CN114860416A - Distributed multi-agent detection task allocation method and device in confrontation scene - Google Patents
Distributed multi-agent detection task allocation method and device in confrontation scene Download PDFInfo
- Publication number
- CN114860416A CN114860416A CN202210633921.6A CN202210633921A CN114860416A CN 114860416 A CN114860416 A CN 114860416A CN 202210633921 A CN202210633921 A CN 202210633921A CN 114860416 A CN114860416 A CN 114860416A
- Authority
- CN
- China
- Prior art keywords
- agent
- target
- strategy
- detection
- detection task
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 264
- 238000000034 method Methods 0.000 title claims abstract description 73
- 238000009826 distribution Methods 0.000 claims abstract description 62
- 230000006870 function Effects 0.000 claims description 63
- 230000009977 dual effect Effects 0.000 claims description 22
- 238000005457 optimization Methods 0.000 claims description 22
- 230000003190 augmentative effect Effects 0.000 claims description 10
- 238000004590 computer program Methods 0.000 claims description 6
- 239000011159 matrix material Substances 0.000 claims description 6
- 230000008569 process Effects 0.000 abstract description 17
- 239000003795 chemical substances by application Substances 0.000 description 214
- 238000004891 communication Methods 0.000 description 24
- 238000010586 diagram Methods 0.000 description 5
- 239000000523 sample Substances 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000005070 sampling Methods 0.000 description 2
- 230000004075 alteration Effects 0.000 description 1
- 230000009191 jumping Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 230000008520 organization Effects 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000009827 uniform distribution Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/46—Multiprogramming arrangements
- G06F9/48—Program initiating; Program switching, e.g. by interrupt
- G06F9/4806—Task transfer initiation or dispatching
- G06F9/4843—Task transfer initiation or dispatching by program, e.g. task dispatcher, supervisor, operating system
- G06F9/4881—Scheduling strategies for dispatcher, e.g. round robin, multi-level priority queues
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/10—Internal combustion engine [ICE] based vehicles
- Y02T10/40—Engine management systems
Landscapes
- Engineering & Computer Science (AREA)
- Software Systems (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computer And Data Communications (AREA)
- Debugging And Monitoring (AREA)
Abstract
The application discloses a distributed multi-agent detection task allocation method and device in a confrontation scene, wherein the method comprises the following steps: establishing a multi-agent detection efficiency function according to detection task distribution weight, target detector configuration and detection capacity carried by the multi-agent system, target disguise strategy and multi-agent detection task distribution strategy; establishing a distributed multi-agent detection task distribution model according to preset multi-agent detection capability constraint, target disguising capability constraint and detection task constraint; and alternately solving a task allocation strategy and a corresponding target disguise strategy of the multi-agent system according to the gradient information to generate a distributed multi-agent detection task allocation result. Therefore, the technical problem that the execution result of the detection task is easily influenced by the target disguise strategy due to the fact that the potential disguise countermeasure process of the target cannot be fully considered through a distributed detection task allocation method in the related art is solved, and therefore the acquisition amount of target characteristic information is reduced.
Description
Technical Field
The application relates to the technical field of intelligent decision making of a multi-agent system, in particular to a distributed multi-agent detection task allocation method and device in a confrontation scene.
Background
Task allocation is a key problem of multiple intelligent agents in cooperative target detection, and good task allocation can fully play the capability advantages of different intelligent agents, particularly under a confrontation scene, a target can disguise one type of characteristic information of the target and cause the failure of part of detection means, so that an intelligent agent set and a detection task set are correctly matched according to the type and the capability of a detector carried by the intelligent agents, and the method is an important basis for acquiring more target characteristic information.
The task allocation method can be divided into a centralized type and a distributed type according to the organization form of the multi-agent system. The centralized task allocation method is characterized in that a central node collects information of all intelligent agents, calculates and sends task allocation results to all intelligent agents, and the central node can be one intelligent agent or a central base station in the multi-intelligent-agent system. In the distributed task allocation method, each agent can independently decide and dynamically adjust the task allocation result according to the state information and the communication result of the agent, and compared with a centralized task allocation method, the distributed task allocation method has higher flexibility and robustness and is less influenced by the scale of the agent.
However, in the related art, the distributed detection task allocation method does not fully consider the target potential disguise countermeasure process, and the execution result of the detection task is susceptible to the target disguise strategy and needs to be improved.
Disclosure of Invention
The application provides a distributed multi-agent detection task allocation method and device in a countermeasure scene, and aims to solve the technical problem that in the related technology, due to the fact that a target potential disguise countermeasure process cannot be fully considered through a distributed detection task allocation method, execution results of detection tasks are easily affected by a target disguise strategy, and therefore the acquisition amount of target characteristic information is reduced.
The embodiment of the first aspect of the application provides a distributed multi-agent detection task allocation method in a confrontation scene, which comprises the following steps: establishing a multi-agent detection efficiency function according to detection task distribution weight, target detector configuration and detection capacity carried by the multi-agent system, target disguise strategy and multi-agent detection task distribution strategy; establishing a distributed multi-agent detection task distribution model according to preset multi-agent detection capability constraint, target disguising capability constraint and detection task constraint; and based on the distributed multi-agent detection task allocation model, alternately solving a task allocation strategy and a corresponding target disguise strategy of the multi-agent system according to the gradient information to generate a distributed multi-agent detection task allocation result.
Optionally, in an embodiment of the present application, before solving the task allocation policy and the corresponding target masquerading policy of the multi-agent system, the method further includes: setting optimization parameters and termination conditions; and establishing an augmented Lagrange function of the detection efficiency, and increasing a non-convergence penalty term of the detection efficiency function.
Optionally, in an embodiment of the present application, the multi-agent detection performance function is:
wherein, X i Representing the estimation of an agent i on the overall task distribution result of the multi-agent system, B representing the distribution weight parameter between the agent and the target, C representing the type of a target detector carried by the agent system, D representing the target disguise strategy, E i And the matrix represents M rows and N columns of the ith column which are all 1 and the rest is 0, and Lambda is a target detection capability parameter of different detectors.
Optionally, in an embodiment of the present application, the generating a distributed multi-agent detection task assignment result includes: and solving the maximum value of the detection efficiency function under all disguise strategies by using the multi-agent task allocation model.
Optionally, in an embodiment of the present application, the alternately solving the task allocation policy and the corresponding target masquerading policy of the multi-agent system according to the gradient information includes: solving an optimal target disguise strategy under the current detection task allocation strategy; the optimal task allocation strategy of each intelligent agent under the current optimal target camouflage strategy is solved in parallel, so that the current detection task allocation strategy and dual parameters under the optimal target camouflage strategy are solved in parallel; and solving the original problem residual error and the dual problem residual error based on the dual parameters until the optimization is finished, so that the detection task allocation solution of the multi-agent system is the average value of the solution allocation of all agent local detection tasks.
The embodiment of the second aspect of the present application provides a distributed multi-agent detection task allocation device in a confrontation scenario, including: the first function establishing module is used for establishing a multi-agent detection efficiency function according to detection task distribution weight, target detector configuration and detection capacity carried by the multi-agent system, target disguise strategy and multi-agent detection task distribution strategy; the model establishing module is used for establishing a distributed multi-agent detection task distribution model according to preset multi-agent detection capability constraint, target disguising capability constraint and detection task constraint; and the distribution module is used for alternately solving a task distribution strategy of the multi-agent system and a corresponding target camouflage strategy according to the gradient information based on the distributed multi-agent detection task distribution model to generate a distributed multi-agent detection task distribution result.
Optionally, in an embodiment of the present application, the method further includes: the setting module is used for setting optimization parameters and termination conditions; and the second function establishing module is used for establishing an augmented Lagrange function of the detection efficiency and increasing a non-convergence penalty term of the detection efficiency function.
Optionally, in an embodiment of the present application, the multi-agent detection performance function is:
wherein, X i Representing the estimation of an agent i on the overall task distribution result of the multi-agent system, B representing the distribution weight parameter between the agent and the target, C representing the type of a target detector carried by the agent system, D representing the target disguise strategy, E i And the matrix represents M rows and N columns of which the ith column is 1 and the rest is 0, and the lambda is a target detection capability parameter of different detectors.
Optionally, in an embodiment of the present application, the allocating module includes: and the first solving unit is used for solving the maximum value of the detection efficiency function under all disguise strategies by utilizing the multi-agent task allocation model.
Optionally, in an embodiment of the present application, the allocating module further includes: the second solving unit is used for solving the optimal target disguise strategy under the current detection task allocation strategy; the third solving unit is used for solving the optimal task allocation strategy of each intelligent agent under the current optimal target disguising strategy in parallel so as to solve the current detection task allocation strategy and the dual parameters under the optimal target disguising strategy in parallel; and the distribution unit is used for solving the original problem residual error and the dual problem residual error based on the dual parameters until the optimization is finished, so that the detection task distribution solution of the multi-agent system is the average value of the distribution solutions of all the agent local detection tasks.
An embodiment of a third aspect of the present application provides an electronic device, including: 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 distributed multi-agent detection task assignment method in the countermeasure scenario as described in the above embodiments.
A fourth aspect of the present application provides a computer-readable storage medium storing computer instructions for causing the computer to execute the distributed multi-agent detection task allocation method in an confrontation scenario as described in the above embodiments.
According to the detection task distribution weight, the target detector configuration and detection capacity carried by the multi-agent system, the target camouflage strategy and the multi-agent detection task distribution strategy, the multi-agent detection efficiency function and the distributed multi-agent detection task distribution model are utilized to realize reasonable distribution of the multi-agents with different detection capacities, so that the influence of target camouflage on the multi-agent detection efficiency is reduced to the maximum extent, and the collection of target characteristic information under the countermeasure environment is maximized. Therefore, the technical problem that the execution result of the detection task is easily influenced by the target disguise strategy due to the fact that the potential disguise countermeasure process of the target cannot be fully considered through a distributed detection task allocation method in the related art is solved, and therefore the acquisition amount of target characteristic information is reduced.
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 above 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 distributed multi-agent detection task allocation method in an confrontation scenario according to an embodiment of the present application;
FIG. 2 is a flow diagram of a distributed multi-agent detection task assignment method in a confrontation scenario according to one embodiment of the present application;
fig. 3 is a schematic structural diagram of a distributed multi-agent detection task allocation device in a countermeasure scenario according to an embodiment of the present application;
fig. 4 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 following describes a distributed multi-agent detection task allocation method and device in a countermeasure scenario according to an embodiment of the present application with reference to the drawings. Aiming at the technical problems that the execution result of a detection task is easily influenced by a target disguise strategy due to the fact that the potential disguise countermeasure process of a target cannot be fully considered in the related technology mentioned in the background technology center, and the acquisition amount of target characteristic information is reduced, the application provides a distributed multi-agent detection task allocation method in a countermeasure scene, in the method, the reasonable allocation of multi-agents with different detection capacities can be realized according to the detection task allocation weight, the target detector configuration and detection capacity carried by a multi-agent system, the disguise strategy of the target and the multi-agent detection task allocation strategy, a multi-agent detection efficiency function and a distributed multi-agent detection task allocation model, so that the influence of target disguise on the multi-agent detection efficiency is reduced to the maximum extent, thereby maximizing the collection of target characteristic information in the confrontational environment. Therefore, the technical problem that the execution result of the detection task is easily influenced by the target disguise strategy due to the fact that the potential disguise countermeasure process of the target cannot be fully considered through a distributed detection task allocation method in the related art is solved, and therefore the acquisition amount of target characteristic information is reduced.
Specifically, fig. 1 is a schematic flowchart of a distributed multi-agent detection task allocation method in a countermeasure scenario according to an embodiment of the present application.
As shown in fig. 1, the distributed multi-agent detection task allocation method in the countermeasure scenario includes the following steps:
in step S101, a multi-agent detection performance function is established according to the detection task allocation weight, the target detector configuration and detection capability carried by the multi-agent system, the target masquerading policy, and the multi-agent detection task allocation policy.
In the actual execution process, the multi-agent detection efficiency function can be established according to the detection task distribution weight, the target detector configuration and detection capacity carried by the multi-agent system, the target disguising strategy and the multi-agent detection task distribution strategy, so that the reasonable distribution of the multi-agents with different detection capacities can be realized conveniently by subsequently combining a distributed multi-agent detection task distribution model, the influence of the target disguising on the multi-agent detection efficiency is reduced to the maximum extent, and the collection of target characteristic information under the countermeasure environment is maximized.
The multi-agent system is of a distributed topological structure, and only the detection task distribution result of the communication neighborhood agents can be obtained.
Optionally, in one embodiment of the present application, the multi-agent detection efficacy function is:
wherein, X i Representing the estimation of an agent i on the overall task distribution result of the multi-agent system, B representing the distribution weight parameter between the agent and the target, C representing the type of a target detector carried by the agent system, D representing the target disguise strategy, E i And the matrix represents M rows and N columns of which the ith column is 1 and the rest is 0, and the lambda is a target detection capability parameter of different detectors.
Specifically, the detection efficiency function of multi-agent detection task allocation established in the embodiment of the present application may be:
wherein, X i ∈[0,1] M×N Represents the estimation of agent i on the global task assignment of the multi-agent system, [ X ] i ] mn Representing the probability of the target m being assigned to agent n;
representing an allocation weight parameter between the agent and the target; c is formed by {0,1} S×N Indicates the type of object detector, [ C ] carried by the intelligent system] sn 1 denotes agent n with sensor s; d is belonged to [0,1 ]] S×M Represents the target masquerading strategy, [ D ]] sm Indicating that the target m pretends characteristic information that can be detected by the sensor s itself.
In step S102, a distributed multi-agent detection task allocation model is established according to preset multi-agent detection capability constraints, target disguise capability constraints, and detection task constraints.
Furthermore, the distributed multi-agent detection task allocation model can be established by combining preset multi-agent detection capability constraint, target disguising capability constraint and detection task constraint.
The multi-agent detection capability constraint means that at most one detection task can be executed by each agent at the same time; the disguise ability constraint of the target means that the target disguises at most one type of characteristic information of the target at the same time; the detection task constraint means that all targets are at least distributed to one intelligent agent; a multi-agent consistency constraint means that the global task allocation solutions of the agents are the same.
Specifically, the embodiment of the application can establish a constraint condition that the detection capability of the multi-agent is more than or equal to X and is more than or equal to 0 i ≤1，
Each agent is required to execute at most one detection task;
establishing a camouflage capability constraint condition of the target, wherein D is more than or equal to 0 and less than or equal to 1,
and the target is required to disguise at most one type of characteristic information of the target;
establishing a probing task constraint
And requires that all targets be assigned to at least one agent.
Furthermore, the method and the device can estimate the detection task distribution result of each agent to agents in the non-communication neighborhood, combine the detection task distribution results of each agent and the detection task distribution results of the communication neighborhoods to form global estimation of the detection tasks of the multi-agent system, and increase the consistency constraint condition of the multi-agent system
And requires that the global estimates of the probing task assignments of all agents to the multi-agent system remain consistent.
In step S103, based on the distributed multi-agent detection task allocation model, the task allocation strategy and the corresponding target masquerading strategy of the multi-agent system are alternately solved according to the gradient information, and a distributed multi-agent detection task allocation result is generated.
In the actual execution process, the distributed multi-agent detection task allocation model can be based on the distributed multi-agent detection task allocation model, multi-agent detection tasks are allocated according to an optimal solution, task allocation strategies of a multi-agent system and corresponding target disguise strategies are alternately solved according to gradient information, distributed multi-agent detection task allocation results are generated, reasonable allocation of the multi-agents with different detection capabilities is achieved, the influence of the target disguise on the multi-agent detection efficiency is reduced to the maximum extent, and then target characteristic information collection under the countermeasure environment is maximized.
Optionally, in an embodiment of the present application, before solving the task allocation policy and the corresponding target masquerading policy of the multi-agent system, the method further includes: setting optimization parameters and termination conditions; and establishing an augmented Lagrange function of the detection efficiency, and increasing a non-convergence penalty term of the detection efficiency function.
As a possible implementation manner, the embodiment of the present application may set optimization parameters and termination conditions, and establish an augmented lagrangian function of the detection efficiency, so as to increase a non-convergence penalty item of the detection efficiency function, and alternately solve a task allocation policy and a corresponding target masquerading policy of the multi-agent system according to gradient information until the termination conditions are satisfied.
Specifically, the embodiments of the present application may add a non-convergence penalty term
The punishment item punishs the distribution result which is not {0,1}, so that the distribution result of the distributed tasks is guaranteed to be converged to the integer set {0,1 }.
Further, the augmented Lagrangian function of the multi-agent detection efficiency function may be:
wherein g (X) i ) Assigning a policy X to a target i H (d) is an indication function of the masquerading policy:
optionally, in an embodiment of the present application, generating a distributed multi-agent probing task assignment result includes: and solving the maximum value of the detection efficiency function under all disguise strategies by using a multi-agent task allocation model.
Further, the maximum value of the detection efficiency function under all masquerading strategies solved by the multi-agent task allocation model can be as follows:
0≤D≤1，
optionally, in an embodiment of the present application, alternately solving the task allocation policy and the corresponding target masquerading policy of the multi-agent system according to the gradient information includes: solving an optimal target disguise strategy under the current detection task allocation strategy; the optimal task allocation strategies of all the intelligent agents under the current optimal target disguise strategy are solved in parallel, and dual parameters under the current detection task allocation strategy and the optimal target disguise strategy are solved in parallel; and solving the original problem residual error and the dual problem residual error based on the dual parameters until the optimization is finished, so that the detection task allocation solution of the multi-agent system is the average value of the allocation solutions of all agent local detection tasks.
Specifically, the method and the device can initialize the optimization step length rho, initialize the multi-agent detection task parameters B, C and Lambda and set the multi-agent communication topology
Where V ═ {1, …, N } is a multi-agent set,
initialization of a probing task allocation strategy for a multi-agent communication edge { X i } 0 Initializing target masquerading policy D 0 Setting an optimization termination condition E pri 、∈ dual 。
Further, the embodiment of the application can solve the optimal target disguise strategy under the current detection task allocation strategy:
further, the embodiment of the application can solve the optimal task allocation strategy of each agent in parallel under the current optimal target disguise strategy:
wherein,
further, the embodiment of the application can solve dual parameters under the current detection task allocation strategy and the optimal target disguise strategy in parallel:
furthermore, the embodiment of the application can solve the original problem residual error
And dual problem residual
If at the same time satisfy
And
the optimization is terminated, otherwise, the process is repeated until the optimization time is consumed.
Further, the detection task allocation solution of the multi-agent system can be made to be an average value of all agent local detection task allocation solutions:
to sum up, compared with the related art, the method and the device solve the problem that the disguising capability of the target in the multi-target detection task influences the detection efficiency, have strong robustness, are suitable for the multi-agent distributed detection task with the communication topology, have high convergence rate, and can search the reasonable detection task distribution result under the target disguising in a short time.
Specifically, the working principle of the distributed multi-agent detection task allocation method in the countermeasure scenario of the embodiment of the present application is described in detail with reference to fig. 2.
As shown in fig. 2, the embodiment of the present application may include the following steps:
step S201: initializing parameters and setting termination conditions. The embodiment of the application can set the multi-agent communication topology
Initial detection task allocation weight B, target detector configuration parameter C carried by multi-agent system, target detection capability parameter Lambda of different detectors, and target camouflage strategy D 0 Multi-agent detection task allocation strategy
Multi-agent communication topology
Represents the communication topology of a multi-agent system, where V ═ {1, …, N } is the multi-agent set,
is a multi-agent communication edge set.
The embodiments of the present applicationAccording to the communication range of the current multi-agent system, if the distance between the agent i and the agent j is smaller than the communication distance threshold value, the agent i is considered to be capable of continuously and stably communicating with the agent j, and the communication topology is considered to be communication topology in the invention
Is a connected graph.
It should be noted that the communication distance threshold may be set by those skilled in the art according to practical situations, and is not particularly limited herein.
The probe task assignment weight B represents the weight of the agent performing the probe task, where [ B] mn As a scalar value, [ B ] is taken] mn Is not less than 0 and
[B] mn the weight of the detection task m executed by the agent n is represented, the weight of the detection task executed by the agent can represent the execution cost of the detection task generated by factors such as the distance between multiple agents and a target, and the smaller the weight value is, the higher the execution cost is.
The target detector configuration parameter C represents the type of detector carried by the different agents, such as infrared detectors, lidar, cameras, etc. If the multi-agent system has S-type detectors in common, [ C ] is selected] sn ∈{0,1}，[C] sn 1 means that agent n has an s-type detector, otherwise 0.
The target detection capability parameter Lambda of different detectors represents the acquisition capability of the detectors to different characteristic information of the target, and the parameter Lambda is taken as diag (Lambda) 1 ,…，λ S ) Wherein λ is s The target detection capability of the s-shaped detector is represented, the influence of various complex meteorological conditions such as low visibility and night on the detector capability can be represented through the target detection capability parameter lambda, and the larger the parameter value is, the stronger the detection capability is.
The target camouflage strategy D represents the self characteristic information type of the target camouflage corresponding to the target detector type, wherein [ D] ms ∈[0,1]The type of the characteristic information indicating the masquerading of the target m is s, whereUnder the disguise strategy, the target detector s cannot detect the target m. In the initialization of the target disguise policy D, the embodiment of the present application may use the interval [0,1]S x M dimensional D of uniform distribution sampling 0 。
Multi-agent detection task allocation strategy { X i Denotes the result of the allocation of the detection task by agent i, where [ X ] i ] mn ∈[0,1]Representing the probability that agent i considers to probe any m assigned to agent n. The method and the device can adopt a multi-agent detection task allocation strategy { X } i Initialization of the device in the interval [0,1 ]]Uniform distributed sampling of N MxN dimensions
Step S202: and optimizing the target disguise strategy. The embodiment of the application can input the current detection task allocation strategy
Updating target masquerading policy D k+1 . The target of the target camouflage strategy is to minimize the detection efficiency function and simultaneously meet the constraint condition that the target camouflage capacity is more than or equal to 0 and less than or equal to 1,
the current detection task can be distributed with a strategy by combining with an augmented Lagrange function
And substituting the target camouflage optimization function to obtain a target camouflage strategy at the moment of k + 1.
The target camouflage strategy optimization method is based on an alternating direction multiplier method, and the target camouflage strategy at the k +1 moment is solved in an iterative mode. Specifically, the embodiment of the application may first initialize the optimal target masquerading policy D at time k k Is an initial value, i.e. D k+1,0 ＝D k (ii) a Secondly, alternately optimizing the target function of the camouflage strategy and the local optimal value of the constraint function, wherein the initial value of the local optimal value of the target function of the camouflage strategy is
And updated by the following formula:
wherein,
U d ＝0 M×N the local optimum of the constraint function is initially
And updated by the following formula:
prox is a near-end operator, and can be defined as follows:
thirdly, the embodiment of the application can update the step t +1
Finally, when the convergence error is
And
for a sufficient time (usually 10 times) -3 ) Let the target at the time k +1 pretend policy
Step S203: and optimizing the intelligent agent detection task allocation strategy. The embodiment of the application can input k +1 stepsTarget masquerading strategy D k+1 Parallel updating of k +1 multi-agent detection task allocation strategy
The objective of the multi-agent detection task allocation strategy is to maximize the detection efficiency function and simultaneously satisfy the multi-agent capability constraint condition that 0 is less than or equal to X i ≤1,
Satisfy the constraint condition | X of the exploration task m | ∞ Combining an augmented Lagrange function, and carrying out a target camouflage strategy D of the step k +1 k+1 And substituting the detection task allocation strategy optimization function to obtain a detection task allocation strategy at the moment of k + 1.
The embodiment of the application can iteratively solve the detection task allocation strategy at the moment of k +1 on the basis of an alternative direction multiplier method. Specifically, for agent i, the embodiment of the present application may first initialize the optimal probe task allocation strategy at time k
Is an initial value, i.e.
Secondly, alternately optimizing the target function and the local optimal value of the constraint function of the detection task allocation strategy, wherein the initial value of the local optimal value of the target function of the detection task allocation is
And updated by the following formula:
wherein,
the initial value of the local optimum value of the constraint function of the detection task allocation strategy is
And can be updated by the following formula:
thirdly, updating the step t +1
Finally, when the convergence error is
And
for a sufficient time (usually 10 times) -3 ) Let the detection task at the time of k +1 distribute the strategy
The embodiment of the application can solve the residual error according to the following formula
And dual problem residual
If at the same time satisfy
And
terminating the optimization, otherwise, jumping to the above steps until the optimization time is consumed.
The embodiment of the application can output the optimal detection task allocation strategy
And a corresponding worst target masquerading policy D * ＝ k 。
Step S204: and judging whether the optimal maximum step number is reached. If the maximum number of steps is reached, the process proceeds to step S206, otherwise, the process proceeds to step S205.
Step S205: and judging whether consistency error and optimality error threshold conditions are met. If yes, the process proceeds to step S206, otherwise, the process proceeds to step S203.
Step S206: and returning the optimal solution of the multi-agent detection task allocation.
According to the distributed multi-agent detection task allocation method in the countermeasure scene, reasonable allocation of the multi-agents with different detection capabilities can be achieved by using the multi-agent detection efficiency function and the distributed multi-agent detection task allocation model according to the detection task allocation weight, the target detector configuration and detection capability carried by the multi-agent system, the target disguising strategy and the multi-agent detection task allocation strategy, so that the influence of the target disguising on the multi-agent detection efficiency is reduced to the maximum extent, and the collection of target characteristic information in the countermeasure environment is maximized. Therefore, the technical problem that the execution result of the detection task is easily influenced by the target disguise strategy due to the fact that the potential disguise countermeasure process of the target cannot be fully considered through a distributed detection task allocation method in the related art is solved, and therefore the acquisition amount of target characteristic information is reduced.
Next, a distributed multi-agent detection task allocation apparatus in a countermeasure scenario proposed according to an embodiment of the present application is described with reference to the drawings.
Fig. 3 is a block diagram of a distributed multi-agent detection task assignment device in a countermeasure scenario in accordance with an embodiment of the present application.
As shown in fig. 3, the distributed multi-agent detection task assigning apparatus 10 in the countermeasure scenario includes: a first function building module 100, a model building module 200 and an assignment module 300.
Specifically, the first function establishing module 100 is configured to establish a multi-agent detection efficiency function according to the detection task allocation weight, the configuration and detection capability of the target detector carried by the multi-agent system, the disguising policy of the target, and the multi-agent detection task allocation policy.
The model building module 200 is used for building a distributed multi-agent detection task distribution model according to preset multi-agent detection capability constraints, target disguise capability constraints and detection task constraints.
And the distribution module 300 is configured to alternately solve the task distribution strategy and the corresponding target disguise strategy of the multi-agent system according to the gradient information based on the distributed multi-agent detection task distribution model, and generate a distributed multi-agent detection task distribution result.
Optionally, in an embodiment of the present application, the distributed multi-agent detection task assigning apparatus 10 in the confrontation scenario further includes: the device comprises a setting module and a second function establishing module.
The setting module is used for setting optimization parameters and termination conditions.
And the second function establishing module is used for establishing an augmented Lagrange function of the detection efficiency and increasing a non-convergence penalty term of the detection efficiency function.
Optionally, in one embodiment of the present application, the multi-agent detection efficacy function is:
wherein, X i Represents the estimation of the global task allocation result of the multi-agent system by the agent i, and B represents the allocation weight parameter between the agent and the targetThe number of the target detector carried by the intelligent system is C, the target disguise strategy is D, and the number of the target detector carried by the intelligent system is E i And the matrix represents M rows and N columns of which the ith column is 1 and the rest is 0, and the lambda is a target detection capability parameter of different detectors.
Optionally, in an embodiment of the present application, the allocating module 300 includes: a first solving unit.
The first solving unit is used for solving the maximum value of the detection efficiency function under all disguise strategies by utilizing the multi-agent task allocation model.
Optionally, in an embodiment of the present application, the allocating module 300 further includes: the device comprises a second solving unit, a third solving unit and an allocating unit.
And the second solving unit is used for solving the optimal target disguise strategy under the current detection task allocation strategy.
And the third solving unit is used for solving the optimal task allocation strategy of each intelligent agent under the current optimal target disguising strategy in parallel so as to solve the dual parameters under the current detection task allocation strategy and the optimal target disguising strategy in parallel.
And the distribution unit is used for solving the original problem residual error and the dual problem residual error based on the dual parameters until the optimization is finished, so that the detection task distribution solution of the multi-agent system is the average value of the distribution solutions of all the agent local detection tasks.
It should be noted that the foregoing explanation on the embodiment of the distributed multi-agent detection task allocation method in the countermeasure scenario is also applicable to the distributed multi-agent detection task allocation apparatus in the countermeasure scenario of this embodiment, and details are not described here.
According to the distributed multi-agent detection task allocation device in the countermeasure scene, the multi-agent detection efficiency function and the distributed multi-agent detection task allocation model are utilized to realize reasonable allocation of the multi-agents with different detection capacities according to the detection task allocation weight, the target detector configuration and detection capacity carried by the multi-agent system, the target disguising strategy and the multi-agent detection task allocation strategy, so that the influence of the target disguising on the multi-agent detection efficiency is reduced to the maximum extent, and the collection of target characteristic information in the countermeasure environment is maximized. Therefore, the technical problem that the execution result of the detection task is easily influenced by the target disguise strategy due to the fact that the potential disguise countermeasure process of the target cannot be fully considered through a distributed detection task allocation method in the related art is solved, and therefore the acquisition amount of target characteristic information is reduced.
Fig. 4 is a schematic structural diagram of an electronic device according to an embodiment of the present application. The electronic device may include:
The processor 402, when executing the program, implements the distributed multi-agent detection task allocation method in the countermeasure scenario provided in the above-described embodiment.
Further, the electronic device further includes:
a communication interface 403 for communication between the memory 401 and the processor 402.
A memory 401 for storing computer programs executable on the processor 402.
If the memory 401, the processor 402 and the communication interface 403 are implemented independently, the communication interface 403, the memory 401 and the processor 402 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. 4, but this does not indicate only one bus or one type of bus.
Alternatively, in practical implementation, if the memory 401, the processor 402 and the communication interface 403 are integrated on a chip, the memory 401, the processor 402 and the communication interface 403 may complete communication with each other through an internal interface.
The processor 402 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 having stored thereon a computer program which, when executed by a processor, implements the distributed multi-agent detection task allocation method in the countermeasure scenario 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 to implicitly indicate 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, e.g., 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 by the method for 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 when the program is executed, the program 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 stand-alone 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. Although embodiments of the present application have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting the present application, and that variations, modifications, substitutions and alterations may be made to the above embodiments by those of ordinary skill in the art within the scope of the present application.
Claims (12)
1. A distributed multi-agent detection task allocation method in a confrontation scene is characterized by comprising the following steps:
establishing a multi-agent detection efficiency function according to detection task distribution weight, target detector configuration and detection capacity carried by the multi-agent system, target disguise strategy and multi-agent detection task distribution strategy;
establishing a distributed multi-agent detection task distribution model according to preset multi-agent detection capability constraint, target disguising capability constraint and detection task constraint;
and based on the distributed multi-agent detection task allocation model, alternately solving a task allocation strategy and a corresponding target disguise strategy of the multi-agent system according to the gradient information to generate a distributed multi-agent detection task allocation result.
2. The method of claim 1, prior to solving the task allocation strategy and the corresponding target masquerading strategy of the multi-agent system, further comprising:
setting optimization parameters and termination conditions;
and establishing an augmented Lagrange function of the detection efficiency, and increasing a non-convergence penalty term of the detection efficiency function.
3. The method of claim 1, wherein the multi-agent detection performance function is:
wherein, X i Representing the estimation of an agent i on the overall task distribution result of the multi-agent system, B representing the distribution weight parameter between the agent and the target, C representing the type of a target detector carried by the agent system, D representing the target disguise strategy, E i And the matrix represents M rows and N columns of which the ith column is 1 and the rest is 0, and the lambda is a target detection capability parameter of different detectors.
4. The method of claim 1, wherein generating distributed multi-agent probing task assignment results comprises:
and solving the maximum value of the detection efficiency function under all disguise strategies by using the multi-agent task allocation model.
5. The method according to any one of claims 1-4, wherein the alternately solving task allocation strategies and corresponding target masquerading strategies of the multi-agent system according to the gradient information comprises:
solving an optimal target disguise strategy under the current detection task allocation strategy;
the optimal task allocation strategy of each intelligent agent under the current optimal target camouflage strategy is solved in parallel, so that the current detection task allocation strategy and dual parameters under the optimal target camouflage strategy are solved in parallel;
and solving the original problem residual error and the dual problem residual error based on the dual parameters until the optimization is finished, so that the detection task allocation solution of the multi-agent system is the average value of the solution allocation of all agent local detection tasks.
6. A distributed multi-agent detection task assignment device in a confrontation scenario, comprising:
the first function establishing module is used for establishing a multi-agent detection efficiency function according to detection task distribution weight, target detector configuration and detection capacity carried by the multi-agent system, target disguise strategy and multi-agent detection task distribution strategy;
the model establishing module is used for establishing a distributed multi-agent detection task distribution model according to preset multi-agent detection capability constraint, target disguising capability constraint and detection task constraint;
and the distribution module is used for alternately solving a task distribution strategy of the multi-agent system and a corresponding target camouflage strategy according to the gradient information based on the distributed multi-agent detection task distribution model to generate a distributed multi-agent detection task distribution result.
7. The apparatus of claim 6, further comprising:
the setting module is used for setting optimization parameters and termination conditions;
and the second function establishing module is used for establishing an augmented Lagrange function of the detection efficiency and increasing a non-convergence penalty term of the detection efficiency function.
8. The apparatus of claim 6, wherein said multi-agent detection performance function is:
wherein, X i Representing the estimation of an agent i on the overall task distribution result of the multi-agent system, B representing the distribution weight parameter between the agent and the target, C representing the type of a target detector carried by the agent system, D representing the target disguise strategy, E i And the matrix represents M rows and N columns of which the ith column is 1 and the rest is 0, and the lambda is a target detection capability parameter of different detectors.
9. The apparatus of claim 6, wherein the assignment module comprises:
and the first solving unit is used for solving the maximum value of the detection efficiency function under all disguise strategies by utilizing the multi-agent task allocation model.
10. The apparatus of any of claims 6-9, wherein the assignment module further comprises:
the second solving unit is used for solving the optimal target disguise strategy under the current detection task allocation strategy;
a third solving unit, configured to solve the optimal task allocation strategy of each agent in parallel under the current optimal target masquerading strategy, so as to solve the current detection task allocation strategy and the dual parameter under the optimal target masquerading strategy in parallel;
and the distribution unit is used for solving the original problem residual error and the dual problem residual error based on the dual parameters until the optimization is finished, so that the detection task distribution solution of the multi-agent system is the average value of the distribution solutions of all the agent local detection tasks.
11. An electronic device, comprising: memory, processor and computer program stored on the memory and executable on the processor, the processor executing the program to implement the distributed multi-agent detection task allocation method in a countermeasure scenario according to any of claims 1-5.
12. A computer-readable storage medium, having stored thereon a computer program, characterized in that the program is executable by a processor for implementing a distributed multi-agent detection task allocation method in a confrontation scenario according to any of claims 1-5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210633921.6A CN114860416B (en) | 2022-06-06 | 2022-06-06 | Distributed multi-agent detection task allocation method and device in countermeasure scene |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210633921.6A CN114860416B (en) | 2022-06-06 | 2022-06-06 | Distributed multi-agent detection task allocation method and device in countermeasure scene |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114860416A true CN114860416A (en) | 2022-08-05 |
| CN114860416B CN114860416B (en) | 2024-04-09 |
Family
ID=82624075
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210633921.6A Active CN114860416B (en) | 2022-06-06 | 2022-06-06 | Distributed multi-agent detection task allocation method and device in countermeasure scene |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114860416B (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20190049975A1 (en) * | 2017-08-11 | 2019-02-14 | Tata Consultancy Services Limited | Method and system for optimally allocating warehouse procurement tasks to distributed robotic agents |
| CN109947567A (en) * | 2019-03-14 | 2019-06-28 | 深圳先进技术研究院 | A kind of multiple agent intensified learning dispatching method, system and electronic equipment |
| CN110712206A (en) * | 2019-10-16 | 2020-01-21 | 北京洛必德科技有限公司 | Multitask allocation method, multitask allocation device, multitask allocation equipment and storage medium of intelligent robot |
| WO2021258988A1 (en) * | 2020-06-23 | 2021-12-30 | 平安科技（深圳）有限公司 | Method for task assignment in distributed computing, and related device |
| CN114340016A (en) * | 2022-03-16 | 2022-04-12 | 北京邮电大学 | Power grid edge calculation unloading distribution method and system |
| US20220114301A1 (en) * | 2021-12-23 | 2022-04-14 | Intel Corporation | Methods and devices for a collaboration of automated and autonomous machines |
-
2022
- 2022-06-06 CN CN202210633921.6A patent/CN114860416B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20190049975A1 (en) * | 2017-08-11 | 2019-02-14 | Tata Consultancy Services Limited | Method and system for optimally allocating warehouse procurement tasks to distributed robotic agents |
| CN109947567A (en) * | 2019-03-14 | 2019-06-28 | 深圳先进技术研究院 | A kind of multiple agent intensified learning dispatching method, system and electronic equipment |
| CN110712206A (en) * | 2019-10-16 | 2020-01-21 | 北京洛必德科技有限公司 | Multitask allocation method, multitask allocation device, multitask allocation equipment and storage medium of intelligent robot |
| WO2021258988A1 (en) * | 2020-06-23 | 2021-12-30 | 平安科技（深圳）有限公司 | Method for task assignment in distributed computing, and related device |
| US20220114301A1 (en) * | 2021-12-23 | 2022-04-14 | Intel Corporation | Methods and devices for a collaboration of automated and autonomous machines |
| CN114340016A (en) * | 2022-03-16 | 2022-04-12 | 北京邮电大学 | Power grid edge calculation unloading distribution method and system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114860416B (en) | 2024-04-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110316193B (en) | Preview distance setting method, device, equipment and computer readable storage medium | |
| US20190369625A1 (en) | Automatic charging system for robot and method thereof | |
| CN111680673B (en) | Method, device and equipment for detecting dynamic object in grid map | |
| CN109067473B (en) | A kind of quantum bit reads the demodulation analysis method and device of signal | |
| JP2019191145A (en) | Identification method for charging stand, device, robot, and computer readable storage | |
| CN113219993A (en) | Path planning method and cleaning robot | |
| CN111737395A (en) | Method and device for generating occupancy grid map and robot system | |
| CN114968573A (en) | Computing resource scheduling method and device and computer readable storage medium | |
| CN115236611A (en) | Multi-jammer cooperative suppression resource scheduling method for radar system | |
| CN114860416B (en) | Distributed multi-agent detection task allocation method and device in countermeasure scene | |
| US20230089320A1 (en) | Logical node layout method and apparatus, computer device, and storage medium | |
| CN112097772B (en) | Robot and map construction method and device thereof | |
| CN111880926B (en) | Load balancing method and device and computer storage medium | |
| CN117295158A (en) | WiFi positioning method, device, equipment and medium based on fingerprint matching | |
| CN108830007A (en) | A kind of radar transmission power distribution method based on secondary cost function | |
| CN108512894B (en) | Distributed load balancing method and system for self-powered sensor network | |
| CN115268968A (en) | Internet of things control system and method based on cloud platform | |
| CN114204979B (en) | Unmanned aerial vehicle ad hoc network method and device based on relative positions | |
| CN115542346A (en) | Ground detection method, device, vehicle and storage medium | |
| CN115150437A (en) | Node deployment method, device and equipment applied to automatic driving system of vehicle | |
| CN111142513B (en) | Method for acquiring initialization coordinates, scheduling method, electronic device and storage medium | |
| CN113971687A (en) | Object tracking method, device electronic equipment and storage medium | |
| CN111580508A (en) | Robot positioning method and device, electronic equipment and storage medium | |
| CN111833199A (en) | Community structure dividing method, device, equipment and computer readable medium | |
| CN117290560B (en) | Method and device for acquiring graph data in graph calculation task |
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 |