CN108829136B - The a wide range of synergic monitoring method of unmanned aerial vehicle group - Google Patents
The a wide range of synergic monitoring method of unmanned aerial vehicle group Download PDFInfo
- Publication number
- CN108829136B CN108829136B CN201810997631.3A CN201810997631A CN108829136B CN 108829136 B CN108829136 B CN 108829136B CN 201810997631 A CN201810997631 A CN 201810997631A CN 108829136 B CN108829136 B CN 108829136B
- Authority
- CN
- China
- Prior art keywords
- unmanned plane
- unmanned
- flight
- aerial vehicle
- vehicle group
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000012544 monitoring process Methods 0.000 title claims abstract description 42
- 230000002195 synergetic effect Effects 0.000 title claims abstract description 23
- 238000000034 method Methods 0.000 title claims abstract description 22
- 230000002159 abnormal effect Effects 0.000 claims abstract description 22
- 238000011161 development Methods 0.000 claims abstract description 20
- 238000001514 detection method Methods 0.000 claims abstract description 10
- 230000006641 stabilisation Effects 0.000 claims abstract description 8
- 238000011105 stabilization Methods 0.000 claims abstract description 8
- 230000015572 biosynthetic process Effects 0.000 claims abstract description 6
- 239000013598 vector Substances 0.000 claims description 24
- 230000004888 barrier function Effects 0.000 claims description 18
- 239000011159 matrix material Substances 0.000 claims description 16
- 238000000605 extraction Methods 0.000 claims description 9
- 230000008859 change Effects 0.000 claims description 7
- 238000013528 artificial neural network Methods 0.000 claims description 6
- 238000011835 investigation Methods 0.000 claims description 6
- 239000000523 sample Substances 0.000 claims description 6
- 238000004364 calculation method Methods 0.000 claims description 5
- 238000004080 punching Methods 0.000 claims 1
- 238000012806 monitoring device Methods 0.000 description 5
- 235000011034 Rubus glaucus Nutrition 0.000 description 4
- 244000235659 Rubus idaeus Species 0.000 description 4
- 235000009122 Rubus idaeus Nutrition 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000002708 enhancing effect Effects 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 230000001105 regulatory effect Effects 0.000 description 2
- 230000019771 cognition Effects 0.000 description 1
- 230000000295 complement effect Effects 0.000 description 1
- 230000008030 elimination Effects 0.000 description 1
- 238000003379 elimination reaction Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000010191 image analysis Methods 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 230000008092 positive effect Effects 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Classifications
-
- 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
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S17/00—Systems using the reflection or reradiation of electromagnetic waves other than radio waves, e.g. lidar systems
- G01S17/88—Lidar systems specially adapted for specific applications
- G01S17/89—Lidar systems specially adapted for specific applications for mapping or imaging
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N7/00—Television systems
- H04N7/18—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- General Physics & Mathematics (AREA)
- Electromagnetism (AREA)
- Computer Networks & Wireless Communication (AREA)
- Aviation & Aerospace Engineering (AREA)
- Automation & Control Theory (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention discloses a wide range of synergic monitoring method and apparatus of unmanned aerial vehicle group, belong to air vehicle technique field.The device includes several unmanned planes, is respectively mounted on each unmanned plane and flies control device, 360 degree of laser scanning and ranging radars, development board, high-definition camera, three axis holders, light stream sensor, high brightness supplementary lighting sources and air speed measuring apparatus.Fly control device control unmanned plane according to formation autonomous flight, each unmanned plane automatically opens high brightness supplementary lighting sources if environment is very dark by 360 degree of laser scanning and ranging radar detection ambient enviroments.High-definition camera is to lower part environment shooting and monitoring in flight course, and light stream sensor and three axis holders keep the stabilization of itself fuselage and high-definition camera；After entering conflict situation, flies the heading that control device changes unmanned plane, carry out conflict Resolution.Finally shooting image is transmitted to development board, detects whether that there are abnormal areas.The present invention is able to achieve large-scale monitoring, has high efficiency, reduces human cost.
Description
Technical field
The invention belongs to air vehicle technique field, specifically a kind of a wide range of synergic monitoring method of unmanned aerial vehicle group.
Background technique
With the continuous development of unmanned air vehicle technique, application field is also constantly expanding: including crops monitoring, movies-making
With Post disaster relief etc..Meanwhile unmanned aerial vehicle group cooperation also becomes important development trend, unmanned aerial vehicle group can control bigger model
It encloses, realization has complementary functions with task sharing etc..Therefore unmanned aerial vehicle group system is able to carry out complex task, shorten execution task when
Between, improve efficiency of turning out for work.
Environmental monitoring under condition of uncertainty is a very important job, and traditional method is carried out by manpower
Monitoring, this monitoring mode needs to consume a large amount of human cost, and the environment of some danger may threaten patrol officer
Life security.Simultaneously as everyone ability to work is not quite similar, manpower monitoring is it is possible that carelessness.And as mountainous region,
The regions such as lake, forest can not be also monitored since area is huge by installation fixing camera.
Summary of the invention
The present invention provides one kind using unmanned aerial vehicle group synergic monitoring for complex environments such as mountainous region, forest or lakes
The a wide range of synergic monitoring method of unmanned aerial vehicle group；By installing high-definition camera on each unmanned plane, complex environment is carried out past
Synergic monitoring is returned, while instant analysis is carried out to the image of shooting, if it find that abnormal area, unmanned plane is then right on the way in return
Abnormal area carries out emphasis shooting and monitoring.
The a wide range of synergic monitoring device of the unmanned aerial vehicle group includes several unmanned planes, carries out coordinating to fly by swarm algorithm
Row；It is respectively mounted on each unmanned plane and flies control device, 360 degree of laser scanning and ranging radars, development board, high-definition camera, three axis clouds
Platform, light stream sensor, high brightness supplementary lighting sources and air speed measuring apparatus.
Environment around 360 degree of laser scanning and ranging radar detection unmanned planes, development board carry out the image after shooting
Analysis；High-definition camera is fixed on unmanned plane by three axis holders, and unmanned plane keeps itself and high definition by light stream sensor
The stabilization of video camera.Fly control device to be used to control unmanned plane during flying, the flight angle deflection of unmanned plane controlled under conflict situation,
Change of flight direction carries out conflict Resolution.
The specific work process of a wide range of synergic monitoring device of the unmanned aerial vehicle group are as follows:
Under the control for flying control device, each unmanned plane carries out autonomous flight according to formation, unglazed and without GPS signal
Under equal condition of uncertainty, each unmanned plane passes through the ambient enviroment of 360 degree of laser scanning and ranging radar detections itself；Environment very
Under conditions of dark, high brightness supplementary lighting sources are automatically opened；In flight course by high-definition camera to itself lower part environment into
Row shooting and monitoring, light stream sensor and three axis holders are able to maintain the stabilization of itself fuselage and high-definition camera；In flight course,
It encounters after barrier enters conflict situation, flies control device and the flight angle of unmanned plane is deflected, change the flight of unmanned plane
Direction carries out conflict Resolution.Finally shooting image is transmitted to development board, detects whether that there are abnormal areas.
The a wide range of synergic monitoring method of the unmanned aerial vehicle group, the specific steps are as follows:
Step 1: by each unmanned plane and respective winged control device, 360 degree of laser scanning and ranging radars, development board, light streams
Sensor, high-definition camera, three axis holders, high brightness supplementary lighting sources and air speed measuring apparatus are assembled and are carried out debugging flight,
Detect each flight parameter, it is ensured that unmanned plane normal flight.
Step 2: several unmanned planes for assembling and having debugged, which are formed into columns, forms unmanned aerial vehicle group, coordinated by swarm algorithm each
Unmanned plane carries out extensive self monitor to complex environment under condition of uncertainty.
Step 3: each unmanned plane flies under condition of uncertainty, 360 degree of laser scanning and ranging radars itself to be in
The heart respectively carries out conflict probe and frees.
Firstly, unmanned aerial vehicle group is when just starting formation flight, velocity magnitude is consistent with direction, keeps rank constant.
Then, in flight course, each unmanned plane respectively carries out conflict probe；
Unmanned plane has radius of safety Rc, Rc< Rd, RdFor the radius of investigation of ambient enviroment；Centered on unmanned plane, if
360 degree of laser scanning and ranging detections of radar are less than radius of safety R to barrier at a distance from the unmanned planecWhen, then the unmanned plane
In conflict situation.
Finally, flying control device when unmanned plane is in conflict situation and being deflected to the flight angle of unmanned plane, change nothing
Man-machine heading carries out conflict Resolution.
Unmanned plane is centered on itself, using heading as z-axis, using direction straight up as y-axis, with vertical y-z plane
Space coordinates are established for x-axis.The line direction of unmanned plane and barrier is denoted as by unmanned plane according to the location information of barrier
W axis, in w-z plane, when minimum range of the unmanned plane apart from barrier reaches RcWhen, calculate the flight angle deflection of itself most
Small angle theta, and conflict Resolution is realized according to the route flight after deflection by flying control device control unmanned plane.
Step 4: adjusting each unmanned plane during flying direction in unmanned aerial vehicle group by Vicsek model after conflict Resolution.
Circular are as follows:
For each unmanned plane, directional velocity takes a time step in each unmanned plane radius of investigation RdIt is interior it is all nobody
The average speed direction of machine；Calculation formula are as follows:Wherein V (t+1) indicates the t+1 moment this nobody
The directional velocity of machine,Indicate detection radius RdThe average speed direction of interior all unmanned planes, Δ φ are that angle is missed
Difference.
Unmanned aerial vehicle group adjusts the directional velocity of each unmanned plane by Vicsek model, to keep rank.
Step 5: each unmanned plane enhances algorithm based on the feature of global Gauss, by respective development board to shooting
Image is analyzed, and has detected whether abnormal area；
Specific step is as follows:
Step 501, each unmanned plane input the shooting picture in the respective channel 1024dpi × 1024dpi × 3 to exploitation
Plate carries out image characteristics extraction by neural network, generates the picture in the channel 8dpi × 8dpi × 256；
Step 502, the vector X=(X that the picture after feature extraction is regarded as to 64 256 dimensions1,X2,…,X64), to 64
Each component of vector is averaged, and average vector μ is obtained；
Step 503, the vector Y=(Y that the picture after feature extraction is regarded as to 256 64 dimensions again1,Y2,…,Y256), it calculates
The covariance matrix ∑ of 256 vectors；
Each element ∑ of matrixm_nFor vector YmWith YnCovariance；M, n=1,2 ... .256.
Covariance matrix ∑ and average vector μ are constituted a 257 new dimension square matrix ∑s by step 504*；
Step 505 ties up square matrix ∑ for 257*It is launched into the feature vector of one 257 × 257 dimension, then passes through neural network
Full articulamentum can be detected out the abnormal area of unmanned plane shooting.
Step 6: unmanned aerial vehicle group is returned after flying through region to be monitored by former route, and to exception in return course
Region carries out emphasis camera monitoring, completes task.
The present invention has the advantages that
1), a kind of a wide range of synergic monitoring method of unmanned aerial vehicle group can realize the association of unmanned aerial vehicle group under condition of uncertainty
With cognition, monitoring on a large scale is realized to environment such as mountainous region, forest, lakes.
2), a kind of a wide range of synergic monitoring method of unmanned aerial vehicle group, unmanned aerial vehicle group can be realized autonomous in flight course
It conflict Resolution and is kept rank by Vicsek model, moreover it is possible to the image of shooting is analyzed immediately, if it find that it is abnormal,
Emphasis shooting then is carried out to abnormal area in return course, there is high efficiency.
3), a kind of a wide range of synergic monitoring method of unmanned aerial vehicle group, can largely reduce human cost, ensure patrol officer's
Safety realizes the monitoring to extensive area, is of great significance to the timely discovery and elimination of some dangerous situations.
Detailed description of the invention
Fig. 1 is the structure chart of unmanned plane in a wide range of synergic monitoring device of unmanned aerial vehicle group of the present invention.
Fig. 2 is the schematic diagram of unmanned plane conflict Resolution of the present invention.
Fig. 3 is the schematic diagram that unmanned aerial vehicle group of the present invention adjusts heading by Vicsek model.
Fig. 4 is a wide range of synergic monitoring method flow diagram of unmanned aerial vehicle group of the present invention；
Fig. 5 is the stream that each unmanned plane of the present invention enhances that algorithm detects whether abnormal area based on the feature of global Gauss
Cheng Tu.
1- unmanned plane in figure, 2- fly control device, 3-360 degree laser scanning and ranging radar, 4- development board, 5- light stream sensing
Device, 6- high-definition camera, tri- axis holder of 7-, 8- high brightness supplementary lighting sources, 9- air speed measuring apparatus.
Specific embodiment
In order to make the object, technical scheme and advantages of the embodiment of the invention clearer, below in conjunction in present example
Attached drawing, the technical scheme in the embodiment of the invention is clearly and completely described.
The present invention provides a kind of a wide range of synergic monitoring method of unmanned aerial vehicle group and specifically includes that unmanned aerial vehicle group in condition of uncertainty
Lower autonomous flight can independently carry out conflict Resolution and be regulated the speed direction by Vicsek model, while unmanned plane can assist
Emphasis monitoring is carried out to abnormal area with monitoring lower part environment, and based on the feature of global Gauss enhancing algorithm.
The a wide range of synergic monitoring device of the unmanned aerial vehicle group includes eight rotor wing unmanned aerial vehicles, real by included winged control device
Now to the control of fuselage, 360 degree of laser scanning and ranging radars are housed simultaneously on unmanned plane, week can be detected under condition of uncertainty
Collarette border, and contacted with other unmanned planes foundation in radius of investigation；The high-definition camera and three axis holders being equipped with, can be under
Portion's environment is shot, and unmanned plane tests and analyzes shooting image immediately, if it find that it is abnormal, then it is right in return course
Abnormal area carries out emphasis shooting and monitoring.
As shown in Figure 1, several unmanned planes carry out coordinated flight by swarm algorithm；Each unmanned plane selects T-1200 to fold
Eight rotor wing unmanned aerial vehicles 1 are respectively mounted Pixhawk 2.1 on each unmanned plane and fly control device 2, Rplidar A3360 degree laser scanning
Range radar 3, Raspberry pi 3b+ development board 4, high-definition camera 6, three axis holders 7, light stream sensor 5, high brightness are mended
Radiant 8 and air speed measuring apparatus 9.
360 degree of laser scanning and ranging radars 3 detect the environment around the unmanned plane, Raspberry pi 3b+ development board 4
Image after shooting is analyzed；High-definition camera 6 is fixed on unmanned plane by three axis holders 7, and unmanned plane passes through light stream
The stabilization of the holding of sensor 5 itself and high-definition camera 6.Pixhawk 2.1 flies control device 2 and is used to control unmanned plane during flying,
The flight angle deflection of unmanned plane is controlled under conflict situation, change of flight direction carries out conflict Resolution.
The specific work process of a wide range of synergic monitoring device of the unmanned aerial vehicle group are as follows:
Under the control for flying control device, each unmanned plane carries out autonomous flight according to formation, unglazed and without GPS signal
Under equal condition of uncertainty, each unmanned plane passes through the unmanned plane and barrier around 360 degree of laser scanning and ranging radar detections
State；Under conditions of environment is very dark, high brightness supplementary lighting sources are automatically opened；By high-definition camera to certainly in flight course
The lower part environment of body carries out round-trip shooting and monitoring, and light stream sensor and three axis holders are able to maintain itself fuselage and high-definition camera
Stablize；To carry out normal photographing monitoring.In flight course, encountering barrier, then unmanned plane leads in the case where ensuring secured premise
It crosses and flies control device control unmanned plane with the autonomous conflict Resolution of the smallest angle realization of current direction of advance deflection, to reduce power
Consumption.Unmanned plane carry out conflict Resolution after, a group of planes by Vicsek model come direction of regulating the speed, to keep rank.
If there is fortuitous event occurs in unmanned plane, for example it not can be realized conflict Resolution and crash, then distance in a group of planes
The nearest unmanned plane of the unmanned plane fills up its position.Last unmanned plane is based on the feature enhancing algorithm of global Gauss to shooting image
It is transmitted to development board to be analyzed, detects whether that there are abnormal areas；If it find that it is abnormal, then to exceptions area in return course
Domain carries out emphasis shooting and monitoring.
The a wide range of synergic monitoring method of the unmanned aerial vehicle group, as shown in Figure 4, the specific steps are as follows:
Step 1: by each unmanned plane and respective winged control device, 360 degree of laser scanning and ranging radars, development board, light streams
Sensor, high-definition camera, three axis holders, high brightness supplementary lighting sources and air speed measuring apparatus are assembled and are carried out debugging flight,
Detect each flight parameter, it is ensured that unmanned plane normal flight.
T-1200 is folded eight rotor wing unmanned aerial vehicles to sweep with 360 degree of winged control device of Pixhawk 2.1, Rplidar A3 laser
Retouch range radar, Raspberry pi 3b+ development board, light stream sensor, high-definition camera, three axis holders, high brightness light filling light
The devices such as source, air speed measuring apparatus assemble, and carry out debugging flight, detect each flight parameter, it is ensured that unmanned plane can be just
Often flight.
Step 2: several unmanned planes for assembling and having debugged, which are formed into columns, forms unmanned aerial vehicle group, coordinated by swarm algorithm each
Unmanned plane carries out extensive self monitor to complex environment under condition of uncertainty.
Unmanned aerial vehicle group is realizing the extensive autonomous prison to complex environments such as mountainous region, forest, lakes under condition of uncertainty
It surveys.For under some complex environments, in fact it could happen that the unstable situation of some areas wind speed, this will will cause the fuselage of unmanned plane
Vibration, influences shooting and monitoring effect.The stabilization that fuselage can be at this time kept by light stream sensor is kept with three axis holders
The stabilization of high-definition camera, to preferably carry out shooting record.
Step 3: each unmanned plane flies under condition of uncertainty, 360 degree of laser scanning and ranging radars itself to be in
The heart respectively judges whether there is conflict, if it is, carrying out conflict probe and freeing conflict, otherwise enters step five.
Firstly, unmanned aerial vehicle group is in flight course, due to that may there is no GPS signal under some condition of uncertainty, so
Unmanned plane detects ambient enviroment by Rplidar A3360 degree laser scanning and ranging radar.360 degree of laser scanning and ranging radars
It can detect centered on unmanned plane, radius RdIn the range of environment, the position shape including other unmanned planes in a group of planes
State information and barrier etc..For unmanned aerial vehicle group when just starting formation flight, velocity magnitude is consistent with direction, keeps rank
It is constant, convenient for the mutual exchange connection between a group of planes.
Then, in flight course, each unmanned plane respectively carries out conflict probe；
Unmanned plane has radius of safety Rc, Rc< Rd；Centered on unmanned plane, if 360 degree of laser scanning and ranging radar inspections
It measures barrier and is less than radius of safety R at a distance from the unmanned planecWhen, then the unmanned plane is in conflict situation.
Finally, flying control device when unmanned plane is in conflict situation and being deflected to the flight angle of unmanned plane, change nothing
Man-machine heading carries out conflict Resolution.
Unmanned plane is centered on itself, using heading as z-axis, using direction straight up as y-axis, with vertical y-z plane
Space coordinates are established for x-axis.Unmanned plane is according to the location information of barrier, as shown in Fig. 2, by the company of unmanned plane and barrier
Line direction is denoted as w axis, and in w-z plane, unmanned plane deflects the smallest angle, θ, so that fly along the direction after deflection, nobody
Minimum range of the machine apart from barrier is Rc, conflict Resolution just may be implemented.The deflection angle for minimizing unmanned plane can be with
Reduce power consumption, while but also the flight of unmanned plane is safer, after avoiding deflection angle excessive with it is other in a group of planes
Unmanned plane generates conflict.If there is fortuitous event in flight course in unmanned plane, for example has little time avoiding barrier to fall
It ruins, the nearest unmanned plane of the unmanned aerial vehicle group peripheral distance crash unmanned plane can fill up its position, to guarantee entire unmanned aerial vehicle group
Stabilization.
Step 4: adjusting each unmanned plane during flying direction in unmanned aerial vehicle group by Vicsek model after conflict Resolution.
After conflict Resolution, direction of the unmanned plane due to changing speed in unmanned aerial vehicle group, no longer as original state along
Same direction flight, at this time needs to adjust the unmanned plane during flying direction in unmanned aerial vehicle group by Vicsek model.Specific meter
Calculation method are as follows:
For each unmanned plane, directional velocity takes a time step in each unmanned plane radius of investigation RdIt is interior it is all nobody
The average speed direction of machine；As shown in figure 3, calculation formula are as follows:Wherein V (t+1) indicates t+1
The directional velocity of the moment unmanned plane,Indicate detection radius RdThe average speed direction of interior all unmanned planes, Δ
φ is a low-angle, and expression is uncertain factor.It may be specifically the unmanned plane error that information is collected under complex environment,
And the error etc. of practical adjustment heading.
Unmanned aerial vehicle group adjusts the directional velocity of each unmanned plane by Vicsek model, as shown in figure 3, to keep team
Shape.
Step 5: each unmanned plane enhances algorithm based on the feature of global Gauss, pass through respective Raspberry pi 3b
+ development board analyzes the image of shooting, has detected whether abnormal area；
As shown in Figure 5, the specific steps are as follows:
Step 501, each unmanned plane input the shooting picture in the respective channel 1024dpi × 1024dpi × 3 to exploitation
Plate carries out image characteristics extraction by neural network, generates the picture in the channel 8dpi × 8dpi × 256；
Step 502, the vector X=(X that the picture after feature extraction is regarded as to 64 256 dimensions1,X2,…,X64), to 64
Each component of vector is averaged, and average vector μ is obtained；
Step 503, the vector Y=(Y that the picture after feature extraction is regarded as to 256 64 dimensions again1,Y2,…,Y256), it calculates
The covariance matrix ∑ of 256 vectors；
Each element ∑ of matrixm_nFor vector YmWith YnCovariance；M, n=1,2 ... .256.
Covariance matrix matrix ∑ and average vector μ are constituted a 257 new dimension square matrix ∑s by step 504*；
Step 505 ties up square matrix ∑ for 257*It is launched into the feature vector of one 257 × 257 dimension, then passes through neural network
Full articulamentum can be detected out the abnormal area of unmanned plane shooting.
Step 6: unmanned aerial vehicle group is returned after flying through region to be monitored by former route, and to exception in return course
Region carries out emphasis camera monitoring, completes task.
Unmanned plane will do it image analysis after the picture is taken, if it find that abnormal area, can return on the way to abnormal area
Carry out emphasis shooting and monitoring.
The present invention (unglazed, without GPS signal etc.) can realize unmanned aerial vehicle group to mountainous region, forest, lake under condition of uncertainty
The extensive self monitor of the complex environments such as pool, high-efficient, precision is high, while can save human cost, ensures patrol officer
The safety of work.It realizes that unmanned aerial vehicle group recognizes the synergic monitoring of external environment under condition of uncertainty, monitoring effect can be improved
Rate is removed a hidden danger in time, has positive effect.
Claims (3)
1. a wide range of synergic monitoring method of unmanned aerial vehicle group, which is characterized in that be based on several unmanned planes, assisted by swarm algorithm
Adjust flight；Specific step is as follows:
Step 1: each unmanned plane and respective winged control device, 360 degree of laser scanning and ranging radars, development board, light stream are sensed
Device, high-definition camera, three axis holders, high brightness supplementary lighting sources and air speed measuring apparatus are assembled and are carried out debugging flight, detection
Each flight parameter, it is ensured that unmanned plane normal flight；
Under conditions of environment is very dark, high brightness supplementary lighting sources are automatically opened；By high-definition camera to itself in flight course
Lower part environment carry out shooting and monitoring, high-definition camera is fixed on unmanned plane by three axis holders, and unmanned plane passes through light stream biography
Sensor keeps the stabilization of itself and high-definition camera；
Step 2: by several assemblings and the unmanned planes debugged form into columns and form unmanned aerial vehicle groups, by swarm algorithm coordinate it is each nobody
Machine carries out extensive self monitor to complex environment under condition of uncertainty；
Step 3: each unmanned plane flies under condition of uncertainty, 360 degree of laser scanning and ranging radars are centered on itself, respectively
From progress conflict probe and free；
In flight course, encounters after barrier enters conflict situation, fly the flight angle of control device control unmanned plane, conflicting
Angular deflection is controlled under state, change of flight direction carries out conflict Resolution；
Step 4: adjusting each unmanned plane during flying direction in unmanned aerial vehicle group by Vicsek model after conflict Resolution；
Step 5: each unmanned plane enhances algorithm based on the feature of global Gauss, by respective development board to the image of shooting
It is analyzed, has detected whether abnormal area；
Shooting image is transmitted to development board, and each unmanned plane enhances algorithm based on the feature of global Gauss, passes through respective exploitation
Plate analyzes the image of shooting, detects whether that there are abnormal areas；
Specific step is as follows:
Step 501, each unmanned plane input the shooting picture in the respective channel 1024dpi × 1024dpi × 3 to development board, lead to
It crosses neural network and carries out image characteristics extraction, generate the picture in the channel 8dpi × 8dpi × 256；
Step 502, the vector X=(X that the picture after feature extraction is regarded as to 64 256 dimensions1,X2,…,X64), to 64 vectors
Each component is averaged, and average vector μ is obtained；
Step 503, the vector Y=(Y that the picture after feature extraction is regarded as to 256 64 dimensions again1,Y2,…,Y256), calculate 256
The covariance matrix ∑ of vector；
Each element ∑ of matrixm_nFor vector YmWith YnCovariance；M, n=1,2 ... .256；
Covariance matrix ∑ and average vector μ are constituted a 257 new dimension square matrix ∑s by step 504*；
Step 505 ties up square matrix ∑ for 257*It is launched into the feature vector of one 257 × 257 dimension, then connecting entirely by neural network
Layer is connect, detects the abnormal area of unmanned plane shooting；
Step 6: unmanned aerial vehicle group is returned after flying through region to be monitored by former route, and to abnormal area in return course
Emphasis camera monitoring is carried out, task is completed.
2. a wide range of synergic monitoring method of unmanned aerial vehicle group as described in claim 1, which is characterized in that the step three is specific
Are as follows:
Firstly, unmanned aerial vehicle group is when just starting formation flight, velocity magnitude is consistent with direction, keeps rank constant；
Then, in flight course, each unmanned plane respectively carries out conflict probe；
Unmanned plane has radius of safety Rc, Rc< Rd, RdFor the radius of investigation of ambient enviroment；Centered on unmanned plane, if 360 degree
Laser scanning and ranging detections of radar is less than radius of safety R to barrier at a distance from the unmanned planecWhen, then the unmanned plane is in punching
Prominent state；
Finally, flying control device when unmanned plane is in conflict situation and being deflected to the flight angle of unmanned plane, change unmanned plane
Heading carry out conflict Resolution；
Unmanned plane is centered on itself, using heading as z-axis, using direction straight up as y-axis, using vertical y-z plane as x-axis
Establish space coordinates；The line direction of unmanned plane and barrier is denoted as w axis according to the location information of barrier by unmanned plane,
In w-z plane, when minimum range of the unmanned plane apart from barrier reaches RcWhen, the flight angle for calculating itself deflects minimum angle
θ is spent, and realizes conflict Resolution according to the route flight after deflection by flying control device control unmanned plane.
3. a wide range of synergic monitoring method of unmanned aerial vehicle group as described in claim 1, which is characterized in that the step four is specific
Calculation method are as follows:
For each unmanned plane, directional velocity takes a time step in each unmanned plane radius of investigation RdInterior all unmanned planes
Average speed direction；Calculation formula are as follows:Wherein V (t+1) indicates the t+1 moment unmanned plane
Directional velocity,Indicate detection radius RdThe average speed direction of interior all unmanned planes, Δ φ are angular errors；
Unmanned aerial vehicle group adjusts the directional velocity of each unmanned plane by Vicsek model, to keep rank.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810997631.3A CN108829136B (en) | 2018-08-29 | 2018-08-29 | The a wide range of synergic monitoring method of unmanned aerial vehicle group |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810997631.3A CN108829136B (en) | 2018-08-29 | 2018-08-29 | The a wide range of synergic monitoring method of unmanned aerial vehicle group |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108829136A CN108829136A (en) | 2018-11-16 |
| CN108829136B true CN108829136B (en) | 2019-06-25 |
Family
ID=64150884
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810997631.3A Active CN108829136B (en) | 2018-08-29 | 2018-08-29 | The a wide range of synergic monitoring method of unmanned aerial vehicle group |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108829136B (en) |
Families Citing this family (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109443366B (en) * | 2018-12-20 | 2020-08-21 | 北京航空航天大学 | Unmanned aerial vehicle group path planning method based on improved Q learning algorithm |
| CN109601212A (en) * | 2019-01-09 | 2019-04-12 | 四川万智沃达科技有限公司 | A kind of weather influence operational method, unmanned plane and computer readable storage medium based on unmanned plane |
| CN109782798B (en) * | 2019-01-22 | 2020-03-27 | 北京航空航天大学 | Boid model-based unmanned aerial vehicle cluster formation method |
| CN110794872A (en) * | 2019-11-18 | 2020-02-14 | 云南电网有限责任公司电力科学研究院 | Substation unmanned aerial vehicle group intelligent early warning monitoring system and method |
| CN112105032B (en) * | 2020-07-06 | 2021-10-26 | 天津大学 | Unmanned aerial vehicle cooperative cognitive wireless network transmission method based on cache |
| CN112146615B (en) * | 2020-09-23 | 2022-03-29 | 招商局重庆交通科研设计院有限公司 | Slope monitoring method based on multiple unmanned aerial vehicles |
| CN112556691B (en) * | 2020-11-26 | 2022-08-02 | 广东工业大学 | Method for unmanned aerial vehicle autonomous navigation and temperature measurement system |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106292709A (en) * | 2016-10-13 | 2017-01-04 | 北京航空航天大学 | Many unmanned vehicles collision avoidance control method and device |
| CN107424443A (en) * | 2017-08-30 | 2017-12-01 | 北京航空航天大学 | A kind of aircraft cluster regulation and control method and device based on Vicsek models |
| CN108196582A (en) * | 2018-02-12 | 2018-06-22 | 深圳技术大学（筹） | A kind of indoor Visual Navigation unmanned plane cluster flight control system and method |
| CN108227746A (en) * | 2018-01-23 | 2018-06-29 | 深圳市科卫泰实业发展有限公司 | A kind of unmanned plane cluster control system and method |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101908138B (en) * | 2010-06-30 | 2012-05-23 | 北京航空航天大学 | Identification method of image target of synthetic aperture radar based on noise independent component analysis |
| CN107832716B (en) * | 2017-11-15 | 2020-05-12 | 中国科学技术大学 | Anomaly detection method based on active and passive Gaussian online learning |
-
2018
- 2018-08-29 CN CN201810997631.3A patent/CN108829136B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106292709A (en) * | 2016-10-13 | 2017-01-04 | 北京航空航天大学 | Many unmanned vehicles collision avoidance control method and device |
| CN107424443A (en) * | 2017-08-30 | 2017-12-01 | 北京航空航天大学 | A kind of aircraft cluster regulation and control method and device based on Vicsek models |
| CN108227746A (en) * | 2018-01-23 | 2018-06-29 | 深圳市科卫泰实业发展有限公司 | A kind of unmanned plane cluster control system and method |
| CN108196582A (en) * | 2018-02-12 | 2018-06-22 | 深圳技术大学（筹） | A kind of indoor Visual Navigation unmanned plane cluster flight control system and method |
Non-Patent Citations (2)
| Title |
|---|
| 四旋翼无人机一致性编队飞行控制方法;陈杰敏等;《航空兵器》;20171231;第25-31页 |
| 多无人机协同控制方法及应用研究;韩亮等;《导航定位与授时》;20180731;第1-7页 |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108829136A (en) | 2018-11-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108829136B (en) | The a wide range of synergic monitoring method of unmanned aerial vehicle group | |
| CN106526551B (en) | A kind of radar antenna dynamic performance testing system and method | |
| CN109887057A (en) | The method and apparatus for generating high-precision map | |
| Merino et al. | Vision-based multi-UAV position estimation | |
| CN110308457A (en) | A kind of power transmission line polling system based on unmanned plane | |
| CN111983936B (en) | Unmanned aerial vehicle semi-physical simulation system and evaluation method | |
| CN110231025B (en) | Dynamic orientation method and system based on strapdown polarized light compass | |
| WO2023138007A1 (en) | High-reliability and high-precision navigation positioning method and system for gps-denied unmanned aerial vehicle | |
| CN109828274A (en) | Adjust the method, apparatus and unmanned plane of the main detection direction of airborne radar | |
| CN113532499B (en) | Sensor security detection method and device for unmanned system and storage medium | |
| CN109573088A (en) | A kind of Shipborne UAV photoelectricity guidance carrier landing system and warship method | |
| CN102654917B (en) | Method and system for sensing motion gestures of moving body | |
| CN114004977A (en) | Aerial photography data target positioning method and system based on deep learning | |
| Dufek et al. | Visual pose stabilization of tethered small unmanned aerial system to assist drowning victim recovery | |
| Zhang et al. | A bio-inspired navigation strategy fused polarized skylight and starlight for unmanned aerial vehicles | |
| Rosser et al. | Reducing the complexity of visual navigation: Optical track controller for long‐range unmanned aerial vehicles | |
| CN105807083A (en) | Real-time speed measuring method and system for unmanned aerial vehicle | |
| KR20200109116A (en) | Method and system for position estimation of unmanned aerial vehicle using graph structure based on multi module | |
| CN109764864A (en) | A kind of indoor UAV position and orientation acquisition methods and system based on color identification | |
| Amidi et al. | Research on an autonomous vision-guided helicopter | |
| Moore et al. | Vision-only estimation of wind field strength and direction from an aerial platform | |
| CN102706360B (en) | Method utilizing optical flow sensors and rate gyroscope to estimate state of air vehicle | |
| CN209728170U (en) | A kind of laser irradiation formula GPS coordinate acquisition system | |
| CN202084081U (en) | Moving object motion attitude sensing system | |
| Li et al. | Small UAV autonomous localization based on multiple sensors fusion |
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 |