CN110209195A - The tele-control system and control method of marine unmanned plane - Google Patents
The tele-control system and control method of marine unmanned plane Download PDFInfo
- Publication number
- CN110209195A CN110209195A CN201910509094.8A CN201910509094A CN110209195A CN 110209195 A CN110209195 A CN 110209195A CN 201910509094 A CN201910509094 A CN 201910509094A CN 110209195 A CN110209195 A CN 110209195A
- Authority
- CN
- China
- Prior art keywords
- unmanned plane
- safety index
- ship
- landing
- detection data
- 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
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course or altitude of land, water, air, or space vehicles, e.g. automatic pilot
- 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
- G07—CHECKING-DEVICES
- G07C—TIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE
- G07C5/00—Registering or indicating the working of vehicles
- G07C5/08—Registering or indicating performance data other than driving, working, idle, or waiting time, with or without registering driving, working, idle or waiting time
- G07C5/0808—Diagnosing performance data
-
- G—PHYSICS
- G07—CHECKING-DEVICES
- G07C—TIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE
- G07C5/00—Registering or indicating the working of vehicles
- G07C5/08—Registering or indicating performance data other than driving, working, idle, or waiting time, with or without registering driving, working, idle or waiting time
- G07C5/0841—Registering performance data
-
- 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
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation
Abstract
The present invention relates to the tele-control systems and control method of a kind of marine unmanned plane, the system comprises attitude of ship detection modules, ship environment detection module, ship capacity check module, UAV Attitude detection module, unmanned plane context detection module, drone status detection module, flight safety index computing module, landing safety index computing module and unmanned aerial vehicle (UAV) control module, the unmanned aerial vehicle (UAV) control module judges the state of current unmanned plane, if current unmanned plane is in state of flight, then obtain the flight safety index and landing safety index of unmanned plane, if the flight safety index of unmanned plane and landing safety index meet preset unmanned plane drop conditions, unmanned plane is then controlled to drop on landing platform, if current unmanned plane is in parked state, then obtain the safety index that takes off for the ship that unmanned plane is parked, such as The fruit safety index that takes off meets preset unmanned plane takeoff condition, then controls unmanned plane and take off from landing platform, sufficiently guarantee flight safety.
Description
Technical field
The present invention relates to the tele-control systems and control of marine air vehicle technique field, in particular to a kind of marine unmanned plane
Method processed.
Background technique
The fast development of unmanned plane determines that it can be not only used for solving the problems, such as land, and can be also used for solving
Certainly marine problem.Regrettably, the offshore applications of unmanned plane are also very difficult at present.This is significantly limited by unmanned plane
Marine landing technology.Unmanned plane lands on ship and is achieved by a variety of factors, size, the size of wave, wind such as deck
Speed etc..Therefore, application technology of the research unmanned plane on ship, which is one, extremely realistic meaning project.
Unmanned plane is in flight course, the problem of can be potentially encountered electricity and the case where can encounter bad weather, if
It cannot recall in time, then the flight course of unmanned plane is it is possible that danger.And unmanned plane is during takeoff and landing, nothing
Man-machine and ship mutual cooperation is also particularly significant.
Accordingly, it is desirable to provide it is a kind of for unmanned plane can remotely control its state of flight and takeoff and landing when
Machine ensures the flight of unmanned plane and using safe.
Summary of the invention
In order to solve the problems in the prior art, the present invention provides a kind of tele-control system of marine unmanned plane and controls
Method processed can be suitble to fly by the detection of ship status and the detection of drone status with accurate judgement unmanned plane current state
It goes or is suitble to park, ensure the flight of unmanned plane and using safe.
To achieve the goals above, the present invention has following constitute:
The present invention provides a kind of tele-control system of marine unmanned plane, the system comprises:
Attitude of ship detection module, for detecting the operation posture for being configured with the ship of landing platform;
Ship environment detection module, for detecting the Weather information being configured at the ship of landing platform;
Ship capacity check module, the unmanned plane quantity that the landing platform for detecting ship is currently parked;
UAV Attitude detection module, for detecting the flight attitude of unmanned plane;
Unmanned plane context detection module, for detecting the Weather information around unmanned plane;
Drone status detection module, for detecting the electricity of unmanned plane and the fault message of unmanned plane;
Flight safety index computing module, for by the flight attitude of unmanned plane, around Weather information, electricity and nobody
The fault message of machine inputs trained flight safety index computation model, the flight safety index exported;
Landing safety index computing module, the day at the operation posture of the ship for landing platform will to be configured with, ship
The unmanned plane quantity that gas information and landing platform are currently parked inputs trained safety index computation model and the instruction of taking off respectively
The landing safety index computation model perfected respectively obtains the safety index that takes off of the safety index computation model output of taking off
With the landing safety index of the landing safety index computation model output;
Unmanned aerial vehicle (UAV) control module, for judging the state of current unmanned plane, if current unmanned plane is in state of flight,
The flight safety index and landing safety index of unmanned plane are then obtained, if the flight safety index of the unmanned plane and landing peace
Total index number meets preset unmanned plane drop conditions, then controls the unmanned plane and drop on the landing platform, if currently
Unmanned plane is in parked state, then obtains the safety index that takes off for the ship that unmanned plane is parked, if described take off refers to safely
Number meets preset unmanned plane takeoff condition, then controls the unmanned plane and take off from the landing platform.
Optionally, the attitude of ship detection module obtains the three axis accelerometer and three being set at the landing platform
The detection data of axis gyroscope is calculated according to the detection data of three axis accelerometer and three-axis gyroscope at the landing platform
Obtain acceleration a1, a2, a3 of the ship on three axis directions.
Optionally, the location data of the ship is sent to cloud server by the ship environment detection module, from institute
State wind speed v1, wind direction d1 and thunderstorm grade y1 of the cloud server inquiry ship current location in the following preset time period, institute
State the detection that ship environment detection module also obtains the detection data v2, anemoscope of the airspeedometer being set at the landing platform
Data d2 and udometric detection data y2.
Optionally, acceleration a1 of the landing safety index computing module by the ship on three axis directions,
A2, a3, wind speed v1, wind direction d1 and thunderstorm grade y1 and described of the ship current location in the following preset time period
It drops the detection data v2 of airspeedometer, the detection data d2 of anemoscope and udometric detection data y2 at platform and inputs the instruction
Before the safety index computation model that takes off perfected, increase detection data v2, the anemoscope of the airspeedometer at the landing platform
Detection data d2 and udometric detection data y2 weight, then trained take off the data input after weighting is described
Safety index computation model;
Acceleration a1, a2, a3 of the landing safety index computing module by the ship on three axis directions, the ship
Wind of the oceangoing ship current location at wind speed v1, wind direction d1 and the thunderstorm grade y1 and the landing platform in the following preset time period
Detection data d2 and udometric detection data the y2 input of the detection data v2, anemoscope of speed the meter trained landing peace
Before total index number computation model, increase wind speed v1, wind direction d1 and thunder of the ship current location in the following preset time period
The weight of the detection data v2 of airspeedometer at rain grade y1 and the landing platform, the detection data d2 of anemoscope, then
Data after weighting are inputted into the trained landing safety index computation model.
Optionally, the UAV Attitude detection module obtains the three axis accelerometer and three being set in the unmanned plane
Acceleration b1, b2, b3 of the unmanned plane on three axis directions is calculated in the detection data of axis gyroscope.
Optionally, the location data of the unmanned plane is sent to cloud server by the unmanned plane context detection module,
The detection data v3 of airspeedometer, the detection data d3 of anemoscope and rain from cloud server inquiry unmanned plane current location
The detection data y3 of meter;
The unmanned plane context detection module obtains the heading and flying speed of unmanned plane, predicts that the unmanned plane exists
The position of prediction is sent to cloud server by the position reached after the following preset time period, is obtained from the cloud server
Wind speed v4, wind direction d4 and thunderstorm grade y4 at the position of the following preset time period interior prediction.
Optionally, the flight safety index computing module by the flight attitude of the unmanned plane, around Weather information,
When the fault message of electricity and unmanned plane inputs trained flight safety index computation model, whether the electricity is first determined whether
Greater than default power threshold and the current fault-free of unmanned plane, if it is, the flight safety index computing module is improved not
The weight for carrying out wind speed v4, the wind direction d4 and thunderstorm grade y4 at the position of preset time period interior prediction, then by unmanned plane three
The detection of the detection data v3, anemoscope of the airspeedometer of acceleration b1, b2, b3, unmanned plane current location on a axis direction
Data d3 and udometric detection data y3, wind speed v4, wind direction d4 and thunder at the position of the following preset time period interior prediction
The electricity data of rain grade y4 and unmanned plane is input to the flight safety index computation model;
When the electricity currently breaks down less than default power threshold or unmanned plane, unmanned plane is improved three axis sides
Upward acceleration b1, b2, b3, the detection data v3 of the airspeedometer of unmanned plane current location, the detection data d3 of anemoscope and
The weight of udometric detection data y3, then acceleration b1, b2, b3, the unmanned plane by unmanned plane on three axis directions
The detection data v3 of the airspeedometer of current location, the detection data d3 of anemoscope and udometric detection data y3 are default in future
The event of the electricity data and unmanned plane of wind speed v4, wind direction d4 and thunderstorm grade y4, unmanned plane at the position of period interior prediction
Barrier grade is input to the flight safety index computation model.
Optionally, the system also includes:
Flight safety index calculates model training module, for constructing convolutional neural networks, the convolutional neural networks packet
Three convolutional layers, three pond layers, full articulamentum and softmax function layer are included, multiple arrays in training set, each number are configured
Each element respectively indicates the corresponding attribute value of a unmanned plane in group, and marks flight safety index for each array, will instruct
Practice collection and be input to the convolutional neural networks, training to loss function minimum obtains trained flight safety index and calculates mould
Type.
Optionally, the system also includes:
Landing safety index computation model training module, for constructing the first convolutional neural networks and the second convolution mind respectively
Through network, first convolutional neural networks and the second convolutional neural networks respectively include three convolutional layers, three pond layers, complete
Articulamentum and softmax function layer configure multiple arrays in training set, each element respectively indicates a ship in each array
The corresponding attribute value of oceangoing ship, and take off safety index and landing safety index are marked for each array, the training set is distinguished defeated
Enter first convolutional neural networks and the second convolutional neural networks, is respectively trained to loss function minimum, obtains trained
Take off safety index computation model and trained landing safety index computation model.
The embodiment of the present invention also provides a kind of long-range control method of marine unmanned plane, using the marine unmanned plane
Tele-control system, described method includes following steps:
The operation posture of ship of the detection configured with landing platform;
Detection is configured with the Weather information at the ship of landing platform;
The unmanned plane quantity that the landing platform of detection ship is currently parked;
Detect the flight attitude of unmanned plane;
Detect the Weather information around unmanned plane;
Detect the electricity of unmanned plane and the fault message of unmanned plane;
The fault message input of the flight attitude of unmanned plane, the Weather information of surrounding, electricity and unmanned plane is trained
Flight safety index computation model, the flight safety index exported;
The operation posture of ship configured with landing platform, the Weather information at ship and landing platform are currently parked
Unmanned plane quantity inputs trained take off safety index computation model and trained landing safety index computation model respectively,
Respectively obtain take off safety index and the landing safety index computation model of the safety index computation model output of taking off
The landing safety index of output;
Judge the state of current unmanned plane, if current unmanned plane is in state of flight, obtains the flight of unmanned plane
Safety index and landing safety index, if the flight safety index of the unmanned plane and landing safety index meet preset nothing
Man-machine drop conditions then control the unmanned plane and drop on the landing platform, if current unmanned plane, which is in, is parked shape
State then obtains the safety index that takes off for the ship that unmanned plane is parked, if the safety index that takes off meets preset unmanned plane
Takeoff condition then controls the unmanned plane and takes off from the landing platform.
Therefore, the present invention can be worked as by the detection of ship status and the detection of drone status with accurate judgement unmanned plane
Preceding state is suitble to flight to be still suitble to park, and ensures the flight of unmanned plane and using safe;It is right under the different conditions of unmanned plane
The different weight of different data settings, raising unmanned plane is not on the basis of the use of model is utmostly reduced with realization
With the adaptability of scene;By the status predication to unmanned plane during flying next stage, ensure unmanned plane at following one section
Interior flight safety.
Detailed description of the invention
Fig. 1 is the structural block diagram of the tele-control system of the marine unmanned plane of one embodiment of the invention;
Fig. 2 is the flow chart of the long-range control method of the marine unmanned plane of one embodiment of the invention;
Fig. 3 is the flow chart that unmanned plane is controlled according to safety index of one embodiment of the invention;
Fig. 4 is the structural schematic diagram of the convolutional neural networks of one embodiment of the invention.
Specific embodiment
Example embodiment is described more fully with reference to the drawings.However, example embodiment can be with a variety of shapes
Formula is implemented, and is not understood as limited to embodiment set forth herein;On the contrary, thesing embodiments are provided so that the present invention will
Fully and completely, and by the design of example embodiment comprehensively it is communicated to those skilled in the art.It is identical attached in figure
Icon note indicates same or similar structure, thus will omit repetition thereof.
Described feature, structure or characteristic can be incorporated in one or more embodiments in any suitable manner
In.In the following description, many details are provided to provide and fully understand to embodiments of the present invention.However,
One of ordinary skill in the art would recognize that without one or more in specific detail, or using other methods, constituent element, material
Material etc., can also practice technical solution of the present invention.In some cases, be not shown in detail or describe known features, material or
Person operates to avoid the fuzzy present invention.
As shown in Figure 1, the present invention provides a kind of tele-control system of marine unmanned plane, the system comprises:
Attitude of ship detection module M100, for detecting the operation posture for being configured with the ship of landing platform;
Ship environment detection module M200, for detecting the Weather information being configured at the ship of landing platform;
Ship capacity check module M300, the unmanned plane quantity that the landing platform for detecting ship is currently parked;
UAV Attitude detection module M400, for detecting the flight attitude of unmanned plane;
Unmanned plane context detection module M500, for detecting the Weather information around unmanned plane;
Drone status detection module M600, for detecting the electricity of unmanned plane and the fault message of unmanned plane;
Flight safety index computing module M700, for by the flight attitude of unmanned plane, around Weather information, electricity and
The fault message of unmanned plane inputs trained flight safety index computation model, the flight safety index exported;
Landing safety index computing module M800, at the operation posture of the ship for landing platform will to be configured with, ship
Weather information and the unmanned plane quantity currently parked of landing platform input the trained safety index computation model that takes off respectively
With trained landing safety index computation model, the safety of taking off of the safety index computation model output of taking off is respectively obtained
The landing safety index of index and the landing safety index computation model output;
Unmanned aerial vehicle (UAV) control module M900, for judging the state of current unmanned plane, if current unmanned plane is in flight
State, then obtain unmanned plane flight safety index and landing safety index, if the flight safety index of the unmanned plane and
Landing safety index meets preset unmanned plane drop conditions, then controls the unmanned plane and drop on the landing platform, such as
The current unmanned plane of fruit is in parked state, then the safety index that takes off for the ship that unmanned plane is parked is obtained, if described take off
Safety index meets preset unmanned plane takeoff condition, then controls the unmanned plane and take off from the landing platform.
As shown in Fig. 2, the embodiment of the present invention also provides a kind of long-range control method of marine unmanned plane, using the sea
The tele-control system of upper unmanned plane, described method includes following steps:
S100: the operation posture of ship of the detection configured with landing platform;
S200: detection is configured with the Weather information at the ship of landing platform;
S300: the unmanned plane quantity that the landing platform of ship is currently parked is detected;
S400: the flight attitude of unmanned plane is detected;
S500: the Weather information around detection unmanned plane;
S600: the electricity of unmanned plane and the fault message of unmanned plane are detected;
S700: the fault message of the flight attitude of unmanned plane, the Weather information of surrounding, electricity and unmanned plane is inputted into training
Good flight safety index computation model, the flight safety index exported;
S800: by the operation posture of ship configured with landing platform, ship Weather information and landing platform it is current
The unmanned plane quantity parked inputs trained safety index computation model and the trained landing safety index meter of taking off respectively
Model is calculated, take off safety index and the landing safety index meter of the safety index computation model output of taking off are respectively obtained
Calculate the landing safety index of model output;
S900: unmanned plane is remotely controlled according to the flight safety index of unmanned plane and landing safety index.
As shown in figure 3, specifically, in this embodiment, step S900 includes the following steps:
S901: judge the state of current unmanned plane;
S902: if current unmanned plane is in state of flight, the flight safety index and landing peace of unmanned plane are obtained
Total index number;
S903: judge whether to meet preset unmanned plane drop conditions;
S904: if the flight safety index of the unmanned plane and landing safety index meet preset unmanned plane landing item
Part then controls the unmanned plane and drops on the landing platform;For example, flight safety refers to when preset unmanned plane drop conditions
Number be less than first threshold and landing safety index be greater than second threshold, at this time unmanned plane continue flight safety index it is lower, be
The safe handling for ensureing unmanned plane, when unmanned plane landing safety coefficient is higher than second threshold, the landing of priority acccess control unmanned plane;
First threshold and second threshold can be set as needed herein;
S905: it if current unmanned plane is in parked state, obtains taking off for the ship that unmanned plane is parked and refers to safely
Number;
S906: judge whether to meet preset unmanned plane takeoff condition;
S907: if the safety index that takes off meets preset unmanned plane takeoff condition, control the unmanned plane from
It takes off on the landing platform;For example, preset unmanned plane takeoff condition is to take off safety coefficient greater than third threshold value, herein the
The value of three threshold values can be set as needed;
S908: it if being unsatisfactory for situation as above, controls unmanned plane current state and remains unchanged.
Therefore, the present invention can be worked as by the detection of ship status and the detection of drone status with accurate judgement unmanned plane
Preceding state is suitble to flight to be still suitble to park, and ensures the flight of unmanned plane and using safe.
In this embodiment, the attitude of ship detection module obtains the 3-axis acceleration being set at the landing platform
The detection data of meter and three-axis gyroscope, according to the testing number of three axis accelerometer and three-axis gyroscope at the landing platform
According to acceleration a1, a2, a3 of the ship on three axis directions is calculated.
In this embodiment, the location data of the ship is sent to cloud service by the ship environment detection module
Device, from wind speed v1, wind direction d1 and thunderstorm etc. of the cloud server inquiry ship current location in the following preset time period
Grade y1, the ship environment detection module also obtain detection data v2, the wind direction for the airspeedometer being set at the landing platform
The detection data d2 of instrument and udometric detection data y2.
In this embodiment, acceleration of the landing safety index computing module by the ship on three axis directions
Spend a1, a2, a3, wind speed v1, wind direction d1 and thunderstorm grade y1 of the ship current location in the following preset time period and
The detection data v2 of airspeedometer at the landing platform, the detection data d2 of anemoscope and udometric detection data y2 input
Before the trained safety index computation model that takes off, increase the airspeedometer at the landing platform detection data v2,
The weight of the detection data d2 of anemoscope and udometric detection data y2, then by the landing of data and ship after weighting
The unmanned plane quantity parked on platform inputs the trained safety index computation model that takes off.Take off safe system in calculating
For number, since unmanned plane current location and vessel position are consistent, and unmanned plane is parked on ship, the appearance of unmanned plane
State and the posture of ship are also almost the same, consider some attitude datas and environmental data at current time, emphatically to judge to take off
The height of safety coefficient.
Acceleration a1, a2, a3 of the landing safety index computing module by the ship on three axis directions, the ship
Wind of the oceangoing ship current location at wind speed v1, wind direction d1 and the thunderstorm grade y1 and the landing platform in the following preset time period
Detection data d2 and udometric detection data the y2 input of the detection data v2, anemoscope of speed the meter trained landing peace
Before total index number computation model, increase wind speed v1, wind direction d1 and thunder of the ship current location in the following preset time period
The weight of the detection data v2 of airspeedometer at rain grade y1 and the landing platform, the detection data d2 of anemoscope, then
Data after weighting are inputted into the trained landing safety index computation model.I.e. when calculating landing safety coefficient, by
There is a certain distance in unmanned plane potential range ship, unmanned plane, which flies to potential range current time when ship is nearby landed, to be had
For a period of time, therefore, some appearances of (such as half an hour in, 20 minute in etc.) ship are considered in the following preset time period emphatically
State data and environmental data, to predict the landing safety coefficient when unmanned plane is come at landing platform.
It only needs to acquire one group of data when acquiring data as a result, by different ranking operations, can be respectively applied to
The calculating of safety coefficient of taking off and landing safety coefficient is very convenient quick.
In this embodiment, the UAV Attitude detection module obtains the 3-axis acceleration being set in the unmanned plane
The detection data of meter and three-axis gyroscope, is calculated acceleration b1, b2, b3 of the unmanned plane on three axis directions.
In this embodiment, the location data of the unmanned plane is sent to cloud clothes by the unmanned plane context detection module
Business device inquires the detection data v3 of the airspeedometer of unmanned plane current location, the detection data of anemoscope from the cloud server
D3 and udometric detection data y3;
The unmanned plane context detection module obtains the heading and flying speed of unmanned plane, predicts that the unmanned plane exists
The position of prediction is sent to cloud server by the position reached after the following preset time period, is obtained from the cloud server
Wind speed v4, wind direction d4 and thunderstorm grade y4 at the position of the following preset time period interior prediction.
In this embodiment, the flight safety index computation model by the flight attitude of the unmanned plane, around day
When the fault message of gas information, electricity and unmanned plane inputs trained flight safety index computation model, first determine whether described
Whether electricity is greater than default power threshold and the current fault-free of unmanned plane, if it is, the flight safety index computing module
The weight for improving wind speed v4, the wind direction d4 and thunderstorm grade y4 at the position of the following preset time period interior prediction, then by nothing
Man-machine acceleration b1, b2, b3 on three axis directions, unmanned plane current location airspeedometer detection data v3, wind direction
The detection data d3 of instrument and udometric detection data y3, wind speed v4, wind at the position of the following preset time period interior prediction
The flight safety index computation model is input to the electricity data of d4 and thunderstorm grade y4 and unmanned plane;I.e. in unmanned plane
Electricity is sufficient and unmanned plane currently without failure in the case where, unmanned plane can also continue to flight one end time, then considers emphatically
The data of unmanned plane future a period of time interior prediction ensure the safety that unmanned plane flies within following a period of time;
When the electricity currently breaks down less than default power threshold or unmanned plane, unmanned plane is improved three axis sides
Upward acceleration b1, b2, b3, the detection data v3 of the airspeedometer of unmanned plane current location, the detection data d3 of anemoscope and
The weight of udometric detection data y3, then acceleration b1, b2, b3, the unmanned plane by unmanned plane on three axis directions
The detection data v3 of the airspeedometer of current location, the detection data d3 of anemoscope and udometric detection data y3 are default in future
The event of the electricity data and unmanned plane of wind speed v4, wind direction d4 and thunderstorm grade y4, unmanned plane at the position of period interior prediction
Barrier grade is input to the flight safety index computation model;I.e. when unmanned plane not enough power supply or unmanned plane break down, need
The current status data of unmanned plane is considered emphatically, if unmanned plane current environment is relatively more severe or unmanned plane jolts ratio
It is more serious, then it needs that unmanned plane is preferentially made to return to landing platform to be rewarded.
Thus, it is only necessary to use a flight safety coefficient computation model, and acquire one group of data, it can be suitable for not
With the judgement of the flight safety of unmanned plane under scene different conditions, calculation amount is greatly saved, reduces the operation of each equipment
Burden.
In this embodiment, the tele-control system of the marine unmanned plane further include:
Flight safety index calculates model training module, for constructing convolutional neural networks, the convolutional neural networks packet
Three convolutional layers, three pond layers, full articulamentum and softmax function layer are included, multiple arrays in training set, each number are configured
Each element respectively indicates the corresponding attribute value of a unmanned plane in group, may include unmanned plane three axis sides specifically
The detection data v3 of airspeedometer, the detection data d3 of anemoscope of upward acceleration b1, b2, b3, unmanned plane current location and
Wind speed v4, wind direction d4 and thunderstorm grade y4 of the udometric detection data y3 at the position of the following preset time period interior prediction,
The electricity data of unmanned plane and the fault level of unmanned plane, and flight safety index is marked for each array, training set is inputted
To the convolutional neural networks, training obtains trained flight safety index computation model to loss function minimum.Input
Array can be one-dimension array, also can be constructed as Multidimensional numerical.The schematic diagram of convolutional neural networks may refer to Fig. 4.Convolution
Every layer of convolutional layer is made of several convolution units in neural network, and the parameter of each convolution unit is to pass through back-propagation algorithm
What optimization obtained.The purpose of convolution algorithm is to extract the different characteristic of input.The parameter of each convolution unit is by anti-
It is optimized to propagation algorithm.The purpose of convolution algorithm is to extract the different characteristic of input.Feature is carried out in convolutional layer to mention
After taking, the feature of output can be passed to pond layer and carry out feature selecting and information filtering.Pond layer includes presetting pond
Function, function are that the result of a single point in characteristic pattern is replaced with to the characteristic pattern statistic of its adjacent area.Convolutional Neural net
Full articulamentum in network is equivalent to the hidden layer in conventional feed forward neural network.Full articulamentum is usually built in convolutional neural networks
The decline of hidden layer, and only signal is transmitted to other full articulamentums.Softmax function, also known as normalization exponential function.It
It is two classification function sigmoid in how classificatory popularization, it is therefore an objective to show polytypic result in the form of probability.
Wherein, to the calculating of flight safety index, it is equivalent to the calculating to flight safety reliability.
In this embodiment, the tele-control system of the marine unmanned plane further include:
Landing safety index computation model training module, for constructing the first convolutional neural networks and the second convolution mind respectively
Through network, first convolutional neural networks and the second convolutional neural networks respectively include three convolutional layers, three pond layers, complete
Articulamentum and softmax function layer configure multiple arrays in training set, each element respectively indicates a ship in each array
The corresponding attribute value of oceangoing ship, specifically may include acceleration a1, a2, a3 of the ship on three axis directions, and the ship is worked as
Airspeedometer of the front position at wind speed v1, wind direction d1 and the thunderstorm grade y1 and the landing platform in the following preset time period
Detection data v2, the detection data d2 and udometric detection data y2 of anemoscope and the landing platform of ship currently stop
By the quantity of aircraft, and take off safety index and landing safety index are marked for each array, the training set is inputted respectively
First convolutional neural networks and the second convolutional neural networks are respectively trained to loss function minimum, obtain trained
Femto-ampere total index number computation model and trained landing safety index computation model.The array of input can be one-dimension array,
It can be constructed as Multidimensional numerical.The schematic diagram of convolutional neural networks may refer to Fig. 4.
In conclusion detection of the present invention by the detection of ship status and drone status, can with accurate judgement nobody
Machine current state is suitble to flight to be still suitble to park, and ensures the flight of unmanned plane and using safe;In the different conditions of unmanned plane
Under, the weight different to different data settings, to improve unmanned plane on the basis of the realization utmostly use of reduction model
For the adaptability of different scenes;By the status predication to unmanned plane during flying next stage, ensure unmanned plane following
Flight safety in a period of time.
In this description, the present invention is described with reference to its specific embodiment.But it is clear that can still make
Various modifications and alterations are without departing from the spirit and scope of the invention.Therefore, the description and the appended drawings should be considered as illustrative
And not restrictive.
Claims (10)
1. a kind of tele-control system of sea unmanned plane, which is characterized in that the system comprises:
Attitude of ship detection module, for detecting the operation posture for being configured with the ship of landing platform;
Ship environment detection module, for detecting the Weather information being configured at the ship of landing platform;
Ship capacity check module, the unmanned plane quantity that the landing platform for detecting ship is currently parked;
UAV Attitude detection module, for detecting the flight attitude of unmanned plane;
Unmanned plane context detection module, for detecting the Weather information around unmanned plane;
Drone status detection module, for detecting the electricity of unmanned plane and the fault message of unmanned plane;
Flight safety index computing module, for by the flight attitude of unmanned plane, around Weather information, electricity and unmanned plane
Fault message inputs trained flight safety index computation model, the flight safety index exported;
Landing safety index computing module, the weather letter at the operation posture of the ship for landing platform will to be configured with, ship
Breath and the unmanned plane quantity currently parked of landing platform input trained take off respectively and safety index computation model and train
Landing safety index computation model, respectively obtain take off safety index and the institute of the safety index computation model output of taking off
State the landing safety index of landing safety index computation model output;
Unmanned aerial vehicle (UAV) control module, if current unmanned plane is in state of flight, is obtained for judging the state of current unmanned plane
The flight safety index and landing safety index for taking unmanned plane, if the flight safety index of the unmanned plane and landing refer to safely
Number meets preset unmanned plane drop conditions, then controls the unmanned plane and drop on the landing platform, if it is current nobody
Machine is in parked state, then obtains the safety index that takes off for the ship that unmanned plane is parked, if the safety index that takes off is full
The preset unmanned plane takeoff condition of foot, then control the unmanned plane and take off from the landing platform.
2. the tele-control system of sea unmanned plane according to claim 1, which is characterized in that the attitude of ship detection
Module obtains the detection data of the three axis accelerometer and three-axis gyroscope that are set at the landing platform, according to the landing
Acceleration of the ship on three axis directions is calculated in the detection data of three axis accelerometer and three-axis gyroscope at platform
Spend a1, a2, a3.
3. the tele-control system of sea unmanned plane according to claim 2, which is characterized in that the ship environment detection
The location data of the ship is sent to cloud server by module, from cloud server inquiry ship current location not
Carry out wind speed v1, the wind direction d1 and thunderstorm grade y1 in preset time period, the ship environment detection module, which also obtains, is set to institute
State the detection data v2 of the airspeedometer at landing platform, the detection data d2 of anemoscope and udometric detection data y2.
4. the tele-control system of sea unmanned plane according to claim 3, which is characterized in that the landing safety index
Acceleration a1, a2, a3 of the computing module by the ship on three axis directions, the ship current location are default in future
Detection data v2, the wind of wind speed v1, wind direction d1 and thunderstorm grade y1 in period and the airspeedometer at the landing platform
Before inputting detection data d2 from the trained safety index computation model that takes off to instrument and udometric detection data y2,
Increase the detection data v2 of the airspeedometer at the landing platform, the detection data d2 of anemoscope and udometric detection data y2
Weight, the data after weighting are then inputted into the trained safety index computation model that takes off;
Acceleration a1, a2, a3 of the landing safety index computing module by the ship on three axis directions, the ship are worked as
Airspeedometer of the front position at wind speed v1, wind direction d1 and the thunderstorm grade y1 and the landing platform in the following preset time period
Detection data v2, anemoscope detection data d2 and udometric detection data y2 input it is described it is trained landing refer to safely
Before number computation model, increase wind speed v1, wind direction d1 and thunderstorm etc. of the ship current location in the following preset time period
The weight of the detection data d2 of the detection data v2 of airspeedometer, anemoscope at grade y1 and the landing platform, then will plus
Data after power input the trained landing safety index computation model.
5. the tele-control system of sea unmanned plane according to claim 1, which is characterized in that the UAV Attitude inspection
The detection data that module obtains the three axis accelerometer and three-axis gyroscope that are set in the unmanned plane is surveyed, nobody is calculated
Acceleration b1, b2, b3 of the machine on three axis directions.
6. the tele-control system of sea unmanned plane according to claim 5, which is characterized in that the unmanned plane environment inspection
It surveys module and the location data of the unmanned plane is sent to cloud server, inquire unmanned plane present bit from the cloud server
The detection data v3 for the airspeedometer set, the detection data d3 of anemoscope and udometric detection data y3;
The unmanned plane context detection module obtains the heading and flying speed of unmanned plane, predicts the unmanned plane in future
The position of prediction is sent to cloud server by the position reached after preset time period, is obtained from the cloud server not
Carry out wind speed v4, the wind direction d4 and thunderstorm grade y4 at the position of preset time period interior prediction.
7. the tele-control system of sea unmanned plane according to claim 1, which is characterized in that the flight safety index
The fault message of the flight attitude of the unmanned plane, the Weather information of surrounding, electricity and unmanned plane is inputted training by computing module
When the flight safety index computation model got well, first determine whether the electricity is greater than default power threshold and the current nothing of unmanned plane
Failure, if it is, the flight safety index computing module improves the wind at the position of the following preset time period interior prediction
The weight of fast v4, wind direction d4 and thunderstorm grade y4, then the acceleration b1, b2, b3 by unmanned plane on three axis directions, nothing
The detection data v3 of the airspeedometer of man-machine current location, the detection data d3 of anemoscope and udometric detection data y3, not
Carry out the electricity data input of wind speed v4, wind direction d4 and the thunderstorm grade y4 and unmanned plane at the position of preset time period interior prediction
To the flight safety index computation model;
When the electricity currently breaks down less than default power threshold or unmanned plane, unmanned plane is improved on three axis directions
Acceleration b1, b2, b3, the detection data v3 of the airspeedometer of unmanned plane current location, the detection data d3 of anemoscope and rainfall
The weight of the detection data y3 of meter, then acceleration b1, b2, b3, the unmanned plane by unmanned plane on three axis directions are current
The detection data v3 of the airspeedometer of position, the detection data d3 of anemoscope and udometric detection data y3 are in the following preset time
Wind speed v4, wind direction d4 and thunderstorm grade y4, the electricity data of unmanned plane and the failure of unmanned plane at the position of section interior prediction etc.
Grade is input to the flight safety index computation model.
8. the tele-control system of sea unmanned plane according to claim 1, which is characterized in that the system also includes:
Flight safety index calculates model training module, and for constructing convolutional neural networks, the convolutional neural networks include three
A convolutional layer, three pond layers, full articulamentum and softmax function layer configure multiple arrays in training set, in each array
Each element respectively indicates the corresponding attribute value of a unmanned plane, and marks flight safety index for each array, by training set
The convolutional neural networks are input to, training obtains trained flight safety index computation model to loss function minimum.
9. the tele-control system of sea unmanned plane according to claim 1, which is characterized in that the system also includes:
Landing safety index computation model training module, for constructing the first convolutional neural networks and the second convolution nerve net respectively
Network, first convolutional neural networks and the second convolutional neural networks respectively include three convolutional layers, three pond layers, full connection
Layer and softmax function layer configure multiple arrays in training set, each element respectively indicates a ship pair in each array
The attribute value answered, and take off safety index and landing safety index are marked for each array, the training set is inputted into institute respectively
The first convolutional neural networks and the second convolutional neural networks are stated, is respectively trained to loss function minimum, obtains trained take off
Safety index computation model and trained landing safety index computation model.
10. a kind of long-range control method of sea unmanned plane, which is characterized in that using described in any one of claims 1 to 9
The tele-control system of marine unmanned plane, described method includes following steps:
The operation posture of ship of the detection configured with landing platform;
Detection is configured with the Weather information at the ship of landing platform;
The unmanned plane quantity that the landing platform of detection ship is currently parked;
Detect the flight attitude of unmanned plane;
Detect the Weather information around unmanned plane;
Detect the electricity of unmanned plane and the fault message of unmanned plane;
The fault message of the flight attitude of unmanned plane, the Weather information of surrounding, electricity and unmanned plane is inputted into trained flight
Safety index computation model, the flight safety index exported;
The operation posture of ship configured with landing platform, the Weather information at ship and landing platform are currently parked nobody
Machine quantity inputs trained take off safety index computation model and trained landing safety index computation model respectively, respectively
Obtain take off safety index and the landing safety index computation model output of the safety index computation model output of taking off
Landing safety index;
Judge the state of current unmanned plane, if current unmanned plane is in state of flight, obtains the flight safety of unmanned plane
Index and landing safety index, if the flight safety index of the unmanned plane and landing safety index meet preset unmanned plane
Drop conditions then control the unmanned plane and drop on the landing platform, if current unmanned plane is in parked state,
The safety index that takes off of ship that unmanned plane is parked is obtained, if the safety index that takes off meets preset unmanned plane and takes off item
Part then controls the unmanned plane and takes off from the landing platform.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910509094.8A CN110209195B (en) | 2019-06-13 | 2019-06-13 | Remote control system and control method for offshore unmanned aerial vehicle |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910509094.8A CN110209195B (en) | 2019-06-13 | 2019-06-13 | Remote control system and control method for offshore unmanned aerial vehicle |
Publications (2)
Publication Number | Publication Date |
---|---|
CN110209195A true CN110209195A (en) | 2019-09-06 |
CN110209195B CN110209195B (en) | 2023-01-24 |
Family
ID=67792306
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910509094.8A Active CN110209195B (en) | 2019-06-13 | 2019-06-13 | Remote control system and control method for offshore unmanned aerial vehicle |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110209195B (en) |
Cited By (15)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110633791A (en) * | 2019-09-26 | 2019-12-31 | 北航(四川)西部国际创新港科技有限公司 | Convolutional neural network-based unmanned aerial vehicle abnormal behavior identification method |
CN110673642A (en) * | 2019-10-28 | 2020-01-10 | 深圳市赛为智能股份有限公司 | Unmanned aerial vehicle landing control method and device, computer equipment and storage medium |
CN110703790A (en) * | 2019-10-16 | 2020-01-17 | 一飞智控(天津)科技有限公司 | Unmanned aerial vehicle flight safety protection method and protection system based on cloud big data |
CN110888461A (en) * | 2019-12-05 | 2020-03-17 | 西安毫米波光子科技有限公司 | Carrier-borne small-size fixed wing unmanned aerial vehicle gesture adjusting device that takes off |
CN110979568A (en) * | 2019-11-22 | 2020-04-10 | 上海海事大学 | Offshore material supply method |
CN110989663A (en) * | 2019-11-26 | 2020-04-10 | 中国电力科学研究院有限公司 | Method and system for controlling unmanned aerial vehicle |
CN111368971A (en) * | 2020-02-19 | 2020-07-03 | 中国人民解放军军事科学院国防科技创新研究院 | Unmanned aerial vehicle cluster cooperative landing sequencing method and system |
CN112541608A (en) * | 2020-02-19 | 2021-03-23 | 深圳中科保泰科技有限公司 | Unmanned aerial vehicle takeoff point prediction method and device |
CN112749855A (en) * | 2019-10-29 | 2021-05-04 | 顺丰科技有限公司 | Unmanned aerial vehicle scheduling method, device, computer system and storage medium |
CN112904886A (en) * | 2019-12-03 | 2021-06-04 | 顺丰科技有限公司 | Unmanned aerial vehicle flight control method and device, computer equipment and storage medium |
CN112925344A (en) * | 2021-01-25 | 2021-06-08 | 南京航空航天大学 | Unmanned aerial vehicle flight condition prediction method based on data driving and machine learning |
CN112947537A (en) * | 2019-12-10 | 2021-06-11 | 顺丰科技有限公司 | Unmanned aerial vehicle control method and device, computer equipment and storage medium |
CN113068126A (en) * | 2021-02-02 | 2021-07-02 | 浙江嘉蓝海洋电子有限公司 | Unmanned ship maritime communication channel self-adaptive selection method |
CN113296506A (en) * | 2021-05-20 | 2021-08-24 | 深圳市富创优越科技有限公司 | Ship anchoring control system and method |
CN114694453A (en) * | 2022-03-16 | 2022-07-01 | 中国民用航空飞行学院 | Flight simulation cabin low pressure governing system |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102298389A (en) * | 2011-06-10 | 2011-12-28 | 清华大学 | System fully controlled and taken over by ground station during takeoff and landing stages of unmanned plane |
CN105059558A (en) * | 2015-07-16 | 2015-11-18 | 珠海云洲智能科技有限公司 | Take-off and landing system for unmanned ship-borne unmanned aerial vehicle |
CN107885220A (en) * | 2017-11-15 | 2018-04-06 | 广东容祺智能科技有限公司 | Unmanned plane can precisely landing system and its method of work on a kind of naval vessel |
CN107943073A (en) * | 2017-11-14 | 2018-04-20 | 歌尔股份有限公司 | Unmanned plane landing method, equipment, system and unmanned plane |
CN108762298A (en) * | 2018-05-30 | 2018-11-06 | 佛山市神风航空科技有限公司 | A kind of aquatic unmanned aerial vehicle landing self-control system |
CN108829139A (en) * | 2018-07-25 | 2018-11-16 | 哈尔滨工业大学 | A kind of boat-carrying control method that unmanned plane sea is landed |
CN108983812A (en) * | 2018-07-25 | 2018-12-11 | 哈尔滨工业大学 | A kind of onboard control system that unmanned plane sea is landed |
-
2019
- 2019-06-13 CN CN201910509094.8A patent/CN110209195B/en active Active
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102298389A (en) * | 2011-06-10 | 2011-12-28 | 清华大学 | System fully controlled and taken over by ground station during takeoff and landing stages of unmanned plane |
CN105059558A (en) * | 2015-07-16 | 2015-11-18 | 珠海云洲智能科技有限公司 | Take-off and landing system for unmanned ship-borne unmanned aerial vehicle |
CN107943073A (en) * | 2017-11-14 | 2018-04-20 | 歌尔股份有限公司 | Unmanned plane landing method, equipment, system and unmanned plane |
CN107885220A (en) * | 2017-11-15 | 2018-04-06 | 广东容祺智能科技有限公司 | Unmanned plane can precisely landing system and its method of work on a kind of naval vessel |
CN108762298A (en) * | 2018-05-30 | 2018-11-06 | 佛山市神风航空科技有限公司 | A kind of aquatic unmanned aerial vehicle landing self-control system |
CN108829139A (en) * | 2018-07-25 | 2018-11-16 | 哈尔滨工业大学 | A kind of boat-carrying control method that unmanned plane sea is landed |
CN108983812A (en) * | 2018-07-25 | 2018-12-11 | 哈尔滨工业大学 | A kind of onboard control system that unmanned plane sea is landed |
Cited By (21)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110633791A (en) * | 2019-09-26 | 2019-12-31 | 北航(四川)西部国际创新港科技有限公司 | Convolutional neural network-based unmanned aerial vehicle abnormal behavior identification method |
CN110703790A (en) * | 2019-10-16 | 2020-01-17 | 一飞智控(天津)科技有限公司 | Unmanned aerial vehicle flight safety protection method and protection system based on cloud big data |
CN110673642A (en) * | 2019-10-28 | 2020-01-10 | 深圳市赛为智能股份有限公司 | Unmanned aerial vehicle landing control method and device, computer equipment and storage medium |
CN110673642B (en) * | 2019-10-28 | 2022-10-28 | 深圳市赛为智能股份有限公司 | Unmanned aerial vehicle landing control method and device, computer equipment and storage medium |
CN112749855A (en) * | 2019-10-29 | 2021-05-04 | 顺丰科技有限公司 | Unmanned aerial vehicle scheduling method, device, computer system and storage medium |
CN110979568A (en) * | 2019-11-22 | 2020-04-10 | 上海海事大学 | Offshore material supply method |
CN110989663A (en) * | 2019-11-26 | 2020-04-10 | 中国电力科学研究院有限公司 | Method and system for controlling unmanned aerial vehicle |
CN112904886A (en) * | 2019-12-03 | 2021-06-04 | 顺丰科技有限公司 | Unmanned aerial vehicle flight control method and device, computer equipment and storage medium |
CN112904886B (en) * | 2019-12-03 | 2023-08-11 | 丰翼科技(深圳)有限公司 | Unmanned aerial vehicle flight control method and device, computer equipment and storage medium |
CN110888461A (en) * | 2019-12-05 | 2020-03-17 | 西安毫米波光子科技有限公司 | Carrier-borne small-size fixed wing unmanned aerial vehicle gesture adjusting device that takes off |
CN110888461B (en) * | 2019-12-05 | 2022-11-22 | 西安毫米波光子科技有限公司 | Carrier-borne small-size fixed wing unmanned aerial vehicle gesture adjusting device that takes off |
CN112947537A (en) * | 2019-12-10 | 2021-06-11 | 顺丰科技有限公司 | Unmanned aerial vehicle control method and device, computer equipment and storage medium |
CN111368971A (en) * | 2020-02-19 | 2020-07-03 | 中国人民解放军军事科学院国防科技创新研究院 | Unmanned aerial vehicle cluster cooperative landing sequencing method and system |
CN112541608A (en) * | 2020-02-19 | 2021-03-23 | 深圳中科保泰科技有限公司 | Unmanned aerial vehicle takeoff point prediction method and device |
CN112541608B (en) * | 2020-02-19 | 2023-10-20 | 深圳中科保泰空天技术有限公司 | Unmanned aerial vehicle departure point prediction method and device |
CN112925344A (en) * | 2021-01-25 | 2021-06-08 | 南京航空航天大学 | Unmanned aerial vehicle flight condition prediction method based on data driving and machine learning |
CN113068126A (en) * | 2021-02-02 | 2021-07-02 | 浙江嘉蓝海洋电子有限公司 | Unmanned ship maritime communication channel self-adaptive selection method |
CN113296506A (en) * | 2021-05-20 | 2021-08-24 | 深圳市富创优越科技有限公司 | Ship anchoring control system and method |
CN113296506B (en) * | 2021-05-20 | 2023-12-26 | 珠海市美丰船务有限公司 | Ship anchoring control system and method |
CN114694453A (en) * | 2022-03-16 | 2022-07-01 | 中国民用航空飞行学院 | Flight simulation cabin low pressure governing system |
CN114694453B (en) * | 2022-03-16 | 2023-05-12 | 中国民用航空飞行学院 | Flight simulation cabin low pressure governing system |
Also Published As
Publication number | Publication date |
---|---|
CN110209195B (en) | 2023-01-24 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110209195A (en) | The tele-control system and control method of marine unmanned plane | |
CN109214107A (en) | A kind of ship's navigation behavior on-line prediction method | |
CN104965518B (en) | Electric inspection process flying robot's flight course planning method based on Three-dimensional Numeric Map | |
CN109711087B (en) | UUV dynamic threat situation assessment method | |
US11249494B2 (en) | Systems and methods for sensing and avoiding external objects for aircraft | |
CN112100917A (en) | Intelligent ship collision avoidance simulation test system and method based on expert confrontation system | |
CN108153332B (en) | Track simulation system based on large envelope game strategy | |
Cobano et al. | Data retrieving from heterogeneous wireless sensor network nodes using UAVs | |
CN111582740B (en) | Multi-rotor unmanned aerial vehicle risk assessment system | |
CN108609202B (en) | Flight bump prediction method and system | |
CN113848984B (en) | Unmanned aerial vehicle cluster control method and system | |
CN108427400A (en) | A kind of aircraft airspeed pipe method for diagnosing faults based on neural network Analysis design | |
Ghazali et al. | Vibration-based fault detection in drone using artificial intelligence | |
CN113190036A (en) | Unmanned aerial vehicle flight trajectory prediction method based on LSTM neural network | |
CN113496343A (en) | Method and apparatus for managing risks and alerts | |
CN111460676A (en) | Method for evaluating health performance of multi-rotor aircraft under atmospheric turbulence disturbance | |
CN116907282B (en) | Unmanned target aircraft ultra-low altitude flight control method based on artificial intelligence algorithm | |
CN116246366A (en) | Unmanned aerial vehicle healthy operation assessment method based on digital twinning | |
CN112817318B (en) | Multi-unmanned-boat collaborative search control method and system | |
CN107038450A (en) | Unmanned plane policing system based on deep learning | |
CN116310601B (en) | Ship behavior classification method based on AIS track diagram and camera diagram group | |
CN111445063B (en) | Method and device for selecting take-off and landing points based on flight line | |
Klaproth et al. | Investigation of Mission Performance Sensitivities for Unmanned Aerial Vehicles Based on Parametric Similarity Assessment of Mission Requirements | |
CN106597510A (en) | Position data fused filtering method for multi-rotor unmanned aerial vehicle (UAV) based on fuzzy determination algorithm | |
Chen et al. | Integrated air-ground vehicles for uav emergency landing based on graph convolution 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 |