AU2021100719A4 - An Airspace Complexity Evaluation System Based on Deep Learning - Google Patents
An Airspace Complexity Evaluation System Based on Deep Learning Download PDFInfo
- Publication number
- AU2021100719A4 AU2021100719A4 AU2021100719A AU2021100719A AU2021100719A4 AU 2021100719 A4 AU2021100719 A4 AU 2021100719A4 AU 2021100719 A AU2021100719 A AU 2021100719A AU 2021100719 A AU2021100719 A AU 2021100719A AU 2021100719 A4 AU2021100719 A4 AU 2021100719A4
- Authority
- AU
- Australia
- Prior art keywords
- complexity
- module
- sector
- data
- system based
- 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.)
- Ceased
Links
- 238000011156 evaluation Methods 0.000 title claims abstract description 38
- 238000013135 deep learning Methods 0.000 title claims abstract description 17
- 238000013528 artificial neural network Methods 0.000 claims abstract description 16
- 238000012545 processing Methods 0.000 claims abstract description 16
- 238000000034 method Methods 0.000 claims abstract description 9
- 238000001514 detection method Methods 0.000 claims abstract description 7
- 238000004458 analytical method Methods 0.000 claims abstract description 6
- 230000008859 change Effects 0.000 claims description 23
- 239000011159 matrix material Substances 0.000 claims description 7
- 210000002569 neuron Anatomy 0.000 claims description 7
- 230000008569 process Effects 0.000 claims description 5
- 238000004364 calculation method Methods 0.000 abstract description 4
- 238000010586 diagram Methods 0.000 abstract description 3
- 238000013178 mathematical model Methods 0.000 abstract description 2
- 230000006870 function Effects 0.000 description 5
- 230000000694 effects Effects 0.000 description 3
- 238000012549 training Methods 0.000 description 2
- 238000012546 transfer Methods 0.000 description 2
- 230000009194 climbing Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 238000013486 operation strategy Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G5/00—Traffic control systems for aircraft, e.g. air-traffic control [ATC]
- G08G5/0043—Traffic management of multiple aircrafts from the ground
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
- G05D1/10—Simultaneous control of position or course in three dimensions
- G05D1/101—Simultaneous control of position or course in three dimensions specially adapted for aircraft
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
- G05D1/10—Simultaneous control of position or course in three dimensions
- G05D1/101—Simultaneous control of position or course in three dimensions specially adapted for aircraft
- G05D1/106—Change initiated in response to external conditions, e.g. avoidance of elevated terrain or of no-fly zones
- G05D1/1064—Change initiated in response to external conditions, e.g. avoidance of elevated terrain or of no-fly zones specially adapted for avoiding collisions with other aircraft
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- 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
-
- 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
- G06Q10/08—Logistics, e.g. warehousing, loading or distribution; Inventory or stock management
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Molecular Biology (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Health & Medical Sciences (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Aviation & Aerospace Engineering (AREA)
- Traffic Control Systems (AREA)
- Radar Systems Or Details Thereof (AREA)
Abstract
The invention provides an airspace complexity evaluation system based on deep learning,
including a data acquisition module, a data processing module, a complexity evaluation module
and an early warning module which are sequentially connected. Specifically, the data
acquisition module is used to collect, organize and monitor the data that affect the complexity
of the sector in real time; the data processing module is used for normalizing above collected
data, so as to eliminate dimensional differences among various detection indexes of the data
affecting sector complexity; the complexity evaluation module is used for evaluating sector
complexity based on processing result of the data processing module; the early warning module
is used for analysis and early warning according to sector complexity. In the invention, a
mathematical model for evaluating air traffic complexity is established by adopting L-M neural
network algorithm. Compared with the traditional neural network calculation method, the
adopted method in the invention can calculate the result with high approximation accuracy and
accurately evaluate the complexity.
Airspace Complexity Evaluation System Based on Deep Leaminge
Data Acquisition Module,
Data Processing Modulev
Complexity Evaluation
Module<,
Early Wamning Module<,
Fig. 1 A schematic structural diagram of the airspace complexity evaluation system
based on deep learning of the present invention.
Description
Airspace Complexity Evaluation System Based on Deep Leaminge
Data Acquisition Module,
Data Processing Modulev
Complexity Evaluation Module<,
Early Wamning Module<,
Fig. 1 A schematic structural diagram of the airspace complexity evaluation system
based on deep learning of the present invention.
An Airspace Complexity Evaluation System Based on Deep Learning
[01] The invention relates to the technical field of aviation, in particular to an airspace complexity evaluation system based on deep learning.
[02] With the development of air transport industry, in order to ensure the safety and order of various flight activities, air traffic control services came into being and were constantly developed and improved, driven to maturity in 1980s. The main content of modern air traffic control service is that air traffic controllers (referred to as "controllers", the same below) rely on modern communication, navigation and surveillance technologies to manage and control the aircraft under their jurisdiction, coordinate and guide their movement paths and modes, so as to prevent aircraft from colliding with each other and colliding with obstacles in the airport maneuvering area, as well as maintain and speed up the orderly flow of air traffic. Air traffic control sector (referred to as "control sector", the same below) is the basic spatial unit of air traffic control (referred to as "control", the same below). Generally, the airspace providing air traffic control services for aircraft is divided into several control sectors, and each control sector corresponds to a controller. The operational performance of control sector is related to technical index extraction of aircraft operational situation in control sector, which reflects not only the quality and level of control service provided by controllers to control sectors, but also the operational efficiency of specific controlled airspace. Therefore, effective detection of the control sector operation performance is the basis and premise of adjusting the regulation operation strategy and optimizing the controlled airspace structure.
[03] Neural network is good at dealing with complex systems, especially with input-output mode mapping relation, which can get its mathematical expression through online self-learning without describing its mathematical mechanism in advance. In view of this, it has been widely used in many fields. However, traditional algorithms, such as BP and Hopfiled neural network, have shortcomings of long training time, unstable system, dependence on initial value, falling into local minimum and so on.
[04] In view of the problems existing in the prior art, the invention provides an airspace complexity evaluation system based on deep learning, which adopts L-M neural network to evaluate the airspace complexity, has high approximation accuracy, and can accurately evaluate the complexity.
[05] In order to achieve the above purpose, the present invention proposes the following technical scheme.
[06] The invention provides an airspace complexity evaluation system based on deep learning, including a data acquisition module, a data processing module, a complexity evaluation module and an early warning module which are sequentially connected.
[07] Specifically, the data acquisition module is used to collect, organize and monitor the data that affect the complexity of the sector in real time.
[08] The data processing module is used for normalizing above collected data, so as to eliminate dimensional differences among various detection indexes of the data affecting sector complexity.
[09] The complexity evaluation module is used for evaluating sector complexity based on processing result of the data processing module.
[010] The early warning module is used for analysis and early warning according to sector complexity.
[011] Preferably, the data affecting sector complexity includes sector traffic flow, proportion of aircrafts to change altitude, aircraft speed change frequency, aircraft heading change frequency, travel time in sector and conflict quantity.
[012] Further, the complexity evaluation module uses L-M neural network to evaluate airspace complexity.
[013] Moreover, the L-M neural network comprises an input layer, a hidden layer and an output layer.
[014] The input data of the input layer is the data influencing sector complexity.
[015] The number of neurons in the hidden layer is 7.
[016] And the parameter of the neuron in the output layer is the workload of the controller.
[017] Furthermore, the weight adjustment rate of the L-M neural network is:
[018] Aco = (J T J+uI)-1 JT e (1)
[019] Wherein, e is the error vector, Jis the Jacobian matrix of the network error to the weight derivative, u is the scalar, and I is the identity matrix.
[020] Preferably, the workload of the controller involves radar control operation and non-radar control operation.
[021] In particular, the radar control operation workload includes the workload of changing flight height, speed, course, yaw and others,
[022] The workload of non-radar control operation includes the work that the controller needs to handle personally, such as filling in the process list and operating equipment.
[023] Preferably, according to the real-time evaluation results of the complexity evaluation module, the early warning module integrates the working conditions and control means of traffic controllers to analyse and early warn the situation of exceeding the workload limit of traffic controllers.
[024] The invention discloses the following technical effects.
[025] Under the given airspace condition, the evaluation index of air traffic complexity is proposed from the aspects of traffic flow, flight activity characteristics and conflicts, and the workload factor of controllers is considered. Further, a mathematical model for evaluating air traffic complexity is established by adopting L M neural network algorithm. Compared with the traditional neural network calculation method, this way can calculate the result with high approximation accuracy and accurately evaluate the complexity.
[026] In order to explain the embodiments of the present invention or the technical scheme in the prior art more clearly, the figures used in the embodiments will be briefly introduced below. Obviously, the figures in the following description are only some embodiments of the present invention, and other figures can be obtained according to these figures for ordinary technicians in the field without paying creative labour.
[027] Figure 1 is a schematic structural diagram of the airspace complexity evaluation system based on deep learning of the present invention.
[028] The technical scheme in the embodiments of the present invention will be described clearly and completely with reference to the figures in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in the field without creative labour belong to protection scope of the present invention.
[029] In order to make the above objects, features and advantages of the present invention more obvious and easier to understand, the present invention will be further explained in detail with reference to the following figures and specific embodiments.
[030] As shown in Fig. 1, the invention provides an airspace complexity evaluation system based on deep learning, including a data acquisition module, a data processing module, a complexity evaluation module and an early warning module which are sequentially connected.
[031] The data acquisition module is used to collect and pre-process data that affect the complexity of the sector.
[032] In this embodiment, six parameters- sector traffic flow, proportion of aircrafts to change altitude, aircraft speed change frequency, aircraft heading change frequency, flight time in sector and conflict quantity, are adopted as the influencing parameters of the sector airspace complexity.
[033] Among them, sector traffic flow refers to the aircraft sorties under the jurisdiction of the control sector per unit time. The system obtains the position information of aerial aircraft by quoting the comprehensive flight path data of the air traffic control automation system and calculates the sector traffic flow by combining the configured sector boundary information.
[034] The sector navigation time refers to the total navigation time of aircrafts under jurisdiction within sector unit time. If the number of aircraft sorties per unit time
in the control sector is Q, the flight time of the aircraft is T , and the total flight time Q Tt, = T, in the sector is Toa, , then q4= can be obtained. The system obtains the position information of aerial aircraft by quoting the comprehensive flight path data of the air traffic control automation system and calculates the sector flight time by combining the configured sector boundary information.
[035] Sector aircraft change times refer to the sum of aircraft speed change times per unit time in the control sector. If the number of aircrafts in the control sector per
unit time is Q, the speed changes number of the qaircraft is Sq, and the number of
Stotal=> ,Sq speed changes in the sector is olal, then q=1 . The real-time integrated flight data is introduced to monitor and count the speed changes of the aircrafts in the sector. Taking a continuous change of aircraft speed to a set parameter as once speed change, the speed change times of the aircraft in the sector are calculated.
[036] Sector aircraft heading change frequency refer to the sum of aircraft heading change times per unit time in the control sector. If the number of aircrafts in
the control sector per unit time is Q, the heading changes number of the q aircraft is Q
H HHtotal=Z H H H,1,,,=1H , and the number of heading changes in the sector is otal, then q=1 . The real-time integrated flight data is introduced to monitor and count the heading changes of the aircrafts in the sector. Taking a continuous change of aircraft heading to a set parameter as once heading change, the heading change times of the aircraft in the sector are calculated.
[037] The proportion of aircrafts to change altitude includes the climbing proportion and the descending proportion.
[038] Based on the real-time data collected by the server, the data acquisition module monitors the real-time operation data by controlling the sector operation performance index detection server and comprehensive detection server.
[039] The data processing module is used for normalizing above collected data, so as to eliminate dimensional differences among various detection indexes of the data affecting sector complexity.
[040] The specific process is as follows:
[041] Let i be the original data of the i index, and ' be the normalized data of X, wherein x. , Then the function after normalization of the original data is
expressed as follows:
x - min(x1,x 2... xi)
[042] max(x 1,x 2 ... x)-min(x 1,x 2 x) -... (1)
[043] The complexity evaluation module is used for evaluating sector complexity based on the data affecting sector complexity.
[044] In this embodiment, L-M neural network is utilized to evaluate airspace complexity. The L-M algorithm uses the nonlinear least square method to get the approximate form of the matrix, thereby greatly reduce the amount of calculation. Besides, the weight adjustment rate of the L-M neural network is:
[045] Aco = (J T J+uI)-1 0 JT e (2)
[046] Wherein, e is the error vector, Jis the Jacobian matrix of the network error to the weight derivative, u is the scalar, and I is the identity matrix.
[047] Furthermore, six influencing parameters of the sector airspace complexity are taken as the input layer neurons, the workload of controllers are taken as the output layer neurons. A three-layer BP neural network with one hidden layer is adopted, and the number of neurons in hidden layer is 7.
[048] The mean square error (MSE) is selected as the expected error, specifically,
MSE = I p ,y,32
[049] mpP1ij1 (3)
[050] Wherein, m is the number of output nodes; P is the number of training
samples; P/ is the desired output of network;Y7I is the actual output of network.
[051] The learning rate determines the weight variation in each cycle. A large learning rate may lead to the instability of the system. In order to ensure that the error value of the network does not jump out of the low valley of the error surface and finally tends to the minimum error value, this embodiment selects a small learning rate. Small learning rate will lead to long learning time and slow convergence speed. In general, it tends to choose a smaller learning rate to ensure the stability of the system. In this embodiment, the learning rate is 0.5.
[052] Moreover, this embodiment uses tansig function as the hidden layer transfer function and purelin function as the output layer transfer function.
[053] The complexity of air traffic can be represented by the workload borne by controllers. In particular, the workload involves radar control operation and non-radar control operation. Wherein, the radar control operation workload includes the workload of changing flight height, speed, course, yaw and others. The workload of non-radar control operation includes the work that the controller needs to handle personally, such as filling in the process list and operating equipment.
[054] This embodiment obtains data by simulating the busy flight situation of an airport airspace, and the specific data is shown in Table 1.
[056] Table 1
Secto Proportio Averag Aircraft Aircraft Perio r n of Total e time speed heading Controlle d of traffic aircrafts conflict through change change r time flow to change s sector frequenc frequenc workload altitude /min y y 1 6 0.4 3 10 4 15 363 2 8 0.2 1 11 3 14 321 3 7 0.3 0 10 2 12 290 4 6 0.4 1 9 4 13 334 5 8 0.4 0 12 3 16 270 6 7 0.5 3 11 5 11 356
[057] According to calculation, the maximum error obtained by the L-M algorithm in this embodiment is 17. Compared with the traditional BP algorithm, this method has higher approximation accuracy, thus verifying the effectiveness of the system.
[058] According to the real-time evaluation results of the complexity evaluation module, the early warning module integrates the working conditions and control means of traffic controllers to analyse and early warn the situation of exceeding the workload limit of traffic controllers.
[059] Although the invention has been described with reference to specific examples, it will be appreciated by those skilled in the art that the invention may be embodied in many other forms, in keeping with the broad principles and the spirit of the invention described herein.
[060] The present invention and the described embodiments specifically include the best method known to the applicant of performing the invention. The present invention and the described preferred embodiments specifically include at least one feature that is industrially applicable
Claims (7)
1. An airspace complexity evaluation system based on deep learning, characterized by including a data acquisition module, a data processing module, a complexity evaluation module and an early warning module which are sequentially connected.
Wherein, the data acquisition module is used to collect, organize and monitor the data that affect the complexity of the sector in real time.
The data processing module is used for normalizing above collected data, so as to eliminate dimensional differences among various detection indexes of the data affecting sector complexity.
The complexity evaluation module is used for evaluating sector complexity based on processing result of the data processing module.
The early warning module is used for analysis and early warning according to sector complexity.
2. The airspace complexity evaluation system based on deep learning according to Claim 1, characterized in that the data affecting sector complexity includes sector traffic flow, proportion of aircrafts to change altitude, aircraft speed change frequency, aircraft heading change frequency, travel time in sector and conflict quantity.
3. The airspace complexity evaluation system based on deep learning according to Claim 1, characterized in that the complexity evaluation module uses L-M neural network to evaluate airspace complexity.
4. The airspace complexity evaluation system based on deep learning according to Claim 3, characterized in that the L-M neural network comprises an input layer, a hidden layer and an output layer.
The input data of the input layer is the data influencing sector complexity.
The number of neurons in the hidden layer is 7.
And the parameter of the neuron in the output layer is the workload of the controller.
5. The airspace complexity evaluation system based on deep learning according to Claim 3, characterized in that the weight adjustment rate of the L-M neural network is:
Ac)= (J T J+uI)-1 0 JT e (1)
Wherein, e is the error vector, Jis the Jacobian matrix of the network error to the weight derivative, u is the scalar, and I is the identity matrix.
6. The airspace complexity evaluation system based on deep learning according to Claim 4, characterized in that the workload of the controller involves radar control operation and non-radar control operation.
In particular, the radar control operation workload includes the workload of changing flight height, speed, course, yaw and others,
The workload of non-radar control operation includes the work that the controller needs to handle personally, such as filling in the process list and operating equipment.
7. The airspace complexity evaluation system based on deep learning according to Claim 6, characterized in that according to the real-time evaluation results of the complexity evaluation module, the early warning module integrates the working conditions and control means of traffic controllers to analyse and early warn the situation of exceeding the workload limit of traffic controllers.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
AU2021100719A AU2021100719A4 (en) | 2021-02-05 | 2021-02-05 | An Airspace Complexity Evaluation System Based on Deep Learning |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
AU2021100719A AU2021100719A4 (en) | 2021-02-05 | 2021-02-05 | An Airspace Complexity Evaluation System Based on Deep Learning |
Publications (1)
Publication Number | Publication Date |
---|---|
AU2021100719A4 true AU2021100719A4 (en) | 2021-04-22 |
Family
ID=75502305
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
AU2021100719A Ceased AU2021100719A4 (en) | 2021-02-05 | 2021-02-05 | An Airspace Complexity Evaluation System Based on Deep Learning |
Country Status (1)
Country | Link |
---|---|
AU (1) | AU2021100719A4 (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN115131947A (en) * | 2022-06-28 | 2022-09-30 | 浙江省测绘科学技术研究院 | Early warning method for urban road safety in networking environment |
-
2021
- 2021-02-05 AU AU2021100719A patent/AU2021100719A4/en not_active Ceased
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN115131947A (en) * | 2022-06-28 | 2022-09-30 | 浙江省测绘科学技术研究院 | Early warning method for urban road safety in networking environment |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106340208B (en) | Working method of air traffic control system based on 4D track operation | |
CN106157700B (en) | Air Traffic Control Method Based on 4D Track Operation | |
CN102289714B (en) | Method for controlling autonomous take-off and landing of small unmanned rotorcraft based on behavioral model | |
CN105261240B (en) | A kind of sector runnability method for comprehensive detection and system based on cluster analysis | |
CN111897316A (en) | Multi-aircraft autonomous decision-making method under scene fast-changing condition | |
AU2021100719A4 (en) | An Airspace Complexity Evaluation System Based on Deep Learning | |
CN105160201A (en) | Genetic algorithm back propagation (GABP) neural network based controller workload prediction method and system | |
CN106127407B (en) | Airplane travel scoring method and system based on multi-sensor information fusion | |
CN113900449A (en) | Multi-unmanned aerial vehicle trajectory planning method and device, unmanned aerial vehicle and storage medium | |
CN110765597A (en) | Sector number estimation system | |
CN114679729A (en) | Radar communication integrated unmanned aerial vehicle cooperative multi-target detection method | |
CN102968664B (en) | A kind of mobile robot's variable farm chemical applying Using Intelligent Decision-making Method and system | |
CN110825112A (en) | Oil field dynamic invasion target tracking system and method based on multiple unmanned aerial vehicles | |
EP3469571A1 (en) | Runway optimization system and method | |
CN116520890B (en) | Unmanned aerial vehicle control platform capable of three-dimensional holographic inspection | |
CN116414153B (en) | Unmanned aerial vehicle take-off and landing correction method based on artificial intelligence | |
CN110826891A (en) | Relative collision risk degree obtaining method based on ship cluster situation | |
CN113110558B (en) | Hybrid propulsion unmanned aerial vehicle demand power prediction method | |
CN108831195A (en) | Air traffic Workflow Management System and method based on vertical sectional view | |
CN114578846A (en) | AGIMM tracking method based on maneuver detection sorting | |
Wang et al. | Analysis of air traffic flow control through agent-based modeling and simulation | |
Xue et al. | Autonomous evaluation method of unmanned equipment based on OODA-I framework | |
Li et al. | Intelligent Early Warning Method Based on Drone Inspection | |
Qing et al. | Path Optimization of Biological Control of Mosquitoes in UAV Based on Particle Swarm Optimization | |
CN112056292B (en) | Pesticide application control system and method based on reduced-order model under influence of random environmental wind |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
FGI | Letters patent sealed or granted (innovation patent) | ||
MK22 | Patent ceased section 143a(d), or expired - non payment of renewal fee or expiry |