CN110222406A - Unmanned aerial vehicle autonomous capacity assessment method based on task stage complexity - Google Patents
Unmanned aerial vehicle autonomous capacity assessment method based on task stage complexity Download PDFInfo
- Publication number
- CN110222406A CN110222406A CN201910460861.0A CN201910460861A CN110222406A CN 110222406 A CN110222406 A CN 110222406A CN 201910460861 A CN201910460861 A CN 201910460861A CN 110222406 A CN110222406 A CN 110222406A
- Authority
- CN
- China
- Prior art keywords
- complexity
- task
- unmanned plane
- autonomous
- aerial vehicle
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
-
- 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)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Hardware Design (AREA)
- Evolutionary Computation (AREA)
- Geometry (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides an unmanned aerial vehicle autonomous ability evaluation method based on task stage complexity, which comprises the following steps: establishing an environment complexity evaluation system, and calculating the environment complexity of the unmanned aerial vehicle system in the task execution process; establishing a task complexity evaluation system, and acquiring task complexity of the unmanned aerial vehicle system at different stages; and establishing an unmanned aerial vehicle autonomous capability evaluation model, inputting the environment complexity and the task complexity into the unmanned aerial vehicle autonomous capability evaluation model, and classifying and outputting the unmanned aerial vehicle autonomous level according to the environment complexity, the task complexity and the autonomous level in the man-machine autonomous level division standard by the unmanned aerial vehicle autonomous capability evaluation model. And the unmanned aerial vehicle autonomous capability evaluation model is used for evaluating the autonomous level of the unmanned aerial vehicle by taking the man-machine autonomous level division standard as a reference and combining the environment complexity and the task complexity, so that the operation mode of the unmanned aerial vehicle system can be dynamically adjusted according to the autonomous level evaluation result, and the control authority of an operator is changed. The invention is applied to the technical field of unmanned aerial vehicle systems.
Description
Technical field
The present invention relates to UAV system technical field more particularly to a kind of unmanned planes of task based access control stage complexity certainly
Main capability assessment method.
Background technique
From application, UAV system task complexity also has higher researching value, for a UAV system
The unmanned aerial vehicle platform that the complexity evaluation result of task can be used for that selection is instructed to execute the task.By comprehensive evaluation model to spy
Determine task to be evaluated, obtain its complexity, task complexity assessment result can be with environmental complexity assessment result and man-machine
Interaction assessment result combines the final autonomous grade assessment result of UAV system of composition, when for instructing unmanned plane independently to fight
The distribution of control authority.How people role and degree of participation UAV system task execution during is determined, to assist nothing
The man-machine direction that maximum autonomous fighting efficiency is played in actual combat as unmanned plane research.The involvement level and unmanned plane of people
The autonomy of system is closely related in any case, therefore the assessment of the independence of UAV system is for instructing unmanned plane
Control authority distribution in practical applications is of great significance.
It is current less for the research of UAV system task complexity both at home and abroad, complexity of not offering the challenge systematically
Assessment models.Some scholars advance a theory method for the assessment of complex task, if Zhou Yanmei, Li Weihua et al. are for complicated ring
The evaluation of task scheme gives a kind of index system of stratification in border, and some researchs are to be directed to extensive unmanned systems, and one
The main body of a little non-concrete regulation task executions of research, Sun Yang are established using automatic driving vehicle as research object by environment complexity
The automatic driving vehicle evaluation and test model of degree, task complexity, manual intervention degree composition.But task complexity is ground in the research
Studying carefully is to execute performance to the task based on automatic driving vehicle, is evaluated in advance with according to task parameters task complexity
There are still difference.
Summary of the invention
Aiming at the shortcomings in the prior art, the object of the present invention is to provide a kind of unmanned planes of task based access control stage complexity
Capacity of will appraisal procedure.
Itself the technical solution adopted is that:
A kind of unmanned plane capacity of will appraisal procedure of task based access control stage complexity, comprising the following steps:
Step 101, environmental complexity evaluation system is established, it is complicated to environment of UAV system during execution task
Degree is calculated；
Step 102, task complexity evaluations system is established, obtains UAV system in the task complexity of different phase；
Step 103, unmanned plane capacity of will assessment models are established, environment complexity and task complexity are inputted into unmanned plane
Capacity of will assessment models, unmanned plane capacity of will assessment models are according to environment complexity, task complexity and man-machine autonomous etc.
Autonomous grade separation in the grade criteria for classifying exports the autonomous grade of unmanned plane.
As a further improvement of the above technical scheme, in step 101, the environment complexity include terrain complexity,
Meteorological complexity, target identification complexity, threatens complexity at communication complexity.
As a further improvement of the above technical scheme, the calculating process of the terrain complexity are as follows:
Step 201, real-time landform picture is obtained；
Step 202, the image entropy of real-time landform picture and the contrast value of gray level co-occurrence matrixes are calculated；
Step 203, place is normalized in the contrast value of the image entropy to real-time landform picture and gray level co-occurrence matrixes respectively
Reason, obtains the normalized value of the normalized value of Image entropy and the contrast value of gray level co-occurrence matrixes；
Step 204, calculate ground according to the normalized value of the contrast value of the normalized value of Image entropy and gray level co-occurrence matrixes
Shape complexity.
As a further improvement of the above technical scheme, the calculating process for threatening complexity are as follows:
Step 301, damage volume model is established for three kinds of radar, antiaircraft gun and surface-to-air ballistic missile battle antiaircraft defense firepower；
Step 302, battle antiaircraft defense firepower distribution map is drawn in the model of damage volume according to the position of threat point；
Step 303, the safety zone ratio in battle antiaircraft defense firepower distribution map is calculated, and then obtains and threatens complexity.
As a further improvement of the above technical scheme,
The calculating process of the meteorology complexity are as follows:
Step 401, wind shear, wind scale, Thunderstorm Weather and rainy weather are chosen and carries out fuzzy overall evaluation；
Step 402, for evaluation result occur the case where not meeting convention, take degree of membership time it is big tend to evaluation etc.
The poor opinion rating of grade is as evaluation as a result, obtaining meteorological complexity in turn；
The calculating process of the communication complexity are as follows:
Step 501, choose includes packet loss, the bit error rate, the sets of factors and Comment gathers of time delay and interruption；
Step 502, overall merit is carried out according to the method for fuzzy overall evaluation, and then obtains communication complexity；
The calculating process of the target identification complexity are as follows:
Step 601, obscure for target and the method for generating object construction feature space is taken to be measured；
Step 602, covering for target takes the method for calculating target and local background contrast to be measured；
Step 603, target identification complexity is calculated.
As a further improvement of the above technical scheme, in step 102, the calculating process of task complexity are as follows:
Step 701, by the evaluation index of task complexity be quantified as task and tactics behavior, collaboration with cooperate, plan with
Analysis, Situation Awareness；
Step 702, the subjective complexity Yu objective complexity for seeking each evaluation index in step 701 are counted by weighting
It calculates subjective complexity and objective complexity obtains the compositive complexity of each evaluation index；
Step 703, the compositive complexity of comprehensive four kinds of evaluation indexes obtains task complexity in turn.
As a further improvement of the above technical scheme, in step 103, in the man-machine autonomous grading standard from
Main grade separation includes: that machine is holotype, the auxiliary mode of owner people, the auxiliary mode of people's host and artificial holotype.
As a further improvement of the above technical scheme, in step 103, using the adaptive resonance net in unsupervised learning
Network model ART is as unmanned plane capacity of will assessment models, the finding process of the autonomous grade of unmanned plane are as follows:
Step 801, according to the autonomous grade separation in man-machine autonomous grading standard to adaptive resonance network model
Each neuron of identification layer is classified in ART；
Step 802, according to environment complexity, the maximum activation of task complicated dynamic behaviour adaptive resonance network model ART
Value；
Step 803, each neuron of maximum activation value identification layer is compared, the mind nearest apart from maximum activation value
It is the autonomous grade of unmanned plane through the corresponding autonomous grade separation of member.
As a further improvement of the above technical scheme, in step 802, the finding process of the maximum activation value are as follows:
In formula, S is maximum activation value；G is neuron nonlinear activation function；xiIt is inputted for neuron, n=9, wherein
(x1,x2,x3,x4,x5) it is environment complexity, (x6,x7,x8,x9) it is task complexity；ωiFor propagated forward weight.
A kind of unmanned plane capacity of will assessment system of task based access control stage complexity, including memory and processor, institute
It states memory and is stored with computer program, when the processor executes the computer program the step of realization above method.
Advantageous effects of the invention:
The present invention obtains unmanned plane by establishing environmental complexity evaluation system and task complexity evaluations system
Environment complexity and task complexity of the system during execution task, finally using unmanned plane capacity of will assessment models with
Man-machine autonomous grading standard is that benchmark combining environmental complexity and task complexity make assessment to the autonomous grade of unmanned plane,
The operation mode of UAV system is adjusted according to autonomous grade assessment result dynamic, to change operator's control
Limit.
Detailed description of the invention
Fig. 1 is the flow diagram of the unmanned plane capacity of will appraisal procedure of task based access control stage complexity in the present invention；
Fig. 2 is the assessment result exemplary diagram of environment complexity evaluation system in the present invention；
Fig. 3 is the assessment result exemplary diagram of task complexity evaluation system in the present invention；
Fig. 4 is the acquisition flow diagram of mesorelief complexity of the present invention；
Fig. 5 is the acquisition flow diagram that complexity is threatened in the present invention；
Fig. 6 is the acquisition flow diagram of meteorological complexity in the present invention；
Fig. 7 is the acquisition flow diagram of communication complexity in the present invention；
Fig. 8 is the acquisition flow diagram of target identification complexity in the present invention；
Fig. 9 is the acquisition flow diagram of task complexity in the present invention；
Figure 10 is each phased mission complexity exemplary diagram in the present invention；
Figure 11 is the schematic diagram of man-machine autonomous grading standard in the present invention；
Figure 12 is the acquisition flow diagram of the autonomous grade of unmanned plane in the present invention.
Specific embodiment
In order to which the purposes, technical schemes and advantages of the disclosure are more clearly understood, under in conjunction with specific embodiments, and according to
Attached drawing, the present invention is described in more detail.It should be noted that in attached drawing or specification description, the content that does not describe with
And part English is abbreviated as content known to those of ordinary skill in technical field.The some spies given in the present embodiment
Parameter is determined only as demonstration, and the value can change accordingly to suitably be worth in various embodiments.
A kind of unmanned plane capacity of will appraisal procedure of task based access control stage complexity as shown in Figure 1, including following step
It is rapid:
Step 101, environmental complexity evaluation system is established, it is complicated to environment of UAV system during execution task
Degree is calculated；Environmental complexity evaluation system carries out environment complexity with two aspect of mission effectiveness mainly for influencing to fly
Assessment, therefore, environment complexity specifically include the terrain complexity for influencing flight safety and meteorological complexity, and and influence
Communication complexity, target identification complexity and the threat complexity of mission effectiveness, i.e., as shown in Figure 2.
Step 102, task complexity evaluations system is established, obtains UAV system in the task complexity of different phase；
The Task-decomposing of UAV system will be quantified first, complexity evaluations then are carried out to the task after decomposition.Task-decomposing side
Method uses the decomposition method based on finite state machine, by each unmanned plane in UAV system and each function on unmanned plane
The each module of energy is considered as a finite state machine, and a series of state for converting finite state machines for task execution process is converted
Journey, and then carry out the complexity evaluations of subtask.The evaluation index of task complexity is quantified as task and war in the present embodiment
Art behavior, collaboration with cooperate, planning and analysis, Situation Awareness, i.e., as shown in Figure 3.
Step 103, unmanned plane capacity of will assessment models are established, environment complexity and task complexity are inputted into unmanned plane
Capacity of will assessment models, unmanned plane capacity of will assessment models are according to environment complexity, task complexity and man-machine autonomous etc.
Autonomous grade separation in the grade criteria for classifying exports the autonomous grade of unmanned plane.I.e. using unmanned plane capacity of will assessment models as point
Class device, contingency table of the autonomous grade separation as unmanned plane capacity of will assessment models in man-machine autonomous grading standard
Standard inputs the environment complexity and task of current UAV system in unmanned plane capacity of will assessment models after repeatedly training
Complexity can export the autonomous grade of unmanned plane of the UAV system.
With reference to Fig. 4, in step 101, the calculating process of terrain complexity are as follows:
Step 201, real-time landform picture is obtained；
Step 202, the image entropy of real-time landform picture and the contrast value of gray level co-occurrence matrixes are calculated；
Step 203, place is normalized in the contrast value of the image entropy to real-time landform picture and gray level co-occurrence matrixes respectively
Reason, obtains the normalized value of the normalized value of Image entropy and the contrast value of gray level co-occurrence matrixes；
Step 204, calculate ground according to the normalized value of the contrast value of the normalized value of Image entropy and gray level co-occurrence matrixes
Shape complexity: Land=0.2 × Entropy+0.8 × Contrast, wherein Land indicates that terrain complexity, Entropy indicate
The normalized value of Image entropy, Contrast indicate the normalized value of the contrast value of gray level co-occurrence matrixes.
With reference to Fig. 5, the calculating process of complexity is threatened are as follows:
Step 301, damage volume model is established for three kinds of radar, antiaircraft gun and surface-to-air ballistic missile battle antiaircraft defense firepower；
Step 302, battle antiaircraft defense firepower distribution map is drawn in the model of damage volume according to the position of threat point；
Step 303, the safety zone ratio in battle antiaircraft defense firepower distribution map is calculated, and then obtains and threatens complexity.
With reference to Fig. 6, the calculating process of meteorological complexity are as follows:
Step 401, wind shear, wind scale are chosen, Thunderstorm Weather and rainy weather carry out fuzzy overall evaluation.Synthesis is commented
Valence method are as follows:
TR=F (U) → F (V)
Wherein, F (*) is smear out effect, and U is set of factors, including information evaluation index as Uncrossed as possible；V is comment
Collection, the set formed by various different evaluation ranks:
U={ wind, wind shear, thunderstorm, precipitation }
V=it is good, and it is preferably, medium, it is poor, very poor
Step 402, for evaluation result occur the case where not meeting convention, take degree of membership time it is big tend to evaluation etc.
The poor opinion rating of grade is as evaluation as a result, the result of final fuzzy overall evaluation is meteorological complexity.
With reference to Fig. 7, the calculating process of communication complexity are as follows:
Step 501, the set of factors and Comment gathers that can reflect communication environment superiority and inferiority comprehensively are chosen.
Here set of factors U and Comment gathers V are as follows:
U={ packet loss, the bit error rate, time delay are interrupted }
V=it is good, and it is preferably, medium, it is poor, poor
Wherein error rate calculation method are as follows:
Packet loss calculation method are as follows:
Step 502, overall merit, the evaluation result of final fuzzy overall evaluation are carried out according to the method for fuzzy overall evaluation
As communication complexity.
With reference to Fig. 8, the calculating process of target identification complexity are as follows:
Step 601, obscure for target and the method for generating object construction feature space is taken to be measured；
Target degree of aliasing RSS calculation method are as follows:
RSS=[(μT-μB)2+σT 2]1/2
Wherein, σTFor the gray standard deviation of target, μTFor the gray average of target, μBFor the gray average of background；
Step 602, covering for target takes the method for calculating target and local background contrast to be measured；
Target coverage degree DTS calculation method are as follows:
Wherein SIt is blockedFor the area that is blocked, STargetFor target area.
Step 603, target identification complexity, target complexity are calculated according to target degree of aliasing and target coverage rate
Target calculation method are as follows:
Wherein RSS is that target mixes degree of disappearing, and DTS is target coverage degree, and DFA is target false-alarm degree, target false-alarm degree calculating side
Method are as follows:
Wherein, n is the quantity of suspected target.
With reference to Fig. 9, in step 102, the calculating process of task complexity are as follows:
Step, 701, by the evaluation index of task complexity be quantified as task and tactics behavior, collaboration with cooperate, plan with
Analysis, Situation Awareness；
Step 702, the subjective complexity Yu objective complexity for seeking each evaluation index in step 401 are counted by weighting
It calculates subjective complexity and objective complexity obtains the compositive complexity of each evaluation index；
Step 703, the compositive complexity of comprehensive four kinds of evaluation indexes obtains task complexity in turn.
In a step 702, the subjective complexity of each evaluation index determine Quan Falai and is sought by subjectivity, and objective complexity is answered
Miscellaneous degree is sought by objective-weight method, and in this implementation, the subjective method of power surely is that can expand analytic hierarchy process (AHP), and objective-weight method is entropy
Quan Fa, therefore, for the compositive complexity of any one evaluation index are as follows:
Wn=α W1n+β·W2n
Alpha+beta=1, α > 0, β > 0
In formula, WnIndicate a kind of compositive complexity of evaluation index；W1nIndicate the evaluation index by the way that level point can be expanded
The subjective complexity that analysis method obtains；W2nIndicate the objective complexity that the evaluation index is obtained by entropy assessment；
With reference to Figure 10, the process that UAV system executes task is divided into eight stages in the present embodiment, by above-mentioned
Calculation method carries out seeking for task complexity for every kind of stage, and what wherein EAHP referred to is that can expand analytic hierarchy process (AHP).
In step 103, the autonomous grade separation in man-machine autonomous grading standard includes: that machine is holotype, Ji Zhuren
Auxiliary mode, the auxiliary mode of people's host and artificial holotype.Be machine with reference to Figure 11, R it is holotype, refers to before having man-machine supervision
It puts, UAV system autonomous control, realizes the work such as analysis situation, identification target, decision and trajectory planning；RH is owner people
Auxiliary mode is referred to by having man-machine carry out target identification, authorization decision request, plane planning to work with task control, by nobody
Machine independently carries out Situation Awareness, decision requests, airborne load-carrying planning, is semiautomatic control mode；HR is the auxiliary mould of people's host
Formula refers to carrying out prompt situation and target by unmanned plane, provides decision support.Offline weight-normality, which is drawn, flies control work with autonomous, by
There are man-machine carry out Situation Awareness, target identification, assignment decisions and distribution and trajectory planning work；H is that people is holotype, is referred to
By the instruction for having man-machine publication analysis situation, identifying target, decision and trajectory planning, specifically executed by unmanned plane.Wherein, people
For the autonomous grade of holotype be it is minimum, need and man-machine realize target identification, assignment decisions, trajectory planning, bottom control etc.
Function；The autonomous grade of the auxiliary mode of people's host takes second place, target identification need it is man-machine do, assignment decisions and trajectory planning are someone
Machine and unmanned plane are completed jointly, and flight control is completed by unmanned plane；Owner people is auxiliary autonomous higher ranked, is carried out certainly by unmanned plane
Main flight and Situation Awareness, the assignment decisions that unmanned plane is made by have it is man-machine authorize, have it is man-machine plan initial track, nobody
Machine does track weight-normality and draws.Machine is the autonomous grade highest of holotype, and entire Situation Awareness target identification, is made decisions on one's own, track rule
It draws, flight control has unmanned plane completion.
In step 103, commented using the adaptive resonance network model ART in unsupervised learning as unmanned plane capacity of will
Estimate model, with reference to Figure 12, the finding process of the autonomous grade of unmanned plane are as follows:
Step 801, according to the autonomous grade separation in man-machine autonomous grading standard to adaptive resonance network model
Each neuron of identification layer is classified in ART；To in adaptive resonance network model ART by the way of training classifier
Each neuron of identification layer is classified.
Step 802, according to environment complexity, the maximum activation of task complicated dynamic behaviour adaptive resonance network model ART
Value, the finding process of maximum activation value are as follows:
In formula, S is maximum activation value；G is neuron nonlinear activation function；xiIt is inputted for neuron, n=9, wherein
(x1,x2,x3,x4,x5) it is environment complexity, (x6,x7,x8,x9) it is task complexity；ωiFor propagated forward weight.
Step 803, each neuron of maximum activation value identification layer is compared, the mind nearest apart from maximum activation value
It is the autonomous grade of unmanned plane through the corresponding autonomous grade separation of member.
Contain the explanation of the preferred embodiment of the present invention above, this be for the technical characteristic that the present invention will be described in detail, and
Be not intended to for summary of the invention being limited in concrete form described in embodiment, according to the present invention content purport carry out other
Modifications and variations are also protected by this patent.The purport of the content of present invention is to be defined by the claims, rather than by embodiment
Specific descriptions are defined.
Claims (10)
1. a kind of unmanned plane capacity of will appraisal procedure of task based access control stage complexity, which comprises the following steps:
Step 101, establish environmental complexity evaluation system, to environment complexity of UAV system during execution task into
Row calculates；
Step 102, task complexity evaluations system is established, obtains UAV system in the task complexity of different phase；
Step 103, unmanned plane capacity of will assessment models are established, environment complexity and task complexity input unmanned plane is autonomous
Capability assessment model, unmanned plane capacity of will assessment models are drawn according to environment complexity, task complexity and man-machine autonomous grade
Autonomous grade separation in minute mark standard exports the autonomous grade of unmanned plane.
2. the unmanned plane capacity of will appraisal procedure of task based access control stage complexity according to claim 1, which is characterized in that
In step 101, the environment complexity include terrain complexity, meteorological complexity, communication complexity, target identification complexity,
Threaten complexity.
3. the unmanned plane capacity of will appraisal procedure of task based access control stage complexity according to claim 2, which is characterized in that
The calculating process of the terrain complexity are as follows:
Step 201, real-time landform picture is obtained；
Step 202, the image entropy of real-time landform picture and the contrast value of gray level co-occurrence matrixes are calculated；
Step 203, the contrast value of the image entropy to real-time landform picture and gray level co-occurrence matrixes is normalized respectively, obtains
Obtain the normalized value of the normalized value of Image entropy and the contrast value of gray level co-occurrence matrixes；
Step 204, landform is calculated according to the normalized value of the contrast value of the normalized value of Image entropy and gray level co-occurrence matrixes to answer
Miscellaneous degree.
4. the unmanned plane capacity of will appraisal procedure of task based access control stage complexity according to claim 2, which is characterized in that
The calculating process for threatening complexity are as follows:
Step 301, damage volume model is established for three kinds of radar, antiaircraft gun and surface-to-air ballistic missile battle antiaircraft defense firepower；
Step 302, battle antiaircraft defense firepower distribution map is drawn in the model of damage volume according to the position of threat point；
Step 303, the safety zone ratio in battle antiaircraft defense firepower distribution map is calculated, and then obtains and threatens complexity.
5. the unmanned plane capacity of will appraisal procedure of task based access control stage complexity according to claim 2, which is characterized in that
The calculating process of the meteorology complexity are as follows:
Step 401, wind shear, wind scale, Thunderstorm Weather and rainy weather are chosen and carries out fuzzy overall evaluation；
Step 402, for evaluation result occur the case where not meeting convention, take degree of membership time it is big tend to opinion rating compared with
The opinion rating of difference is as evaluation as a result, obtaining meteorological complexity in turn；
The calculating process of the communication complexity are as follows:
Step 501, choose includes packet loss, the bit error rate, the sets of factors and Comment gathers of time delay and interruption；
Step 502, overall merit is carried out according to the method for fuzzy overall evaluation, and then obtains communication complexity；
The calculating process of the target identification complexity are as follows:
Step 601, obscure for target and the method for generating object construction feature space is taken to be measured；
Step 602, covering for target takes the method for calculating target and local background contrast to be measured；
Step 603, target identification complexity is calculated.
6. according to claim 1 to the unmanned plane capacity of will appraisal procedure of any one of 5 task based access control stage complexity,
It is characterized in that, in step 102, the calculating process of task complexity are as follows:
Step 701, by the evaluation index of task complexity be quantified as task and tactics behavior, collaboration with cooperate, planning and analysis,
Situation Awareness；
Step 702, the subjective complexity Yu objective complexity for seeking each evaluation index in step 701, pass through weighted calculation master
It sees complexity and objective complexity obtains the compositive complexity of each evaluation index；
Step 703, the compositive complexity of comprehensive four kinds of evaluation indexes obtains task complexity in turn.
7. according to claim 1 to the unmanned plane capacity of will appraisal procedure of any one of 5 task based access control stage complexity,
It is characterized in that, in step 103, the autonomous grade separation in the man-machine autonomous grading standard includes: that machine is holotype, machine
The auxiliary mode of owner, the auxiliary mode of people's host and artificial holotype.
8. according to claim 1 to the unmanned plane capacity of will appraisal procedure of any one of 5 task based access control stage complexity,
It is characterized in that, in step 103, using the adaptive resonance network model ART in unsupervised learning as unmanned plane capacity of will
Assessment models, the finding process of the autonomous grade of unmanned plane are as follows:
Step 801, according to the autonomous grade separation in man-machine autonomous grading standard in adaptive resonance network model ART
Each neuron of identification layer is classified；
Step 802, according to environment complexity, the maximum activation value of task complicated dynamic behaviour adaptive resonance network model ART；
Step 803, each neuron of maximum activation value identification layer is compared, the neuron nearest apart from maximum activation value
Corresponding autonomous grade separation is the autonomous grade of unmanned plane.
9. the unmanned plane capacity of will appraisal procedure of task based access control stage complexity according to claim 8, which is characterized in that
In step 802, the finding process of the maximum activation value are as follows:
In formula, S is maximum activation value；G is neuron nonlinear activation function；xiFor neuron input, n=9, wherein (x1,x2,
x3,x4,x5) it is environment complexity, (x6,x7,x8,x9) it is task complexity；ωiFor propagated forward weight.
10. a kind of unmanned plane capacity of will assessment system of task based access control stage complexity, including memory and processor, described
Memory is stored with computer program, which is characterized in that the processor realizes claim 1 when executing the computer program
The step of to any one of 9 the method.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910460861.0A CN110222406B (en) | 2019-05-30 | 2019-05-30 | Unmanned aerial vehicle autonomous capacity assessment method based on task stage complexity |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910460861.0A CN110222406B (en) | 2019-05-30 | 2019-05-30 | Unmanned aerial vehicle autonomous capacity assessment method based on task stage complexity |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110222406A true CN110222406A (en) | 2019-09-10 |
| CN110222406B CN110222406B (en) | 2023-04-07 |
Family
ID=67818590
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910460861.0A Active CN110222406B (en) | 2019-05-30 | 2019-05-30 | Unmanned aerial vehicle autonomous capacity assessment method based on task stage complexity |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110222406B (en) |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110703803A (en) * | 2019-11-06 | 2020-01-17 | 中国人民解放军国防科技大学 | Unmanned aerial vehicle group flight control method, unmanned aerial vehicle, system and medium |
| CN111160439A (en) * | 2019-12-24 | 2020-05-15 | 西北工业大学 | Unmanned aerial vehicle system autonomous capability evaluation method and system and readable storage medium |
| CN111813083A (en) * | 2020-07-09 | 2020-10-23 | 吉林大学 | Scene task complexity quantification model |
| CN112465145A (en) * | 2020-12-02 | 2021-03-09 | 西北工业大学 | Unmanned cluster intelligent qualitative evaluation method based on logical reasoning and fuzzy synthesis |
| CN113449238A (en) * | 2020-03-24 | 2021-09-28 | 丰翼科技(深圳)有限公司 | Unmanned aerial vehicle safe operation method and device, electronic equipment and storage medium |
| CN114148542A (en) * | 2020-09-08 | 2022-03-08 | 丰翼科技(深圳)有限公司 | Unmanned aerial vehicle testing method and device and storage medium |
| CN114815594A (en) * | 2021-12-04 | 2022-07-29 | 中国船舶工业系统工程研究院 | Autonomous level transformation method for nondeterministic multi-variable factors of water surface unmanned system |
| US11420655B2 (en) * | 2019-09-26 | 2022-08-23 | Hrl Laboratories, Llc | System and method for safety and efficacy override of an autonomous system |
| US11907815B1 (en) | 2019-09-26 | 2024-02-20 | Hrl Laboratories, Llc | System and method for improved generalization from concept constrained dreams |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102829980A (en) * | 2012-03-29 | 2012-12-19 | 中国科学院自动化研究所 | Intelligent degree evaluation method of intelligent vehicle |
| CN103234763A (en) * | 2013-04-09 | 2013-08-07 | 北京理工大学 | System and method for quantitatively evaluating unmanned vehicles |
| CN103824084A (en) * | 2014-03-12 | 2014-05-28 | 西安电子科技大学 | Polarimetric SAR (Synthetic Aperture Radar) image classification method based on SDIT (Secretome-Derived Isotopic Tag) and SVM (Support Vector Machine) |
| CN103824259A (en) * | 2013-11-01 | 2014-05-28 | 华南理工大学 | Image composition beautifying method and system based on visual area proportion balance rule |
| US9488979B1 (en) * | 2015-04-14 | 2016-11-08 | Zipline International Inc. | System and method for human operator intervention in autonomous vehicle operations |
| US9606539B1 (en) * | 2015-11-04 | 2017-03-28 | Zoox, Inc. | Autonomous vehicle fleet service and system |
| CN107392388A (en) * | 2017-07-31 | 2017-11-24 | 南昌航空大学 | A kind of method for planning no-manned plane three-dimensional flight path using artificial fish-swarm algorithm is improved |
| CN108509728A (en) * | 2018-04-04 | 2018-09-07 | 西北工业大学 | One kind weighing design method to extra large cooperation aircraft viability |
| CN109344737A (en) * | 2018-09-12 | 2019-02-15 | 中国农业大学 | One-dimensional DCNN land use classes method based on SAR polarization decomposing |
-
2019
- 2019-05-30 CN CN201910460861.0A patent/CN110222406B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102829980A (en) * | 2012-03-29 | 2012-12-19 | 中国科学院自动化研究所 | Intelligent degree evaluation method of intelligent vehicle |
| CN103234763A (en) * | 2013-04-09 | 2013-08-07 | 北京理工大学 | System and method for quantitatively evaluating unmanned vehicles |
| CN103824259A (en) * | 2013-11-01 | 2014-05-28 | 华南理工大学 | Image composition beautifying method and system based on visual area proportion balance rule |
| CN103824084A (en) * | 2014-03-12 | 2014-05-28 | 西安电子科技大学 | Polarimetric SAR (Synthetic Aperture Radar) image classification method based on SDIT (Secretome-Derived Isotopic Tag) and SVM (Support Vector Machine) |
| US9488979B1 (en) * | 2015-04-14 | 2016-11-08 | Zipline International Inc. | System and method for human operator intervention in autonomous vehicle operations |
| US9606539B1 (en) * | 2015-11-04 | 2017-03-28 | Zoox, Inc. | Autonomous vehicle fleet service and system |
| CN107392388A (en) * | 2017-07-31 | 2017-11-24 | 南昌航空大学 | A kind of method for planning no-manned plane three-dimensional flight path using artificial fish-swarm algorithm is improved |
| CN108509728A (en) * | 2018-04-04 | 2018-09-07 | 西北工业大学 | One kind weighing design method to extra large cooperation aircraft viability |
| CN109344737A (en) * | 2018-09-12 | 2019-02-15 | 中国农业大学 | One-dimensional DCNN land use classes method based on SAR polarization decomposing |
Non-Patent Citations (3)
| Title |
|---|
| 严建林: "基于进化算法无人机航路规划技术研究", 《中国优秀硕士学位论文全文数据库》 * |
| 吴立珍等: "无人机战场环境感知与理解技术研究", 《系统仿真学报》 * |
| 樊胜利等: "装甲目标威胁评估智能计算方法研究", 《装备指挥技术学院学报》 * |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US11420655B2 (en) * | 2019-09-26 | 2022-08-23 | Hrl Laboratories, Llc | System and method for safety and efficacy override of an autonomous system |
| US11907815B1 (en) | 2019-09-26 | 2024-02-20 | Hrl Laboratories, Llc | System and method for improved generalization from concept constrained dreams |
| CN110703803A (en) * | 2019-11-06 | 2020-01-17 | 中国人民解放军国防科技大学 | Unmanned aerial vehicle group flight control method, unmanned aerial vehicle, system and medium |
| CN111160439A (en) * | 2019-12-24 | 2020-05-15 | 西北工业大学 | Unmanned aerial vehicle system autonomous capability evaluation method and system and readable storage medium |
| CN113449238A (en) * | 2020-03-24 | 2021-09-28 | 丰翼科技(深圳)有限公司 | Unmanned aerial vehicle safe operation method and device, electronic equipment and storage medium |
| CN111813083A (en) * | 2020-07-09 | 2020-10-23 | 吉林大学 | Scene task complexity quantification model |
| CN111813083B (en) * | 2020-07-09 | 2022-11-01 | 吉林大学 | Scene task complexity quantitative evaluation method |
| CN114148542A (en) * | 2020-09-08 | 2022-03-08 | 丰翼科技(深圳)有限公司 | Unmanned aerial vehicle testing method and device and storage medium |
| CN114148542B (en) * | 2020-09-08 | 2024-05-31 | 丰翼科技(深圳)有限公司 | Unmanned aerial vehicle testing method, unmanned aerial vehicle testing device and storage medium |
| CN112465145A (en) * | 2020-12-02 | 2021-03-09 | 西北工业大学 | Unmanned cluster intelligent qualitative evaluation method based on logical reasoning and fuzzy synthesis |
| CN112465145B (en) * | 2020-12-02 | 2024-04-05 | 西北工业大学 | Unmanned cluster intelligent qualitative evaluation method based on logic reasoning and fuzzy synthesis |
| CN114815594A (en) * | 2021-12-04 | 2022-07-29 | 中国船舶工业系统工程研究院 | Autonomous level transformation method for nondeterministic multi-variable factors of water surface unmanned system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110222406B (en) | 2023-04-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110222406A (en) | Unmanned aerial vehicle autonomous capacity assessment method based on task stage complexity | |
| CN106979784B (en) | Non-linear track planning based on hybrid pigeon swarm algorithm | |
| CN105427032A (en) | Confrontation decision evaluation method for unmanned aerial vehicle | |
| CN113392521B (en) | Method and system for constructing resource marshalling model for air-sea joint combat mission | |
| CN112198892B (en) | Multi-unmanned aerial vehicle intelligent cooperative penetration countermeasure method | |
| Duan et al. | Multiple UCAVs cooperative air combat simulation platform based on PSO, ACO, and game theory | |
| CN106959700A (en) | A kind of unmanned aerial vehicle group collaboration patrol tracing path planing method based on upper limit confidential interval algorithm | |
| CN101893441A (en) | Unmanned aerial vehicle flight path optimization method based on deviation maximization and grey correlation analysis | |
| CN113625569B (en) | Small unmanned aerial vehicle prevention and control decision method and system based on hybrid decision model | |
| CN107506022A (en) | A kind of someone/unmanned collaboration teams and groups Command Aided System | |
| CN116051319A (en) | Tactical collaborative combat simulation training system and tactical collaborative combat simulation training method | |
| Wang et al. | An efficient clonal selection algorithm to solve dynamicweapon-target assignment game model in UAV cooperative aerial combat | |
| CN114444201A (en) | Autonomous capability evaluation method of ground attack unmanned aerial vehicle based on Bayesian network | |
| Hill et al. | Using agent-based simulation and game theory to examine the WWII Bay of Biscay U-boat campaign | |
| CN112396298A (en) | Unmanned helicopter multi-machine cooperative task planning method | |
| CN107194155A (en) | A kind of threat assessment modeling method based on small data set and Bayesian network | |
| Cruz et al. | Team dynamics and tactics for mission planning | |
| Goldman | The US military in uncertain times: Organizations, ambiguity, and strategic adjustment | |
| Jiuyao et al. | Weapon system portfolio selection based on structural robustness | |
| Ye et al. | Multi-UAV task assignment based on satisficing decision algorithm | |
| CN114756049A (en) | Target allocation method, system, equipment and medium in unmanned aerial vehicle cluster countermeasure | |
| Naikar et al. | Cognitive work analysis for air defense applications in Australia | |
| Lindelauf et al. | Military helicopter flight mission planning using data science and operations research | |
| Tan et al. | Framework of wargame CGF system based on multi-agent | |
| Wang et al. | Modeling of Reef Distributed Reconnaissance and Early Warning System Based on DoDAF |
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 |