CN104699983A - Confrontation simulation optimizing method and system - Google Patents
Confrontation simulation optimizing method and system Download PDFInfo
- Publication number
- CN104699983A CN104699983A CN201510132160.6A CN201510132160A CN104699983A CN 104699983 A CN104699983 A CN 104699983A CN 201510132160 A CN201510132160 A CN 201510132160A CN 104699983 A CN104699983 A CN 104699983A
- Authority
- CN
- China
- Prior art keywords
- particle
- optimal strategy
- result
- optimum point
- adaptive value
- 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
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides a confrontation simulation optimizing method. The confrontation simulation optimizing method comprises the following steps of S1, sending alternative strategies and confrontation conditions to a plurality of simulation platforms to be simulated to obtain a plurality of confrontation results of a preset interference strategy under the confrontation conditions; S2, processing a plurality of confrontation results to obtain an optimal strategy; S3 judging whether the optimal strategy satisfies a preset condition or not, enabling the optimal strategy to be served as a result to be output if yes and repeatedly executing S1 to S3 if no. The confrontation simulation optimizing method is efficient and allows parallel execution. The invention also provides a confrontation simulation optimizing system.
Description
Technical field
The present invention relates to computer simulation technique field, particularly relate to a kind of confronting simulation optimization method and system.
Background technology
Confronting simulation optimization system may be used for finding the optimal strategy in confronting simulation.There is a lot of Counter Simulation System both at home and abroad now, as long-range countermeasure mock battle system, remote tank laser countermeasure (s) training system etc.But these Counter Simulation Systems are all for assessment of the battle tactics inputted or the fight capability directly assessing user, the characteristic utilizing analogue system to find antagonistic process, and find optimal strategy, auxiliary operational front does not relate to.
Summary of the invention
The present invention is intended to solve one of technical matters in correlation technique at least to a certain extent.For this reason, first aspect present invention object is to propose a kind of parallel, efficient confronting simulation optimization method.
Second aspect present invention object is to propose a kind of confronting simulation optimization system.
To achieve these goals.The confronting simulation optimization method that first aspect present invention embodiment proposes, comprises the following steps: S1, Resisting Condition is sent to multiple emulation platform and emulates, with multiple antagonism results of predetermined jamming exposure area under obtaining described Resisting Condition; S2, processes described multiple antagonism result, to obtain optimal strategy.S3, judges whether described optimal strategy meets predetermined condition, if so, then by described optimal strategy as a result and export, if not, then repeats S1 ~ S3.
According to the confronting simulation optimization method of the embodiment of the present invention, by sending Resisting Condition to multiple emulation platform, emulation platform is parallel to be emulated, the antagonism result of predetermined jamming exposure area under returning this Resisting Condition, process these antagonism results, until find best strategy.Method of the present invention, efficiently also can executed in parallel.
In some instances, described step S2 utilizes the population iterative algorithm of Corpus--based Method information to process described multiple antagonism result.
In some instances, the population iterative algorithm of described Corpus--based Method information comprises the following steps: S21, initialization particle, and the adaptive value calculating described particle; S22, obtains the current optimum point in population according to described adaptive value; S23, described particle constantly follows the tracks of up-to-date described current optimum point by death process, and the optimum interference position of final acquisition.
In some instances, described step S21 utilizes auto-adaptive function to obtain described adaptive value.
In some instances, described death process comprises:
S231, selects described current optimum point;
S232, calculates the normalized cumulant between described particle and described current optimum point;
S233, judges whether described normalized cumulant is greater than predetermined threshold value, if so, then judges particle existence, if not, then judges that particle is dead.
The confronting simulation optimization system of second aspect present invention embodiment, comprising: interface module, emulates for Resisting Condition being sent to multiple emulation platform, with multiple antagonism results of predetermined jamming exposure area under obtaining described Resisting Condition; Optimizing module, for processing described multiple antagonism result, to obtain optimal strategy.Judge module, for judging whether described optimal strategy meets predetermined condition, if so, then by described optimal strategy as a result and export.
According to the confronting simulation optimization system of the embodiment of the present invention, interface module is by sending Resisting Condition to multiple emulation platform, and emulation platform is parallel to be emulated, the antagonism result of predetermined jamming exposure area under returning this Resisting Condition, these antagonism results of optimizing resume module, until find best strategy.System of the present invention, efficiently also can executed in parallel.
In some instances, described optimizing module is also for utilizing the population iterative algorithm of Corpus--based Method information to process described multiple antagonism result.
In some instances, described optimizing module comprises: pretreatment unit, for initialization particle, and calculates the adaptive value of described particle; Iteration unit, for obtaining the current optimum point in population according to described adaptive value; Optimizing unit, constantly follows the tracks of up-to-date described current optimum point for described particle by death process, and the optimum interference position of final acquisition.
In some instances, described pretreatment unit utilizes auto-adaptive function to obtain described adaptive value.
In some instances, described system is also drawn together: task management module, for managing the task between described system and described emulation platform.
The aspect that the present invention adds and advantage will part provide in the following description, and part will become obvious from the following description, or be recognized by practice of the present invention.
Accompanying drawing explanation
Fig. 1 is the process flow diagram of confronting simulation optimization method according to an embodiment of the invention;
Fig. 2 is the process flow diagram of the population iterative algorithm of the Corpus--based Method information of one embodiment of the invention;
Fig. 3 is the death process schematic diagram of one embodiment of the invention;
Fig. 4 is the searching process schematic diagram of one embodiment of the invention;
Fig. 5 is the structured flowchart of confronting simulation optimization system according to an embodiment of the invention;
Fig. 6 is the scheduling simulation platform process schematic diagram of one embodiment of the invention; With
Fig. 7 is that the scheduling simulation platform of one embodiment of the invention runs schematic diagram.
Embodiment
In describing the invention, it will be appreciated that, term " " center ", " longitudinal direction ", " transverse direction ", " length ", " width ", " thickness ", " on ", D score, " front ", " afterwards ", " left side ", " right side ", " vertically ", " level ", " top ", " end " " interior ", " outward ", " clockwise ", " counterclockwise ", " axis ", " radial direction ", orientation or the position relationship of the instruction such as " circumference " are based on orientation shown in the drawings or position relationship, only the present invention for convenience of description and simplified characterization, instead of indicate or imply that the device of indication or element must have specific orientation, with specific azimuth configuration and operation, therefore limitation of the present invention can not be interpreted as.
In addition, term " first ", " second " only for describing object, and can not be interpreted as instruction or hint relative importance or imply the quantity indicating indicated technical characteristic.Thus, be limited with " first ", the feature of " second " can express or impliedly comprise at least one this feature.In describing the invention, the implication of " multiple " is at least two, such as two, three etc., unless otherwise expressly limited specifically.
In the present invention, unless otherwise clearly defined and limited, the term such as term " installation ", " being connected ", " connection ", " fixing " should be interpreted broadly, and such as, can be fixedly connected with, also can be removably connect, or integral; Can be mechanical connection, also can be electrical connection; Can be directly be connected, also indirectly can be connected by intermediary, can be the connection of two element internals or the interaction relationship of two elements, unless otherwise clear and definite restriction.For the ordinary skill in the art, above-mentioned term concrete meaning in the present invention can be understood as the case may be.
In the present invention, unless otherwise clearly defined and limited, fisrt feature second feature " on " or D score can be that the first and second features directly contact, or the first and second features are by intermediary indirect contact.And, fisrt feature second feature " on ", " top " and " above " but fisrt feature directly over second feature or oblique upper, or only represent that fisrt feature level height is higher than second feature.Fisrt feature second feature " under ", " below " and " below " can be fisrt feature immediately below second feature or tiltedly below, or only represent that fisrt feature level height is less than second feature.
Be described below in detail embodiments of the invention, the example of described embodiment is shown in the drawings, and wherein same or similar label represents same or similar element or has element that is identical or similar functions from start to finish.Be exemplary below by the embodiment be described with reference to the drawings, be intended to for explaining the present invention, and can not limitation of the present invention be interpreted as.
See Fig. 1, the confronting simulation optimization method of first aspect present invention embodiment, comprises the following steps:
S1, is sent to multiple emulation platform by alternate strategies and Resisting Condition and emulates, with multiple antagonism results of predetermined jamming exposure area under obtaining Resisting Condition;
S2, processes multiple antagonism result, to obtain optimal strategy.
S3, judges whether optimal strategy meets predetermined condition, if so, then by optimal strategy as a result and export, if not, then repeats S1 ~ S3.
Specific implementation process prescription is as follows:
Step S1, is sent to multiple emulation platform by alternate strategies and Resisting Condition and emulates, with multiple antagonism results of predetermined jamming exposure area under obtaining Resisting Condition.
By the data interaction between emulation platform, alternate strategies and Resisting Condition can be sent to multiple emulation platform and emulate, Parallel Scheduling emulation platform, with multiple antagonism results of predetermined jamming exposure area under obtaining Resisting Condition.
In real process, in communication, have three: artificial tasks (comprising Resisting Condition), frame data, result data.Therefore emulation platform needs to realize three data request interface: emulation platform sends artificial tasks request, obtains artificial tasks data structure; Emulation platform sends the frame data in simulation process; Emulation platform sends antagonism result data.
Step S2, processes multiple antagonism result, to obtain optimal strategy.
Concrete, utilize the population iterative algorithm of Corpus--based Method information to process multiple antagonism result.In one embodiment of the invention, the population iterative algorithm of Corpus--based Method information comprises the following steps:
S21, initialization particle, and the adaptive value calculating particle;
S22, obtains the current optimum point in population according to adaptive value;
S23, particle constantly follows the tracks of up-to-date current optimum point by death process, and the optimum interference position of final acquisition.
Population iterative algorithm needs constantly to call emulation platform and obtains emulated data (antagonism result).One time iteration needs some emulated datas, and the search target of population is exactly optimum jamming exposure area.
Iterative formula based on particle cluster algorithm is expressed as follows:
Wherein Vi (t) the flying speed vector that is t No. i-th particle, i is positive integer.The inertial coefficient that w (t) is t, P
ithe position that t adaptive value that () lives through for No. i-th particle self is the highest, the position that the adaptive value in all positions that Pg (t) is population is the highest,
for adjustment factor, for controlling the ratio that particle is optimum to self and global optimum is close, the speed of convergence of population can be controlled by adjusting these two parameters.
Below in conjunction with Fig. 2, introduce the implementation procedure of the population iterative algorithm of the Corpus--based Method information of the embodiment of the present invention in detail.
Step S21, initialization particle, and the adaptive value calculating particle.
In one embodiment of the invention, auto-adaptive function is utilized to obtain the adaptive value of particle.Auto-adaptive function is defined as follows:
R
ijt () represents the distance between particle i and particle j, i and j is respectively positive integer.Res
it () is the weighting of emulation (antagonism) result of i-th particle, wherein disturb successful Res
it ()=1, disturbs failed Res
i(t)=-2.Each emulation terminate to recalculate adaptive value a little, the adaptive value of particle constantly changes, and does not consider the impact of the history optimal location of particle self in iterative process.
Step S22, obtains the current optimum point in population according to adaptive value.
In one embodiment of the invention, the highest position of adaptive value is chosen as the current optimum point in population.
Step S23, particle constantly follows the tracks of up-to-date current optimum point by death process, and the optimum interference position of final acquisition.
As shown in Figure 3, the death process of one embodiment of the invention comprises the following steps:
S231, selects current optimum point;
S232, calculates the normalized cumulant between particle and current optimum point;
S233, judges whether normalized cumulant is greater than predetermined threshold value, if so, then judges particle existence, if not, then judges that particle is dead.
Step S231, selects current optimum point.
After selecting current optimum point by step S22, all particles in population all get close to this current optimum point.
Step S232, calculates the normalized cumulant between particle and current optimum point.
Step S233, judges whether normalized cumulant is greater than predetermined threshold value, if so, then judges particle existence, if not, then judges that particle is dead.
As shown in the pilot process schematic diagram of certain optimizing of Fig. 4 one embodiment of the invention, the successful particle of '+' representative interference, the particle that ' o ' representative interference is failed.Initialized 80 particles are calculated by adaptive value, have selected the particle in the upper left corner as potential optimal location.Remaining particle is just drawn close to optimal location, find that many interference failed point have appearred in the surrounding of optimal location, cause the adaptive value of former optimal location to decline, and the particle position below other particles is as optimal location.After very long moving process, finally converge in following position in population, can see that particles all in the circle in the lower right corner all achieves and successfully disturb, illustrated herein for this kind follows the tracks of the optimum interference position of situation.
Step S3, judges whether optimal strategy meets predetermined condition, if so, then by optimal strategy as a result and export, if not, then repeats S1 ~ S3.
According to the confronting simulation optimization method of the embodiment of the present invention, by sending Resisting Condition to multiple emulation platform, emulation platform is parallel to be emulated, the antagonism result of predetermined jamming exposure area under returning this Resisting Condition, process these antagonism results, until find best strategy.Method of the present invention, efficiently also can executed in parallel.
As shown in Figure 5, the confronting simulation optimization system 100 of second aspect present invention embodiment comprises interface module 10, optimizing module 20 and judge module 30.
Interface module 10 is sent to multiple emulation platform for anti-condition and emulates, with multiple antagonism results of predetermined jamming exposure area under obtaining Resisting Condition.Optimizing module 20 processes multiple antagonism result, to obtain optimal strategy.Judge module 30 for judging whether optimal strategy meets predetermined condition, if so, then by optimal strategy as a result and export.
Concrete, the optimization system 100 of emulation platform and the embodiment of the present invention is by interface module 10, and optimization system 100 just can be applied to this emulation platform.Optimization system 100 can Parallel Scheduling emulation platform (as shown in Figure 6), thus more efficiently can complete emulated data (antagonism result) and obtain and the search of optimal strategy.Hereafter for sea Infrared simulator, to find optimum jamming exposure area in infrared counteraction for target, the embodiment of optimization system 100 is described.
Optimization system 100 needs to communicate with emulation platform, and both present C/S structure, and optimization system serves as the role of server, and emulation platform serves as the role of client.In actual moving process, data are transmitted by JSON serializing mode.
Three are had: artificial tasks, frame data, result data in communication.So emulation platform needs to realize three data request interface:
(1) emulation platform sends artificial tasks request, obtains artificial tasks data structure.
(2) emulation platform sends the frame data in simulation process.
(3) emulation platform sends result data.
Optimization system 100 needs to realize three services:
(1) optimization system accepts artificial tasks request, sends artificial tasks data structure.
(2) optimization system accepts the frame data in simulation process, and response receives.
(3) optimization system accepts result data, and response receives.
The data type of definition comprises all (JsonIO, Request, Response, Task) in AirObject, NetworkHelper, SystemBase, System2_Client, System2_Server and Handler.
NetworkHelper realizes the network communication interface of bottom, mainly provides two method: Listen and Send.Listen binds the IP and port that specify, opens a circulation, monitors the request being sent to this port.Circulation receive character string again ' e ' time exit; This request of a thread process is opened when receiving other data.Send sends data to the IP specified and port, and returns the data received.
SystemXXX opens bottom communication, and the packet that Preliminary Analysis bottom receives, be distributed to high-rise packet handler.Run method opens bottom communication thread, also opens an order receiving thread, in order to receive the input control of user.System2_Client/Server is client and server respectively.
JsonIO provides the serializing of data, and the type instance sequence that can comprise some data by changes into a character string (json form), then by Internet Transmission, or a character string antitone sequence is changed into the example of a type.Conveniently type is held as one man to communicate with C++, JsonIO only supports serializing and the unserializing of a class simple types (referring to the type by int, float, bool, unicode, str and simple type definitions and corresponding list), the serializing (being equivalent to the data redefining base class) after also supporting type to inherit.The method that can call has Load, Save (input and output are files), LoadToString, SaveToString (during input and output character string).
AirObject refers to the type transmitted between server and client side, comprises Request, Response two kinds.Request refers to that client is sent to the request type of server end, specifically comprises SimulationTaskRequest, ResultData, FrameData tri-kinds.The base class of Request type is all MachineBase, and the inside contains the flag information of emulation platform.Response refers to the data type that server returns, and comprises SimulationTask (inherit ResponseBase) or is directly ResponseBase.A return code is all comprised, in order to manage the operation of emulation platform inside ResponseBase.Be any type in order to indicate in transmission over networks, also need the type name of the character string of serializing to send together.When actual realization, by the serializing character string of those types and the name of type are placed on inside Task above.So real transmission only has Task type.
Handler is responsible for assuring reason, calls different process functions to different bags.Process function is all " Handle+ request type name " definition like this.Such as SimulationTaskRequest data can call HandleSimulationTaskRequest, thus to high level requests task, and task packing can be sent.All emulation platforms and its task index emulated is also stored for inside Handler.
Optimizing module 20 processes multiple antagonism result, to obtain optimal strategy.
Optimizing module 20 comprises: pretreatment unit 201, iteration unit 202 and optimizing unit 203.
Pretreatment unit 201 for initialization particle, and calculates the adaptive value of particle.Iteration unit 202 is for obtaining the current optimum point in population according to adaptive value.Optimizing unit 203 constantly follows the tracks of up-to-date current optimum point for particle by death process, and the optimum interference position of final acquisition.
It should be noted that, specific implementation and the first aspect present invention of optimizing module 20 are that the content of the step S2 of embodiment is consistent, are specifically embodiment parts see first aspect present invention, repeat no more here.
In addition, in one embodiment of the invention, optimization system 100 also comprises task management module 40.Task management module 40 is for the task between management system 100 and emulation platform.
In actual moving process, task management module 40 realizes the management treating the task of emulation, realizes primarily of TaskManger.Task management module 40 stores all needing the task of emulation, not completing of task, completing of task, completing of tasks.If task all finishes, task management module 40 can call optimizing module 20, produces the task that some are new.
Optimization system 100 and emulation platform call the operation sectional drawing of emulation as Fig. 7.
According to the confronting simulation optimization system of the embodiment of the present invention, interface module is by sending Resisting Condition to multiple emulation platform, and emulation platform is parallel to be emulated, the antagonism result of predetermined jamming exposure area under returning this Resisting Condition, these antagonism results of optimizing resume module, until find best strategy.System of the present invention, efficiently also can executed in parallel.
In the description of this instructions, specific features, structure, material or feature that the description of reference term " embodiment ", " some embodiments ", " example ", " concrete example " or " some examples " etc. means to describe in conjunction with this embodiment or example are contained at least one embodiment of the present invention or example.In this manual, to the schematic representation of above-mentioned term not must for be identical embodiment or example.And the specific features of description, structure, material or feature can combine in one or more embodiment in office or example in an appropriate manner.In addition, when not conflicting, the feature of the different embodiment described in this instructions or example and different embodiment or example can carry out combining and combining by those skilled in the art.
Although illustrate and describe embodiments of the invention above, be understandable that, above-described embodiment is exemplary, can not be interpreted as limitation of the present invention, and those of ordinary skill in the art can change above-described embodiment within the scope of the invention, revises, replace and modification.
Claims (10)
1. a confronting simulation optimization method, is characterized in that, comprises the following steps:
S1, is sent to multiple emulation platform by alternate strategies and Resisting Condition and emulates, with multiple antagonism results of predetermined jamming exposure area under obtaining described Resisting Condition;
S2, processes described multiple antagonism result, to obtain optimal strategy;
S3, judges whether described optimal strategy meets predetermined condition, if so, then by described optimal strategy as a result and export, if not, then repeats S1 ~ S3.
2. the method for claim 1, is characterized in that, described step S2 utilizes the population iterative algorithm of Corpus--based Method information to process described multiple antagonism result.
3. method as claimed in claim 2, it is characterized in that, the population iterative algorithm of described Corpus--based Method information comprises the following steps:
S21, initialization particle, and the adaptive value calculating described particle;
S22, obtains the current optimum point in population according to described adaptive value;
S23, described particle constantly follows the tracks of up-to-date described current optimum point by death process, and the optimum interference position of final acquisition.
4. method as claimed in claim 3, it is characterized in that, described step S21 utilizes auto-adaptive function to obtain described adaptive value.
5. method as claimed in claim 3, it is characterized in that, described death process comprises:
S231, selects described current optimum point;
S232, calculates the normalized cumulant between described particle and described current optimum point;
S233, judges whether described normalized cumulant is greater than predetermined threshold value, if so, then judges particle existence, if not, then judges that particle is dead.
6. a confronting simulation optimization system, is characterized in that, comprising:
Interface module, emulates for Resisting Condition being sent to multiple emulation platform, with multiple antagonism results of predetermined jamming exposure area under obtaining described Resisting Condition;
Optimizing module, for processing described multiple antagonism result, to obtain optimal strategy.
Judge module, for judging whether described optimal strategy meets predetermined condition, if so, then by described optimal strategy as a result and export.
7. system as claimed in claim 6, it is characterized in that, described optimizing module is also for utilizing the population iterative algorithm of Corpus--based Method information to process described multiple antagonism result.
8. system as claimed in claim 7, it is characterized in that, described optimizing module comprises:
Pretreatment unit, for initialization particle, and calculates the adaptive value of described particle;
Iteration unit, for obtaining the current optimum point in population according to described adaptive value;
Optimizing unit, constantly follows the tracks of up-to-date described current optimum point for described particle by death process, and the optimum interference position of final acquisition.
9. system as claimed in claim 8, it is characterized in that, described pretreatment unit utilizes auto-adaptive function to obtain described adaptive value.
10. as the system that claim 6 is stated, it is characterized in that, described system is also drawn together:
Task management module, for managing the task between described system and described emulation platform.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510132160.6A CN104699983B (en) | 2015-03-24 | 2015-03-24 | Confronting simulation optimization method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510132160.6A CN104699983B (en) | 2015-03-24 | 2015-03-24 | Confronting simulation optimization method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN104699983A true CN104699983A (en) | 2015-06-10 |
| CN104699983B CN104699983B (en) | 2018-08-03 |
Family
ID=53347095
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510132160.6A Active CN104699983B (en) | 2015-03-24 | 2015-03-24 | Confronting simulation optimization method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104699983B (en) |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20060200333A1 (en) * | 2003-04-10 | 2006-09-07 | Mukesh Dalal | Optimizing active decision making using simulated decision making |
| CN101741642A (en) * | 2009-12-17 | 2010-06-16 | 北京航空航天大学 | Task deployment system for distributed simulation of computer network attack and defense training |
-
2015
- 2015-03-24 CN CN201510132160.6A patent/CN104699983B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20060200333A1 (en) * | 2003-04-10 | 2006-09-07 | Mukesh Dalal | Optimizing active decision making using simulated decision making |
| CN101741642A (en) * | 2009-12-17 | 2010-06-16 | 北京航空航天大学 | Task deployment system for distributed simulation of computer network attack and defense training |
Non-Patent Citations (4)
| Title |
|---|
| 于昌荣，等: "基于知识的潜艇作战辅助决策技术", 《2013第一届中国指挥控制大会论文集》 * |
| 范超赞: "改进粒子群算法研究", 《中国优秀硕士学位论文全文数据库信息科技辑》 * |
| 袁立鹏，等.: "基于改进遗传算法的坦克发动机道路模拟测试平台轨迹寻优", 《东南大学学报(自然科学版)》 * |
| 赵志宁.: "基于改进离散粒子群优化算法的作战弹药分配研究", 《数值计算与计算机应用》 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN104699983B (en) | 2018-08-03 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20210003412A1 (en) | Method and Device of Path Optimization for UAV, and Storage Medium thereof | |
| CN112001585A (en) | Multi-agent decision method and device, electronic equipment and storage medium | |
| CN111352352A (en) | Method and system for determining system settings of an industrial system | |
| CN114596553B (en) | Model training method, trajectory prediction method and device and automatic driving vehicle | |
| CN109983480A (en) | Use cluster loss training neural network | |
| CN102778235A (en) | Multiple-unmanned aerial vehicle collaborative area searching method under communication constrains | |
| CN106227043A (en) | adaptive optimal control method | |
| CN116187207B (en) | Land battle equipment system simulation evaluation method, device and storage medium | |
| US11323177B2 (en) | Method and system for free space optical communication performance prediction | |
| Xie et al. | Application of improved Cuckoo search algorithm to path planning unmanned aerial vehicle | |
| CN109063978A (en) | Energy Internet resources dispatching method and system, readable storage medium storing program for executing and terminal | |
| CN111814117A (en) | Model interpretation method, device and readable storage medium | |
| Zhao et al. | Adaptive swarm intelligent offloading based on digital twin-assisted prediction in VEC | |
| Agogino et al. | Learning indirect actions in complex domains: action suggestions for air traffic control | |
| CN104699983A (en) | Confrontation simulation optimizing method and system | |
| Cheng et al. | Application of Neural Network in Performance Evaluation of Satellite Communication System: Review and Prospect | |
| Gaowei et al. | Using multi-layer coding genetic algorithm to solve time-critical task assignment of heterogeneous UAV teaming | |
| Zhang et al. | Energy-and Cost-Efficient Transmission Strategy for UAV Trajectory Tracking Control: A Deep Reinforcement Learning Approach | |
| Wang et al. | Superior relation‐based firefly algorithm for superior solution set search problem | |
| US11620575B2 (en) | Interactive and dynamic mapping engine (iDME) | |
| Zhang et al. | Reinforcement Learning from Demonstrations by Novel Interactive Expert and Application to Automatic Berthing Control Systems for Unmanned Surface Vessel | |
| CN112926198A (en) | Credibility evaluation method and system of MSaaS simulation architecture | |
| CN106920041A (en) | Model selection method for overhead transmission line fixed wing unmanned aerial vehicle system | |
| CN113296893A (en) | Cloud platform low-resource-loss virtual machine placement method based on hybrid sine and cosine particle swarm optimization algorithm | |
| Wei | Improved ant colony algorithm based on information entropy |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |