CN113191586B - Task-oriented man-machine unmanned aerial vehicle matching method - Google Patents
Task-oriented man-machine unmanned aerial vehicle matching method Download PDFInfo
- Publication number
- CN113191586B CN113191586B CN202110315209.7A CN202110315209A CN113191586B CN 113191586 B CN113191586 B CN 113191586B CN 202110315209 A CN202110315209 A CN 202110315209A CN 113191586 B CN113191586 B CN 113191586B
- Authority
- CN
- China
- Prior art keywords
- task
- unmanned aerial
- aerial vehicle
- fitness
- manned
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
- G06Q10/06311—Scheduling, planning or task assignment for a person or group
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/18—Complex mathematical operations for evaluating statistical data, e.g. average values, frequency distributions, probability functions, regression analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0635—Risk analysis of enterprise or organisation activities
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Strategic Management (AREA)
- Entrepreneurship & Innovation (AREA)
- Economics (AREA)
- Theoretical Computer Science (AREA)
- Operations Research (AREA)
- Data Mining & Analysis (AREA)
- Educational Administration (AREA)
- Computational Mathematics (AREA)
- Pure & Applied Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Mathematical Physics (AREA)
- Tourism & Hospitality (AREA)
- Quality & Reliability (AREA)
- Marketing (AREA)
- Mathematical Optimization (AREA)
- Mathematical Analysis (AREA)
- Game Theory and Decision Science (AREA)
- Development Economics (AREA)
- Software Systems (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Biology (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Probability & Statistics with Applications (AREA)
- Databases & Information Systems (AREA)
- Algebra (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a task-oriented man-machine unmanned aerial vehicle matching method. Step 1: establishing a task fitness rule base according to the manned characteristics and/or the unmanned characteristic; step 2: acquiring all task targets to be executed to form a task target set, and forming a cluster set by units of which one party has a man machine and/or an unmanned aerial vehicle; and step 3: acquiring attribute sets of all tasks; and 4, step 4: quantifying different attributes of the task target according to the battlefield environment and the task attribute difference; and 5: obtaining fitness values of the unmanned machine and the man-machine to the task; step 6: setting gain coefficients with different attributes; and 7: determining the fitness value of the manned and/or unmanned aerial vehicle to the task; and 8: establishing a task fitness function; and step 9: and obtaining a man-machine and/or unmanned aerial vehicle configuration scheme. The invention solves the problem of the inadequacy of being not based on different types of manned or unmanned aerial vehicles suitable for executing different types of tasks.
Description
Technical Field
The invention relates to the field of task allocation of unmanned aerial vehicles, in particular to a task-oriented method for matching unmanned aerial vehicles.
Background
At present, the intelligent weaponry represented by the unmanned aerial vehicle is paid unprecedented attention and developed, and the intelligent cooperative air combat of the manned/unmanned aerial vehicle is used as a foreseeable brand-new combat power and is taken as an effective way for generating the combat capability of a system, so that huge changes are brought to the future air combat style.
In the aspect of effect evaluation of manned/unmanned aerial vehicle cooperative combat, current research mainly considers the manned and unmanned aerial vehicles as different nodes in a cooperative combat network according to the difference of communication capacity, control capacity and decision-making capacity, and effect evaluation is performed when the manned and unmanned aerial vehicles cooperatively execute tasks. The indexes for evaluating the operational benefits of the unmanned aerial vehicle and the manned vehicle during task allocation mainly comprise the loss degree of each unmanned aerial vehicle or manned vehicle, the target income value and the flight range, the adaptive degree of the unmanned aerial vehicle/manned vehicle to the task is not fully considered by the evaluation modes or the income indexes, the income is only evaluated from two aspects of task acquisition and unmanned aerial vehicle consumption, and the task allocation is carried out.
The method of selecting the unmanned aerial vehicle by only considering the income obtained by completing the task target does not fully consider the complexity of the task and the corresponding relationship between the complexity and the heterogeneity difference of the unmanned aerial vehicle, and has certain defects in the aspect of reflecting the real battle scene.
Disclosure of Invention
The invention provides a task-oriented man-machine unmanned aerial vehicle matching method, which aims at solving the problem that different types of man-machine unmanned aerial vehicles or unmanned aerial vehicles are not suitable for executing different types of tasks when man-machine unmanned aerial vehicles and unmanned aerial vehicles evaluate cooperative income and carry out task allocation aiming at the cooperative battle of a man-machine unmanned aerial vehicle cluster.
The invention is realized by the following technical scheme:
a task-oriented manned and unmanned aerial vehicle matching method comprises the following steps:
step 1: establishing a task fitness rule base according to the manned characteristics and/or the unmanned characteristic;
and 2, step: acquiring all task targets to be executed to form a task target set, and forming a cluster set by units of which one party has a man machine and/or an unmanned aerial vehicle;
and step 3: subdividing the task target set in the step 2 into contents, requirements, properties and characteristics of different tasks according to the combat requirements to obtain attribute sets of all the tasks;
and 4, step 4: quantizing different attributes of the task target according to the battlefield environment and the task attribute difference and the prior statistical probability characteristic or numerical simulation;
and 5: according to the quantitative parameters in the step 4 and the task fitness rule base in the step 1, the fitness values of the unmanned machine and the unmanned aerial vehicle to the tasks are obtained;
and 6: setting gain coefficients with different attributes for the combat targets and the task requirements according to the prior knowledge;
and 7: according to different attribute parameters and task fitness, determining fitness values of the unmanned person and/or unmanned aerial vehicle to the tasks;
and 8: establishing a task fitness function according to different attribute parameters, task fitness and gain coefficients of different attributes;
and step 9: and (3) obtaining a human-machine and/or unmanned aerial vehicle configuration scheme according to the task fitness function in the step (8) and the cluster set in the step (2).
Further, the establishment of the task fitness rule base in the step 1 is specifically that the unmanned aerial vehicle does not participate in a pilot, is suitable for executing a task with long duration, does not have personnel safety risks, and is suitable for executing a dangerous task;
the unmanned aerial vehicle is better than the unmanned aerial vehicle in human-computer maneuverability, is suitable for executing tasks with strong maneuverability and executing close-range fighting tasks.
Further, the task target set in step 2 is specifically that the task target set is MB = { MB ] in cooperative combat 1 ,MB 2 ,…,MB m A total of m targets;
the cluster set is specifically that the cluster set of the local computers isN total people/unmanned planes, the jth person/unmanned plane can be recorded asTaking the superscript function epsilon as:
Further, the attribute set of all tasks in step 3 is specifically that the ith task target can be recorded asWhich share α attributes for reconnaissance, strike, and battlefield evaluation, the set of attributes for the mission target may be defined as
Further, the step 4 is specifically to decompose and analyze all attributes of the task to obtain characteristic parameters of success rate, risk and cost, and complete digital representation of each sub-attribute according to the actual combat environment and the task type.
Further, the step 5 of obtaining fitness values of the human-computer and the unmanned aerial vehicle to the task specifically includes obtaining the goodness of the human-computer and the unmanned aerial vehicle to execute the task under different tasks, different attribute types and different attribute proportions according to the statistical probability of the past actual combat data or the numerical simulation of the current battlefield.
Further, the task fitness function in step 8 is specifically that the jth manned/unmanned aerial vehicleFitness function F for ith task target ij Can be expressed as:
wherein the content of the first and second substances,beta attribute p for the i task target for manned/unmanned aerial vehicle β Is a β For the task attribute gain coefficient, ε j And e { M, U } represents the model, alpha is the number of all attribute categories of the ith task target, and beta is the beta-th attribute in the attribute set.
Further, in step 9, specifically, the goal of matching the unmanned aerial vehicle and the manned vehicle is to obtain a task assignment matrix Γ that maximizes the task fitness value, that is:
wherein F is a global gain function, m is a total number of task targets, and n is a total number of human/unmanned aerial vehicles.
The invention has the beneficial effects that:
the invention provides a task fitness set, realizes the matching of the manned machine and the unmanned machine under different tasks by establishing a task fitness function, obtains more task benefits with smaller resource consumption, and ensures that the manned machine and the unmanned machine obtain better synergistic effect.
Drawings
FIG. 1 is a schematic flow diagram of the process of the present invention.
Fig. 2 is a schematic diagram of a dual-attribute task fitness function according to the present invention, where (a) is a model task fitness value diagram based on a discovery probability, and (b) is a model task fitness value diagram based on an attacked probability.
Detailed Description
The technical solutions in the embodiments of the present invention will be described clearly and completely with reference to the accompanying drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be obtained by a person skilled in the art without making any creative effort based on the embodiments in the present invention, belong to the protection scope of the present invention.
A task-oriented manned and unmanned aerial vehicle matching method comprises the following steps:
step 1: establishing a task fitness rule base according to the manned characteristics and/or the unmanned characteristic;
step 2: acquiring all task targets to be executed to form a task target set, and forming a cluster set by units of which one party has a man machine and/or an unmanned aerial vehicle;
and step 3: subdividing the task target set in the step 2 into contents, requirements, properties and characteristics of different tasks according to the combat requirements to obtain attribute sets of all the tasks;
and 4, step 4: quantizing different attributes of the task target according to the battlefield environment and the task attribute difference and the prior statistical probability characteristic or numerical simulation;
and 5: according to the quantitative parameters in the step 4 and the task fitness rule base in the step 1, the fitness values of the human machine and the unmanned aerial vehicle to the tasks are obtained;
and 6: setting gain coefficients with different attributes for the combat targets and the task requirements according to the prior knowledge;
and 7: according to different attribute parameters and task fitness, determining the fitness value of the manned and/or unmanned aerial vehicle to the task;
and 8: establishing a task fitness function according to different attribute parameters, task fitness and gain coefficients of different attributes;
and step 9: and (3) obtaining a human-machine and/or unmanned aerial vehicle configuration scheme according to the task fitness function in the step (8) and the cluster set in the step (2).
Further, the establishment of the task fitness rule base in the step 1 is specifically that the unmanned aerial vehicle is suitable for executing tasks with long duration without pilot participation, and meanwhile, the unmanned aerial vehicle is suitable for executing dangerous tasks without personnel safety risks;
the unmanned aerial vehicle is better than the unmanned aerial vehicle in human-computer maneuverability, is suitable for executing tasks with strong maneuverability and executing close-range fighting tasks.
Further, the task target set in step 2 is specifically that the task target set in the cooperative combat is MB = { MB = { (MB) } 1 ,MB 2 ,…,MB m M targets in total;
the cluster set is specifically that the cluster set of the local computers isN total people/unmanned planes, the jth person/unmanned plane can be recorded as
Taking the superscript function ε as:
Further, the attribute set of all tasks in step 3 is specifically that the ith task target can be recorded asWhich share α attributes for reconnaissance, strike, and battlefield evaluation, the set of attributes for the mission target may be defined as
Further, the step 4 specifically includes decomposing and analyzing all attributes of the task to obtain characteristic parameters of success rate, risk and cost, and completing digital representation of each sub-attribute according to the actual combat environment and the task type.
Further, the fitness values of the human machine and the unmanned aerial vehicle to the task obtained in the step 5 are specifically obtained by obtaining the goodness of the human machine and the unmanned aerial vehicle to execute the task under different tasks, different attribute types and different attribute proportions according to the statistical probability of the past actual combat data or the numerical simulation of the current battlefield.
Further, the task fitness function in step 8 is specifically that the jth manned/unmanned aerial vehicleFitness function F for ith task target ij Can be expressed as:
wherein the content of the first and second substances,beta attribute p for the i task target for manned/unmanned aerial vehicle β Is a β For a taskCoefficient of attribute gain, ∈ j E { M, U } represents the model, e j = M is man-machine, ∈ j And = U is the drone, α is the number of all attribute categories of the ith task target, and β is the β -th attribute in the attribute set.
Further, in step 9, specifically, the goal of matching the unmanned aerial vehicle and the manned vehicle is to obtain a task assignment matrix Γ that maximizes the task fitness value, that is:
wherein F is a global gain function, m is a task target total number, and n is a manned/unmanned aerial vehicle total number.
The calculation of the fitness value can be obtained according to actual combat requirements and a task fitness rule base.
The task attribute set in step 3 can be designed as follows:
assuming that the ith task is a single-attribute task, i.e. α =1, the fitness function may be established as a function on the single-task attribute. If the attack task is executed, the task attribute p is the attack attribute, and the task fitness function can be definedWherein ζ ij For the jth individual's/unmanned aerial vehicle's probability of hitting task object i, λ 1 Is the striking gain.
Suppose that the ith task contains two task attributes, p 1 To avoid the scouting attribute, p 2 To counter-hit properties, the task fitness function may be described as:
in the step 4, the quantification of different attributes of the mission target according to the battlefield environment can be designed as follows:
suppose that the ith task contains two task attributes, p 1 To avoid the scouting attribute, p 2 Is reversedHit attribute, the fitness value of a human/unmanned aerial vehicle to each task attribute can be expressed as
ξ ij (ε j ),υ ij (ε j ) Respectively the probabilities that the jth rack of people/unmanned aerial vehicles are found and attacked; xi ij (ε j ) Can be determined by the ratio of the enemy detection range to the target area, upsilon ij (ε j ) May be determined by the ratio of the range of the hostile attack to the target area.
The trend of the fitness value of the manned/unmanned aerial vehicle to the task in the step 5 under different attribute parameters may be as shown in fig. 2:
as shown in fig. 2 (a), when the probability of discovery is small, both the unmanned aerial vehicle and the human-machine can adapt to the task, but the unmanned aerial vehicle has low cost and higher adaptability than the unmanned aerial vehicle; with the increase of the discovered probability, the manned maneuverability is better, the discovered probability can be reduced, and the fitness is improved. Similarly, as shown in fig. 2 (b), when the threat of attack is small, the success rate of executing the task by the human machine is high, and the fitness is correspondingly high; along with the improvement of the attacked risk, in order to reduce casualties, the adaptability of the unmanned aerial vehicle gradually exceeds the adaptability of the unmanned aerial vehicle with human and machine.
Claims (6)
1. A task-oriented man-machine unmanned aerial vehicle matching method is characterized by comprising the following steps:
step 1: establishing a task fitness rule base according to the manned characteristics and/or the unmanned characteristic;
step 2: acquiring all task targets to be executed to form a task target set, and forming a cluster set by units of people and/or unmanned planes on one side;
and step 3: the task target set in the step 2 is subdivided into attribute sets of reconnaissance, attack and battlefield evaluation to obtain all tasks according to the operation requirements;
and 4, step 4: quantizing different attributes of the task target according to the battlefield environment and the task attribute difference and the prior statistical probability characteristic or numerical simulation;
and 5: according to the quantitative value in the step 4 and the task fitness rule base in the step 1, the fitness values of the human machine and the unmanned aerial vehicle to the tasks are obtained;
step 6: setting gain coefficients of different attributes according to the task target and the task attribute and the priori knowledge;
and 7: according to the different attributes of the task target and the fitness value of the task in the step 4, the fitness of the person and/or the unmanned aerial vehicle to the task is determined;
and step 8: establishing a task fitness function according to different attributes of the task target, the fitness of the task and the gain coefficients of the different attributes in the step 4;
and step 9: according to the task fitness function in the step 8 and the cluster set in the step 2, a human-machine and/or unmanned aerial vehicle configuration scheme is obtained;
the step 8 task fitness function is specifically that the jth individual manned/unmanned aerial vehicleFitness function F for ith task target ij Can be expressed as:
wherein, the first and the second end of the pipe are connected with each other,beta attribute for i task target for manned/unmanned aerial vehicleFitness of (a), λ β For the task attribute gain factor, ε j E { M, U } represents the model, e j (= M is man-machine, ∈) j = U is the unmanned aerial vehicle, and alpha is the number of all attribute types of the ith task target; taking the superscript function ε as:
Step 9 is specifically that the goal of matching the unmanned aerial vehicle and the manned aerial vehicle is to obtain a task allocation matrix Γ that maximizes the task fitness value, that is:
wherein F is a global gain function, m is a total number of task targets, and n is a total number of human/unmanned aerial vehicles.
2. The mission-oriented manned unmanned aerial vehicle matching method according to claim 1, wherein the establishment of the mission fitness rule base in step 1 is specifically such that the unmanned aerial vehicle is suitable for executing long-duration missions without pilot participation and without personnel safety risks, and is suitable for executing dangerous missions;
the man-machine maneuverability is superior to that of an unmanned aerial vehicle, and the unmanned aerial vehicle is suitable for executing tasks with strong maneuverability and executing close-range fighting tasks.
3. The method as claimed in claim 1, wherein the task-oriented manned unmanned aerial vehicle matching method in step 2 is characterized in that the task target set in cooperative combat is MB = { MB = MB 1 ,MB 2 ,…,MB m A total of m task targets;
4. The task-oriented manned unmanned aerial vehicle matching method according to claim 1, wherein the attribute set of all tasks in step 3 is specifically that the ith task target can be recorded as the ith task targetWhich share α attributes for reconnaissance, strike, and battlefield evaluation, the set of attributes for the mission target may be defined as
5. The mission-oriented manned unmanned aerial vehicle matching method according to claim 1, wherein the step 4 is quantized specifically to decompose and analyze all attributes of the mission to obtain characteristic parameters of success rate, risk and cost, and to complete digital characterization of reconnaissance, attack and battlefield evaluation according to actual combat environment and mission category.
6. The method for matching manned and unmanned aerial vehicles according to claim 1, wherein the fitness value of the task in step 5 is obtained through statistical probability of past actual combat data or numerical simulation of the current battlefield, and the degree of the performance of the task by the manned and unmanned aerial vehicles is obtained under different tasks, different attribute types and different attribute proportions.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110315209.7A CN113191586B (en) | 2021-03-24 | 2021-03-24 | Task-oriented man-machine unmanned aerial vehicle matching method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110315209.7A CN113191586B (en) | 2021-03-24 | 2021-03-24 | Task-oriented man-machine unmanned aerial vehicle matching method |
Publications (2)
Publication Number | Publication Date |
---|---|
CN113191586A CN113191586A (en) | 2021-07-30 |
CN113191586B true CN113191586B (en) | 2023-01-17 |
Family
ID=76973836
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202110315209.7A Active CN113191586B (en) | 2021-03-24 | 2021-03-24 | Task-oriented man-machine unmanned aerial vehicle matching method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN113191586B (en) |
Family Cites Families (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107045458B (en) * | 2017-03-09 | 2020-05-12 | 西北工业大学 | Unmanned aerial vehicle cooperative task allocation method based on multi-target quantum particle swarm algorithm |
US20190205813A1 (en) * | 2017-12-29 | 2019-07-04 | ANI Technologies Private Limited | Method and system for transportation service routing |
CN110502031B (en) * | 2019-08-02 | 2022-03-22 | 中国航空无线电电子研究所 | Task demand-based heterogeneous unmanned aerial vehicle cluster cooperative optimal configuration method |
CN111311049B (en) * | 2019-12-04 | 2022-09-06 | 南京理工大学 | Multi-agent cooperative task allocation method |
AU2020101065A4 (en) * | 2020-06-19 | 2020-07-23 | Hubei University Of Technology | Method for scheduling UAVs based on chaotic adaptive firefly algorithm |
-
2021
- 2021-03-24 CN CN202110315209.7A patent/CN113191586B/en active Active
Also Published As
Publication number | Publication date |
---|---|
CN113191586A (en) | 2021-07-30 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110222406B (en) | Unmanned aerial vehicle autonomous capacity assessment method based on task stage complexity | |
CN111240353B (en) | Unmanned aerial vehicle collaborative air combat decision method based on genetic fuzzy tree | |
CN111798539B (en) | Adaptive camouflage online design method and system | |
CN110175773A (en) | Drones for surveillance's Combat Efficiency Evaluation method based on Bayesian network | |
CN108549402B (en) | Unmanned aerial vehicle group task allocation method based on quantum crow group search mechanism | |
CN110619052B (en) | Knowledge graph-based battlefield situation sensing method | |
CN109146334A (en) | A kind of multi-object Threat appraisal procedure suitable for high dynamic environment | |
CN111311049A (en) | Multi-agent task allocation method based on income maximization | |
CN110059932A (en) | Air-to-ground attack type unmanned plane Combat Efficiency Evaluation method based on SVM | |
CN113625569B (en) | Small unmanned aerial vehicle prevention and control decision method and system based on hybrid decision model | |
CN113887919A (en) | Hybrid-discrete particle swarm algorithm-based multi-unmanned aerial vehicle cooperative task allocation method and system | |
CN104199788A (en) | Multi-target air-to-ground semi-supervised machine adaption independent decision-making real-time attack method | |
CN111797966B (en) | Multi-machine collaborative global target distribution method based on improved flock algorithm | |
CN111240366A (en) | Swarm unmanned aerial vehicle cooperative attack method based on genetic simulated annealing algorithm | |
CN111121784A (en) | Unmanned reconnaissance aircraft route planning method | |
Oleksenko et al. | The development of the method of radar observation system construction of the airspace on the basis of genetic algorithm | |
CN112950008A (en) | Flight path planning evaluation method of aircraft | |
CN115993835A (en) | Target maneuver intention prediction-based short-distance air combat maneuver decision method and system | |
CN113191586B (en) | Task-oriented man-machine unmanned aerial vehicle matching method | |
CN111797840A (en) | Self-adaptive camouflage effect on-line evaluation and system | |
CN106897837A (en) | A kind of electric inspection process unmanned helicopter system efficiency estimation method | |
CN116595864A (en) | Multi-unmanned aerial vehicle task allocation method based on mean shift clustering algorithm optimization | |
Gaowei et al. | Using multi-layer coding genetic algorithm to solve time-critical task assignment of heterogeneous UAV teaming | |
CN116774721A (en) | Target allocation method and system for game countermeasure of multiple unmanned aerial vehicles | |
CN113435780B (en) | Emergency communication sensing equipment system efficiency evaluation method based on neural network |
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 |