CN116452306B - Bid distribution method for intelligent combat task - Google Patents
Bid distribution method for intelligent combat task Download PDFInfo
- Publication number
- CN116452306B CN116452306B CN202310217931.6A CN202310217931A CN116452306B CN 116452306 B CN116452306 B CN 116452306B CN 202310217931 A CN202310217931 A CN 202310217931A CN 116452306 B CN116452306 B CN 116452306B
- Authority
- CN
- China
- Prior art keywords
- task
- intelligent
- bidding
- bid
- unit
- 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
- 238000000034 method Methods 0.000 title claims abstract description 34
- 238000011156 evaluation Methods 0.000 claims abstract description 40
- 230000015572 biosynthetic process Effects 0.000 claims abstract description 11
- 238000004891 communication Methods 0.000 claims abstract description 10
- 238000012216 screening Methods 0.000 claims description 38
- 230000007613 environmental effect Effects 0.000 claims description 22
- 230000006996 mental state Effects 0.000 claims description 16
- 230000008901 benefit Effects 0.000 claims description 15
- 230000006870 function Effects 0.000 claims description 13
- 238000000354 decomposition reaction Methods 0.000 claims description 8
- 238000004364 calculation method Methods 0.000 claims description 6
- 238000012544 monitoring process Methods 0.000 claims description 4
- 230000000694 effects Effects 0.000 claims description 3
- 238000004519 manufacturing process Methods 0.000 claims description 3
- GOLXNESZZPUPJE-UHFFFAOYSA-N spiromesifen Chemical compound CC1=CC(C)=CC(C)=C1C(C(O1)=O)=C(OC(=O)CC(C)(C)C)C11CCCC1 GOLXNESZZPUPJE-UHFFFAOYSA-N 0.000 claims description 3
- 238000012163 sequencing technique Methods 0.000 claims 1
- 230000036541 health Effects 0.000 abstract description 3
- 239000003795 chemical substances by application Substances 0.000 description 8
- 230000008569 process Effects 0.000 description 7
- 238000004445 quantitative analysis Methods 0.000 description 6
- 239000000463 material Substances 0.000 description 4
- 239000000446 fuel Substances 0.000 description 3
- 230000009471 action Effects 0.000 description 2
- 230000016571 aggressive behavior Effects 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 230000005484 gravity Effects 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012552 review Methods 0.000 description 2
- 230000004888 barrier function Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 239000006185 dispersion Substances 0.000 description 1
- 238000012854 evaluation process Methods 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 230000001681 protective effect Effects 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 230000007474 system interaction Effects 0.000 description 1
- 230000009897 systematic effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/08—Auctions
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
- G06Q10/06311—Scheduling, planning or task assignment for a person or group
Landscapes
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Engineering & Computer Science (AREA)
- Strategic Management (AREA)
- Entrepreneurship & Innovation (AREA)
- Economics (AREA)
- General Physics & Mathematics (AREA)
- Accounting & Taxation (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Development Economics (AREA)
- Finance (AREA)
- Theoretical Computer Science (AREA)
- Marketing (AREA)
- Educational Administration (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention belongs to the technical field of intelligent combat command control, and relates to a bidding distributing method. A bid distribution method for intelligent fight tasks is characterized in that a decision support unit converts fight intents of commanders into fight tasks, a task bid unit decomposes the fight tasks into fight subtasks, and the task bid unit interacts with a task bid unit through a task distribution protocol to automatically realize automatic distribution of the fight tasks. The task bidding unit interacts with the task bidding unit based on the resources and capabilities of the intelligent twin body, and signs part of the combat task with the task bidding unit according to the evaluation of the resource state, the health state and the communication state of the corresponding combat formation. The task bid evaluation unit evaluates the bidding scheme provided by the intelligent twin to determine whether the bidding intelligent twin has task execution capability, and the bid intelligent twin can be signed and confirmed after the bid evaluation meets the conditions. The invention effectively improves the combat capability.
Description
Technical Field
The invention belongs to the technical field of intelligent combat command control, and relates to a bidding distributing method.
Background
In future informatization warfare, the battlefield environment is increasingly complex and changeable instantaneously, and tactical action forms are various, but the common characteristics are agile response and flexible decision. With the dynamic change of battlefield environment and the complex diversity of battlefields, the traditional battlefield mode can not meet the requirement of systematic battlefield, and a new battlefield mode is urgently required to be designed for future battlefield so as to fill the current capability shortboards, so that mosaic battlefields and similar battlefield styles are generated. In the mosaic combat and the like combat patterns, a single platform is converted into a scattered capability unit, namely a mosaic unit, in a form of a complete combat unit, so that a more flexible and complex combination mode is realized, and the form can break through the limitation of the platform on combat capability and support the construction of a more complex killing net.
Taking a military unmanned aerial vehicle as an example, in a traditional combat style, the capability of a single unmanned aerial vehicle is taken as a basic unit, and the single unmanned aerial vehicle is taken as a dispatching unit. On the one hand, the single-frame unmanned aerial vehicle has limited self capacity, has high probability of damaged execution tasks, cannot meet the war requirement, and on the other hand, the single-frame unmanned aerial vehicle has limited capacity, and is difficult to support complex combat actions. Compared with single unmanned aerial vehicle, the multi-unmanned aerial vehicle collaborative combat occupies great advantages in time and space and the type of combat task which can be supported, and has better flexibility. The combined application of a plurality of combat platforms based on digitization can fully exert the advantages of each platform of the combat platform to complete more complex work, and improve the working efficiency and the success rate of tasks.
The mosaic type combat style further releases the potential of the combat platform, but also puts higher requirements on the command control mode, and the technical difficulty becomes high. In the technical aspect, the combination of mosaic elements is needed to be realized from bottom to top, so that the combat capability of physical dispersion and logic integration is formed; the decomposition and distribution of tasks to the individual mosaic elements need to be achieved from top to bottom.
Still take unmanned aerial vehicle cluster as an example, single frame unmanned aerial vehicle can be equipped with ability such as reconnaissance, communication relay, striking, and single frame unmanned aerial vehicle platform still receives constraints such as navigation journey, speed, task state, and unmanned aerial vehicle's function and performance attribute can form the agent in the command system through the way of digital modeling, and here agent is similar to mosaic element, and when command control system was down to unmanned aerial vehicle cluster, the agent can be based on the ability and the constraint of the combat platform that it proxied and command control system interaction, confirm whether can accomplish the subscription, carry out the task or carry out a part of task.
The Chinese patent with application number 202210181524.X discloses a scene self-adaptive collaborative command control system and a scene self-adaptive collaborative command control method based on situation awareness. The cooperative control based on situation awareness is characterized in that the change of a command control process and the generation of the combat capability of an autonomous unmanned system are realized, the human commander provides flexible and creative insight, the machine provides speed and expandability, multiple dilemmas can be manufactured for enemies, and the combat capability is effectively improved. The combat task decomposition and distribution protocol is the key for constructing the combat system. In the process of decomposing and distributing the combat task, the accurate assessment of the self ability of the agent and the accurate assessment of the ability of the command control system to execute the task of the agent are the basis of the combat process. The accurate assessment of the ability of the agent and the ability of the agent to effectively conduct the combat task is the basis of the decomposition and distribution of the automatic combat task.
Disclosure of Invention
The purpose of the invention is that: the method is used for digitally and intelligently upgrading an operational system, and provides a bid and ask distribution method for an intelligent operational task, which is used for decomposing and evaluating the task based on a contract network to realize the decomposition and distribution of the task.
The technical scheme of the invention is as follows: a bid distribution method facing intelligent combat task, bidding unit includes: the task bid unit and the task bid evaluation unit are arranged in the decision support unit, and the task bid unit is respectively arranged in each intelligent twin body; the task bidding unit, the task bidding unit and the task bid evaluation unit adopt contract network protocols to realize the decomposition and distribution of combat tasks; the protocol comprises the following steps:
A. and (5) bidding.
A1. The commander inputs the combat task to the decision support unit.
A2. The task bidding unit decomposes the combat task into a plurality of combat subtasks, and establishes screening conditions according to combat subtask requirements.
A3. And screening the intelligent twin bodies of a certain group in the database according to the screening conditions.
And if the intelligent twin body passes the screening, adding the intelligent twin body passing the screening into the invitation bidding object, and entering the step B.
And (3) if no intelligent twin passes the screening, replacing the groups in the database, repeating the step (A3) until all intelligent twin in the groups in the database are traversed, and if the intelligent twin passing the screening still does not appear, continuing broadcasting bid-inviting to all registered intelligent twin.
B. And (5) bidding.
B1. The task bidding unit bid the intelligent twin passing the screening and invites the bidding.
B2. The intelligent twin utilizes the task bidding unit of the intelligent twin to evaluate the received invitation and select to accept the task or reject the task.
If the intelligent twin body receives the task, the intelligent twin body combines the proposal of the implementation scheme with the self state and the resource to manufacture a bidding document, and sends the bidding document to a task bidding unit to enter the step C.
And if the intelligent twin body does not accept the task, returning to the step A3.
C. And (5) evaluating the mark.
C1. The task evaluation unit evaluates all the bidding books of the intelligent twin bodies participating in bidding and judges whether the intelligent twin bodies have the capability of executing the task or not.
For intelligent twins thought to be able to complete a task, the comprehensive value of each intelligent twins is calculated.
And (5) considering that no intelligent twin can complete the task, and ending the step.
C2. And determining the highest comprehensive value as a winner, and feeding back a task allocation scheme to the intelligent twin body by the task bidding unit, and signing a task contract with the task bidding unit in the intelligent twin body.
On the basis of the above scheme, further, after step C2, the protocol further includes:
D. and executing and updating.
D1. After the contract is signed, the intelligent twin body sends a task executing instruction to a combat unit in the unmanned combat formation.
D2. The intelligent twin body evaluates the task execution effect by combining the extracted battlefield situation, the monitoring resources of the battlefield elements and the communication state while the unmanned battlefield formation executes the task, forms feedback information and sends the feedback information to the decision support unit.
D3. And (3) the decision support unit evaluates the execution condition of the combat task according to the feedback information, synchronously updates the capability data and database information of the intelligent twin body, forms new task information, and circularly enters the step (A2) until the task is ended.
On the basis of the above scheme, in the step a, the basic capability and the environmental impact of each intelligent twin are considered first, if the basic capability is satisfied and the environmental impact is smaller than the set threshold, three mental state parameters of Trust, familiarity F and aggressiveness P of each intelligent twin are further considered, and the bid-seeking screening evaluation function value J is obtained by using an evaluation function. The trust degree represents the success rate of executing the previous task, the better the successful bid is after the successful bid is accepted, the more the number of times of the successful bid is, the more experienced the bid-winning person issues the bid-winning task, and the higher the trust degree of the bid-winning person. Familiarity means that the sender is more prone to multiple successful completions of the bidder with whom it cooperates, representing the familiarity of the sender with the bidder. The product level indicates the degree of aggressiveness of the bidder, and is a representation of the willingness of the bidder to complete a task, regardless of whether the bidder is bidding, and the bidder would like to bid to the bidder with more aggression under the same condition.
And if J is greater than or equal to the expected value theta, screening through bid-inviting. If J is smaller than the expected value θ, the screening is not passed.
On the basis of the above scheme, in the step B, the method for bid evaluation of the intelligent twin body on the task is as follows:
according to the task value TVAlue of the target task, the probability P of completing the task C During execution of tasksProbability of surviving P s The benefit of this task, reward, is calculated.
Reward=Tvalue×P c ×P s
According to the distance D from the intelligent twin body to the task target, the value SVALue of the intelligent twin body and the probability 1-P of being knocked down by enemy C The Cost of this task is calculated.
cost=Svalue×(1-P c )×D
The net benefit of executing the task is calculated from the task benefit review and the Cost.
If the net benefit is greater than the expected value ψ, then the bidding task is accepted.
If the net benefit is less than or equal to the expected value ψ, the bidding task is refused.
Based on the above scheme, in the step C, the method for evaluating the label is as follows:
and (5) carrying out weighted calculation on the basic Capability, the mental state J, the loading degree TL and the environmental impact factor Ef of the intelligent twin to obtain the comprehensive value ACapability of the intelligent twin.
After the ACapabilitys are ordered, the highest comprehensive value becomes the winning bid.
Based on the scheme, the calculation method of the bid-recruitment screening evaluation function value J is as follows:
J=α×Trust+β×F+γ×P,α+β+γ=1
wherein: TO is the total number of times the task is marked in the mark person, SC is the secondary time the task is successfully completedNumber N cfb N is the total number of times of issuing bidding tasks in the past bid The total number of bids for bidders, α, β, γ, are constant weighting factors that characterize the specific gravity of ability, confidence, familiarity, aggressiveness for the final screening.
Based on the scheme, the method for calculating the comprehensive value comprises the following steps of:
ACapability=ρ×Capability+ω×J+η×Ef+δ×TL,ρ+ω+η+δ=1
wherein: ρ, ω, η, δ are constant weighting factors.
After receiving bidding information of bidders, the bidders not only take basic capacity Capability, mental state J and load degree TL as evaluation indexes, but also quantify (quantitatively analyze) the influence of the environment on the bidders and incorporate the quantitative analysis into the evaluation indexes for comprehensive evaluation. Therefore, the constructor comprehensive value evaluation function, the mental state, the environmental impact factor Ef (environmental impact factor quantitative analysis) and the load degree are different from each other in the influence of each factor on task allocation, and therefore, the influence degree of the basic capacity, the mental state, the environmental impact factor and the load degree on the comprehensive capacity of the constructor is respectively expressed by rho, omega, eta and delta.
The beneficial effects are that: the bid competing unit is divided into a task bid unit, a task bid unit and a task bid evaluation unit, the task bid unit receives a decision support unit, the decision support unit converts the fight intention of a commander into a fight task, the task bid unit divides the fight task into fight subtasks, and the task bid unit interacts with the task bid unit through a task distribution protocol to automatically realize the automatic distribution of the fight task. The task bidding unit is embedded in an intelligent twin body of the intelligent combat system, the intelligent twin body virtualizes the resources and the capabilities of the corresponding combat unit, interacts with the task bidding unit based on the resources and the capabilities of the intelligent twin body, and signs part of combat tasks with the task bidding unit according to the evaluation of the resource state, the health state and the communication state of the corresponding combat formation. The task bid evaluation unit is the same as the task bid inviting unit and accepts the decision support unit, and evaluates the bidding scheme provided by the intelligent twin, determines whether the intelligent twin bidding has task execution capability, and can sign a contract to the intelligent twin bidding after the bid evaluation meets the conditions. The invention improves the speed, expandability and flexibility of command control and effectively improves the combat capability.
Drawings
FIG. 1 is a schematic diagram of an architecture of the present invention;
FIG. 2 is a flow chart of the method of the present invention;
FIG. 3 is a flow chart of the bidding process of the present invention;
FIG. 4 is a flow chart of a bidding process of the present invention;
FIG. 5 is a flowchart of the evaluation process in the present invention.
Detailed Description
Example 1: referring to fig. 1, a bid distribution method for an intelligent combat task, a bidding unit includes: the task bid unit and the task bid evaluation unit are arranged in the decision support unit, and the task bid unit is respectively arranged in each intelligent twin body; the task bidding unit, the task bidding unit and the task evaluation unit adopt contract network protocols to realize the decomposition and distribution of the combat task.
Referring to fig. 2, the protocol includes the steps of:
see fig. 3, a. Bid.
A1. The commander inputs the combat task to the decision support unit.
A2. The task bidding unit decomposes the combat task into a plurality of combat subtasks, and establishes screening conditions according to combat subtask requirements.
A3. And screening the intelligent twin bodies of a certain group in the database according to the screening conditions.
In this example: firstly, considering the basic capability and the environmental influence of each intelligent twin, if the basic capability is met and the environmental influence is smaller than a set threshold, further considering three mental state parameters of Trust, familiarity F and aggressiveness P of each intelligent twin, and calculating by using an evaluation function to obtain a bid-recruitment screening evaluation function value J; the trust degree represents the success rate of executing the previous task, the better the successful bid is after the successful bid is accepted, the more the number of times of the successful bid is, the more experienced the bid-winning person issues the bid-winning task, and the higher the trust degree of the bid-winning person. Familiarity means that the sender is more prone to multiple successful completions of the bidder with whom it cooperates, representing the familiarity of the sender with the bidder. The product level indicates the degree of aggressiveness of the bidder, and is a representation of the willingness of the bidder to complete a task, regardless of whether the bidder is bidding, and the bidder would like to bid to the bidder with more aggression under the same condition.
The calculation method of the bid-recruitment screening evaluation function value J comprises the following steps:
J=α×Trust+β×F+γ×P,α+β+γ=1
wherein: TO is the total number of winning tasks in the label, SC is the number of successful completion of the task, N cfb N is the total number of times of issuing bidding tasks in the past bid The total number of bids for bidders, α, β, γ, are constant weighting factors that characterize the specific gravity of ability, confidence, familiarity, aggressiveness for the final screening.
And if J is greater than or equal to the expected value theta, screening through bid-inviting. If J is smaller than the expected value θ, the screening is not passed.
And if the intelligent twin body passes the screening, adding the intelligent twin body passing the screening into the invitation bidding object, and entering the step B.
And (3) if no intelligent twin passes the screening, replacing the groups in the database, repeating the step (A3) until all intelligent twin in the groups in the database are traversed, and if the intelligent twin passing the screening still does not appear, continuing broadcasting bid-inviting to all registered intelligent twin.
See fig. 4, b. Bid.
B1. The task bidding unit bid the intelligent twin passing the screening and invites the bidding.
B2. The intelligent twin utilizes the task bidding unit of the intelligent twin to evaluate the received invitation and select to accept the task or reject the task.
In this example, the method for bid evaluation of the task by the intelligent twin comprises the following steps:
according to the task value TVAlue of the target task, the probability P of completing the task C Probability P of surviving during execution of a task s The benefit of this task, reward, is calculated.
Reward=Tvalue×P c ×P s
According to the distance D from the intelligent twin body to the task target, the value SVALue of the intelligent twin body and the probability 1-P of being knocked down by enemy C The Cost of this task is calculated.
cost=Svalue×(1-P c )×D
The net benefit of executing the task is calculated from the task benefit review and the Cost.
If the net benefit is greater than the expected value ψ, then the bidding task is accepted.
If the net benefit is less than or equal to the expected value ψ, the bidding task is refused.
If the intelligent twin body receives the task, the intelligent twin body combines the proposal of the implementation scheme with the self state and the resource to manufacture a bidding document, and sends the bidding document to a task bidding unit to enter the step C.
And if the intelligent twin body does not accept the task, returning to the step A3.
See fig. 5, c. Rating scale.
C1. The task bidding unit evaluates all the bidding books of the intelligent twin bodies participating in bidding and judges whether the intelligent twin bodies have the capability of executing tasks.
For intelligent twins thought to be able to complete a task, the comprehensive value of each intelligent twins is calculated.
And (5) considering that no intelligent twin can complete the task, and ending the step.
C2. And determining the highest comprehensive value as a winner, and feeding back a task allocation scheme to the intelligent twin body by the task bidding unit, and signing a task contract with the task bidding unit in the intelligent twin body.
In this example, the method for evaluating the label is as follows:
and (5) carrying out weighted calculation on the basic Capability, the mental state J, the loading degree TL and the environmental impact factor Ef of the intelligent twin to obtain the comprehensive value ACapability of the intelligent twin.
After the ACapabilitys are ordered, the highest comprehensive value becomes the winning bid.
Based on the scheme, the method for calculating the comprehensive value comprises the following steps of:
ACapability=ρ×Capability+ω×J+η×Ef+δ×TL,ρ+ω+η+δ=1
wherein: ρ, ω, η, δ are constant weighting factors.
After receiving bidding information of bidders, the bidders not only take basic capacity Capability, mental state J and load degree TL as evaluation indexes, but also quantify (quantitatively analyze) the influence of the environment on the bidders and incorporate the quantitative analysis into the evaluation indexes for comprehensive evaluation. Therefore, the constructor comprehensive value evaluation function, the mental state, the environmental impact factor Ef (environmental impact factor quantitative analysis) and the load degree are different from each other in the influence of each factor on task allocation, and therefore, the influence degree of the basic capacity, the mental state, the environmental impact factor and the load degree on the comprehensive capacity of the constructor is respectively expressed by rho, omega, eta and delta.
Preferably, after step C2, the protocol further includes:
D. and executing and updating.
D1. After the contract is signed, the intelligent twin body sends a task executing instruction to a combat unit in the unmanned combat formation.
D2. The intelligent twin body evaluates the task execution effect by combining the extracted battlefield situation, the monitoring resources of the battlefield elements and the communication state while the unmanned battlefield formation executes the task, forms feedback information and sends the feedback information to the decision support unit.
D3. And (3) the decision support unit evaluates the execution condition of the combat task according to the feedback information, synchronously updates the capability data and database information of the intelligent twin body, forms new task information, and circularly enters the step (A2) until the task is ended.
The method for evaluating the mark comprises the following steps:
and (5) carrying out weighted calculation on the basic Capability, the mental state J, the loading degree TL and the environmental impact factor Ef of the intelligent twin to obtain the comprehensive value ACapability of the intelligent twin.
After the ACapabilitys are ordered, the highest comprehensive value becomes the winning bid.
Based on the scheme, the method for calculating the comprehensive value comprises the following steps of:
ACapability=ρ×Capability+ω×J+η×Ef+δ×TL,ρ+ω+η+δ=1
wherein: ρ, ω, η, δ are constant weighting factors.
After receiving bidding information of bidders, the bidders not only take basic capacity Capability, mental state J and load degree TL as evaluation indexes, but also quantify (quantitatively analyze) the influence of the environment on the bidders and incorporate the quantitative analysis into the evaluation indexes for comprehensive evaluation. Therefore, the constructor comprehensive value evaluation function, the mental state, the environmental impact factor Ef (environmental impact factor quantitative analysis) and the load degree are different from each other in the influence of each factor on task allocation, and therefore, the influence degree of the basic capacity, the mental state, the environmental impact factor and the load degree on the comprehensive capacity of the constructor is respectively expressed by rho, omega, eta and delta.
Example 2: based on the embodiment 1, taking unmanned aerial vehicle and unmanned vehicle in the complex countermeasure scene to realize the guard of the combat materials in a cooperative way as an example, the application scene of the method is further explained.
The unmanned combat formation comprises the following steps: the unmanned aerial vehicle is reconnaissance unmanned aerial vehicle, fighter unmanned aerial vehicle, transportation unmanned aerial vehicle, unmanned aerial vehicle has partial perceptibility ability to manage in a distributed mode. The task targets are as follows: the unmanned aerial vehicle is protected and is sent important material to arrive the destination under unmanned aerial vehicle protective equipment, probably can meet with enemy in the transportation, and whole transportation task is responsible for the enemy on the reconnaissance transportation route by reconnaissance unmanned aerial vehicle, destroys by fight unmanned aerial vehicle after finding enemy, guarantees that transportation unmanned aerial vehicle is safe smooth with the material delivery. The environmental influencing factors influencing the successful completion of the task in the task execution process comprise meteorological environments such as air temperature, air pressure, wind speed, rain and snow, geographical environments such as roads, bridges, barriers and the like, hydrologic environments such as rivers, lakes and the like, electromagnetic environments such as electromagnetic interference, pulses, communication ranges and the like, battlefield environments such as artillery, guided missile firepower coverage and the like, and other environmental factors.
The intelligent twin body comprehensively agents the resource state, the health state, the communication state and the like of the unmanned combat formation. Through state feedback, each combat unit in unmanned combat formation faces the following problems: unmanned aerial vehicles have limited resources and may face enemy attacks. The unmanned aerial vehicle fuel resources are limited, gradually consume along with the time, and return to the base to acquire fuel again when the fuel cannot guarantee tasks. Unmanned aerial vehicles and unmanned vehicles have limited communication signal coverage. Unmanned aerial vehicles and unmanned vehicles may be greatly affected by the environmental factors in which the task being performed is located. In a complex challenge environment, enemies will attempt to destroy the unmanned aerial vehicle, destroy the unmanned aerial vehicle and intercept the supplies, and the unmanned aerial vehicle needs to avoid these losses. If the enemy intercepts the replenishment, the task will fail. If the material is able to reach the target, the task is done successfully. At the same time, the drone must be close enough to identify the target, which can also be dangerous, so the distance between the drone and the unknown target should be controlled. During task execution, enemies may be either mobile or static. They will launch an attack on seeing the drone, then attack the fleet, and finally intercept replenishment.
The task bidding units and the task bidding units adopt a contract network protocol to realize the decomposition and distribution of the tasks, in the protocol, the task bidding units send out a task to a plurality of task bidding units, and each task bidding unit provides an implementation scheme according to the resources and the capabilities of the intelligent twin body where the task bidding unit is located. The task bidding unit decides how to assign tasks to the different task bidding units 3 and then assigns the workload. In the process of executing the task, the task bidding unit adjusts task allocation and workload by combining the battlefield situation, the monitoring resources of the battlefield elements and the communication state, and keeps the optimal battlefield scheme until the task target is completed.
While the invention has been described in detail in the foregoing general description and specific examples, it will be apparent to those skilled in the art that modifications and improvements can be made thereto. Accordingly, such modifications or improvements may be made without departing from the spirit of the invention and are intended to be within the scope of the invention as claimed.
Claims (4)
1. The bid distribution method for the intelligent combat task is characterized in that the bidding unit comprises the following steps: the task bid unit and the task bid evaluation unit are arranged in the decision support unit, and the task bid unit is respectively arranged in each intelligent twin body; the task bidding unit, the task bidding unit and the task bid evaluation unit adopt contract network protocols to realize the decomposition and distribution of combat tasks; the protocol comprises the following steps:
A. bidding;
A1. the commander inputs the combat task to the decision support unit;
A2. the task bidding unit decomposes the fight task into a plurality of fight subtasks, and formulates screening conditions according to the fight subtask requirements;
A3. screening intelligent twin bodies of a certain group in the database according to screening conditions;
firstly, considering the basic capability and the environmental influence of each intelligent twin, if the basic capability is met and the environmental influence is smaller than a set threshold, further considering three mental state parameters of Trust, familiarity F and aggressiveness P of each intelligent twin, and calculating by using an evaluation function to obtain a bid-recruitment screening evaluation function value J; if J is greater than or equal to the expected value theta, screening through bid-bidding; if J is smaller than the expected value theta, failing to pass the screening;
if the intelligent twin body passes the screening, adding the intelligent twin body passing the screening into the invitation bidding object, and entering a step B;
if no intelligent twin passes the screening, replacing the groups in the database, repeating the step A3 until all intelligent twin in the groups in the database are traversed, and if the intelligent twin passing the screening still does not appear, continuing broadcasting bid-inviting to all registered intelligent twin;
B. bidding;
B1. the task bidding unit performs bidding on the intelligent twin bodies passing through screening and invites bidding;
B2. the intelligent twin utilizes the task bidding unit of the intelligent twin to evaluate the received invitation and select to accept the task or reject the task;
the method for bid evaluation of the intelligent twin body on the task comprises the following steps:
according to the task value TVAlue of the target task, the probability P of completing the task C Probability P of surviving during execution of a task s Calculating the income Reward of the task;
;
according to the distance D from the intelligent twin body to the task target, the value SVALue of the intelligent twin body and the probability 1-P of being knocked down by enemy C Calculating the Cost of the task;
;
calculating the net benefit of executing the task by using the task benefit Reward and the Cost;
if the net gain is greater than the expected value psi, accepting the bid-inviting task;
if the net benefit is less than or equal to the expected value psi, rejecting the bidding task;
if the intelligent twin body receives the task, the intelligent twin body combines the proposal of the implementation scheme with the self state and the resource to manufacture a bidding document, and sends the bidding document to a task bidding unit to enter the step C;
if no intelligent twin body accepts the task, returning to the step A3;
C. evaluating the mark;
C1. the task evaluation unit evaluates all bidding books of the intelligent twin bodies participating in bidding and judges whether the intelligent twin bodies have the capability of executing tasks or not;
the method for evaluating the mark comprises the following steps:
the comprehensive value ACapability of the intelligent twin is obtained by carrying out weighted calculation on the basic ability Capability, mental state J, loading degree TL and environmental impact factor Ef of the intelligent twin;
after sequencing the ACapabilitys, the comprehensive value is the highest and becomes the winner;
for intelligent twin which is considered to be capable of completing the task, calculating the comprehensive value of each intelligent twin;
if no intelligent twin can complete the task, ending the step;
C2. and determining the highest comprehensive value as a winner, and feeding back a task allocation scheme to the intelligent twin body by a task bid evaluation unit, and signing a task contract with a task bid unit in the intelligent twin body.
2. The intelligent combat mission oriented bid distribution method of claim 1, wherein said protocol further comprises, after step C2:
D. executing and updating;
D1. after the contract is signed, the intelligent twin body sends a task executing instruction to a combat unit in unmanned combat formation;
D2. the intelligent twin body evaluates the task execution effect by combining the extracted battlefield situation, the monitoring resources of the battlefield elements and the communication state while the unmanned battlefield formation executes the task, forms feedback information and sends the feedback information to the decision support unit;
D3. and (3) the decision support unit evaluates the execution condition of the combat task according to the feedback information, synchronously updates the capability data and database information of the intelligent twin body, forms new task information, and circularly enters the step (A2) until the task is ended.
3. The bid dispensing method for an intelligent combat mission according to claim 1 or 2, wherein the bid screening evaluation function value J is calculated by:
;
wherein:for the total number of winning bid tasks in the subject +.>For the number of successful completion of the task +.>For the total number of times of issuing bidding tasks in the past, < ->The total number of bids for bidders, α, β, γ are constant weighting factors.
4. The bid dispensing method for an intelligent combat mission of claim 1 or 2, wherein the method for calculating the comprehensive value is as follows:
;
wherein: ρ, ω, η, δ are constant weighting factors.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310217931.6A CN116452306B (en) | 2023-03-03 | 2023-03-03 | Bid distribution method for intelligent combat task |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310217931.6A CN116452306B (en) | 2023-03-03 | 2023-03-03 | Bid distribution method for intelligent combat task |
Publications (2)
Publication Number | Publication Date |
---|---|
CN116452306A CN116452306A (en) | 2023-07-18 |
CN116452306B true CN116452306B (en) | 2023-10-10 |
Family
ID=87126475
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202310217931.6A Active CN116452306B (en) | 2023-03-03 | 2023-03-03 | Bid distribution method for intelligent combat task |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN116452306B (en) |
Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101815326A (en) * | 2010-01-11 | 2010-08-25 | 北京邮电大学 | Method for allocating tasks in wireless sensor network based on negotiation |
CN102903028A (en) * | 2012-09-28 | 2013-01-30 | 中国人民解放军国防科学技术大学 | Emergency-orientated co-cooperation allocation method for multi-airship earth observation tasks |
CN105139069A (en) * | 2015-07-30 | 2015-12-09 | 江苏科技大学 | Method for improving contract net based on particle swarm algorithm |
CN110009242A (en) * | 2019-04-12 | 2019-07-12 | 网易(杭州)网络有限公司 | Tender Evaluation Method neural network based and device, storage medium |
CN114565268A (en) * | 2022-02-25 | 2022-05-31 | 军事科学院系统工程研究院网络信息研究所 | Situation awareness-based scene self-adaptive cooperative command control system and method |
CN114578710A (en) * | 2022-02-25 | 2022-06-03 | 军事科学院系统工程研究院网络信息研究所 | Multi-agent-based combat simulation system and method with unmanned cooperative system |
CN115392476A (en) * | 2022-07-07 | 2022-11-25 | 中国人民解放军军事科学院系统工程研究院 | Intelligent twin in unmanned cooperative combat system |
CN115412289A (en) * | 2022-07-19 | 2022-11-29 | 中国人民解放军军事科学院系统工程研究院 | Network isolation safety system, method and medium based on edge cloud intelligent twin |
CN115525068A (en) * | 2022-10-29 | 2022-12-27 | 中国电子科技集团公司第十五研究所 | Unmanned aerial vehicle cluster cooperative task allocation method based on iterative optimization |
-
2023
- 2023-03-03 CN CN202310217931.6A patent/CN116452306B/en active Active
Patent Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101815326A (en) * | 2010-01-11 | 2010-08-25 | 北京邮电大学 | Method for allocating tasks in wireless sensor network based on negotiation |
CN102903028A (en) * | 2012-09-28 | 2013-01-30 | 中国人民解放军国防科学技术大学 | Emergency-orientated co-cooperation allocation method for multi-airship earth observation tasks |
CN105139069A (en) * | 2015-07-30 | 2015-12-09 | 江苏科技大学 | Method for improving contract net based on particle swarm algorithm |
CN110009242A (en) * | 2019-04-12 | 2019-07-12 | 网易(杭州)网络有限公司 | Tender Evaluation Method neural network based and device, storage medium |
CN114565268A (en) * | 2022-02-25 | 2022-05-31 | 军事科学院系统工程研究院网络信息研究所 | Situation awareness-based scene self-adaptive cooperative command control system and method |
CN114578710A (en) * | 2022-02-25 | 2022-06-03 | 军事科学院系统工程研究院网络信息研究所 | Multi-agent-based combat simulation system and method with unmanned cooperative system |
CN115392476A (en) * | 2022-07-07 | 2022-11-25 | 中国人民解放军军事科学院系统工程研究院 | Intelligent twin in unmanned cooperative combat system |
CN115412289A (en) * | 2022-07-19 | 2022-11-29 | 中国人民解放军军事科学院系统工程研究院 | Network isolation safety system, method and medium based on edge cloud intelligent twin |
CN115525068A (en) * | 2022-10-29 | 2022-12-27 | 中国电子科技集团公司第十五研究所 | Unmanned aerial vehicle cluster cooperative task allocation method based on iterative optimization |
Non-Patent Citations (3)
Title |
---|
刘跃峰 ; 张安 ; .有人机/无人机编队协同任务分配方法.系统工程与电子技术.2010,(第03期),全文. * |
李娟 ; 张昆玉 ; .基于改进合同网算法的异构多AUV协同任务分配.水下无人系统学报.2017,(第06期),全文. * |
邓烨 ; 奉祁林 ; 赵健 ; .数字孪生战场建设探讨.防护工程.2020,(第03期),全文. * |
Also Published As
Publication number | Publication date |
---|---|
CN116452306A (en) | 2023-07-18 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN112733421B (en) | Task planning method for cooperation of unmanned aerial vehicle with ground fight | |
US7765038B2 (en) | Mission planning system for vehicles with varying levels of autonomy | |
Grove et al. | Digitalization impacts on corporate governance | |
US8776074B1 (en) | Methods, devices and systems for coordinating and optimizing resources | |
CN113009934A (en) | Multi-unmanned aerial vehicle task dynamic allocation method based on improved particle swarm optimization | |
CN115755963B (en) | Unmanned aerial vehicle group collaborative mission planning method considering carrier delivery mode | |
CN114185362A (en) | Unmanned aerial vehicle cluster task dynamic allocation method based on suburb information entropy | |
CN115239204B (en) | Collaborative task planning method for multi-platform unmanned aerial vehicle-mounted radio frequency system | |
Oh et al. | Market-based distributed task assignment of multiple unmanned aerial vehicles for cooperative timing mission | |
CN114326827B (en) | Unmanned aerial vehicle cluster multitasking dynamic allocation method and system | |
CN115903896A (en) | Multi-unmanned aerial vehicle path planning method based on proxy model optimization | |
Blaker | Transforming military force: the legacy of Arthur Cebrowski and network centric warfare | |
CN116452306B (en) | Bid distribution method for intelligent combat task | |
Xie et al. | Mathematical problems in engineering improved CNP‐Method‐Based local real‐time cooperative task allocation of heterogeneous multi‐UAV in communication‐constrained environment | |
CN116088586A (en) | Method for planning on-line tasks in unmanned aerial vehicle combat process | |
Bialos et al. | The NATO Response Force: facilitating coalition warfare through technology transfer and information sharing | |
Mawdsley | A European agenda for security technology: from innovation policy to export controls | |
CN115963724A (en) | Unmanned aerial vehicle cluster task allocation method based on crowd-sourcing-inspired alliance game | |
CN115220473A (en) | Multi-unmanned aerial vehicle swarm cooperative task dynamic allocation method | |
Robbins | Discovery of counter IADS swarming autonomy behaviors with machine learning | |
Su et al. | A Decision‐Making Method for Distributed Unmanned Aerial Vehicle Swarm considering Attack Constraints in the Cooperative Strike Phase | |
Nurkin et al. | Emerging Technologies and the Future of US-Japan Defense Collaboration | |
CN114529205B (en) | Mosaic warfare system capacity demand satisfaction evaluation method and related equipment | |
Barnawi | Integrated consensus-based frameworks for unmanned vehicle routing and targeting assignment | |
Cohen | MDC2 war game spurs Air Force to shift budget, experimentation priorities |
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 |