program for execution by a processor for implementing a multi-agent confrontation scenario oriented defense situation assessment method as claimed in any one of claims 1-6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210115950.3A CN114492058B (en) | 2022-02-07 | 2022-02-07 | Multi-agent confrontation scene oriented defense situation assessment method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210115950.3A CN114492058B (en) | 2022-02-07 | 2022-02-07 | Multi-agent confrontation scene oriented defense situation assessment method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114492058A CN114492058A (en) | 2022-05-13 |
| CN114492058B true CN114492058B (en) | 2023-02-03 |
Family
ID=81478347
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210115950.3A Active CN114492058B (en) | 2022-02-07 | 2022-02-07 | Multi-agent confrontation scene oriented defense situation assessment method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114492058B (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112861442A (en) * | 2021-03-10 | 2021-05-28 | 中国人民解放军国防科技大学 | Multi-machine collaborative air combat planning method and system based on deep reinforcement learning |
| CN113791634A (en) * | 2021-08-22 | 2021-12-14 | 西北工业大学 | Multi-aircraft air combat decision method based on multi-agent reinforcement learning |
| CN113805569A (en) * | 2021-09-23 | 2021-12-17 | 北京理工大学 | Multi-agent technology-based countermeasure system, method, terminal and storage medium |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20220027798A1 (en) * | 2020-07-24 | 2022-01-27 | SparkCognition, Inc. | Autonomous behaviors in a multiagent adversarial scene |
-
2022
- 2022-02-07 CN CN202210115950.3A patent/CN114492058B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112861442A (en) * | 2021-03-10 | 2021-05-28 | 中国人民解放军国防科技大学 | Multi-machine collaborative air combat planning method and system based on deep reinforcement learning |
| CN113791634A (en) * | 2021-08-22 | 2021-12-14 | 西北工业大学 | Multi-aircraft air combat decision method based on multi-agent reinforcement learning |
| CN113805569A (en) * | 2021-09-23 | 2021-12-17 | 北京理工大学 | Multi-agent technology-based countermeasure system, method, terminal and storage medium |
Non-Patent Citations (5)
| Title |
|---|
| An Interactive Self-Learning Game and Evolutionary Approach Based on Non-Cooperative Equilibrium;Li,Y et al.;《ELECTRONICS》;20220103;第10卷(第23期);2977 * |
| Research on the decision model of multi-agent cooperative confrontation;Zhongqiu Zhang;《2020 International Conference on Big Data and Informatization Education (ICBDIE)》;20200911;375-378 * |
| 基于势场函数战场态势可视化分析方法研究;张建伟等;《计算机与数字工程》;20090820(第08期);92-95 * |
| 基于深度学习的空天防御态势感知方法;高晓阳等;《火力与指挥控制》;20180815(第08期);10-14 * |
| 基于贝叶斯推理的海战场空中目标意图分层识别方法;杨璐等;《火力与指挥控制》;20180715(第07期);88-95 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114492058A (en) | 2022-05-13 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105306248A (en) | Operation loop based operational effectiveness assessment method of weapon equipment system operation network | |
| CN114492059B (en) | Multi-agent confrontation scene situation assessment method and device based on field energy | |
| CN112633415B (en) | Unmanned aerial vehicle cluster intelligent task execution method and device based on rule constraint training | |
| CN116360503B (en) | Unmanned plane game countermeasure strategy generation method and system and electronic equipment | |
| CN112749761A (en) | Enemy combat intention identification method and system based on attention mechanism and recurrent neural network | |
| CN111784135A (en) | System combat capability quantitative analysis method based on hyper-network and OODA (object oriented data acquisition) ring theory | |
| CN112651377A (en) | Ice and snow movement accident detection method and device and terminal equipment | |
| CN110163519B (en) | UUV red and blue threat assessment method for base attack and defense tasks | |
| CN114492058B (en) | Multi-agent confrontation scene oriented defense situation assessment method and device | |
| CN115953668A (en) | Method and system for detecting camouflage target based on YOLOv5 algorithm | |
| CN115310345A (en) | Artificial potential field-based intelligent algorithm evaluation method and device | |
| CN113283110B (en) | Situation perception method for intelligent confrontation simulation deduction | |
| CN115310257B (en) | Situation estimation method and device based on artificial potential field | |
| CN114548674B (en) | Multi-agent confrontation scene oriented threat situation assessment method, device and equipment | |
| Lei et al. | Technique for target recognition based on intuitionistic fuzzy reasoning | |
| CN108446858A (en) | Vacant lot intimidation estimating method based on particular network structure | |
| CN109724472B (en) | Vehicle-mounted regional comprehensive defense system and method | |
| CN110493035A (en) | A kind of data entry device and device that network security index calculates | |
| Aikins et al. | Resilience analysis of deep q-learning algorithms in driving simulations against cyberattacks | |
| CN117150738B (en) | Action direction pre-judging method under complex scene | |
| CN116680542B (en) | Method and system for generating trunk branch situation and bypass branch situation | |
| CN116796521B (en) | Water surface combat crowd combat simulation method and device, electronic equipment and storage medium | |
| CN114078331B (en) | Overspeed detection method, overspeed detection device, visual sensor and storage medium | |
| Li et al. | Effectiveness evaluation of kill chain based on PCA, AHP and entropy weight method | |
| CN117171960A (en) | Multi-unmanned platform collaborative decision-making method oriented to unmanned scene |
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 |